{"meta":{"query_hash":"90175592dfae","filters":{"topic":"Statistical Methods in Clinical Trials"},"cohort_total":1557,"direct_labels_cover":46,"predictions_cover":1557,"exported":1557,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/90175592dfae","api":"https://metacan.xera.ac/api/v1/cohort?topic=Statistical+Methods+in+Clinical+Trials"},"results":[{"id":"W103694265","doi":"10.1097/ppo.0b013e3181b9c506","title":"Tumor Shrinkage and Objective Response Rates","year":2009,"lang":"en","type":"review","venue":"The Cancer Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Clinical trial; Medicine; Surrogate endpoint; End point; Sample size determination; Clinical endpoint; Intensive care medicine; Oncology; Internal medicine; Computer science; Statistics; Mathematics","score_opus":0.6401582648585327,"score_gpt":0.6455445852726251,"score_spread":0.0053863204140924825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W103694265","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013124376,0.99563015,0.0022304708,0.0002919274,0.0007381255,0.00060703093,0.000100558136,0.000026052689,0.0003625361],"genre_scores_gemma":[9.246713e-7,0.93899167,0.058667988,0.00022680305,0.0016111863,0.000051715248,1.8653547e-7,0.000057858877,0.00039170092],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9909876,0.0066996557,0.0012887312,0.00031835295,0.00035425343,0.00035140337],"domain_scores_gemma":[0.9138407,0.08429782,0.0011202317,0.00042976142,0.000121504134,0.0001899838],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012671251,0.00039020358,0.0022655223,0.00009514068,0.0002547775,0.00017176577,0.0006266284,0.0001929,0.00050706224],"category_scores_gemma":[0.073841736,0.00019950485,0.00044412012,0.00022720247,0.00025282474,0.000043440916,0.00012692204,0.0018825842,0.000020566775],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020351501,0.000023720911,3.820038e-7,0.0011963408,0.00023816401,0.00009212318,0.00007391888,7.623495e-8,3.300404e-7,0.0028406726,0.004810545,0.99052024],"study_design_scores_gemma":[0.0002788774,0.0001161458,0.000016105394,0.00843026,0.0012794645,0.0005729544,0.000018333265,0.0000012495159,0.000002292945,0.5729783,0.4160927,0.00021332779],"about_ca_topic_score_codex":0.000002016424,"about_ca_topic_score_gemma":0.0000013475474,"teacher_disagreement_score":0.99030685,"about_ca_system_score_codex":0.00024948365,"about_ca_system_score_gemma":0.0006230454,"threshold_uncertainty_score":0.93395966},"labels":[],"label_agreement":null},{"id":"W1037076944","doi":"10.1097/pai.0000000000000249","title":"Modeling Canadian Quality Control Test Program for Steroid Hormone Receptors in Breast Cancer: Diagnostic Accuracy Study","year":2015,"lang":"en","type":"article","venue":"Applied immunohistochemistry & molecular morphology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"Health Canada; Partenariat Canadien Contre Le Cancer","keywords":"Gold standard (test); Breast cancer; Progesterone receptor; Medicine; Estrogen receptor; Sensitivity (control systems); Confidence interval; Internal medicine; Gynecology; Computer science; Oncology; Cancer","score_opus":0.17922236163295144,"score_gpt":0.4901022869271244,"score_spread":0.31087992529417297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1037076944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9552781,0.00046659156,0.035897177,0.00076866394,0.00051912625,0.005929652,0.00051658537,0.00017241138,0.0004516947],"genre_scores_gemma":[0.9096886,0.00001580205,0.083461225,0.00037645537,0.00012722089,0.0061661657,0.000036830068,0.00010314317,0.000024593814],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954866,0.00045758722,0.0017139497,0.0009722497,0.00039559274,0.0009740243],"domain_scores_gemma":[0.98059994,0.0170285,0.000355041,0.0010918471,0.00037585897,0.00054881076],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003408789,0.00050497195,0.0013107061,0.000114782735,0.000115549505,0.00005337284,0.0007358118,0.00046400444,0.00007158375],"category_scores_gemma":[0.06430667,0.00053744414,0.0001742314,0.00032349877,0.0002545785,0.000042198364,0.000125896,0.0006691988,0.00001601967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00258687,0.005873292,0.0032230539,0.00032954736,0.0006628593,0.0003730263,0.0008650923,0.0018428258,0.9482722,0.0024993496,0.0029648927,0.03050694],"study_design_scores_gemma":[0.15877919,0.006398263,0.0075340588,0.0007063739,0.004452003,0.0005090915,0.009257833,0.025431216,0.04424974,0.731244,0.0005580846,0.010880089],"about_ca_topic_score_codex":0.018241541,"about_ca_topic_score_gemma":0.00027879555,"teacher_disagreement_score":0.9040225,"about_ca_system_score_codex":0.0010150609,"about_ca_system_score_gemma":0.0007247364,"threshold_uncertainty_score":0.9997077},"labels":[],"label_agreement":null},{"id":"W112168112","doi":"10.1023/a:1007521016985","title":"Sensitivity of Empirical Metrics of Rate of Absorption in Bioequivalence Studies","year":2000,"lang":"en","type":"article","venue":"Pharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Deutsche Forschungsgemeinschaft","keywords":"Bioequivalence; Mathematics; Sensitivity (control systems); Absorption (acoustics); Statistics; Analytical Chemistry (journal); Dispersion (optics); Chemistry; Pharmacokinetics; Chromatography; Physics; Pharmacology; Medicine; Optics","score_opus":0.9449494173068114,"score_gpt":0.7713117230809766,"score_spread":0.17363769422583475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W112168112","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918154,0.00045307173,0.004854701,0.00071934744,0.000090062065,0.00059968635,0.00008145526,0.000015554211,0.0013707044],"genre_scores_gemma":[0.92018217,0.0016422024,0.07798343,0.000029929779,0.000046720812,0.000014002862,3.0599668e-7,0.00001555567,0.000085672764],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878307,0.008507151,0.0015453405,0.00037446682,0.0012243273,0.0005180152],"domain_scores_gemma":[0.78929996,0.20924754,0.00014808752,0.00034979155,0.0008046505,0.00014994324],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041723788,0.00013162277,0.0009617787,0.00038617506,0.000027053711,0.000004773763,0.00024959884,0.00014780411,0.00070641865],"category_scores_gemma":[0.30194098,0.000107783584,0.00013452096,0.0019813005,0.0016675743,0.000057657136,0.00021530152,0.0007383975,0.000021099062],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0078970725,0.00782826,0.04064727,0.010201464,0.00070501346,0.00019086902,0.0018807035,0.000082713545,0.25915453,0.1731971,0.0024829055,0.4957321],"study_design_scores_gemma":[0.0014553313,0.00036877094,0.005458762,0.00032979346,0.000073254916,0.000002133729,0.00016432878,0.005750198,0.297704,0.68840337,0.00015440755,0.0001356509],"about_ca_topic_score_codex":0.000040115083,"about_ca_topic_score_gemma":0.000005302203,"teacher_disagreement_score":0.5152063,"about_ca_system_score_codex":0.000079950834,"about_ca_system_score_gemma":0.00010875949,"threshold_uncertainty_score":0.986747},"labels":[],"label_agreement":null},{"id":"W1239915614","doi":"10.1016/j.ejca.2015.08.004","title":"Correlation of single arm versus randomised phase 2 oncology trial characteristics with phase 3 outcome","year":2015,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; McMaster University; Juravinski Hospital; Queen's University","funders":"","keywords":"Clinical endpoint; Medicine; Clinical trial; Internal medicine; Sample size determination; Outcome (game theory); Phases of clinical research; Phase (matter); Clinical study design; Oncology; Statistics","score_opus":0.6506362328123789,"score_gpt":0.5936434193847209,"score_spread":0.05699281342765805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1239915614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4800731,0.0001833138,0.48871705,0.00059624115,0.011952172,0.0010369971,0.00013937498,0.000033042776,0.017268725],"genre_scores_gemma":[0.707226,0.000039096023,0.28926334,0.00010878091,0.0030230933,0.0000058515157,0.0000019479212,0.000076638804,0.00025528524],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947437,0.0023107375,0.0021023636,0.0001341606,0.000535071,0.00017396006],"domain_scores_gemma":[0.983208,0.01270119,0.0028428056,0.0002070213,0.00076957815,0.00027142774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007554365,0.00016043491,0.0010404298,0.000087899054,0.000025025705,0.000020484626,0.00023030792,0.000051910207,0.00031275398],"category_scores_gemma":[0.06541654,0.00011158369,0.0001743562,0.00012799278,0.00017380177,0.00008262678,0.000031238716,0.0003637791,0.000009554413],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.81265986,0.0035778026,0.000035570163,0.000039427425,0.00033463322,0.00030436428,0.00046874286,0.000022632463,0.00060931087,0.0007568404,0.002141326,0.17904946],"study_design_scores_gemma":[0.94387627,0.036324624,0.000028358918,0.00016623843,0.0009824423,0.000023640998,0.000105026746,0.00016043396,0.00066213805,0.005025919,0.012456845,0.00018806399],"about_ca_topic_score_codex":0.0000010180139,"about_ca_topic_score_gemma":9.857716e-7,"teacher_disagreement_score":0.22715288,"about_ca_system_score_codex":0.00016518382,"about_ca_system_score_gemma":0.00028933372,"threshold_uncertainty_score":0.9424558},"labels":[],"label_agreement":null},{"id":"W1436699622","doi":"10.1208/s12249-015-0409-7","title":"Stage 2 Process Performance Qualification (PPQ): a Scientific Approach to Determine the Number of PPQ Batches","year":2015,"lang":"en","type":"review","venue":"AAPS PharmSciTech","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"","keywords":"Robustness (evolution); Computer science; Process engineering; Process (computing); Process validation; Product (mathematics); Reliability engineering; Confidence interval; Data mining; Statistics; Mathematics; Engineering; Chemistry; Verification and validation","score_opus":0.8128477789862868,"score_gpt":0.646023047949426,"score_spread":0.1668247310368608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1436699622","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002516203,0.8613908,0.08655859,0.00016812459,0.004408276,0.02000631,0.0029836146,0.0006631833,0.021304857],"genre_scores_gemma":[0.000283165,0.43371618,0.5566165,0.00006740885,0.0007105602,0.0022423267,0.00008136463,0.00025466832,0.006027847],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932359,0.0013903618,0.0024539228,0.0010330442,0.0013576051,0.0005292044],"domain_scores_gemma":[0.98121,0.014447817,0.0015650406,0.0018200002,0.00068926724,0.0002678723],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01557064,0.00059528963,0.0027054239,0.0001754097,0.00018805543,0.00017660037,0.0019256012,0.0004167523,0.00017829938],"category_scores_gemma":[0.030760895,0.00036319793,0.00041603355,0.0020424298,0.0005491278,0.00013536574,0.0003319143,0.00075818284,0.00024892055],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031204672,0.00048515547,0.000009147349,0.046319906,0.00014552283,0.0000015109655,0.00078600104,0.0000011975698,0.0000064957244,0.0057426365,0.003037172,0.94343406],"study_design_scores_gemma":[0.00055299036,0.00009363845,0.0000019614372,0.006538493,0.0015536222,0.00003712749,0.00020185368,0.00028309107,0.00031143363,0.08632102,0.9032113,0.00089347985],"about_ca_topic_score_codex":0.000003431075,"about_ca_topic_score_gemma":4.8552636e-7,"teacher_disagreement_score":0.9425406,"about_ca_system_score_codex":0.00013471565,"about_ca_system_score_gemma":0.00055825367,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W1484865074","doi":"10.1111/j.1541-0420.2010.01491.x","title":"Estimating the Null Distribution to Adjust Observed Confidence Levels for Genome-Scale Screening","year":2010,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Null distribution; Test statistic; Null hypothesis; Null (SQL); Estimator; Confidence interval; Statistical hypothesis testing; Statistical inference; Frequentist inference; p-value","score_opus":0.7212641075307934,"score_gpt":0.5508548686905355,"score_spread":0.17040923884025794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1484865074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057373896,0.000020413869,0.9378065,0.00073327083,0.0014906115,0.001129624,0.0012576976,0.00010655033,0.00008144299],"genre_scores_gemma":[0.0900409,0.0000010793598,0.90870273,0.0002126855,0.00071380264,0.00012069997,0.000016745551,0.00003495751,0.00015638038],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975039,0.00021025074,0.00088476477,0.00043153967,0.0005010071,0.00046854277],"domain_scores_gemma":[0.93308115,0.065149315,0.00035420147,0.0006979232,0.00047179722,0.00024561177],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006960451,0.00020566654,0.000462702,0.00020023594,0.00030244034,0.00015073316,0.00067406,0.00022486718,0.00012260563],"category_scores_gemma":[0.35046446,0.00015031682,0.00016509659,0.0026545378,0.0001610715,0.00006861854,0.00020786628,0.0003686673,0.000036540598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032896537,0.0006644398,0.002394373,0.0008618698,0.00023122955,0.000010549219,0.00067540293,0.00011018272,0.0758928,0.365658,0.011629113,0.5415431],"study_design_scores_gemma":[0.0018093982,0.00049889303,0.039658904,0.00013572017,0.00031699755,0.0000119792885,0.00017888047,0.026493298,0.010317898,0.906348,0.013385469,0.00084458763],"about_ca_topic_score_codex":0.000019673449,"about_ca_topic_score_gemma":0.000010808984,"teacher_disagreement_score":0.5406985,"about_ca_system_score_codex":0.00004702904,"about_ca_system_score_gemma":0.000050181843,"threshold_uncertainty_score":0.6550069},"labels":[],"label_agreement":null},{"id":"W1485935964","doi":"10.1002/9781118445112.stat06470.pub2","title":"Multivariate Normality Test in Practice","year":2015,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Multivariate statistics; Univariate; Kurtosis; Statistics; Multivariate analysis; Multivariate analysis of variance; Normality; Estimator; Mathematics; Multivariate normal distribution; Skewness; Normality test; Missing data; Econometrics; Statistical hypothesis testing","score_opus":0.5247456815839482,"score_gpt":0.5800756748552308,"score_spread":0.05532999327128263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1485935964","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006526336,0.0006204322,0.34116647,0.00037680462,0.0020154044,0.0025406089,0.25654766,0.00082495506,0.3959011],"genre_scores_gemma":[0.000020365616,0.001267192,0.87239486,0.00031581454,0.0007226795,0.00007846613,0.0017396782,0.0008927445,0.12256818],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9908695,0.0022802022,0.0027086614,0.0014054396,0.0016206916,0.0011154696],"domain_scores_gemma":[0.9198381,0.07456977,0.002227935,0.0017410791,0.0009391569,0.00068397104],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004579198,0.0010764858,0.0024568061,0.00048537913,0.00006370405,0.000109032444,0.0010127944,0.0011933064,0.0036894523],"category_scores_gemma":[0.35975623,0.0009759833,0.00009535788,0.00072091835,0.0005295766,0.00012982654,0.000480467,0.0022952373,0.0005357497],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022964372,0.0027981705,0.000121115154,0.00066011504,0.00022449465,0.00047118432,0.00012409262,0.0000021781825,0.000008093847,0.12097324,0.8552912,0.0190965],"study_design_scores_gemma":[0.002300113,0.00039785836,0.000096570395,0.0012586493,0.0004450289,0.0000143984935,0.00014087789,0.00060434506,0.0000020877337,0.5136098,0.48010042,0.0010298385],"about_ca_topic_score_codex":0.0016877889,"about_ca_topic_score_gemma":0.003827102,"teacher_disagreement_score":0.5312284,"about_ca_system_score_codex":0.00039782107,"about_ca_system_score_gemma":0.001018456,"threshold_uncertainty_score":0.99926907},"labels":[],"label_agreement":null},{"id":"W1486152899","doi":"10.1002/bimj.201100048","title":"Nonparametric confidence intervals for the ratio of marginal hazard rates of paired survival times","year":2012,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Hazard ratio; Confidence interval; Statistics; Nonparametric statistics; Censoring (clinical trials); Mathematics; Hazard; CDF-based nonparametric confidence interval; Econometrics","score_opus":0.6400516550833277,"score_gpt":0.5716085483897604,"score_spread":0.06844310669356735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486152899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015645854,0.0013539903,0.9796299,0.00056237745,0.0018660175,0.00053434353,0.0001078125,0.00001551918,0.0002841929],"genre_scores_gemma":[0.55334127,0.000114143535,0.44582972,0.00003550375,0.00053657504,0.000012822509,4.1736297e-7,0.00001919114,0.000110317356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99564195,0.0010727325,0.0018002861,0.00016814422,0.0008498026,0.00046708854],"domain_scores_gemma":[0.81205505,0.18554445,0.0011590491,0.00032322263,0.0006683114,0.00024991276],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014110622,0.00019183177,0.00096676056,0.00074479065,0.00010357611,0.000053101754,0.0006248288,0.00016940535,0.00063442846],"category_scores_gemma":[0.28100777,0.000113324386,0.0004786481,0.0027358518,0.00042468068,0.00012913336,0.00011753141,0.00033952235,0.000010656586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003546463,0.004695717,0.07256243,0.001326387,0.0028005778,0.000013193048,0.0005478189,0.000011123114,0.013147549,0.55440694,0.049293242,0.29764855],"study_design_scores_gemma":[0.004812751,0.002234479,0.07415864,0.00035515576,0.0011441254,0.000120672754,0.0003874162,0.0023509227,0.0672114,0.8443354,0.002295134,0.00059396046],"about_ca_topic_score_codex":0.0000044388953,"about_ca_topic_score_gemma":1.8158121e-7,"teacher_disagreement_score":0.53769547,"about_ca_system_score_codex":0.00005163726,"about_ca_system_score_gemma":0.00009631998,"threshold_uncertainty_score":0.7250486},"labels":[],"label_agreement":null},{"id":"W1487549987","doi":"10.18433/j32g6p","title":"Do Regulatory Bioequivalence Requirements Adequately Reflect the Therapeutic Equivalence of Modified-Release Drug Products?","year":2010,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Equivalence (formal languages); Pharmacokinetics; Pharmacology; Drug; Metric (unit); Nifedipine; Medicine; Mathematics; Economics; Internal medicine","score_opus":0.6749632427048569,"score_gpt":0.6128134010332944,"score_spread":0.062149841671562456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1487549987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971626,0.0027715117,0.0069727893,0.009207108,0.0060519227,0.0010542606,0.000037299844,0.000065113905,0.0022139838],"genre_scores_gemma":[0.9200097,0.0006877615,0.077631384,0.00067518244,0.00086863927,0.000011152849,8.7668624e-8,0.000028654422,0.0000874554],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916453,0.0018192371,0.0024792594,0.00059097033,0.0026541722,0.00081107335],"domain_scores_gemma":[0.9760323,0.0200687,0.001860029,0.000641564,0.000874944,0.000522461],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023578053,0.00038504336,0.00085950166,0.00021290031,0.00038602768,0.00014687247,0.0027315835,0.00009243288,0.00093563204],"category_scores_gemma":[0.034149334,0.00022296917,0.00038365967,0.0012539515,0.0038085713,0.0006318899,0.00032948295,0.0016974274,0.000019323406],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009714019,0.0012451498,0.0021188864,0.0004998112,0.00027915632,0.0000616318,0.00052509026,0.000051555493,0.64497745,0.1315237,0.0024827062,0.21526344],"study_design_scores_gemma":[0.0027139958,0.0004157643,0.0004533905,0.0002521746,0.00076228613,0.00013444296,0.00015796827,0.0031302017,0.4765505,0.5067198,0.008254567,0.0004548867],"about_ca_topic_score_codex":0.00000815573,"about_ca_topic_score_gemma":9.3791414e-7,"teacher_disagreement_score":0.37519613,"about_ca_system_score_codex":0.00006399856,"about_ca_system_score_gemma":0.00065833563,"threshold_uncertainty_score":0.99997765},"labels":[],"label_agreement":null},{"id":"W1490191373","doi":"10.1111/biom.12344","title":"Assessing Incremental Value of Biomarkers with Multi-phase Nested Case-control Studies","year":2015,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of General Medical Sciences; National Cancer Institute; National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institute on Aging; Harvard Medical School; Brigham and Women's Hospital","keywords":"Nested case-control study; Value (mathematics); Computer science; Statistics; Phase (matter); Mathematics; Case-control study; Chemistry","score_opus":0.8234003999282882,"score_gpt":0.648123226589282,"score_spread":0.17527717333900616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1490191373","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4699535,0.000638716,0.5274117,0.00008476453,0.00067536766,0.0007472599,0.00020117231,0.00010228744,0.00018522948],"genre_scores_gemma":[0.3871131,0.0000055950723,0.6127342,0.000028628101,0.00006569369,0.000013317227,0.0000010062869,0.000025574034,0.000012895371],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99670345,0.0009479202,0.0010272743,0.0003403319,0.00067332474,0.0003076738],"domain_scores_gemma":[0.9538498,0.044251848,0.00061388157,0.00040727248,0.000626519,0.00025068776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006863416,0.00023545686,0.00088349934,0.00087896595,0.00006936062,0.00005901146,0.00019723414,0.00015002218,0.000014985973],"category_scores_gemma":[0.20998058,0.0001694794,0.00009918313,0.003687204,0.00039243535,0.00015728417,0.00010685395,0.00014221405,0.0000057409384],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00826745,0.027904993,0.07419685,0.0059570177,0.024884917,0.021718638,0.0048667844,0.00005040107,0.025929417,0.111182176,0.013970051,0.6810713],"study_design_scores_gemma":[0.27486694,0.020001117,0.010614228,0.002559591,0.014953149,0.004876259,0.059850506,0.059227046,0.060144216,0.48613682,0.0008835268,0.0058866134],"about_ca_topic_score_codex":0.0000477326,"about_ca_topic_score_gemma":0.0000042819033,"teacher_disagreement_score":0.67518467,"about_ca_system_score_codex":0.00016789352,"about_ca_system_score_gemma":0.00012247186,"threshold_uncertainty_score":0.7966741},"labels":[],"label_agreement":null},{"id":"W1492616518","doi":"10.1002/hec.1781","title":"ACCOUNTING FOR BETWEEN‐STUDY VARIATION IN INCREMENTAL NET BENEFIT IN VALUE OF INFORMATION METHODOLOGY","year":2011,"lang":"en","type":"article","venue":"Health Economics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Variation (astronomy); Econometrics; Statistics; Sample (material); Net gain; Net (polyhedron); Value (mathematics); Net present value; Mathematics; Economics; Computer science; Microeconomics","score_opus":0.7584255852675267,"score_gpt":0.5746853839259253,"score_spread":0.1837402013416014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1492616518","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8525033,0.0000043219975,0.14506298,0.000099761004,0.000322891,0.0016676105,0.00009342046,0.000013203145,0.00023248287],"genre_scores_gemma":[0.3039265,0.000011560551,0.6957291,0.00018117994,0.000057802397,0.000077751305,0.0000051301695,0.000010227489,7.9752e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99649954,0.00064514554,0.0023456172,0.0001808546,0.000054959837,0.0002738726],"domain_scores_gemma":[0.9780879,0.02062723,0.0009886881,0.00020235009,0.000042189637,0.00005165956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015172365,0.00010500431,0.00073067634,0.00021743673,0.000028735247,0.000008240752,0.00014853323,0.00013272156,0.000032576147],"category_scores_gemma":[0.017775176,0.00011616147,0.00004426825,0.00011065006,0.00002366751,0.00022006071,0.000064517575,0.00015527461,0.0000037465552],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044123793,0.0005015925,0.285066,0.00073920697,0.00005493155,1.9683823e-7,0.01233929,0.00009132626,0.0000039784,0.63756305,0.00003048195,0.0631687],"study_design_scores_gemma":[0.0016623326,0.0003378528,0.29766965,0.000026814581,0.000013515744,2.142321e-7,0.000453909,0.0021997765,0.000044106862,0.6974962,0.000017738654,0.0000779062],"about_ca_topic_score_codex":0.0013799316,"about_ca_topic_score_gemma":0.00063232885,"teacher_disagreement_score":0.5506661,"about_ca_system_score_codex":0.00023531163,"about_ca_system_score_gemma":0.00012166358,"threshold_uncertainty_score":0.99049854},"labels":[],"label_agreement":null},{"id":"W1494574517","doi":"10.1002/9781118445112.stat05961","title":"Simultaneous Confidence Intervals","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Bonferroni correction; Correctness; Robust confidence intervals; Statistics; Multivariate statistics; Mathematics; Confidence region; Multiple comparisons problem; Confidence distribution; Econometrics; Algorithm","score_opus":0.3993296386183609,"score_gpt":0.5344037049428179,"score_spread":0.13507406632445695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494574517","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004184114,0.0003508158,0.85750073,0.00010669173,0.0017629493,0.0011807964,0.061159257,0.0008486981,0.07708587],"genre_scores_gemma":[0.000097431104,0.0015950819,0.7401651,0.00043239046,0.0010980181,0.000059299815,0.0008201653,0.0011906218,0.25454187],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99131954,0.001687895,0.002671848,0.0016434689,0.0014970992,0.0011801234],"domain_scores_gemma":[0.9226839,0.071659274,0.0022237084,0.0021603478,0.0005770318,0.00069573143],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0018763952,0.0013095353,0.0030958904,0.000415172,0.00011114161,0.00016008654,0.0015742136,0.0012696249,0.021769721],"category_scores_gemma":[0.14689672,0.0011569104,0.0002169745,0.00034708783,0.00094522093,0.000041953925,0.00048241433,0.0017929986,0.0015883631],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083770836,0.00040429502,0.0000062533713,0.00094207877,0.0002556856,0.00019807342,0.00003386955,0.0000032147354,0.0000145351405,0.32311592,0.6298303,0.04511203],"study_design_scores_gemma":[0.0008764518,0.00044283597,0.0000036650335,0.0021073367,0.00038835805,0.000014580919,0.000030347004,0.0014701937,0.000011951251,0.64148796,0.35213482,0.0010315104],"about_ca_topic_score_codex":0.00023891783,"about_ca_topic_score_gemma":0.0008562069,"teacher_disagreement_score":0.31837204,"about_ca_system_score_codex":0.0001681612,"about_ca_system_score_gemma":0.00036581673,"threshold_uncertainty_score":0.9999656},"labels":[],"label_agreement":null},{"id":"W1494822500","doi":"10.22237/jmasm/1036109880","title":"A Test Of Symmetry","year":2002,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Type I and type II errors; Trimming; Statistics; Heteroscedasticity; Statistic; Type (biology); Test statistic; Symmetry (geometry); Econometrics; Statistical hypothesis testing; Computer science; Geometry","score_opus":0.5268173440763403,"score_gpt":0.5765893634832558,"score_spread":0.04977201940691556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494822500","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035983932,0.0002131839,0.9829783,0.00017068426,0.00042415777,0.00025443037,0.00014668661,0.000027325037,0.015425398],"genre_scores_gemma":[0.075387895,0.000064053354,0.92393214,0.00013293274,0.00032387947,0.00000843015,2.794977e-7,0.000059137452,0.00009126918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936305,0.0015579367,0.0030734218,0.00032452404,0.00096882513,0.0004447745],"domain_scores_gemma":[0.80559915,0.19173157,0.0014632874,0.00045524666,0.0003665788,0.00038414056],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009903527,0.00031108994,0.001841172,0.00022080763,0.000056983856,0.000031627456,0.0005675456,0.00027995626,0.0018375969],"category_scores_gemma":[0.21135677,0.00024184544,0.00028602273,0.0003692234,0.000444944,0.000059293372,0.00012451698,0.0009149778,0.000020157988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015135319,0.00079294416,0.00004246202,0.0002004577,0.00014619448,0.00003714949,0.00012534409,0.0000031572279,0.011921371,0.497144,0.0034277602,0.48600778],"study_design_scores_gemma":[0.0014861787,0.0006494604,0.00019622412,0.000089813555,0.00037990505,0.00006879956,0.000035978173,0.006347183,0.0060567134,0.9840455,0.00041019777,0.00023406767],"about_ca_topic_score_codex":8.066716e-7,"about_ca_topic_score_gemma":1.5244575e-7,"teacher_disagreement_score":0.48690146,"about_ca_system_score_codex":0.00007258664,"about_ca_system_score_gemma":0.000052331423,"threshold_uncertainty_score":0.9990749},"labels":[],"label_agreement":null},{"id":"W1498026393","doi":"10.1111/j.1365-2885.2012.01366.x","title":"Demonstrating bioequivalence using clinical endpoint studies","year":2012,"lang":"en","type":"article","venue":"Journal of Veterinary Pharmacology and Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada; Université de Montréal","funders":"","keywords":"Bioequivalence; Clinical endpoint; Clinical trial; Medicine; Endpoint Determination; Medical physics; Clinical study design; Clinical study; Bioavailability; Pharmacology; Internal medicine","score_opus":0.8956633496424353,"score_gpt":0.7074870078984427,"score_spread":0.18817634174399267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498026393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704944,0.0047684098,0.019960025,0.00028966513,0.0042818915,0.00012408796,0.000005774316,0.000013266843,0.00006248236],"genre_scores_gemma":[0.5848585,0.0026347192,0.41070184,0.00059236644,0.0011928899,0.0000010695743,2.2592536e-8,0.000012873194,0.00000571913],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99611586,0.0018443973,0.0014307837,0.00012025844,0.0001757713,0.0003129144],"domain_scores_gemma":[0.9726575,0.025967885,0.00091620465,0.0000984036,0.00017908028,0.0001809197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075863064,0.00016402113,0.0007202243,0.00006623357,0.000115691604,0.000010985592,0.00016460876,0.00015949566,0.000077012926],"category_scores_gemma":[0.0031227893,0.000121611534,0.00016404522,0.0000814345,0.00055705145,0.00017584489,0.00012680146,0.00060843414,0.0000016431472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009609222,0.0065363552,0.1091397,0.0017271987,0.015277216,0.0013939283,0.005276168,0.000015987034,0.45261848,0.04452113,0.0017086773,0.35217592],"study_design_scores_gemma":[0.009590862,0.012309423,0.01177646,0.0005471251,0.00827109,0.008396111,0.0026753896,0.0017422274,0.016345004,0.9157648,0.011453411,0.0011281128],"about_ca_topic_score_codex":1.07661734e-7,"about_ca_topic_score_gemma":1.8550447e-8,"teacher_disagreement_score":0.87124366,"about_ca_system_score_codex":0.00003296182,"about_ca_system_score_gemma":0.0000499594,"threshold_uncertainty_score":0.49591744},"labels":[],"label_agreement":null},{"id":"W1498707895","doi":"10.1016/s0169-7161(07)27016-6","title":"16 Sequential and Group Sequential Designs in Clinical Trials: Guidelines for Practitioners","year":2007,"lang":"en","type":"book-chapter","venue":"Handbook of statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l'Économie, de la Science et de l'Innovation - Québec","keywords":"Sample size determination; Null hypothesis; Sample (material); Computer science; Set (abstract data type); Type I and type II errors; Treatment and control groups; Statistics; Mathematics","score_opus":0.9213858095193868,"score_gpt":0.6772586835422912,"score_spread":0.24412712597709552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498707895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000027912802,0.00075626123,0.97577727,0.00009849404,0.0018831525,0.0025206034,0.007795457,0.00005273671,0.011113219],"genre_scores_gemma":[0.000007707105,0.003649296,0.9795381,0.00032104237,0.0019281801,0.000067692876,0.00019718574,0.00018494962,0.014105867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.986918,0.0015293114,0.0091912905,0.0009566198,0.00087118935,0.00053362537],"domain_scores_gemma":[0.8231528,0.17141412,0.0035107564,0.00051235734,0.0011322588,0.00027769167],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038431365,0.0006645344,0.0037394962,0.00035550157,0.00008586388,0.000063572224,0.00031090318,0.0013965999,0.00087020936],"category_scores_gemma":[0.32971692,0.00061470724,0.00057133246,0.000051485873,0.001004507,0.00007688015,0.00017028286,0.00094047165,0.000013471764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014232028,0.00014416053,0.000008002683,0.00095175847,0.00045823946,0.00006401685,0.00003093167,9.890731e-7,0.00006025395,0.8433909,0.0572825,0.096185036],"study_design_scores_gemma":[0.004322943,0.0007650203,0.0000038895696,0.0020220438,0.001463,0.0000141888995,0.00002046797,0.0002931591,0.0001461462,0.9636676,0.0266995,0.0005820688],"about_ca_topic_score_codex":0.000027358547,"about_ca_topic_score_gemma":0.00017520261,"teacher_disagreement_score":0.29128557,"about_ca_system_score_codex":0.00017226108,"about_ca_system_score_gemma":0.00039029043,"threshold_uncertainty_score":0.9998998},"labels":[],"label_agreement":null},{"id":"W1517449684","doi":"10.1002/pds.3606","title":"Personalizing medicine: a review of adaptive treatment strategies","year":2014,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Pharmacoepidemiology; Intensive care medicine; Pharmacology","score_opus":0.7129090530951675,"score_gpt":0.6592985743419247,"score_spread":0.05361047875324276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517449684","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.8620066e-8,0.97108716,0.021100618,0.0007941692,0.00048189724,0.0013637639,0.00021715765,0.00005173973,0.0049034627],"genre_scores_gemma":[5.607669e-7,0.8952978,0.10292048,0.0007598392,0.00063908956,0.00017669101,0.000022066997,0.00004598505,0.00013745418],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9768139,0.01817536,0.003665168,0.0007392712,0.00019303113,0.00041325088],"domain_scores_gemma":[0.72633195,0.27099308,0.001980093,0.00039554495,0.00010506382,0.00019426348],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021619715,0.0007028369,0.009971931,0.0001005351,0.000094075236,0.000002764594,0.0003182469,0.00037797148,0.0013189423],"category_scores_gemma":[0.09389074,0.00041342198,0.0008091957,0.00019148963,0.0009056384,0.00003807248,0.00012053214,0.0006466154,0.000022958957],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004238725,0.00004844129,8.638458e-7,0.15115757,0.00061368756,0.000005974939,0.00005331439,4.2764096e-8,6.651189e-8,0.14438269,0.008859812,0.6948352],"study_design_scores_gemma":[0.0005002718,0.00017012458,2.9856565e-7,0.11253845,0.0053660376,0.000029020046,0.00003120677,0.000014804261,2.3909075e-7,0.16877922,0.71231085,0.00025944994],"about_ca_topic_score_codex":0.000035775098,"about_ca_topic_score_gemma":0.0000021847366,"teacher_disagreement_score":0.70345104,"about_ca_system_score_codex":0.000100924175,"about_ca_system_score_gemma":0.000256389,"threshold_uncertainty_score":0.99983174},"labels":[],"label_agreement":null},{"id":"W1518621087","doi":"10.1023/a:1022451015903","title":"The Exact and Limiting Distributions for the Number of Successes in Success Runs Within a Sequence of Markov-Dependent Two-State Trials","year":2002,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Toronto Public Health; University of Manitoba","funders":"","keywords":"Mathematics; Markov chain; Bernoulli trial; Statistic; Limiting; Statistics; Sufficient statistic; Applied mathematics; Beta-binomial distribution; Binomial distribution; Bernoulli's principle; Bernoulli distribution; Negative binomial distribution; Combinatorics; Random variable; Poisson distribution","score_opus":0.5820460240127906,"score_gpt":0.5564590340817828,"score_spread":0.02558698993100783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518621087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20367092,0.00035480707,0.77743566,0.0036409716,0.0007943563,0.0034162465,0.009622441,0.00002687455,0.001037741],"genre_scores_gemma":[0.6266818,0.0003880067,0.37272567,0.000026124475,0.000034850706,0.00006880525,0.0000022212269,0.000023113953,0.00004939524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99380136,0.000882319,0.0038920373,0.00027415628,0.0007726827,0.00037742895],"domain_scores_gemma":[0.84229934,0.15389942,0.0024295442,0.00073125237,0.0005590987,0.000081373655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012033276,0.0002773517,0.0015676705,0.000048844387,0.00019385599,0.00004278677,0.0009400587,0.000112003996,0.000060768543],"category_scores_gemma":[0.25941253,0.00014230491,0.000275667,0.00038427723,0.002380601,0.00012272254,0.00029994504,0.00030278086,9.0127656e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018319197,0.0005631295,0.00043886164,0.0019324081,0.00028505523,0.0000029445996,0.0005321261,0.0001032308,0.00053586153,0.98849946,0.00030307224,0.0066206423],"study_design_scores_gemma":[0.0009667623,0.00010620864,0.00034329048,0.0010008994,0.0003331705,0.000011315142,0.00023939888,0.007352672,0.012198974,0.9772462,0.0000441316,0.00015694431],"about_ca_topic_score_codex":0.00015004817,"about_ca_topic_score_gemma":0.00012780543,"teacher_disagreement_score":0.4230109,"about_ca_system_score_codex":0.000019728002,"about_ca_system_score_gemma":0.000100375146,"threshold_uncertainty_score":0.8771423},"labels":[],"label_agreement":null},{"id":"W1522084651","doi":"10.1002/0470842555.ch37","title":"<i>N</i> ‐of‐1 Randomized Clinical Trials in Pharmacoepidemiology","year":2000,"lang":"en","type":"other","venue":"Pharmacoepidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph's Hospital; McMaster University","funders":"","keywords":"Pharmacoepidemiology; Randomized controlled trial; Medicine; Clinical trial; Alternative medicine; Family medicine; Medical physics; Pharmacology; Internal medicine; Pathology","score_opus":0.7984979951863306,"score_gpt":0.7095090898873713,"score_spread":0.08898890529895931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522084651","genre_codex":"other","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008168402,0.012040014,0.13799234,0.005713077,0.017210146,0.012303531,0.0018672817,0.0010337506,0.81175816],"genre_scores_gemma":[0.00034273518,0.06623373,0.8186931,0.009678411,0.009014085,0.0016335046,0.000093022056,0.0018757841,0.09243561],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.40715307,0.5517258,0.03568626,0.0027833732,0.00061398017,0.0020374795],"domain_scores_gemma":[0.06851023,0.9173388,0.012166579,0.0013298136,0.000076440505,0.00057818263],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4262567,0.0011858211,0.03562736,0.001030697,0.00002874352,0.0000067247424,0.0013757643,0.0030886438,0.038881827],"category_scores_gemma":[0.87132907,0.0008935822,0.0045365305,0.000502771,0.0027635633,0.000035310255,0.0002848132,0.003204935,0.00028212115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027221086,0.00058766117,0.0006812649,0.0005267972,0.0018447792,0.000059579004,0.00001528015,0.0000040139735,0.00002995584,0.044663258,0.8943354,0.030030962],"study_design_scores_gemma":[0.110938355,0.000088056324,0.000009081809,0.000426867,0.0020428274,0.000012663674,0.0000031009422,0.0006628096,0.00005110077,0.5607587,0.3243685,0.00063793204],"about_ca_topic_score_codex":0.0002934152,"about_ca_topic_score_gemma":0.000035119087,"teacher_disagreement_score":0.71932256,"about_ca_system_score_codex":0.000049939314,"about_ca_system_score_gemma":0.00025470083,"threshold_uncertainty_score":0.99995035},"labels":[],"label_agreement":null},{"id":"W1529953445","doi":"10.1161/01.cir.0000074251.89176.6d","title":"Regional Pathologies and Globalization of Clinical Trials: Has the Time for Regional Trials Arrived?","year":2003,"lang":"en","type":"letter","venue":"Circulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"","keywords":"Medicine; Clinical trial; Population; Heart failure; Spironolactone; Internal medicine; Gerontology; Environmental health","score_opus":0.888804080787102,"score_gpt":0.6312691889108916,"score_spread":0.2575348918762105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1529953445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00078453636,0.0005724974,0.66724813,0.32171458,0.0025749165,0.005749692,0.0009351639,0.000118411546,0.00030208175],"genre_scores_gemma":[0.000869779,0.00044451546,0.78241336,0.19627032,0.01787375,0.0006318557,0.0008281678,0.00020356962,0.00046466378],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96668464,0.024367973,0.006941006,0.00081993977,0.00085458485,0.00033186807],"domain_scores_gemma":[0.579237,0.41332537,0.005993486,0.0007572593,0.00062038505,0.00006647462],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08107384,0.00039912038,0.0037289397,0.000109586785,0.00018057338,0.00010319744,0.0003370778,0.001985003,0.00019434317],"category_scores_gemma":[0.6681661,0.00026357672,0.0012058503,0.00018518254,0.00087486545,0.00007371765,0.00005549348,0.00083064014,0.000007638722],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027488612,0.00006278982,0.00025145625,0.00030958303,0.00035007502,0.000004172222,0.000042338692,0.000008868356,0.000037046575,0.020593854,0.96244246,0.015622469],"study_design_scores_gemma":[0.0019662068,0.00009016851,0.0009591679,0.0001947943,0.0011960053,0.00000988526,0.000017798226,0.0007812566,0.000013497107,0.85724014,0.13726935,0.0002616985],"about_ca_topic_score_codex":0.000003389134,"about_ca_topic_score_gemma":6.6299543e-7,"teacher_disagreement_score":0.8366463,"about_ca_system_score_codex":0.000055282766,"about_ca_system_score_gemma":0.00028048223,"threshold_uncertainty_score":0.99998164},"labels":[],"label_agreement":null},{"id":"W1532346271","doi":"10.1002/9781118445112.stat05239","title":"False Positive Rate","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"False positive rate; Complement (music); Mathematics; Statistics; Biology; Genetics","score_opus":0.40291870076620256,"score_gpt":0.5324205651737137,"score_spread":0.12950186440751116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532346271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000060867364,0.0002543627,0.7737215,0.00014838549,0.0014290548,0.0011680535,0.11748138,0.00064977043,0.10514141],"genre_scores_gemma":[0.00001849827,0.0013845576,0.7543112,0.0004967268,0.0011692541,0.0000668757,0.0019019396,0.0012726844,0.23937826],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991395,0.002605759,0.0021917257,0.001558171,0.0011065567,0.0011428164],"domain_scores_gemma":[0.953999,0.041089218,0.0019479676,0.0017598757,0.0005393191,0.00066462945],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024030865,0.0012713418,0.0028351948,0.00043617314,0.00012712732,0.0001348202,0.001076496,0.0012063202,0.013056321],"category_scores_gemma":[0.06923364,0.0011157336,0.00020572337,0.00038236004,0.00074700237,0.000043892225,0.00039223855,0.0016677392,0.0013953493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090841575,0.00040356375,0.000008485132,0.0004759314,0.00029134296,0.00009966757,0.000024274395,5.2461104e-7,0.000016948925,0.3699172,0.6014976,0.027173605],"study_design_scores_gemma":[0.0012389559,0.0003716177,0.00005384822,0.0016079677,0.0005241667,0.0000072839835,0.000022308577,0.0002763409,0.000020505182,0.74979895,0.24495845,0.0011195805],"about_ca_topic_score_codex":0.0002022759,"about_ca_topic_score_gemma":0.0006450433,"teacher_disagreement_score":0.37988174,"about_ca_system_score_codex":0.0001701083,"about_ca_system_score_gemma":0.00035521702,"threshold_uncertainty_score":0.9993822},"labels":[],"label_agreement":null},{"id":"W1538865552","doi":"10.1016/s0169-7161(03)23031-5","title":"An Increasing Hazard Cure Model","year":2003,"lang":"en","type":"book-chapter","venue":"Handbook of statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Hazard; Maximization; Nonparametric statistics; Generalization; Econometrics; Proportional hazards model; Estimation; Statistics; Hazard ratio; Expectation–maximization algorithm; Computer science; Mathematics; Maximum likelihood; Mathematical optimization; Confidence interval; Economics","score_opus":0.4943622739795478,"score_gpt":0.5149359608922042,"score_spread":0.020573686912656375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538865552","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042893294,0.00031325562,0.8568103,0.000018969096,0.00037737592,0.0005540132,0.0064394213,0.00008285194,0.13539954],"genre_scores_gemma":[0.000018492308,0.00090332737,0.94488704,0.0002178921,0.00024235425,0.00001239931,0.000057886056,0.00025646397,0.053404126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99546176,0.00040055838,0.002059271,0.00070169766,0.0009395959,0.00043711546],"domain_scores_gemma":[0.97202975,0.024524286,0.001315077,0.001179328,0.00059287995,0.00035869025],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024181472,0.0006739563,0.0019706676,0.0001668718,0.00010421876,0.00005168082,0.00048903486,0.0008954512,0.0013305739],"category_scores_gemma":[0.021998009,0.0006593751,0.0002315863,0.000033078726,0.0006052571,0.00006328459,0.00010147563,0.0008658994,0.000056675213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001416386,0.000104075996,0.0000052051723,0.00061641954,0.00017234961,0.0000471264,0.000070270726,0.000027399179,0.00010171741,0.9611623,0.02964905,0.007902398],"study_design_scores_gemma":[0.0007135637,0.00028958666,0.0000010801303,0.0015086043,0.0007697997,0.000014900759,0.00000553668,0.004759377,0.0002887287,0.9868835,0.004122085,0.0006432213],"about_ca_topic_score_codex":0.0000038955905,"about_ca_topic_score_gemma":0.0000082202405,"teacher_disagreement_score":0.08807678,"about_ca_system_score_codex":0.000102483165,"about_ca_system_score_gemma":0.0002840619,"threshold_uncertainty_score":0.99958575},"labels":[],"label_agreement":null},{"id":"W1540620236","doi":"10.2174/1874297101003010034","title":"Event Charts for the Analysis of Adverse Events in Longitudinal Studies: An Example from a Smoking Cessation Pharmacotherapy Trial","year":2010,"lang":"en","type":"article","venue":"The Open Epidemiology Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute on Alcohol Abuse and Alcoholism; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Dropout (neural networks); Covariate; Event (particle physics); Smoking cessation; Adverse effect; Event data; Chart; Medicine; Psychology; Statistics; Computer science; Internal medicine; Mathematics; Machine learning","score_opus":0.8723662049186112,"score_gpt":0.6792315876680085,"score_spread":0.19313461725060266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1540620236","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81836575,0.00020400214,0.17559431,0.0018264627,0.0022006787,0.0017260519,0.000057516972,0.000007156399,0.000018052835],"genre_scores_gemma":[0.82843286,0.0006524997,0.16872275,0.0006372498,0.0012452826,0.00025293767,0.000004821033,0.000025722704,0.000025854575],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9900251,0.0066991462,0.0023338269,0.00035545768,0.00022601122,0.00036046462],"domain_scores_gemma":[0.76207703,0.23501787,0.0019951623,0.00060584827,0.00020678248,0.00009729889],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.068522595,0.00018915725,0.001585363,0.00013149479,0.0003069937,0.000007904968,0.0012982953,0.00015972611,0.0007323299],"category_scores_gemma":[0.08467561,0.00009627129,0.00041524807,0.00034547097,0.00028294534,0.00017654357,0.00017446661,0.0008586606,7.852761e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.1738383,0.004579924,0.39105648,0.00011317989,0.05881274,0.000025255373,0.020628588,0.009718956,0.002870594,0.15305118,0.0042764843,0.1810283],"study_design_scores_gemma":[0.021038782,0.00027676823,0.03460226,0.000043077733,0.0026417398,0.000004708134,0.0006938092,0.0079933815,0.000083788684,0.93232393,0.00017010584,0.0001276341],"about_ca_topic_score_codex":0.00057087984,"about_ca_topic_score_gemma":0.0007733525,"teacher_disagreement_score":0.77927274,"about_ca_system_score_codex":0.000055917306,"about_ca_system_score_gemma":0.00007661657,"threshold_uncertainty_score":0.959152},"labels":[],"label_agreement":null},{"id":"W1544773317","doi":"10.18433/j3zw2c","title":"Regulatory and Study Conditions for the Determination of Bioequivalence of Highly Variable Drugs","year":2009,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Confidence interval; Statistics; Interim; Interim analysis; Econometrics; Point estimation; Mathematics; Coefficient of variation; Medicine; Clinical trial; Internal medicine; Pharmacokinetics","score_opus":0.5561569704818745,"score_gpt":0.6313217930774202,"score_spread":0.07516482259554569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544773317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88901895,0.0008811689,0.10382701,0.0032935857,0.0009395981,0.0013788615,0.00008503399,0.000017229375,0.0005585333],"genre_scores_gemma":[0.8030279,0.00012091175,0.19652875,0.00015754571,0.00014319851,0.0000050810177,4.464749e-8,0.0000043636833,0.000012178474],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99705726,0.0005093194,0.0012919612,0.00017383945,0.0007515617,0.00021608736],"domain_scores_gemma":[0.96529514,0.033121206,0.0009006518,0.00011950487,0.0004175243,0.00014596371],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010319326,0.000120922974,0.0004755359,0.00011401383,0.00017303294,0.000030937434,0.0005133857,0.000032244927,0.00010217593],"category_scores_gemma":[0.013188088,0.00007280623,0.00012823803,0.00041531556,0.0009485631,0.00024289163,0.000051045667,0.00021499622,2.9116927e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012790948,0.0039635287,0.003195703,0.0004893231,0.00027075046,0.000012873848,0.0017604466,0.000057339286,0.21741635,0.35121113,0.0013561568,0.41898733],"study_design_scores_gemma":[0.0046910797,0.001981952,0.0019762067,0.00015285457,0.0012697548,0.000033063385,0.0008514007,0.013753953,0.14427374,0.829376,0.0014549446,0.00018508913],"about_ca_topic_score_codex":0.000002695242,"about_ca_topic_score_gemma":1.6255342e-7,"teacher_disagreement_score":0.47816485,"about_ca_system_score_codex":0.000021720549,"about_ca_system_score_gemma":0.00013830462,"threshold_uncertainty_score":0.9951242},"labels":[],"label_agreement":null},{"id":"W1564744230","doi":"10.1007/bf03261932","title":"Fundamentals of Population Pharmacokinetic Modelling","year":2012,"lang":"en","type":"review","venue":"Clinical Pharmacokinetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":116,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"","keywords":"Population; Pharmacokinetics; Context (archaeology); NONMEM; Physiologically based pharmacokinetic modelling; Terminology; Medicine; Computer science; Intensive care medicine; Pharmacology; Biology","score_opus":0.9077627310124843,"score_gpt":0.7051695231200288,"score_spread":0.2025932078924555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564744230","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016985472,0.9554203,0.03465593,0.000020241507,0.0056159175,0.002370764,0.00052411587,0.00017893821,0.001196795],"genre_scores_gemma":[0.00005284596,0.7303368,0.26613507,0.00010755526,0.0027526452,0.00008674423,0.000060042385,0.00023499156,0.00023329911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.983573,0.0045163305,0.009006326,0.0010402087,0.000977359,0.0008867279],"domain_scores_gemma":[0.90653527,0.08730275,0.0039990395,0.0011544361,0.00033382318,0.00067468366],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0091296015,0.0010401479,0.0072859363,0.00028411552,0.00007790951,0.000037766687,0.0011527186,0.001190355,0.0020107583],"category_scores_gemma":[0.019878281,0.00086326833,0.002544611,0.00067882746,0.0005040525,0.00009986925,0.0005312286,0.0020866562,0.000208625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004322931,0.00096473657,0.00001847271,0.023812026,0.00072098087,0.000007811625,0.000009380868,0.000023827539,5.503449e-7,0.0034122304,0.0023963081,0.96859044],"study_design_scores_gemma":[0.0012978602,0.00017009668,0.0000028616328,0.0063244146,0.016638463,0.000013445707,0.0000028773193,0.0011234215,0.0000067378332,0.10517152,0.86831796,0.0009303692],"about_ca_topic_score_codex":0.0000062787562,"about_ca_topic_score_gemma":1.8802426e-7,"teacher_disagreement_score":0.96766007,"about_ca_system_score_codex":0.00012762232,"about_ca_system_score_gemma":0.00012250197,"threshold_uncertainty_score":0.9993818},"labels":[],"label_agreement":null},{"id":"W156660833","doi":"10.1007/978-3-7908-2693-7_6","title":"Optimal Adaptive Designs in Phase III Clinical Trials for Continuous Responses with Covariates","year":2004,"lang":"en","type":"book-chapter","venue":"Contributions to statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Covariate; Limiting; Adaptive design; Phase (matter); Optimal design; Binary number; Mathematical optimization; Computer science; Clinical trial; Mathematics; Statistics; Medicine; Engineering; Arithmetic","score_opus":0.6744937956957335,"score_gpt":0.619896906355848,"score_spread":0.05459688933988549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W156660833","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017421571,0.00010152757,0.85643154,0.00038136434,0.0007656088,0.0074422127,0.13227862,0.00013380131,0.00244789],"genre_scores_gemma":[0.00068538723,0.000104857114,0.9736857,0.0002772405,0.0009108314,0.00081930653,0.00037732202,0.00021666873,0.022922726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98720276,0.0029248374,0.0068308213,0.0013428403,0.0007231676,0.0009755608],"domain_scores_gemma":[0.685891,0.30872566,0.002006178,0.00080635835,0.00201597,0.00055488676],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.028328778,0.00095081504,0.005974613,0.00042999262,0.00025533084,0.00014450736,0.00056830916,0.0012855585,0.0008231008],"category_scores_gemma":[0.5532296,0.00081507553,0.0005792704,0.00017282585,0.00081458536,0.00006225302,0.00016804606,0.0013466624,0.00008887927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020344226,0.00067401084,0.0000031815368,0.00008986093,0.0008131989,0.00025672343,0.00006732328,0.000057085028,0.000008397648,0.9493908,0.01750382,0.0107913185],"study_design_scores_gemma":[0.028329154,0.0061895032,0.000012207788,0.0011098968,0.002375674,0.000013890154,0.000032632463,0.0004301053,0.000063271065,0.94717944,0.013272679,0.0009915531],"about_ca_topic_score_codex":0.000021491589,"about_ca_topic_score_gemma":0.000064321684,"teacher_disagreement_score":0.5249008,"about_ca_system_score_codex":0.0007410724,"about_ca_system_score_gemma":0.0022498746,"threshold_uncertainty_score":0.99943},"labels":[],"label_agreement":null},{"id":"W1569677164","doi":"10.18433/j3sw36","title":"Random Allocation in Controlled Clinical Trials: A Review","year":2014,"lang":"en","type":"review","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Keele University","keywords":"Random assignment; Computer science; Optimal allocation; Sample size determination; Strengths and weaknesses; Operations research; Statistics; Mathematics; Psychology; Mathematical optimization","score_opus":0.9235310171550787,"score_gpt":0.7794690731806396,"score_spread":0.14406194397443906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569677164","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019451072,0.9789399,0.010278339,0.0016412386,0.0040068356,0.0041677775,0.000022385182,0.000030036104,0.0009115475],"genre_scores_gemma":[0.000007225983,0.9243115,0.07091224,0.0015764548,0.0029559536,0.00013458036,9.3043195e-7,0.000052585594,0.00004848133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.90702844,0.06724838,0.021735772,0.00086516805,0.0022706564,0.0008516105],"domain_scores_gemma":[0.43478242,0.5483637,0.014471597,0.00053610996,0.00067575637,0.0011704129],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35115823,0.00082597084,0.020783665,0.00058009155,0.00013155086,0.00016420771,0.0022957246,0.00040048332,0.0017679284],"category_scores_gemma":[0.63125813,0.0004625215,0.0056707123,0.0015767274,0.0011703836,0.00028548023,0.0002306263,0.0034457755,0.00009022999],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008302915,0.00061823905,0.000007191396,0.024111744,0.0004965398,0.00006452228,0.000005719844,5.8481635e-7,7.9317294e-7,0.0025369783,0.00809052,0.96323687],"study_design_scores_gemma":[0.02081279,0.0002727683,2.3595997e-7,0.05510323,0.010471913,0.00014742221,0.0000035417536,0.00057167956,0.0000026511989,0.029973721,0.8821975,0.0004425323],"about_ca_topic_score_codex":0.000002814166,"about_ca_topic_score_gemma":9.26627e-7,"teacher_disagreement_score":0.96279436,"about_ca_system_score_codex":0.0002004516,"about_ca_system_score_gemma":0.0017474836,"threshold_uncertainty_score":0.9997826},"labels":[],"label_agreement":null},{"id":"W1569938899","doi":"10.1002/pds.2324","title":"Challenges in the design and analysis of sequentially monitored postmarket safety surveillance evaluations using electronic observational health care data","year":2012,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centers for Disease Control and Prevention; Hamilton Health Sciences Foundation; U.S. Department of Health and Human Services","keywords":"Observational study; Medicine; Interim analysis; Type I and type II errors; Confounding; Interim; Sample size determination; Pharmacoepidemiology; Patient safety; Population; Randomized controlled trial; Research design; Health care; Clinical study design; Clinical trial; Statistics; Data mining; Computer science; Internal medicine; Environmental health","score_opus":0.8308158335019783,"score_gpt":0.642883352138763,"score_spread":0.18793248136321528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569938899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056208905,0.06089255,0.85547024,0.022237316,0.0006549924,0.0022436094,0.0019648576,0.000055315897,0.0002722123],"genre_scores_gemma":[0.5833056,0.0141676,0.40146413,0.0007275838,0.0001583006,0.000019507524,0.00014176105,0.0000134815555,0.0000020184923],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9738587,0.023653593,0.0013521569,0.00043417184,0.00021878567,0.00048256735],"domain_scores_gemma":[0.8510298,0.14778063,0.0005135302,0.0004774023,0.00010444726,0.0000942046],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06567924,0.00017590384,0.0009898944,0.00011352496,0.00017422141,0.0000048506704,0.00033419294,0.00010551787,0.00004204273],"category_scores_gemma":[0.04499788,0.00012955179,0.00007165997,0.00037642138,0.00023061162,0.00013449388,0.00016922712,0.0003528004,3.6394158e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003125406,0.0006792438,0.5459879,0.00083739875,0.0043285727,0.0000026101359,0.009037561,0.0027213148,0.0002254475,0.29616585,0.0017032484,0.13518545],"study_design_scores_gemma":[0.0015062387,0.00006811932,0.7956821,0.000045835808,0.0014696823,0.000009593856,0.00070328265,0.082842305,0.000013818816,0.11666696,0.00071913894,0.0002729304],"about_ca_topic_score_codex":0.00008093452,"about_ca_topic_score_gemma":0.00010167016,"teacher_disagreement_score":0.5270967,"about_ca_system_score_codex":0.000082803934,"about_ca_system_score_gemma":0.00020671567,"threshold_uncertainty_score":0.9630465},"labels":[],"label_agreement":null},{"id":"W1572657933","doi":"10.1111/j.2044-8317.2011.02014.x","title":"Effect of non‐normality on test statistics for one‐way independent groups designs","year":2011,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; York University","funders":"","keywords":"Statistics; Normality; Estimator; Truncated mean; Type I and type II errors; Mathematics; Test statistic; Nominal level; Parametric statistics; Statistic; Statistical hypothesis testing; Normal distribution; Variance (accounting); Econometrics; Nonparametric statistics; Asymptotic distribution; Confidence interval","score_opus":0.4357774667779384,"score_gpt":0.5329337513487912,"score_spread":0.09715628457085279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1572657933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028451428,0.00004363883,0.9671117,0.00005918967,0.000349489,0.0007620359,0.0013045676,0.00001734825,0.0019006036],"genre_scores_gemma":[0.21534178,0.00007459577,0.7841613,0.00014768264,0.00015654271,0.00003278505,0.0000029546015,0.000047595964,0.00003473833],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99431026,0.0013699055,0.0027064723,0.00042305392,0.00065723713,0.0005330935],"domain_scores_gemma":[0.88555586,0.1124012,0.000915735,0.0002933421,0.0003873402,0.00044653128],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009202754,0.00033154697,0.0019648215,0.00012182138,0.000100401245,0.00004057855,0.00042054214,0.00036222025,0.0011151247],"category_scores_gemma":[0.13245636,0.0002834386,0.00022535802,0.00012353693,0.0008919203,0.00007332848,0.00008069435,0.00076653546,0.000017510632],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038759273,0.0045464817,0.00043405185,0.0027256452,0.00039004214,0.00055518595,0.00022097019,2.1508338e-7,0.0003245818,0.79152846,0.0075644185,0.187834],"study_design_scores_gemma":[0.004247807,0.012894307,0.00704985,0.0005756752,0.00054211356,0.0009003656,0.000020296597,0.00020272298,0.00089997455,0.97237486,0.00002164644,0.00027037048],"about_ca_topic_score_codex":0.000005134364,"about_ca_topic_score_gemma":0.0000028400498,"teacher_disagreement_score":0.18756361,"about_ca_system_score_codex":0.000031126565,"about_ca_system_score_gemma":0.000043762255,"threshold_uncertainty_score":0.9999618},"labels":[],"label_agreement":null},{"id":"W1575868305","doi":"10.1159/000316124","title":"Clinical Trials: Planning and Analysis","year":2010,"lang":"en","type":"review","venue":"Endocrine development","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Clinical trial; Clinical study design; Research design; Randomization; Subgroup analysis; Medicine; Medical physics; Intensive care medicine; Computer science; Management science; Statistics; Internal medicine; Mathematics; Engineering; Meta-analysis","score_opus":0.8931780125645961,"score_gpt":0.7301812478824343,"score_spread":0.16299676468216173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1575868305","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040891123,0.94373536,0.052166656,0.000021782418,0.0015688351,0.0012880339,0.00008417819,0.00013929403,0.0009917658],"genre_scores_gemma":[7.8114724e-8,0.5025349,0.4963326,0.000018331368,0.000444956,0.00015167649,0.000025291498,0.000047889265,0.00044425903],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9829848,0.0069955396,0.007826386,0.0010909929,0.0005585723,0.0005437046],"domain_scores_gemma":[0.7808848,0.21575391,0.0021359767,0.0007450804,0.00009002655,0.0003901868],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03538766,0.0007156968,0.011297764,0.00050958374,0.00012331484,0.00010188301,0.00051832356,0.00059420004,0.000651279],"category_scores_gemma":[0.33236185,0.0004942744,0.0016472941,0.0007439838,0.0001771414,0.000031020358,0.00050762587,0.0019465389,0.00008824357],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000093177405,0.00009589649,0.0000727105,0.003313558,0.0035175947,0.000082452156,0.00002548007,1.6500545e-8,1.2072719e-8,0.0028949385,0.0010152473,0.9889728],"study_design_scores_gemma":[0.00044486308,0.000021905775,0.000053499178,0.0027501457,0.012056658,0.000022632114,0.000004745675,0.000004150664,7.646169e-7,0.028944442,0.9551528,0.00054340996],"about_ca_topic_score_codex":0.0000010728936,"about_ca_topic_score_gemma":0.0000023447305,"teacher_disagreement_score":0.98842937,"about_ca_system_score_codex":0.000068251335,"about_ca_system_score_gemma":0.000490984,"threshold_uncertainty_score":0.9997509},"labels":[],"label_agreement":null},{"id":"W1576255678","doi":"10.1002/9780470571224.pse200","title":"Introduction to Clinical Trials","year":2010,"lang":"en","type":"other","venue":"Pharmaceutical Sciences Encyclopedia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Juravinski Cancer Centre","funders":"","keywords":"Clinical trial; Drug development; Drug trial; Disease; Medicine; Intensive care medicine; Drug; Pharmacology; Pathology","score_opus":0.7502160516990037,"score_gpt":0.6875786571471404,"score_spread":0.06263739455186335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1576255678","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021590604,0.0001799417,0.041869633,0.009952734,0.030892748,0.002401751,0.00021746426,0.0007335112,0.9137306],"genre_scores_gemma":[0.0000065740587,0.001126518,0.6745661,0.0013622561,0.052137505,0.00012920909,0.000002850865,0.0003313649,0.2703376],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9859483,0.00660665,0.0032554138,0.0018327368,0.0014003126,0.0009565908],"domain_scores_gemma":[0.87205654,0.12323289,0.001454843,0.0012748834,0.00013993961,0.0018408723],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.06433106,0.0005961728,0.002598661,0.00036898794,0.00015390663,0.00014502721,0.0014174017,0.0011809298,0.06646363],"category_scores_gemma":[0.52304983,0.0004292659,0.0006000653,0.0009477529,0.0015247627,0.00006522343,0.00044745367,0.0021401688,0.0027755243],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043130145,0.00020814687,0.00007605162,0.0000667494,0.0000622676,0.0000073593874,0.000009461082,1.2093606e-7,0.000023815948,0.038999308,0.76980686,0.1906967],"study_design_scores_gemma":[0.0004894256,0.00015902906,0.000019207011,0.00007009838,0.0003227805,0.0000047335125,0.000005825274,0.00004050502,0.00005348754,0.1884835,0.8098827,0.00046868625],"about_ca_topic_score_codex":0.000022902776,"about_ca_topic_score_gemma":0.000040032126,"teacher_disagreement_score":0.643393,"about_ca_system_score_codex":0.000043516404,"about_ca_system_score_gemma":0.00025876402,"threshold_uncertainty_score":0.99981594},"labels":[],"label_agreement":null},{"id":"W1586667517","doi":"10.48550/arxiv.1212.4966","title":"Combining p-values via averaging","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Research Promotion Foundation; European Commission","keywords":"Harmonic mean; Mathematics; Bonferroni correction; Scaling; Geometric mean; Applied mathematics; Statistics; Factor (programming language); Combinatorics; Algorithm; Computer science; Geometry","score_opus":0.6551768040700748,"score_gpt":0.4072740225850241,"score_spread":0.24790278148505074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586667517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111598484,0.000049008417,0.87155765,0.000049767616,0.0025504562,0.0005262656,0.000055672714,0.0004076118,0.013205093],"genre_scores_gemma":[0.80467546,0.000060614144,0.19337955,0.00008249787,0.00042203817,0.0000015578058,0.000005305529,0.00006769218,0.0013052883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964509,0.0011772043,0.0006442798,0.0009574988,0.00016778315,0.00060235034],"domain_scores_gemma":[0.97923297,0.018340856,0.00063963904,0.0012814847,0.00017166712,0.00033340135],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026772337,0.0004586411,0.0010509742,0.00016610972,0.00016804223,0.00005863335,0.0008998196,0.00050964806,0.0006597985],"category_scores_gemma":[0.011253988,0.0005074323,0.00041862685,0.0002739611,0.00028188096,0.00011907431,0.0017010055,0.0013629717,0.0002479908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015065892,0.0004450377,0.0045053842,0.00067936856,0.00053902325,0.00034359508,0.00041594412,0.0022413607,0.000049623417,0.9864549,0.0013661073,0.0028090014],"study_design_scores_gemma":[0.0006721314,0.000029002016,0.00029993392,0.0002703987,0.00053399894,0.0000042547244,0.000068641835,0.019526381,0.00015045378,0.9777645,0.00013443737,0.0005458768],"about_ca_topic_score_codex":0.000044106437,"about_ca_topic_score_gemma":0.0000029659338,"teacher_disagreement_score":0.69307697,"about_ca_system_score_codex":0.00022381428,"about_ca_system_score_gemma":0.00008829293,"threshold_uncertainty_score":0.99973774},"labels":[],"label_agreement":null},{"id":"W1591775948","doi":"10.1002/cjs.11184","title":"Adaptive clinical trial designs to detect interaction between treatment and a dichotomous biomarker","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Institutes of Health; National Science Foundation","keywords":"Biomarker; Covariate; Computer science; Clinical trial; Perspective (graphical); Data mining; Machine learning; Medicine; Artificial intelligence; Internal medicine","score_opus":0.7304746457778881,"score_gpt":0.5602635379820747,"score_spread":0.1702111077958134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591775948","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10165246,0.000035182024,0.8942242,0.00035202247,0.0015432544,0.0011761464,0.0007842836,0.00000993924,0.00022251019],"genre_scores_gemma":[0.20529625,0.000023328412,0.79377496,0.00012450483,0.00064726145,0.000021764237,0.000001401811,0.0000319725,0.00007856155],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963844,0.0010496163,0.0017566186,0.0002312419,0.00020778137,0.00037036496],"domain_scores_gemma":[0.95630616,0.04059553,0.00065834285,0.00021793222,0.0004537353,0.001768294],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022587061,0.00021775885,0.00087928824,0.00025249075,0.00010384444,0.00012909836,0.00018473549,0.0001778128,0.0004813298],"category_scores_gemma":[0.061502896,0.00017212363,0.00013367199,0.00015495822,0.00021138694,0.000096585136,0.000018335832,0.00034328166,0.000050776296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003204875,0.00008984703,0.0017149244,0.000025032565,0.0006346208,0.0002434019,0.00035819024,0.0000014047794,0.00002273381,0.005239084,0.03127478,0.9571911],"study_design_scores_gemma":[0.021373292,0.012276777,0.012543151,0.00018708754,0.00081443903,0.00008690004,0.00026722398,0.00025322015,0.000089439345,0.9474627,0.0042248336,0.00042092963],"about_ca_topic_score_codex":0.0016270693,"about_ca_topic_score_gemma":0.0027144582,"teacher_disagreement_score":0.9567702,"about_ca_system_score_codex":0.0003115798,"about_ca_system_score_gemma":0.00074292184,"threshold_uncertainty_score":0.9464025},"labels":[],"label_agreement":null},{"id":"W1594888675","doi":"10.1002/pds.2343","title":"The U.S. Food and Drug Administration's Mini‐Sentinel program: status and direction","year":2012,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":290,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hamilton Health Sciences Foundation; U.S. Department of Health and Human Services","keywords":"Medicine; Medical prescription; Food and drug administration; Pharmacy; Formulary; Mandate; Health care; Medical diagnosis; Medical emergency; Family medicine; Nursing","score_opus":0.2928198787070505,"score_gpt":0.5376139426936772,"score_spread":0.24479406398662673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594888675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91650385,0.01690138,0.0127624925,0.041233286,0.0035971466,0.002787192,0.00020500965,0.0005038694,0.005505766],"genre_scores_gemma":[0.8533343,0.007020317,0.13756338,0.00082996767,0.0007164751,0.00015351293,0.00000537003,0.000027397835,0.00034927015],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99448574,0.0035910816,0.00086532545,0.00036350088,0.00011092788,0.0005834334],"domain_scores_gemma":[0.9076727,0.091441415,0.00030286337,0.00018369904,0.000051633546,0.00034767212],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0126104625,0.00022454288,0.00054938724,0.000029437935,0.00048012563,0.000028957244,0.000081586986,0.00012524669,0.00003953691],"category_scores_gemma":[0.04249807,0.00014974273,0.00006051299,0.000087155044,0.00067992136,0.00012558606,0.00013432736,0.000403232,0.000003949852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012741077,0.0005363564,0.20458525,0.00033594714,0.00042719487,0.0000028131522,0.00089781027,2.4969782e-7,0.00010470939,0.3255642,0.03266035,0.433611],"study_design_scores_gemma":[0.0028272027,0.00019774855,0.14632848,0.00004951273,0.00055491185,0.00006258768,0.00036043706,0.000580503,0.00053393363,0.67551947,0.17248087,0.00050436234],"about_ca_topic_score_codex":0.000012273112,"about_ca_topic_score_gemma":0.000015656826,"teacher_disagreement_score":0.43310663,"about_ca_system_score_codex":0.000015937665,"about_ca_system_score_gemma":0.000027380069,"threshold_uncertainty_score":0.96556735},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1594902063","doi":"10.1007/s00280-002-0566-8","title":"Phase I and pharmacokinetic study of anhydrovinblastine every 3 weeks in patients with refractory solid tumors","year":2003,"lang":"en","type":"article","venue":"Cancer Chemotherapy and Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Air (Canada)","funders":"National Cancer Institute","keywords":"Pharmacokinetics; Refractory (planetary science); Medicine; Solid tumor; Maximum tolerated dose; Internal medicine; Oncology; Pharmacology; Cancer; Biology","score_opus":0.1627209557731493,"score_gpt":0.5160638178940202,"score_spread":0.35334286212087096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1594902063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99802923,0.00021452659,0.00032142788,0.00005205526,0.0002731475,0.000896668,0.000038821094,0.000017161577,0.00015694812],"genre_scores_gemma":[0.9925454,0.00027339047,0.00644717,0.0004868675,0.00007926589,0.00009265683,6.2413176e-7,0.00003393119,0.000040662333],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9980295,0.0006034466,0.0005946413,0.0003632787,0.00015757454,0.00025161417],"domain_scores_gemma":[0.9955466,0.0038466912,0.000281981,0.00012634866,0.00007739487,0.00012100307],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006526996,0.00021036662,0.0006903749,0.00008945717,0.00003640992,0.0000058135347,0.00009010993,0.0000811807,0.00094959186],"category_scores_gemma":[0.0005203472,0.00016853932,0.000021848446,0.0001784402,0.00022564543,0.00005046762,0.000022675842,0.00026788822,3.3393474e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.046779983,0.08101133,0.4288191,0.0025519102,0.0029196115,0.00016080675,0.011026638,0.000084809435,0.09619059,0.0012583118,0.0062841848,0.32291272],"study_design_scores_gemma":[0.5611614,0.048391413,0.076582566,0.00059192476,0.0019992138,0.000016200402,0.0010780508,0.0011105682,0.22525224,0.0754693,0.005862656,0.0024844818],"about_ca_topic_score_codex":0.000011985294,"about_ca_topic_score_gemma":0.000006024393,"teacher_disagreement_score":0.5143814,"about_ca_system_score_codex":0.000035041507,"about_ca_system_score_gemma":0.000054805136,"threshold_uncertainty_score":0.9999637},"labels":[],"label_agreement":null},{"id":"W1605484689","doi":"10.1002/9781118763070.ch7","title":"Statistical analysis of recurrent adverse events","year":2014,"lang":"en","type":"other","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Adverse effect; Notation; Event (particle physics); Computer science; Sample size determination; Regression; Clinical trial; Statistics; Regression analysis; Medicine; Intensive care medicine; Mathematics; Machine learning; Internal medicine","score_opus":0.47492046014912465,"score_gpt":0.5935420984753306,"score_spread":0.11862163832620592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605484689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040661544,0.000011457056,0.61815053,0.000012042048,0.0004880172,0.00026854622,0.0010632933,0.000091295304,0.37991077],"genre_scores_gemma":[0.00005930655,0.00003066274,0.78408426,0.000037641235,0.00017569611,0.00001564422,0.000028240822,0.0002179527,0.21535057],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964774,0.0009839128,0.0012270943,0.000463599,0.00060213765,0.00024585548],"domain_scores_gemma":[0.9614373,0.036712643,0.0007955903,0.00082053436,0.000066430825,0.00016750123],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018948711,0.00029166893,0.002097373,0.00048250082,0.00001011385,0.0000021783085,0.00032273663,0.00043386576,0.08254009],"category_scores_gemma":[0.06473707,0.00022412388,0.00043991662,0.0004811449,0.00015157864,0.0000053656663,0.00011187398,0.00025012312,0.0002680755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038423183,0.0002715367,0.0003070155,0.00037008928,0.0037484155,0.0000032190446,0.0000065318245,5.273274e-7,7.183524e-7,0.422562,0.56478107,0.007910412],"study_design_scores_gemma":[0.00080074085,0.00019639851,0.0009336776,0.0003550399,0.01413598,2.8806375e-7,0.000009706603,0.0006856079,0.0000085904,0.89997905,0.082384646,0.00051025726],"about_ca_topic_score_codex":0.000043965712,"about_ca_topic_score_gemma":0.00008581489,"teacher_disagreement_score":0.48239645,"about_ca_system_score_codex":0.000028464765,"about_ca_system_score_gemma":0.0000366702,"threshold_uncertainty_score":0.94314104},"labels":[],"label_agreement":null},{"id":"W1605485057","doi":"","title":"Introduction des effets fixes dans un modèle binomial négatif : application à la consommation de médicaments au Canada","year":2010,"lang":"fr","type":"article","venue":"Archipelago (Université du Québec à Montréal)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Forestry; Humanities; Political science; Physics; Mathematics; Geography; Philosophy","score_opus":0.036112660470002576,"score_gpt":0.28679458474627745,"score_spread":0.2506819242762749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605485057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65925837,0.00015476007,0.33074433,0.006776316,0.0011747184,0.00060855725,0.00014817266,0.0000817927,0.0010530065],"genre_scores_gemma":[0.78094155,0.000117922915,0.21668324,0.00013305359,0.0015017044,0.000034504083,0.000021656915,0.00006769434,0.0004986735],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99565864,0.0015634932,0.0008100972,0.0007052233,0.0005447377,0.00071783207],"domain_scores_gemma":[0.98088634,0.016868658,0.00059905177,0.0008706127,0.00022126312,0.00055408874],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020301815,0.00043951487,0.00068027526,0.0001392859,0.0008316362,0.000068985144,0.0006177726,0.0004277783,0.0007338911],"category_scores_gemma":[0.014164966,0.00050215353,0.00019827318,0.0003791679,0.0013000101,0.00028542607,0.00028515054,0.0008881386,0.00008969778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007121584,0.0012595248,0.011773977,0.00068141386,0.0006439423,0.00016102612,0.04456297,0.0006284644,0.020370862,0.34474236,0.009082759,0.5653806],"study_design_scores_gemma":[0.007550494,0.00045831178,0.07124735,0.00029880463,0.0019643381,0.0003626415,0.010248148,0.048934896,0.009908418,0.7982795,0.049126554,0.001620528],"about_ca_topic_score_codex":0.9542184,"about_ca_topic_score_gemma":0.989084,"teacher_disagreement_score":0.56376004,"about_ca_system_score_codex":0.0018447394,"about_ca_system_score_gemma":0.0027923326,"threshold_uncertainty_score":0.999743},"labels":[],"label_agreement":null},{"id":"W163807921","doi":"10.1007/978-3-319-00035-0_27","title":"A New Effective Method for Elimination of Systematic Error in Experimental High-Throughput Screening","year":2013,"lang":"en","type":"book-chapter","venue":"Studies in classification, data analysis, and knowledge organization","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Throughput; Systematic error; Computer science; Reliability engineering; High-throughput screening; Computational biology; Biology; Statistics; Engineering; Mathematics; Bioinformatics; Telecommunications","score_opus":0.5789561825739972,"score_gpt":0.5719166883885102,"score_spread":0.007039494185486994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W163807921","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040206472,0.0033126357,0.99123657,0.00010225443,0.00031158977,0.0032904064,0.00034401112,0.000039687115,0.0013226527],"genre_scores_gemma":[0.011377597,0.001353761,0.9779702,0.000012681291,0.00029317648,0.00026939702,0.0009491975,0.000113416434,0.0076606013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99519676,0.0007978174,0.0024067601,0.0010565912,0.00033301362,0.00020907639],"domain_scores_gemma":[0.9700811,0.025766976,0.0016417911,0.0012144557,0.0012227057,0.000072989846],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0043719555,0.0004382953,0.0024776321,0.0008386019,0.00011137119,0.000044116703,0.0004800739,0.00041685105,0.000114932336],"category_scores_gemma":[0.05903345,0.00039634766,0.000111558664,0.0010566924,0.00021452698,0.00022244023,0.00043900154,0.00023221067,0.000008649955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068010944,0.00030018057,0.00065893977,0.021613907,0.004723,0.0000010782403,0.004382858,0.000007718523,0.0001914588,0.9541776,0.003963697,0.009911538],"study_design_scores_gemma":[0.0039917687,0.00033838526,0.0062249997,0.013539287,0.019020693,0.0000029908235,0.0039880574,0.02784423,0.001355371,0.9219104,0.0003321405,0.0014516612],"about_ca_topic_score_codex":0.00008041212,"about_ca_topic_score_gemma":0.0006036155,"teacher_disagreement_score":0.054661494,"about_ca_system_score_codex":0.00028156547,"about_ca_system_score_gemma":0.00011730479,"threshold_uncertainty_score":0.99984884},"labels":[],"label_agreement":null},{"id":"W1644936210","doi":"10.1002/bdd.1951","title":"Impact of sampling time deviations on the prediction of the area under the curve using regression limited sampling strategies","year":2015,"lang":"en","type":"article","venue":"Biopharmaceutics & Drug Disposition","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Pfizer","keywords":"Sampling (signal processing); Statistics; Mathematics; Regression analysis; Nomogram; Regression; Time point; Sensitivity (control systems); Standard deviation; Computer science; Medicine; Engineering","score_opus":0.7036683677822868,"score_gpt":0.57427740614426,"score_spread":0.12939096163802677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1644936210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8759945,0.0000740674,0.1213634,0.0005904108,0.000471886,0.0008192272,0.00044171556,0.000045501703,0.00019929747],"genre_scores_gemma":[0.9757516,0.00002918512,0.023892885,0.00007525225,0.00017887302,0.000015945227,0.000013087778,0.000030390196,0.000012803456],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681836,0.0012914786,0.00083597924,0.00022247649,0.0006075855,0.00022412662],"domain_scores_gemma":[0.98277146,0.015359499,0.0008071454,0.0005749093,0.000403362,0.000083608786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028144522,0.0002172204,0.00033922622,0.00006556337,0.00028333245,0.00006510303,0.00035070165,0.00012657617,0.000049074413],"category_scores_gemma":[0.006271697,0.00010065793,0.00027063236,0.0004849703,0.00029652624,0.000115007395,0.000117936215,0.00038586417,0.000004073475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025340181,0.0026226311,0.007952243,0.0005063019,0.0016928929,0.0000020395219,0.00623905,0.08675795,0.5812428,0.30315742,0.0025354286,0.0047572064],"study_design_scores_gemma":[0.0017269757,0.00027177713,0.028102094,0.0016046626,0.0014097614,0.000010035114,0.0023455883,0.15586595,0.04148693,0.7667965,0.00003908737,0.00034062206],"about_ca_topic_score_codex":0.000028431537,"about_ca_topic_score_gemma":0.0000017162566,"teacher_disagreement_score":0.5397559,"about_ca_system_score_codex":0.00019953684,"about_ca_system_score_gemma":0.00019923584,"threshold_uncertainty_score":0.750826},"labels":[],"label_agreement":null},{"id":"W164573124","doi":"10.1007/978-1-4939-1471-5_7","title":"Testing for Ordered Alternatives","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Block (permutation group theory); Mathematics; Combinatorics; Distribution (mathematics); Independent and identically distributed random variables; Statistics; Mathematical analysis; Random variable","score_opus":0.7992050603005366,"score_gpt":0.597239062039237,"score_spread":0.20196599826129957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W164573124","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.4403444e-7,0.0000087676635,0.4708128,0.00007526156,0.00038251452,0.0005390747,0.00008476809,0.00011593221,0.5279803],"genre_scores_gemma":[0.000007295181,0.0000022821598,0.57461655,0.000146103,0.0007735254,0.000029630204,0.0000019133283,0.00008514005,0.42433757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99785733,0.00008910059,0.0010292507,0.0004908901,0.00028727602,0.00024615528],"domain_scores_gemma":[0.80693436,0.19175461,0.00050437567,0.00042587443,0.00028565043,0.00009513733],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021130156,0.00034599414,0.0010826474,0.00006273277,0.000059307982,0.00003671929,0.00032453518,0.00040737513,0.0017652857],"category_scores_gemma":[0.24028516,0.0002740956,0.0002487014,0.000014536602,0.00014372607,0.000012416204,0.00011540196,0.00029940283,0.000126925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020529918,0.000009536993,0.000001182717,0.00022998397,0.0000991595,0.0000017582457,0.00000554757,7.701314e-8,0.000011593654,0.91503507,0.009701359,0.07488419],"study_design_scores_gemma":[0.0005206442,0.00022279519,0.0000016149197,0.00030258333,0.00016455553,0.0000017835755,0.0000013152701,0.00018305481,0.00005649581,0.9316505,0.066575184,0.00031946923],"about_ca_topic_score_codex":0.0000020668374,"about_ca_topic_score_gemma":0.000002375676,"teacher_disagreement_score":0.23817213,"about_ca_system_score_codex":0.000031484567,"about_ca_system_score_gemma":0.00004474686,"threshold_uncertainty_score":0.99997115},"labels":[],"label_agreement":null},{"id":"W1647270943","doi":"10.1515/1544-6115.1807","title":"Estimators of the local false discovery rate designed for small numbers of tests","year":2012,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; False discovery rate; Bayes' theorem; Parametric statistics; Feature (linguistics); Negative binomial distribution; Binomial distribution; Prior probability","score_opus":0.1852363415391905,"score_gpt":0.5019122555711589,"score_spread":0.31667591403196843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1647270943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07222192,0.00016120545,0.9260218,0.000055287226,0.000062077605,0.0008882987,0.0005220931,0.0000050676117,0.00006223723],"genre_scores_gemma":[0.46389118,0.000015506455,0.53587705,0.000033420085,0.000012067531,0.0001501528,0.00000583561,0.000011143916,0.0000036432843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838763,0.0003891768,0.0006805419,0.0002209939,0.000068354544,0.00025331756],"domain_scores_gemma":[0.98246074,0.016806178,0.00021159781,0.000353795,0.00008454233,0.00008316676],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010257534,0.00013041182,0.00040541176,0.00003623965,0.000034559373,0.0000050542308,0.00019766025,0.00014612709,0.0000061980845],"category_scores_gemma":[0.0093452465,0.000092663955,0.00006359824,0.00015707812,0.00085997273,0.0000079533975,0.00011915104,0.000095452815,4.2955585e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030417901,0.00018769395,0.0065938607,0.00012315229,0.000029223316,1.2252258e-7,0.000027119875,0.000008707602,0.017254034,0.9667095,0.000022066015,0.009014116],"study_design_scores_gemma":[0.0004229254,0.00011035614,0.00599828,0.000017479919,0.00009973707,0.0000011039228,0.000029689698,0.00032985487,0.028954972,0.96376187,0.0001672416,0.00010648917],"about_ca_topic_score_codex":0.000011385034,"about_ca_topic_score_gemma":0.000009012882,"teacher_disagreement_score":0.39166927,"about_ca_system_score_codex":0.0000139072345,"about_ca_system_score_gemma":0.000046514677,"threshold_uncertainty_score":0.9989995},"labels":[],"label_agreement":null},{"id":"W1729931698","doi":"10.1515/ijb-2016-0004","title":"Multiple Comparisons Using Composite Likelihood in Clustered Data","year":2016,"lang":"en","type":"preprint","venue":"The International Journal of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Quasi-maximum likelihood; Statistics; Monte Carlo method; Computer science; Gaussian; Mathematics; Algorithm; Data mining; Econometrics; Expectation–maximization algorithm; Maximum likelihood","score_opus":0.683109364844231,"score_gpt":0.5842110733642264,"score_spread":0.09889829148000462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1729931698","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013832651,0.0001585629,0.9670631,0.003353422,0.0073250397,0.00039371278,0.007702887,0.000016987296,0.0001535843],"genre_scores_gemma":[0.1689982,0.00015300946,0.8289876,0.00025679704,0.0015086511,0.0000021943135,0.000028645461,0.000050230494,0.000014685202],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99396765,0.0011331004,0.0028317503,0.000381004,0.0013663548,0.0003201285],"domain_scores_gemma":[0.93999857,0.054774296,0.002995412,0.001084937,0.0010014239,0.00014537564],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058995956,0.0003384636,0.0010793038,0.000267493,0.000055370547,0.00019456251,0.0046634264,0.00027673534,0.00008921746],"category_scores_gemma":[0.06606848,0.00021541031,0.00018617438,0.00009295625,0.00030381983,0.00009898094,0.003546551,0.0014221886,0.000011087861],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014806869,0.008761457,0.05696252,0.002059965,0.018001698,0.0060235383,0.0032860585,0.00358985,0.014686959,0.21382248,0.43659326,0.22140533],"study_design_scores_gemma":[0.0022747752,0.00006354955,0.0014933135,0.0019340119,0.00036462027,0.00014855122,0.00007520342,0.038408656,0.00033709925,0.9538571,0.0007386048,0.00030451364],"about_ca_topic_score_codex":0.00006540492,"about_ca_topic_score_gemma":0.00008364357,"teacher_disagreement_score":0.74003464,"about_ca_system_score_codex":0.0003466513,"about_ca_system_score_gemma":0.00049556326,"threshold_uncertainty_score":0.94179845},"labels":[],"label_agreement":null},{"id":"W1736389262","doi":"10.1002/0470013192.bsa420","title":"Multiple Comparison Procedures","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistics in Behavioral Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Manitoba","funders":"","keywords":"Pairwise comparison; Variance (accounting); Homogeneity (statistics); Statistics; Analysis of variance; Normality; Multiple comparisons problem; Mathematics; Simple (philosophy); Variance components; Computer science; Econometrics","score_opus":0.3089900183529948,"score_gpt":0.5481415482586365,"score_spread":0.2391515299056417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1736389262","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001339521,0.0003431769,0.14073196,0.000047985362,0.0036124808,0.0027403734,0.005136548,0.0003610463,0.8456869],"genre_scores_gemma":[0.0017292732,0.0003543864,0.9320994,0.0000128711745,0.00032982655,0.00006152257,0.000008630746,0.00024173745,0.06516235],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953458,0.00021107522,0.0015900764,0.0008025909,0.001399736,0.00065076625],"domain_scores_gemma":[0.98955387,0.008238949,0.0010841991,0.00071173033,0.000166101,0.00024514642],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002154943,0.00041792364,0.0012732195,0.0005446664,0.000059029564,0.00003617278,0.0011906282,0.00037118618,0.0028479958],"category_scores_gemma":[0.04975908,0.00038383887,0.000072430754,0.00083065993,0.0019669568,0.000069133755,0.0002893975,0.00061435124,0.000053604286],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073322735,0.00316644,0.041188978,0.0009981191,0.000020107236,0.00007207987,0.00071838574,0.000007022379,0.00013225625,0.12888178,0.6451008,0.1796407],"study_design_scores_gemma":[0.004395514,0.0012300917,0.025059452,0.0038165366,0.0006833976,0.0000120412315,0.00044898718,0.001205105,0.0005042876,0.72823566,0.23090357,0.0035053452],"about_ca_topic_score_codex":0.00048762307,"about_ca_topic_score_gemma":0.0026691644,"teacher_disagreement_score":0.7913674,"about_ca_system_score_codex":0.00016070865,"about_ca_system_score_gemma":0.00058705884,"threshold_uncertainty_score":0.99986136},"labels":[],"label_agreement":null},{"id":"W1756140406","doi":"10.2217/17520363.1.3.387","title":"Biomarkers and the Design of Clinical Trials in Cancer","year":2007,"lang":"en","type":"article","venue":"Biomarkers in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Juravinski Cancer Centre","funders":"","keywords":"Medicine; Clinical trial; Biomarker; Biomarker discovery; Drug development; Disease; Clinical study design; Intensive care medicine; Bioinformatics; Pathology; Drug; Pharmacology; Proteomics","score_opus":0.8302961066093231,"score_gpt":0.6900401105416882,"score_spread":0.14025599606763484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1756140406","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1078992,0.007886132,0.8441472,0.017480545,0.007078039,0.008184321,0.000050114195,0.00009033082,0.007184113],"genre_scores_gemma":[0.20453513,0.0031238543,0.790491,0.00084508717,0.0008038194,0.000100860416,8.425501e-7,0.000047089507,0.00005234214],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9678186,0.02095516,0.009191789,0.0006478887,0.0008150332,0.00057152595],"domain_scores_gemma":[0.48597535,0.5121775,0.0011850165,0.00043131597,0.00007920487,0.00015158649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32928035,0.00020959995,0.0027166817,0.00028580695,0.00002487513,0.0000052315013,0.00031549344,0.0003121904,0.00025029332],"category_scores_gemma":[0.66370136,0.000111867084,0.00016322845,0.0007286126,0.0024593875,0.000027710577,0.00008393066,0.00036505275,9.669368e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04364918,0.00069174584,0.091731206,0.0006557877,0.0016462624,0.00016439812,0.0012396694,0.0000027236879,0.0013497618,0.067962006,0.023430195,0.76747704],"study_design_scores_gemma":[0.038420115,0.0004461165,0.07014833,0.001699951,0.00044619126,0.000006452958,0.0010411604,0.0014792848,0.00038778243,0.8851903,0.00046128238,0.0002730327],"about_ca_topic_score_codex":0.00040284544,"about_ca_topic_score_gemma":0.0001242673,"teacher_disagreement_score":0.8172283,"about_ca_system_score_codex":0.000047430156,"about_ca_system_score_gemma":0.00009540975,"threshold_uncertainty_score":0.9061716},"labels":[],"label_agreement":null},{"id":"W176211925","doi":"10.1007/978-1-4939-2428-8_9","title":"Randomized Controlled Trials 1: Design","year":2015,"lang":"en","type":"article","venue":"Methods in molecular biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.7531881906213166,"score_gpt":0.6760882135058548,"score_spread":0.07709997711546179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W176211925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010519196,0.000799819,0.9888135,0.00050493435,0.0014916485,0.004103062,0.000007212576,0.000094945055,0.004079686],"genre_scores_gemma":[0.00016014933,0.000043684347,0.9977966,0.00055114407,0.00017150801,0.0010543467,0.0000012404615,0.000046684498,0.0001746747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.72110456,0.27249956,0.0048623406,0.000670625,0.00028193608,0.00058094226],"domain_scores_gemma":[0.36499384,0.632376,0.0013420327,0.0007556595,0.00026392244,0.00026851543],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35545772,0.0003739155,0.010612626,0.00029301873,0.000024829013,0.000029622639,0.00046426165,0.00058777584,0.00022364767],"category_scores_gemma":[0.9395638,0.0002315723,0.0011938004,0.00034292316,0.00053405185,0.00001988912,0.00015374034,0.00045882945,0.00002241362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.18188792,0.00020421755,0.000010212792,0.000021303698,0.00078495615,0.000059149213,0.000109381246,0.00003392021,0.020725114,0.77272004,0.00044325955,0.023000548],"study_design_scores_gemma":[0.30575845,0.00012214224,1.9377003e-7,0.000019352829,0.00035723305,0.0000043221035,0.00001673819,0.0012090715,0.012314505,0.67988205,0.00014154622,0.00017437027],"about_ca_topic_score_codex":0.000012360794,"about_ca_topic_score_gemma":5.600662e-7,"teacher_disagreement_score":0.5841061,"about_ca_system_score_codex":0.000071077106,"about_ca_system_score_gemma":0.00018067406,"threshold_uncertainty_score":0.9443244},"labels":[],"label_agreement":null},{"id":"W177060379","doi":"10.1007/978-1-4939-1471-5_4","title":"Testing for Randomness, Agreement, and Interaction","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Randomness; Ranking (information retrieval); Pairwise comparison; Statistic; Rank (graph theory); Point (geometry); Mathematics; Space (punctuation); Statistics; Combinatorics; Computer science; Artificial intelligence; Geometry","score_opus":0.721261744871989,"score_gpt":0.5754645987678396,"score_spread":0.1457971461041494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W177060379","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026448934,0.000013416915,0.49258497,0.00007065094,0.00051087036,0.0007010218,0.00003020296,0.000054828688,0.5060314],"genre_scores_gemma":[0.00004508188,0.000008673671,0.7178565,0.00013473813,0.00063975324,0.00003856937,0.0000025825518,0.000048902726,0.28122514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99842227,0.00007571481,0.00082594214,0.00036066642,0.00016602692,0.00014936858],"domain_scores_gemma":[0.86400175,0.13509278,0.0004357715,0.0002423927,0.00015774839,0.00006953926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023488265,0.00024494465,0.0008319239,0.000052246345,0.000057829147,0.000042888478,0.00009604587,0.00029562422,0.0009129218],"category_scores_gemma":[0.108216174,0.00019284477,0.00012962923,0.00000911361,0.00008628897,0.00002017411,0.000079003956,0.00023543651,0.000039066883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121238714,0.000007211309,0.0000026311516,0.00036285634,0.00007353023,7.554802e-7,0.000004479246,3.0412746e-8,0.000015063657,0.86584264,0.007511893,0.12605764],"study_design_scores_gemma":[0.0017103133,0.00016474156,0.0000021351689,0.0003946947,0.00027255004,0.0000040271084,0.0000024435558,0.00019682331,0.000029883404,0.9445899,0.052418042,0.00021444204],"about_ca_topic_score_codex":0.0000024114236,"about_ca_topic_score_gemma":0.000003925162,"teacher_disagreement_score":0.22527158,"about_ca_system_score_codex":0.000025448573,"about_ca_system_score_gemma":0.000016359381,"threshold_uncertainty_score":0.99958533},"labels":[],"label_agreement":null},{"id":"W177904137","doi":"10.1007/s12630-014-0132-y","title":"Understanding non-inferiority trials: an introduction","year":2014,"lang":"en","type":"letter","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health Research Institute; University of Calgary; Vancouver Coastal Health","funders":"","keywords":"Psychology","score_opus":0.4482066136243411,"score_gpt":0.43541797513783304,"score_spread":0.012788638486508075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W177904137","genre_codex":"commentary","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052992105,0.00025329093,0.041544344,0.9393445,0.011656066,0.0010772524,0.00011077181,0.000056153578,0.0006584055],"genre_scores_gemma":[0.03379249,0.00028972843,0.33351886,0.12879665,0.4989842,0.000041435233,0.00012198148,0.001746443,0.0027082132],"study_design_codex":"not_applicable","study_design_gemma":"case_report","domain_scores_codex":[0.98096037,0.008684537,0.0057912935,0.0007938244,0.0017319556,0.002038043],"domain_scores_gemma":[0.9578417,0.024418298,0.0086832745,0.0014063532,0.002457346,0.005193009],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04945776,0.0011518156,0.0050800378,0.002142533,0.00093973195,0.0011751219,0.002154925,0.002561793,0.0014209877],"category_scores_gemma":[0.11532794,0.0009926108,0.0015517658,0.0006862526,0.00076750555,0.00067203963,0.000020590061,0.009713929,0.000027087317],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000105563304,0.000023064307,0.00005831524,0.00018491643,0.0003168058,0.31389424,0.00027017907,0.0000151103895,0.0000022984027,0.003190989,0.6810292,0.0009093369],"study_design_scores_gemma":[0.0009124421,0.0011839035,0.000020725374,0.00038386873,0.00096285524,0.51962394,0.00020240099,0.000029629142,0.000008013167,0.24937953,0.22658621,0.0007064891],"about_ca_topic_score_codex":0.0018214908,"about_ca_topic_score_gemma":0.0040385183,"teacher_disagreement_score":0.8105478,"about_ca_system_score_codex":0.0045866594,"about_ca_system_score_gemma":0.00951334,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W1819504360","doi":"10.1002/pds.2316","title":"Design considerations in an active medical product safety monitoring system","year":2012,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ministry of Health","funders":"Hamilton Health Sciences Foundation; U.S. Department of Health and Human Services","keywords":"Confounding; Medicine; Spurious relationship; Observational study; Cohort; Cohort study; Product (mathematics); Risk analysis (engineering); Econometrics; Computer science; Machine learning","score_opus":0.5846020368607875,"score_gpt":0.5885438474925444,"score_spread":0.003941810631756915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819504360","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08505889,0.0022155533,0.88774925,0.011278044,0.007109215,0.0029968726,0.0001446032,0.00058485894,0.0028627361],"genre_scores_gemma":[0.62430936,0.00019816795,0.37395796,0.00032882238,0.0010897524,0.00007766998,0.0000020513944,0.000021268645,0.00001494111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98081535,0.016234674,0.0015576633,0.000501044,0.00023877274,0.00065251585],"domain_scores_gemma":[0.77559406,0.22298968,0.00034450108,0.00035619654,0.0000985579,0.00061701005],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036531787,0.00025904257,0.0010347113,0.00008294655,0.0002426956,0.0000082051065,0.00016331176,0.00024046206,0.00032919392],"category_scores_gemma":[0.16049637,0.00021239425,0.00006652908,0.00013603602,0.00032351023,0.00026766618,0.00012199084,0.00084812654,0.000021686506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032860474,0.0015347291,0.20242175,0.00078285474,0.00048467194,0.00012357776,0.005012271,0.00019733519,0.0012754073,0.6862352,0.005067726,0.093578465],"study_design_scores_gemma":[0.008040402,0.00018460224,0.10818447,0.0007231032,0.0006342966,0.0003787972,0.0015745247,0.009773756,0.014099485,0.85401493,0.00100622,0.0013854356],"about_ca_topic_score_codex":0.00002220743,"about_ca_topic_score_gemma":0.000005494894,"teacher_disagreement_score":0.5392505,"about_ca_system_score_codex":0.00012779068,"about_ca_system_score_gemma":0.000110322864,"threshold_uncertainty_score":0.99209327},"labels":[],"label_agreement":null},{"id":"W1835051027","doi":"10.3758/s13423-015-0913-5","title":"Hidden multiplicity in exploratory multiway ANOVA: Prevalence and remedies","year":2015,"lang":"en","type":"article","venue":"Psychonomic Bulletin & Review","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":437,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Psychology; False discovery rate; Null hypothesis; Multiple comparisons problem; Type I and type II errors; Statistical hypothesis testing; Statistics; Analysis of variance; Variance (accounting); Null (SQL); Test (biology); Cognitive psychology; Control (management); Social psychology; Mathematics; Artificial intelligence; Computer science; Data mining","score_opus":0.5931554158815283,"score_gpt":0.536563227896454,"score_spread":0.05659218798507426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1835051027","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14721264,0.73191714,0.021153811,0.05363064,0.008418445,0.016648995,0.0002821383,0.0009968717,0.019739335],"genre_scores_gemma":[0.0048752273,0.11557333,0.87532765,0.002778916,0.0003991329,0.00045565233,0.0000012069708,0.000071459704,0.00051742396],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961703,0.001247652,0.0013802102,0.00062749337,0.0002412021,0.000333165],"domain_scores_gemma":[0.9874932,0.011021735,0.00039072512,0.00070981163,0.00011225979,0.00027224506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007860239,0.00027886528,0.0010980502,0.00005484715,0.000032394222,0.000022955983,0.00035679594,0.00013389692,0.0005086406],"category_scores_gemma":[0.06700167,0.00023718984,0.0001017837,0.00015112097,0.00022750688,0.000045440698,0.0001731736,0.00037101205,0.00044097484],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036487816,0.0009984154,0.009594334,0.028877439,0.00014095908,0.000045027507,0.0009447082,3.5895098e-7,0.000094705385,0.015845153,0.5667989,0.3762951],"study_design_scores_gemma":[0.0064115818,0.00033035697,0.00606827,0.027270949,0.0003828606,0.000034145934,0.00018512491,0.00007409725,0.000088290326,0.50119084,0.4565711,0.0013923927],"about_ca_topic_score_codex":0.0000126718905,"about_ca_topic_score_gemma":0.0000066338016,"teacher_disagreement_score":0.85417384,"about_ca_system_score_codex":0.000084938714,"about_ca_system_score_gemma":0.00004673421,"threshold_uncertainty_score":0.9672321},"labels":[],"label_agreement":null},{"id":"W1863985755","doi":"","title":"Doit-on inclure des données non publiées (abrégés de congrès) dans les évaluations des comités de pharmacologie ?","year":2007,"lang":"fr","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Université de Montréal; Centre Hospitalier Universitaire de Sherbrooke; Hôpital Fleurimont","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.7916952757586057,"score_gpt":0.6118348817823738,"score_spread":0.17986039397623188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1863985755","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26793525,0.00053723576,0.68730307,0.0026541154,0.0013105962,0.0009205262,0.00019055998,0.0002578326,0.038890798],"genre_scores_gemma":[0.1792886,0.0009324194,0.81131613,0.0010812512,0.0009763928,0.000092038026,0.000005662368,0.00009838868,0.0062091486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99125123,0.0035459988,0.002005407,0.0007329784,0.00072924857,0.0017351568],"domain_scores_gemma":[0.81524235,0.18201473,0.00048890297,0.0006717595,0.0007709154,0.0008113264],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02502373,0.00062496046,0.00110416,0.00024246542,0.00094507524,0.0003458105,0.0008887663,0.0011127131,0.006218503],"category_scores_gemma":[0.21293977,0.0005554374,0.00041352326,0.0006993373,0.003166322,0.00034222426,0.00040501033,0.0013540506,0.00028195084],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069505576,0.0035685175,0.035087567,0.0017621333,0.0008221606,0.00028370527,0.0066417633,0.0004273777,0.013564062,0.50096303,0.016556378,0.41962826],"study_design_scores_gemma":[0.0026538216,0.0006789552,0.01822404,0.000703263,0.0010143308,0.00005598163,0.0030082532,0.0058966232,0.07021419,0.8936552,0.0032360079,0.0006593457],"about_ca_topic_score_codex":0.00065484043,"about_ca_topic_score_gemma":0.001645877,"teacher_disagreement_score":0.41896892,"about_ca_system_score_codex":0.0012173711,"about_ca_system_score_gemma":0.0005936555,"threshold_uncertainty_score":0.9996897},"labels":[],"label_agreement":null},{"id":"W1864480020","doi":"10.5489/cuaj.1084","title":"Dr. Izawa’s rebuttal","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rebuttal; Psychoanalysis; Philosophy; Psychology; Epistemology; Political science; Law","score_opus":0.310911143302605,"score_gpt":0.4560660462604958,"score_spread":0.1451549029578908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1864480020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40787435,0.00021386851,0.05691172,0.3747939,0.010459243,0.0024263181,0.0003530466,0.00054142985,0.14642614],"genre_scores_gemma":[0.67025006,0.000040804716,0.3063732,0.013313882,0.0032021601,0.000056964884,0.0000037281666,0.00005628009,0.0067029283],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99667376,0.0010840476,0.00082961906,0.00022456286,0.0004813402,0.0007066684],"domain_scores_gemma":[0.98273116,0.014993227,0.00048511504,0.00017541784,0.00044386674,0.001171238],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0035998216,0.00016082411,0.00043021148,0.00011146248,0.00028569135,0.00024273079,0.00032042703,0.0004382254,0.01174079],"category_scores_gemma":[0.140172,0.00012533765,0.00019565823,0.00020087005,0.00005636665,0.00013529092,0.000029323011,0.000961686,0.0009985693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015119935,0.000098054705,0.09685442,0.000007325418,0.0001797716,0.000073798,0.00007972209,0.0000041230605,0.00006395385,0.10210999,0.77981293,0.020700788],"study_design_scores_gemma":[0.00042070632,0.00011159055,0.0708892,0.0000062482554,0.000035728466,0.00004254006,0.000028886345,0.00009009547,0.000009199263,0.89273745,0.035468705,0.00015965968],"about_ca_topic_score_codex":0.0006613783,"about_ca_topic_score_gemma":0.00023767936,"teacher_disagreement_score":0.7906275,"about_ca_system_score_codex":0.00086331886,"about_ca_system_score_gemma":0.00027772493,"threshold_uncertainty_score":0.9997793},"labels":[],"label_agreement":null},{"id":"W1871418963","doi":"10.1111/rssb.12122","title":"Sequential Selection Procedures and False Discovery Rate Control","year":2015,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":146,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Selection (genetic algorithm); False discovery rate; Multiple comparisons problem; Computer science; Early stopping; Sequential analysis; Control (management); Statistical hypothesis testing; Model selection; Point (geometry); Block (permutation group theory); Algorithm; Mathematics; Machine learning; Statistics; Artificial intelligence; Combinatorics","score_opus":0.4133359249456316,"score_gpt":0.5013623523846276,"score_spread":0.08802642743899597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1871418963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006934206,0.00013344524,0.98721075,0.0024390523,0.001920605,0.00052848185,0.0006249942,0.000049907147,0.00015856502],"genre_scores_gemma":[0.059107818,0.000039428254,0.93843526,0.00094553997,0.0009205438,0.00002149555,0.0000020766204,0.0000650608,0.00046280798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98675555,0.008832128,0.0021772746,0.0005255437,0.00096964935,0.0007398438],"domain_scores_gemma":[0.9035086,0.09350982,0.0011616898,0.00031966344,0.0007659684,0.0007342469],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015459633,0.0004874997,0.0017398114,0.00004764053,0.0003205074,0.00023268304,0.0005597954,0.00046346578,0.00021129209],"category_scores_gemma":[0.3738946,0.00030781692,0.0004069588,0.00030560064,0.002105473,0.00028640844,0.0002960151,0.0014660743,0.000007637349],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039033878,0.00037076286,0.0015188887,0.00043254375,0.00093010993,0.000082929015,0.0004695272,0.00018365335,0.000573917,0.9389342,0.04508151,0.0075185406],"study_design_scores_gemma":[0.003014919,0.0012803185,0.0049733436,0.00009656646,0.00107499,0.00026581154,0.00040840934,0.0023848028,0.00032017342,0.98454154,0.001261761,0.00037738035],"about_ca_topic_score_codex":0.00003968611,"about_ca_topic_score_gemma":0.000020632428,"teacher_disagreement_score":0.35843498,"about_ca_system_score_codex":0.0002670648,"about_ca_system_score_gemma":0.000603039,"threshold_uncertainty_score":0.9999374},"labels":[],"label_agreement":null},{"id":"W1897654487","doi":"10.1002/9780470571224.pse264","title":"Importance of Statistics in the Qualification and Application of Biomarkers","year":2010,"lang":"en","type":"other","venue":"Pharmaceutical Sciences Encyclopedia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Paraza Pharma (Canada)","funders":"","keywords":"Data science; Field (mathematics); Computer science; Management science; Diversity (politics); Statistical analysis; Data mining; Statistics; Engineering; Mathematics; Sociology","score_opus":0.34283793955562386,"score_gpt":0.5686669700328972,"score_spread":0.22582903047727337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1897654487","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016023212,0.0009202052,0.27301085,0.00090244267,0.00089823897,0.0031218827,0.0012377445,0.000082427934,0.7182239],"genre_scores_gemma":[0.004982912,0.0019826242,0.99105227,0.00013665452,0.00022368167,0.00010176351,0.000007036642,0.000085241416,0.001427844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723744,0.0005896906,0.0009339595,0.00039341912,0.00062547514,0.000220009],"domain_scores_gemma":[0.9782171,0.020555262,0.00074532995,0.0003567974,0.00004711751,0.000078353],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00579196,0.00017490317,0.00049750996,0.0001359384,0.000030057481,0.000011833822,0.00058813544,0.00020891728,0.00038116332],"category_scores_gemma":[0.018349642,0.000115247094,0.000042112217,0.0005186103,0.0017979539,0.000025851929,0.00006911747,0.00034938066,0.000003903337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046769474,0.00044136748,0.0131180575,0.0011624385,0.00005165518,0.000002828015,0.00030046634,3.3659092e-7,0.0006045624,0.7383591,0.036446363,0.20946608],"study_design_scores_gemma":[0.0006187441,0.00010226148,0.003582635,0.00014621626,0.00021620883,0.0000033201425,0.00012240048,0.001546709,0.00024898924,0.8995272,0.09355407,0.00033127068],"about_ca_topic_score_codex":0.000085446016,"about_ca_topic_score_gemma":0.00017114633,"teacher_disagreement_score":0.7180414,"about_ca_system_score_codex":0.000009691944,"about_ca_system_score_gemma":0.000069907335,"threshold_uncertainty_score":0.9899192},"labels":[],"label_agreement":null},{"id":"W1905212504","doi":"10.1186/1471-2288-1-8","title":"On the probability of cost-effectiveness using data from randomized clinical trials","year":2001,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Sample size determination; Point estimation; Estimator; Coverage probability; Statistics; Parametric statistics; Bayesian probability; Interval estimation; Randomized controlled trial; Computer science; Credible interval; Econometrics; Mathematics; Medicine; Surgery","score_opus":0.9947389119596108,"score_gpt":0.8325544859025912,"score_spread":0.16218442605701966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1905212504","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09852708,0.00012820106,0.8919743,0.001264575,0.0012834143,0.005971899,0.00019711036,0.00004369359,0.0006097777],"genre_scores_gemma":[0.011403654,0.0004192266,0.9861605,0.00026224818,0.0012108014,0.0004507466,0.000012829434,0.00004840356,0.000031568798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.11786217,0.86907613,0.006464321,0.001570259,0.0040084673,0.0010186577],"domain_scores_gemma":[0.0036152673,0.9898975,0.0011722108,0.0037269064,0.0008552699,0.000732878],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.89741564,0.000313561,0.006587545,0.00017746317,0.00019072542,0.00003485767,0.0033496106,0.0011147006,0.008147381],"category_scores_gemma":[0.9987909,0.00016325958,0.0007986778,0.0007617782,0.0074333814,0.00005993066,0.0020272927,0.0030667214,0.00005939839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24788228,0.0017039736,0.0011676684,0.00038993935,0.00088064646,0.00006370359,0.00006622144,0.000005855379,0.0002644219,0.6219569,0.0028262904,0.12279213],"study_design_scores_gemma":[0.045886885,0.00025899164,0.00028748362,0.00043278598,0.0002627703,0.0000067239653,0.000061002676,0.017570488,0.00034086098,0.9345091,0.00024292854,0.00014000777],"about_ca_topic_score_codex":0.00049518014,"about_ca_topic_score_gemma":0.00013825997,"teacher_disagreement_score":0.3125522,"about_ca_system_score_codex":0.00010466159,"about_ca_system_score_gemma":0.002086758,"threshold_uncertainty_score":0.99923325},"labels":[],"label_agreement":null},{"id":"W1905891062","doi":"10.1002/pst.1704","title":"Bayesian inference in two‐arm trials using relative belief ratios","year":2015,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Inference; Statistical inference; Bayesian inference; Computer science; Artificial intelligence; Bayesian statistics; Fiducial inference; Measure (data warehouse); Machine learning; Frequentist inference; Econometrics; Statistics; Mathematics; Data mining","score_opus":0.8804641098560438,"score_gpt":0.7012657224618299,"score_spread":0.1791983873942139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1905891062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014833735,0.00008675235,0.9921043,0.0003331059,0.0010500144,0.0011783877,0.000749253,0.00011542266,0.0028994123],"genre_scores_gemma":[0.15299295,0.000036038775,0.8458791,0.00043174883,0.00042914436,0.000051265084,0.000009725577,0.000064258806,0.00010579159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98910785,0.005556908,0.002878029,0.0006577001,0.0009963049,0.00080318673],"domain_scores_gemma":[0.8246928,0.17298685,0.000607617,0.00044476494,0.00042462238,0.0008433689],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015221618,0.00044415312,0.0017217424,0.00017063064,0.00009914763,0.00010927119,0.00040747656,0.00020248267,0.0011077534],"category_scores_gemma":[0.5218032,0.00039077588,0.00013824058,0.0005987338,0.00044265206,0.00021278544,0.00023850493,0.0010669231,0.00011675962],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056610967,0.0008102831,0.0024858136,0.00012832927,0.00014031782,0.00018667767,0.00047605622,0.0003587576,0.0001894892,0.9649017,0.001461234,0.028295225],"study_design_scores_gemma":[0.004613851,0.00015552675,0.00006511564,0.00009937152,0.0003263364,0.0000064422347,0.000058906135,0.13091256,0.0007252907,0.8616699,0.00095355604,0.00041314436],"about_ca_topic_score_codex":0.00006889609,"about_ca_topic_score_gemma":0.000038870054,"teacher_disagreement_score":0.50658154,"about_ca_system_score_codex":0.00038558582,"about_ca_system_score_gemma":0.00042066752,"threshold_uncertainty_score":0.9998544},"labels":[],"label_agreement":null},{"id":"W1907556438","doi":"10.1002/0470011815.b2a10032","title":"<scp>M</scp>antel–<scp>H</scp>aenszel Methods","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saskatchewan Health","funders":"","keywords":"Categorical variable; Repeated measures design; Hypergeometric distribution; Econometrics; R package; Statistics; Mathematics; Ordinal data; Generalized linear model; Computer science","score_opus":0.19068908240366636,"score_gpt":0.5000848164344142,"score_spread":0.3093957340307478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1907556438","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009816119,0.001342259,0.41637817,0.0000327386,0.0034484323,0.0011029847,0.005772255,0.00042012008,0.5714932],"genre_scores_gemma":[0.00000120219,0.004687121,0.5728152,0.00016515181,0.0024033897,0.00006215921,0.000070542636,0.0010493675,0.4187459],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886868,0.002896922,0.0037130986,0.0016068484,0.0015979322,0.0014984021],"domain_scores_gemma":[0.77695566,0.21702212,0.0030052995,0.0019733491,0.00037710863,0.0006664729],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0051168674,0.001542067,0.0039713806,0.0007706349,0.00012037937,0.000088075554,0.0016026729,0.0021357704,0.0027446675],"category_scores_gemma":[0.45860314,0.0014511453,0.0006575892,0.00085220544,0.0011442149,0.00006876377,0.0006088801,0.0017303587,0.00078257103],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061293244,0.00046762708,0.000051845273,0.0012582998,0.0005182168,0.00009182433,0.00035883425,8.3506825e-7,0.00002812378,0.08409563,0.86147034,0.051652297],"study_design_scores_gemma":[0.000915634,0.00022851439,0.00008216137,0.0006098187,0.00093690614,0.000015793441,0.00023141298,0.00008607256,0.00021910525,0.2894212,0.7069964,0.00025700883],"about_ca_topic_score_codex":0.00008046358,"about_ca_topic_score_gemma":0.000058802943,"teacher_disagreement_score":0.45348626,"about_ca_system_score_codex":0.00014351642,"about_ca_system_score_gemma":0.00046483942,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W1910761353","doi":"10.1002/sim.6529","title":"Bias in progression‐free survival analysis due to intermittent assessment of progression","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Survival analysis; Clinical endpoint; Progression-free survival; Estimator; Medicine; Kaplan–Meier estimator; Confidence interval; Endpoint Determination; Imputation (statistics); Tumor progression; Clinical trial; Statistics; Oncology; Econometrics; Overall survival; Internal medicine; Cancer; Mathematics; Missing data","score_opus":0.6145995339197039,"score_gpt":0.6510660572099151,"score_spread":0.03646652329021116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1910761353","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024791429,0.000051434166,0.9681013,0.0014027597,0.0010140842,0.0012444857,0.00033255375,0.0000404957,0.0030214507],"genre_scores_gemma":[0.13967246,0.0000127522,0.85986173,0.00008839612,0.00015106217,0.00010041409,0.000016887905,0.000029049774,0.00006726461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9932576,0.0017778858,0.002328598,0.0005172769,0.0016980004,0.00042068606],"domain_scores_gemma":[0.96801406,0.029828485,0.00059205364,0.00074660475,0.00043167366,0.0003870969],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014724493,0.00027264914,0.0018459699,0.00076767855,0.000020068313,0.000012119459,0.00056830636,0.00015481829,0.0002560852],"category_scores_gemma":[0.241273,0.00019369791,0.00007062626,0.0018526107,0.0003448645,0.000032955104,0.0003756447,0.0004923645,0.0000041023613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080591365,0.0024036332,0.22126463,0.00089392764,0.000572109,0.0012057853,0.0031337445,0.00016390401,0.00016709155,0.5101888,0.021969028,0.2372314],"study_design_scores_gemma":[0.003847221,0.0013515495,0.09953153,0.0013019324,0.00043934834,0.0000030762994,0.0007562579,0.0064829253,0.0000670099,0.8858349,0.00012898755,0.00025528608],"about_ca_topic_score_codex":0.000105162966,"about_ca_topic_score_gemma":0.0004993503,"teacher_disagreement_score":0.37564605,"about_ca_system_score_codex":0.00022748859,"about_ca_system_score_gemma":0.00018603039,"threshold_uncertainty_score":0.7898772},"labels":[],"label_agreement":null},{"id":"W191395533","doi":"10.1007/978-94-007-6513-9_9","title":"Clinical Trial Complexity Measure – Balancing Constraints to Achieve Quality","year":2013,"lang":"en","type":"book-chapter","venue":"NATO science for peace and security series. A, Chemistry and biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; SickKids Foundation; Occupational Cancer Research Centre; Alberta Innovates; Hospital for Sick Children","funders":"","keywords":"Measure (data warehouse); Computer science; Quality (philosophy); Data mining; Philosophy","score_opus":0.5801834655810153,"score_gpt":0.5596953065044378,"score_spread":0.020488159076577528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191395533","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4155508,0.0018408471,0.03870122,0.011739692,0.010169322,0.018245418,0.01576007,0.0008144577,0.48717818],"genre_scores_gemma":[0.15207283,0.0016287848,0.7857137,0.0026012126,0.006354654,0.00038299695,0.00018631946,0.00018429554,0.0508752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99588287,0.00023705456,0.0015952657,0.0013685657,0.0003356342,0.00058060454],"domain_scores_gemma":[0.98548764,0.012168602,0.00065999245,0.0005511069,0.0005091459,0.00062352646],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.011313912,0.00046928794,0.0016949326,0.000035931236,0.00039810495,0.00011379957,0.00055655517,0.0012648955,0.00057232764],"category_scores_gemma":[0.0529934,0.00038795552,0.0002461604,0.00007521965,0.0075417166,0.00010417166,0.00046195777,0.0009690442,0.000010135151],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009479157,0.00017462009,0.0000677771,0.0009889108,0.00014693452,0.0000047357134,0.0002922684,1.0038154e-8,0.0033116343,0.9399002,0.0027243819,0.042909354],"study_design_scores_gemma":[0.0052389475,0.00088085455,0.000016998078,0.00013576394,0.00008650069,0.000023175313,0.00010010462,0.000011526547,0.0005937153,0.9669314,0.025451949,0.0005290428],"about_ca_topic_score_codex":0.0000118893,"about_ca_topic_score_gemma":0.00001807973,"teacher_disagreement_score":0.7470125,"about_ca_system_score_codex":0.000056998564,"about_ca_system_score_gemma":0.0003814962,"threshold_uncertainty_score":0.99985725},"labels":[],"label_agreement":null},{"id":"W1924796615","doi":"10.1016/j.cct.2015.11.003","title":"Design of a multi-arm randomized clinical trial with no control arm","year":2015,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Naval Medical Research Center; Henry M. Jackson Foundation","keywords":"Medicine; Sample size determination; Interim; Interim analysis; Randomized controlled trial; Clinical trial; Robotic arm; Research design; Statistics; Surgery; Computer science; Artificial intelligence; Internal medicine","score_opus":0.9195482900152049,"score_gpt":0.6648624745020044,"score_spread":0.25468581551320046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1924796615","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021213354,0.00058350904,0.96198606,0.0010127741,0.009448028,0.020513542,0.00023067677,0.00035410209,0.0037499382],"genre_scores_gemma":[0.15469916,0.00021145512,0.83651274,0.0012525743,0.0053100125,0.00085283286,0.0000095796495,0.00018488319,0.000966787],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.76057214,0.20405145,0.030441983,0.0020043848,0.001992409,0.00093762967],"domain_scores_gemma":[0.08556839,0.8968667,0.0112108085,0.002319385,0.0022386182,0.0017961329],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47486937,0.00089280726,0.017798929,0.00019399011,0.000086274435,0.000107782296,0.001267022,0.0015068072,0.00049834105],"category_scores_gemma":[0.9425508,0.0005587424,0.00342828,0.00045173636,0.0031025202,0.00024343442,0.00023886889,0.0016995305,0.0002663152],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9478859,0.008199124,0.00031710035,0.000091622365,0.0026202414,0.00009322826,0.000051878527,0.000010182438,0.0000089119685,0.008022907,0.02470286,0.007996062],"study_design_scores_gemma":[0.73390436,0.010785332,0.000008280066,0.0002771916,0.0014160828,0.000003605116,0.000036463418,0.0030849667,0.000040232666,0.24845071,0.0014504717,0.000542316],"about_ca_topic_score_codex":0.000027591055,"about_ca_topic_score_gemma":0.0000011064134,"teacher_disagreement_score":0.6928152,"about_ca_system_score_codex":0.000058835605,"about_ca_system_score_gemma":0.002689016,"threshold_uncertainty_score":0.9997894},"labels":[],"label_agreement":null},{"id":"W1931399160","doi":"10.1002/0470013192.bsa421","title":"Multiple Comparison Tests: Nonparametric and Resampling Approaches","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistics in Behavioral Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Resampling; Statistics; Sampling distribution; Test statistic; Mathematics; Nonparametric statistics; Estimator; Quantile; Statistic; Heteroscedasticity; Statistical hypothesis testing; Econometrics; Empirical distribution function; Ancillary statistic","score_opus":0.5022603754661644,"score_gpt":0.5368294770614004,"score_spread":0.03456910159523596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1931399160","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009256191,0.0015045898,0.43271092,0.00006516996,0.0032296332,0.004329818,0.00606968,0.00042068007,0.5424133],"genre_scores_gemma":[0.0039062116,0.00051233073,0.9819985,0.000006884637,0.00022291971,0.000048755108,0.0000080620175,0.0001963792,0.013099939],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99560773,0.00023964547,0.0015073041,0.00091244566,0.001125962,0.000606915],"domain_scores_gemma":[0.9789085,0.019057402,0.001003356,0.00066573237,0.00010395835,0.00026108802],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003213694,0.0004147393,0.0012995095,0.00086928095,0.00007715127,0.00005988526,0.0008123655,0.00037744048,0.0005056304],"category_scores_gemma":[0.054018933,0.0003863611,0.000051369774,0.0013413441,0.0022170437,0.00007817221,0.0003776423,0.0007001604,0.00001318092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008218705,0.003067269,0.124680616,0.0010659349,0.00002934841,0.000060964598,0.00091651076,0.000022391825,0.0000573602,0.15632078,0.06447831,0.6492183],"study_design_scores_gemma":[0.0061261444,0.0017403057,0.08018049,0.0037015292,0.0011230748,0.000023707496,0.0010874821,0.009375531,0.00024062041,0.81395054,0.07770265,0.004747932],"about_ca_topic_score_codex":0.0005105481,"about_ca_topic_score_gemma":0.0007960607,"teacher_disagreement_score":0.6576297,"about_ca_system_score_codex":0.00014655963,"about_ca_system_score_gemma":0.00022849608,"threshold_uncertainty_score":0.99985886},"labels":[],"label_agreement":null},{"id":"W1964059003","doi":"10.1080/07474940802619071","title":"Discussion on “A Hybrid Selection and Testing Procedure with Curtailment for Comparative Clinical Trials” by Elena M. Buzaianu and Pinyuen Chen","year":2009,"lang":"en","type":"article","venue":"Sequential Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Chen; Selection (genetic algorithm); Mathematics; Parametric statistics; Sequential analysis; Statistics; Bernoulli's principle; Statistical hypothesis testing; Computer science; Econometrics; Artificial intelligence; Biology; Engineering","score_opus":0.6773892975891347,"score_gpt":0.6170725358191327,"score_spread":0.060316761770002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964059003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4023705,0.00008395691,0.59169096,0.002720502,0.0001256405,0.0023274196,0.000264459,0.00014799112,0.0002685804],"genre_scores_gemma":[0.64175737,0.000024352395,0.35739902,0.00020644892,0.00033004847,0.000060361297,0.000024774812,0.000017575248,0.00018001904],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956293,0.0015662401,0.0014415283,0.00071961485,0.00035194014,0.00029139477],"domain_scores_gemma":[0.97895056,0.019654222,0.0007670342,0.00020636058,0.00019647123,0.00022537232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0069118184,0.00028091192,0.0016623684,0.00013646428,0.00021117166,0.00010996132,0.00010255228,0.00013359395,0.000036058776],"category_scores_gemma":[0.03484524,0.00015700134,0.0002679426,0.00053698866,0.00013966963,0.000080790305,0.000031276737,0.0002957627,0.0000015182347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02130848,0.007219595,0.038629863,0.0011775515,0.026825191,0.000039666626,0.001774525,0.000545528,0.01973008,0.039248236,0.036163732,0.8073375],"study_design_scores_gemma":[0.008783595,0.00858264,0.0067989104,0.0004287123,0.021625316,0.000015796431,0.0002958383,0.07614546,0.013177923,0.86230624,0.000662225,0.00117737],"about_ca_topic_score_codex":0.000015069071,"about_ca_topic_score_gemma":0.000023763738,"teacher_disagreement_score":0.82305795,"about_ca_system_score_codex":0.00004791325,"about_ca_system_score_gemma":0.00005196615,"threshold_uncertainty_score":0.97328466},"labels":[],"label_agreement":null},{"id":"W1964870095","doi":"10.1111/j.1541-0420.2009.01299.x","title":"Regression Analysis with a Misclassified Covariate from a Current Status Observation Scheme","year":2009,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo; Simon Fraser University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Covariate; Censoring (clinical trials); Statistics; Regression analysis; Nonparametric statistics; Seroconversion; Proportional hazards model; Estimator; Econometrics; Medicine; Mathematics","score_opus":0.7458845379643189,"score_gpt":0.5750133852493857,"score_spread":0.17087115271493314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964870095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1675898,0.0004219218,0.8299822,0.00028291176,0.00041393383,0.0003983405,0.00044606428,0.00017671853,0.00028810775],"genre_scores_gemma":[0.039231766,0.00017501596,0.96009827,0.00011486423,0.00018195984,0.000012480444,0.00006715136,0.000020122563,0.00009834678],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969221,0.00042980112,0.00085657794,0.000535383,0.00086120743,0.00039497126],"domain_scores_gemma":[0.983036,0.01512221,0.0005887505,0.0006783129,0.00031342194,0.0002613012],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001528679,0.0002493273,0.00079492584,0.001213969,0.00008461026,0.000099580684,0.00025318464,0.0001919262,0.00019650963],"category_scores_gemma":[0.061970152,0.0001708414,0.00018850308,0.012030124,0.00006740176,0.000089044224,0.000050377676,0.00027358215,0.00002423009],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017084517,0.0034058394,0.078243695,0.0001787255,0.0024052486,0.00005949524,0.00041925197,0.000012780482,0.0057485644,0.14225544,0.007747266,0.75781524],"study_design_scores_gemma":[0.0030901043,0.00058067223,0.29723495,0.00019805809,0.0023286298,5.121796e-7,0.000044088316,0.008503732,0.0012123857,0.6807596,0.0054176296,0.00062962883],"about_ca_topic_score_codex":0.00003632925,"about_ca_topic_score_gemma":0.0000051223706,"teacher_disagreement_score":0.75718564,"about_ca_system_score_codex":0.00013675707,"about_ca_system_score_gemma":0.000080384096,"threshold_uncertainty_score":0.94593126},"labels":[],"label_agreement":null},{"id":"W1964949252","doi":"10.1016/j.amjmed.2009.12.012","title":"Public Sensationalism and Clinical Trials: How to Address the Challenges of Science?","year":2010,"lang":"en","type":"review","venue":"The American Journal of Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Sensationalism; Clinical trial; MEDLINE; Family medicine; Internal medicine; Media studies; Law","score_opus":0.9014363302717562,"score_gpt":0.6906850512409921,"score_spread":0.21075127903076407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964949252","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007457544,0.89636606,0.0031336376,0.09673955,0.002339859,0.000997842,0.00003751009,0.00000852136,0.0003024257],"genre_scores_gemma":[0.00014696895,0.93366534,0.06091137,0.0004499591,0.004760119,0.000010747573,1.6450231e-7,0.00003481125,0.000020537098],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9773111,0.015396552,0.004804408,0.00033929845,0.0018141572,0.0003345188],"domain_scores_gemma":[0.51704955,0.4672054,0.012740802,0.0011323727,0.001286748,0.000585146],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19918564,0.00033073706,0.007143926,0.00036067714,0.00013852835,0.00004047102,0.0018664212,0.00015093165,0.000060282768],"category_scores_gemma":[0.73857963,0.00011845878,0.00065400096,0.000906639,0.014653687,0.000053743228,0.0002711364,0.001982864,0.0000019514396],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005153447,0.000048301972,6.335961e-7,0.00046867997,0.00030005223,0.0000060444263,0.00020223763,7.682514e-9,0.0000014409579,0.05314772,0.0015884638,0.9441849],"study_design_scores_gemma":[0.0012250411,0.002856639,0.00006391665,0.01253652,0.0051304577,0.0006324397,0.0014937244,0.0000034644968,0.0000010540978,0.3875551,0.5882526,0.00024908187],"about_ca_topic_score_codex":0.0000036837955,"about_ca_topic_score_gemma":0.0000022338204,"teacher_disagreement_score":0.9439358,"about_ca_system_score_codex":0.000038157297,"about_ca_system_score_gemma":0.00083558995,"threshold_uncertainty_score":0.9880279},"labels":[],"label_agreement":null},{"id":"W1965723989","doi":"10.1016/j.cct.2006.09.002","title":"Epidemiology and reporting of randomized trials employing re-randomization of patient groups: A systematic survey","year":2006,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Pfizer Pharmaceuticals","keywords":"Randomization; Medicine; Blinding; Interquartile range; Dosing; Randomized controlled trial; Consolidated Standards of Reporting Trials; Clinical trial; Sample size determination; Epidemiology; Internal medicine; Statistics","score_opus":0.9138940542648892,"score_gpt":0.6652337855323921,"score_spread":0.24866026873249714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965723989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3222748,0.012178085,0.6230502,0.00072907703,0.005330945,0.033675894,0.0006717227,0.00027828757,0.001810979],"genre_scores_gemma":[0.7982067,0.0002776606,0.2004108,0.00011837691,0.0005005079,0.000352676,0.000027764361,0.00006170421,0.000043793752],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.17247838,0.6436286,0.18010557,0.0017546836,0.001244899,0.0007878389],"domain_scores_gemma":[0.01148437,0.89390093,0.09231561,0.001066311,0.0009943659,0.00023842754],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8016219,0.000519081,0.042775292,0.00025885124,0.000081102975,0.000022145203,0.00034355745,0.0008261155,0.00008288695],"category_scores_gemma":[0.9966051,0.00033350757,0.0037144818,0.00041798907,0.00117659,0.00013563287,0.00021071079,0.00048845157,0.0000026325304],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5451585,0.003538911,0.1439437,0.049887788,0.008894079,0.00007169379,0.00047290686,0.000050971972,0.00040468588,0.23154578,0.009853034,0.006177934],"study_design_scores_gemma":[0.16807851,0.00046654703,0.0013863003,0.005859099,0.0018704958,0.000004414096,0.000081320104,0.0004905009,0.00036934554,0.8210625,0.000005172096,0.0003257938],"about_ca_topic_score_codex":0.0003341398,"about_ca_topic_score_gemma":0.000012966889,"teacher_disagreement_score":0.5895167,"about_ca_system_score_codex":0.00002768603,"about_ca_system_score_gemma":0.0002811643,"threshold_uncertainty_score":0.9999117},"labels":[],"label_agreement":null},{"id":"W1965809183","doi":"10.1007/s11136-005-2293-1","title":"Application of Robust Statistical Methods for Sensitivity Analysis of Health-Related Quality of Life Outcomes","year":2006,"lang":"en","type":"article","venue":"Quality of Life Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Cancer Institute","keywords":"Statistics; Parametric statistics; Skewness; Truncated mean; Analysis of variance; Variance (accounting); Mathematics; Sensitivity (control systems); Degrees of freedom (physics and chemistry); Statistic; Econometrics; Statistical hypothesis testing; Medicine","score_opus":0.8894169930143231,"score_gpt":0.7370498386074846,"score_spread":0.15236715440683846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965809183","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11095747,0.00009773031,0.8842333,0.0009924555,0.000046408186,0.0012675762,0.0022182353,0.000023015542,0.00016383205],"genre_scores_gemma":[0.4206909,0.000007121396,0.5791506,0.00001622019,0.000021267118,0.00003627914,0.000035967958,0.000017555541,0.000024099054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94025785,0.047215436,0.009063566,0.000691952,0.0021567808,0.0006144159],"domain_scores_gemma":[0.5875041,0.40587813,0.0030379533,0.0011438273,0.0021991879,0.00023682263],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19862005,0.0002191442,0.0046598488,0.00054763566,0.00009213858,0.0000093704275,0.00038181344,0.00034824995,0.00011830792],"category_scores_gemma":[0.52392316,0.00019491695,0.00071684085,0.0019141001,0.001460024,0.000047530597,0.00020077992,0.00046284098,0.0000014385428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012482528,0.0025259405,0.07332905,0.006875027,0.0021689413,1.6832804e-7,0.00025306467,0.00036827102,0.005162621,0.8846358,0.0004307136,0.023002138],"study_design_scores_gemma":[0.0013117497,0.00024762593,0.35105175,0.00004647455,0.00029295584,5.1991474e-8,0.00028152787,0.011166037,0.001941936,0.633495,0.000009528036,0.00015539628],"about_ca_topic_score_codex":0.013157542,"about_ca_topic_score_gemma":0.00030277664,"teacher_disagreement_score":0.3586627,"about_ca_system_score_codex":0.000098332974,"about_ca_system_score_gemma":0.0005682249,"threshold_uncertainty_score":0.9934139},"labels":[],"label_agreement":null},{"id":"W1966264920","doi":"10.1198/000313008x269738","title":"Confidence Intervals for a Discrete Population Median","year":2008,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Confidence interval; CDF-based nonparametric confidence interval; Robust confidence intervals; Statistics; Population; Confidence distribution; Confidence region; Statistic; Sign test; Mathematics; Credible interval; Sign (mathematics); Computer science; Medicine; Mann–Whitney U test; Wilcoxon signed-rank test","score_opus":0.5415881943883241,"score_gpt":0.581522353994503,"score_spread":0.039934159606178965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966264920","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016037963,0.00000951914,0.9797811,0.0016754714,0.00035238016,0.00081859395,0.0006053085,0.00010539451,0.0006142992],"genre_scores_gemma":[0.4084019,0.000017027469,0.5901673,0.0007966327,0.00027043995,0.0001155584,0.000007511937,0.000035419853,0.00018821518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732363,0.000769955,0.0008036396,0.0003331472,0.0003736427,0.00039595857],"domain_scores_gemma":[0.9370082,0.06155063,0.00064664177,0.0005223149,0.00012676045,0.00014544622],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016768596,0.0002031731,0.00072324823,0.000050861625,0.0002690107,0.0000274724,0.0004198055,0.000035815414,0.00012536542],"category_scores_gemma":[0.07583276,0.00013817128,0.00013233908,0.00025654002,0.0010467008,0.00004897544,0.00006866048,0.00018706915,0.00003665268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000405165,0.000075800635,0.0010113871,0.00006883101,0.00011815824,0.000024754016,0.00093752274,0.0000033486003,0.00011103748,0.915164,0.016599817,0.065480195],"study_design_scores_gemma":[0.00037340954,0.00034862358,0.01524994,0.000042031843,0.000102986276,0.000015355527,0.0001970076,0.0010557817,0.00008294741,0.9819951,0.00033478392,0.00020203728],"about_ca_topic_score_codex":0.00054466404,"about_ca_topic_score_gemma":0.00009604495,"teacher_disagreement_score":0.39236394,"about_ca_system_score_codex":0.000054587086,"about_ca_system_score_gemma":0.000046554484,"threshold_uncertainty_score":0.9319519},"labels":[],"label_agreement":null},{"id":"W1966338615","doi":"10.1002/sim.1877","title":"Two‐stage adaptive strategy for superiority and non‐inferiority hypotheses in active controlled clinical trials","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Cancer Institute","keywords":"Sample size determination; Interim; Type I and type II errors; Flexibility (engineering); Computer science; Margin (machine learning); Adaptive design; Stage (stratigraphy); Early stopping; Statistical hypothesis testing; Statistics; Econometrics; Clinical trial; Mathematics; Medicine; Artificial intelligence; Machine learning","score_opus":0.7120274947519263,"score_gpt":0.6475429193750869,"score_spread":0.06448457537683938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966338615","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069865964,0.0001368929,0.9183394,0.0006171965,0.0012438485,0.006023938,0.0024523884,0.000049169204,0.0012712069],"genre_scores_gemma":[0.3043965,0.0003001381,0.69406223,0.00020362857,0.0006319446,0.0002916728,0.00000935475,0.00004393605,0.00006056977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98952407,0.003997046,0.0045365226,0.00078815676,0.00055140594,0.0006028059],"domain_scores_gemma":[0.7289475,0.2693967,0.0007603608,0.0003674587,0.00026627665,0.00026170223],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03832008,0.00042710674,0.0046313195,0.00022288815,0.00007786651,0.000030183128,0.00025959805,0.00035676121,0.00021178824],"category_scores_gemma":[0.6027522,0.0003203613,0.00016175381,0.00028645858,0.0011601076,0.000084332394,0.00008720239,0.0009798094,0.0000035723008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0137485415,0.0009209234,0.0037228628,0.00033163524,0.00026700276,0.00020835293,0.00093213737,0.000045048128,0.00017846763,0.9418347,0.00022809162,0.037582245],"study_design_scores_gemma":[0.06440975,0.0022397453,0.014534292,0.00039203683,0.00027710272,0.0000025970273,0.0012293934,0.0015061293,0.00006878043,0.9150024,0.00004207176,0.0002956773],"about_ca_topic_score_codex":0.00049213547,"about_ca_topic_score_gemma":0.0013626132,"teacher_disagreement_score":0.56443214,"about_ca_system_score_codex":0.0002009602,"about_ca_system_score_gemma":0.00039720212,"threshold_uncertainty_score":0.99992484},"labels":[],"label_agreement":null},{"id":"W1966359789","doi":"10.1037/1082-989x.12.4.399","title":"Toward using confidence intervals to compare correlations.","year":2007,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":758,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Statistics; Robust confidence intervals; Mathematics; Sample size determination; Dependency (UML); Correlation; Nominal level; Sampling (signal processing); Confidence distribution; Sample (material); Econometrics; Computer science; Artificial intelligence","score_opus":0.915936087266207,"score_gpt":0.7443180110581955,"score_spread":0.1716180762080115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966359789","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025327602,0.000040201518,0.96075314,0.0005206976,0.0022221082,0.00066844875,0.000017511495,0.0002341467,0.010216124],"genre_scores_gemma":[0.11708707,0.000003497593,0.88051605,0.0018735718,0.00035021623,0.00002039245,4.9654824e-7,0.000030880656,0.00011783004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934767,0.0030960476,0.001614716,0.00076377584,0.00041256886,0.000636223],"domain_scores_gemma":[0.9027226,0.09551849,0.00031949137,0.0007088883,0.00022989554,0.00050063705],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020980999,0.0002963858,0.0009653323,0.00014665945,0.000113243135,0.000057130732,0.0006240472,0.00022841204,0.001776686],"category_scores_gemma":[0.2010913,0.00023161687,0.00024217005,0.00069476746,0.00027161004,0.0000603097,0.00022242389,0.00061522936,0.00017105369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068876316,0.0008721092,0.001881923,0.00008779249,0.000102728285,0.00010208923,0.0006326517,0.000023606652,0.010619191,0.6164291,0.0042761047,0.36428395],"study_design_scores_gemma":[0.00050044677,0.00023077152,0.010091083,0.000107650616,0.00007127367,0.00004729715,0.00014804886,0.00041338635,0.0024274606,0.9839951,0.0016230403,0.00034444628],"about_ca_topic_score_codex":0.000009550187,"about_ca_topic_score_gemma":0.0000017086537,"teacher_disagreement_score":0.367566,"about_ca_system_score_codex":0.000084305844,"about_ca_system_score_gemma":0.000012575534,"threshold_uncertainty_score":0.99913585},"labels":[],"label_agreement":null},{"id":"W1966608570","doi":"10.6000/1929-6029.2014.03.04.9","title":"Examining the Probabilities of Type I Error for Unadjusted All Pairwise Comparisons and Bonferroni Adjustment Approaches in Hypothesis Testing for Proportions","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bonferroni correction; Type I and type II errors; Mathematics; Statistics; Pairwise comparison; Sample size determination; Type (biology); Quadratic equation; Sample (material); Econometrics; Biology","score_opus":0.8913149896988433,"score_gpt":0.6204963477873874,"score_spread":0.2708186419114559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966608570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070853494,0.00014518044,0.918503,0.005931475,0.0007666031,0.0023388825,0.0009859741,0.000011357668,0.00046403636],"genre_scores_gemma":[0.22760189,0.000031655938,0.771925,0.000043040443,0.00022973116,0.00011982122,0.000004160885,0.000017129352,0.000027590653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949603,0.0011902889,0.0016559414,0.00019867397,0.0016826713,0.00031213797],"domain_scores_gemma":[0.598545,0.39829025,0.00063253654,0.00018895448,0.0021554243,0.00018781338],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024261119,0.00011106027,0.00051087496,0.00028194883,0.00004862646,0.00003232161,0.00058035494,0.00012253431,0.00011142793],"category_scores_gemma":[0.69796866,0.00007528458,0.000046524856,0.00020362333,0.0007547691,0.000042455435,0.00014153875,0.0006533056,3.761168e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014911116,0.0014860991,0.009357882,0.0010603389,0.00030824068,0.000028020533,0.0013725016,0.00017034619,0.00006414192,0.6037302,0.0145792235,0.3663519],"study_design_scores_gemma":[0.0017316551,0.001018827,0.0092337765,0.0007532503,0.00003779557,0.000015597152,0.0012076758,0.07184968,0.000039235536,0.91338,0.0006513163,0.000081142265],"about_ca_topic_score_codex":0.000036510588,"about_ca_topic_score_gemma":0.00015783207,"teacher_disagreement_score":0.67370754,"about_ca_system_score_codex":0.00015620567,"about_ca_system_score_gemma":0.0005090967,"threshold_uncertainty_score":0.84084684},"labels":[],"label_agreement":null},{"id":"W1968538911","doi":"10.1200/jco.2011.38.5732","title":"Design Issues in Randomized Phase II/III Trials","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"","keywords":"Randomized controlled trial; Medicine; Phase (matter); Selection (genetic algorithm); N of 1 trial; Clinical trial; Accrual; Internal medicine; Computer science; Artificial intelligence","score_opus":0.8981866011790793,"score_gpt":0.7525624720174812,"score_spread":0.14562412916159817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968538911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0856123,0.002551155,0.87233764,0.013144577,0.018056575,0.0027447206,0.000012166026,0.0000510681,0.0054898006],"genre_scores_gemma":[0.08085352,0.0013693753,0.91020066,0.0010787349,0.0060533797,0.000028696766,2.1533725e-7,0.00003284949,0.0003825647],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8999875,0.07475863,0.023342686,0.0003046023,0.0008723922,0.0007341841],"domain_scores_gemma":[0.15606825,0.83105755,0.011161552,0.00040360817,0.00049612566,0.0008129062],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.41896912,0.00027063105,0.013024384,0.00023936214,0.000053374726,0.000017250031,0.0005221357,0.0010158577,0.00180352],"category_scores_gemma":[0.9077305,0.00016601395,0.0019425263,0.00024787287,0.0006316023,0.00024025461,0.00014399068,0.0018682869,0.000031069623],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.50710607,0.017944168,0.00018963669,0.000039863877,0.0012792937,0.00021700384,0.00062306714,0.000007835183,0.00012008195,0.053046834,0.042405307,0.37702084],"study_design_scores_gemma":[0.37378347,0.0054213814,0.000043741988,0.00010080187,0.0008629192,0.000036711688,0.00005316635,0.00012406678,0.0002057337,0.6082229,0.010995887,0.00014920566],"about_ca_topic_score_codex":0.0000073659958,"about_ca_topic_score_gemma":0.0000020036039,"teacher_disagreement_score":0.75629896,"about_ca_system_score_codex":0.0001126217,"about_ca_system_score_gemma":0.0007701681,"threshold_uncertainty_score":0.99910897},"labels":[],"label_agreement":null},{"id":"W1968544498","doi":"10.1016/j.ejca.2015.03.017","title":"Efficacy-effectiveness gap as an obstacle to translating clinical trials to clinical practice","year":2015,"lang":"en","type":"letter","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Scopus; Medicine; Clinical trial; Randomized controlled trial; External validity; MEDLINE; Population; Internal medicine; Medical physics; Oncology; Psychology","score_opus":0.8658882959528195,"score_gpt":0.714443397102945,"score_spread":0.15144489884987444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968544498","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00633178,0.0012458726,0.26990783,0.6507092,0.044659253,0.0057252888,0.0005566979,0.00023088747,0.020633174],"genre_scores_gemma":[0.00045905713,0.00013070022,0.6402708,0.29145792,0.066763535,0.00002237685,0.0000033106537,0.00040410654,0.00048816184],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.77643067,0.20204876,0.015691502,0.0014626303,0.0033168085,0.0010496468],"domain_scores_gemma":[0.6233532,0.36377376,0.00684659,0.0012890712,0.0030474106,0.0016899826],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32581937,0.00081254344,0.006013779,0.00031216207,0.00011547884,0.00031443918,0.0020311202,0.00083660166,0.0006056674],"category_scores_gemma":[0.84881777,0.00062290125,0.0019359504,0.00051468227,0.00025507552,0.00030240172,0.00028827082,0.00811081,0.0004991945],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005401312,0.00048161478,0.000052447034,0.00015166982,0.001014626,0.0032303338,0.00030386512,0.000033036467,0.0000139637705,0.00020166789,0.6379749,0.35114053],"study_design_scores_gemma":[0.007276193,0.0068211635,0.0006107866,0.0023535271,0.002662593,0.00016130196,0.0000801084,0.0000075842077,0.000030623498,0.03552574,0.94364095,0.0008294518],"about_ca_topic_score_codex":0.000012045462,"about_ca_topic_score_gemma":0.0000035872868,"teacher_disagreement_score":0.5229984,"about_ca_system_score_codex":0.00027708084,"about_ca_system_score_gemma":0.0013514678,"threshold_uncertainty_score":0.9996222},"labels":[],"label_agreement":null},{"id":"W1968867356","doi":"10.1191/1740774504cn022oa","title":"Study conduct, monitoring and data management in a trinational trial: the OPTIMA model","year":2004,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"HIV Legal Network; St. Paul's Hospital","funders":"","keywords":"Computer science; Management science; Operations research; Mathematics; Engineering","score_opus":0.972696557185163,"score_gpt":0.7657821579990427,"score_spread":0.2069143991861203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968867356","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7640079,0.00035634142,0.18782048,0.008195468,0.008429105,0.026441135,0.00043122642,0.0003216833,0.003996648],"genre_scores_gemma":[0.20778802,0.00030152997,0.7896323,0.00014644492,0.0015018956,0.0003827735,0.0000034597608,0.00004564398,0.00019792543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9815189,0.009855765,0.0061177057,0.001239955,0.0008478854,0.00041978495],"domain_scores_gemma":[0.67080706,0.32453337,0.0013880187,0.0028426854,0.00013833976,0.00029050958],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13563603,0.0002765957,0.0019712304,0.00009844128,0.00012110703,0.00013550831,0.001221279,0.00022677913,0.000039234354],"category_scores_gemma":[0.45452294,0.00017558556,0.00022143018,0.000309858,0.00031514227,0.00015812427,0.0011076048,0.0007116736,0.000017050024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.044516478,0.018556228,0.002275359,0.00021941739,0.0024900462,0.00036423313,0.00077206106,0.0010656461,0.000019815881,0.7224637,0.0035664185,0.20369054],"study_design_scores_gemma":[0.10026546,0.0005490949,0.0010797505,0.0000830699,0.00045924567,0.000001767953,0.00044704,0.0007556331,0.00001240812,0.8960185,0.000120909564,0.00020713884],"about_ca_topic_score_codex":0.000008318225,"about_ca_topic_score_gemma":0.0000042847428,"teacher_disagreement_score":0.6018118,"about_ca_system_score_codex":0.00006068156,"about_ca_system_score_gemma":0.00012972839,"threshold_uncertainty_score":0.89004457},"labels":[],"label_agreement":null},{"id":"W1969551119","doi":"10.1080/03610920601125920","title":"Statistical Inference of Adaptive Designs with Binary Responses","year":2007,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Health Sciences Centre Foundation","keywords":"Estimator; Test statistic; Contingency table; Statistical hypothesis testing; Statistical inference; Statistics; Mathematics; Consistency (knowledge bases); Goodness of fit; Statistic; Logarithm; Sufficient statistic; Adaptive design; Inference; Restricted randomization; Computer science; Clinical trial; Randomization; Artificial intelligence; Medicine","score_opus":0.6157867327055884,"score_gpt":0.6441146613557368,"score_spread":0.028327928650148437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969551119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052984804,0.00028233908,0.9919338,0.00002940859,0.00006276274,0.00043830663,0.00027436815,0.00003747718,0.0016430491],"genre_scores_gemma":[0.18494865,0.00017164763,0.8146583,0.00005111899,0.000014665071,0.00003256399,0.000005130308,0.00002680188,0.00009113538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9812732,0.016404942,0.0013429662,0.0003528525,0.00028012868,0.00034594335],"domain_scores_gemma":[0.6629996,0.33562657,0.00035959494,0.0006812666,0.00021528611,0.00011768156],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03785541,0.00022677134,0.0007242072,0.0002037705,0.000118609394,0.000020445823,0.0004151965,0.00016328681,0.00017487557],"category_scores_gemma":[0.16046774,0.0001874954,0.000028624609,0.0003547713,0.0015679596,0.000079364974,0.0002273792,0.0005124465,0.0000021517749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037022103,0.00019560092,0.00089083903,0.00010183879,0.00004249648,0.000012571951,0.00075536704,0.0000027104752,0.0005158886,0.8883009,0.000050970528,0.105428606],"study_design_scores_gemma":[0.00089779147,0.00056728325,0.014578961,0.00025914368,0.00010191457,0.000006756636,0.0008159623,0.0002847685,0.0019318295,0.9802598,0.00007357014,0.00022221709],"about_ca_topic_score_codex":0.000020200652,"about_ca_topic_score_gemma":0.000026832848,"teacher_disagreement_score":0.31922165,"about_ca_system_score_codex":0.00004654925,"about_ca_system_score_gemma":0.0001289091,"threshold_uncertainty_score":0.99073035},"labels":[],"label_agreement":null},{"id":"W1970618445","doi":"10.1002/bimj.200410081","title":"Superior Safety in Noninferiority Trials","year":2005,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"Medicine; Computer science","score_opus":0.7445144297138953,"score_gpt":0.6292261979994361,"score_spread":0.11528823171445912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970618445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18355595,0.0012949493,0.7876152,0.010639753,0.005185825,0.0015801624,0.00023052761,0.00025018558,0.009647453],"genre_scores_gemma":[0.11074228,0.000297703,0.88582885,0.0002907374,0.002634,0.000008114042,4.461432e-7,0.0000324183,0.00016547312],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99145615,0.0033652948,0.0033678315,0.00033604386,0.0008777635,0.0005969308],"domain_scores_gemma":[0.8907855,0.10741884,0.00065369287,0.0003627566,0.00020326053,0.00057595875],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03136656,0.00024218536,0.0016908195,0.0012471828,0.00012400714,0.00015584452,0.00047215246,0.00033326764,0.0030699815],"category_scores_gemma":[0.48537412,0.000175425,0.0004804838,0.0029691332,0.00014818682,0.00016642438,0.00012403984,0.0010019031,0.0001743519],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084913307,0.0012778183,0.0060628215,0.000040457668,0.00013648729,0.0001808198,0.0000970389,0.0000036764823,0.0011467854,0.034848057,0.0063765054,0.9489804],"study_design_scores_gemma":[0.010016725,0.0006787859,0.036982425,0.00017691728,0.00020669066,0.00039704036,0.00006664337,0.00044358143,0.0018396919,0.87247723,0.07595668,0.0007575736],"about_ca_topic_score_codex":0.000005347257,"about_ca_topic_score_gemma":0.0000035457008,"teacher_disagreement_score":0.9482228,"about_ca_system_score_codex":0.0003981141,"about_ca_system_score_gemma":0.00015994329,"threshold_uncertainty_score":0.99784136},"labels":[],"label_agreement":null},{"id":"W1971159432","doi":"10.1016/s1470-2045(14)70375-4","title":"Outcomes and endpoints in trials of cancer treatment: the past, present, and future","year":2014,"lang":"en","type":"review","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":218,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Surrogate endpoint; Clinical endpoint; Clinical trial; Intensive care medicine; Quality of life (healthcare); Medicine; Endpoint Determination; Overall survival; Cancer; Disease; Oncology; Internal medicine; Nursing","score_opus":0.7857781232112138,"score_gpt":0.682581246318719,"score_spread":0.1031968768924948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971159432","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038309303,0.9868216,0.000087666456,0.008113361,0.00086652546,0.0022499438,0.00042621625,0.000016625369,0.0013797836],"genre_scores_gemma":[0.0000017739864,0.9759104,0.017563183,0.00016325882,0.0055831396,0.0005243314,0.0000021241942,0.000031947704,0.00021982077],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9843611,0.01291778,0.0019282105,0.00033865235,0.00015147809,0.000302766],"domain_scores_gemma":[0.79889166,0.1990688,0.0013844278,0.0005835702,0.000025646126,0.00004588539],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01370645,0.00034473906,0.008195514,0.000056099092,0.000046743757,0.00001581304,0.00041448197,0.00047662872,0.00013622068],"category_scores_gemma":[0.016484449,0.00012898455,0.00031800976,0.00012311443,0.00044936303,0.000011484653,0.00018631307,0.00046071102,0.000003206503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077623,0.00006846736,0.00014023788,0.0037896594,0.0004403824,0.0000040982195,0.0001319219,2.3413868e-8,5.394221e-8,0.019677699,0.0025469493,0.9731229],"study_design_scores_gemma":[0.0016061615,0.00018035852,0.00020385582,0.00075278786,0.001685013,0.000008635299,0.000017925548,0.0000015052088,3.3544532e-7,0.18328075,0.8121597,0.00010297039],"about_ca_topic_score_codex":0.00006389874,"about_ca_topic_score_gemma":0.0001058075,"teacher_disagreement_score":0.9730199,"about_ca_system_score_codex":0.00008960785,"about_ca_system_score_gemma":0.00013472085,"threshold_uncertainty_score":0.9918001},"labels":[],"label_agreement":null},{"id":"W1971341357","doi":"10.1371/journal.pone.0051039","title":"Efficiency of New Dose Escalation Designs in Dose-Finding Phase I Trials of Molecularly Targeted Agents","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Institut National Du Cancer","keywords":"Clinical trial; Maximum tolerated dose; Medicine; Clinical study design; Oncology; Internal medicine","score_opus":0.8582517285798497,"score_gpt":0.5847323821987291,"score_spread":0.2735193463811205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971341357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7492911,0.00010633172,0.24903083,0.000035275723,0.000120634904,0.0010104578,0.00005361966,0.000026840633,0.00032487535],"genre_scores_gemma":[0.51006806,0.0000097958555,0.48975223,0.000011264975,0.00009143828,0.000012936392,0.0000024732137,0.000018328528,0.000033461307],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99457717,0.0018653558,0.002329778,0.0002147798,0.0006756735,0.0003372239],"domain_scores_gemma":[0.96935004,0.028867226,0.0010933125,0.000385196,0.00011689268,0.00018730572],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010498526,0.0001635375,0.0013693633,0.00020068829,0.00002072365,0.000009605375,0.00020936712,0.00018462073,0.0005479601],"category_scores_gemma":[0.23195569,0.00014574816,0.0001697163,0.00048230073,0.000071874194,0.00010792626,0.000056679997,0.000185046,0.00001382414],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010318443,0.020579886,0.003975888,0.00081604853,0.00046861818,0.0000052918117,0.0017267033,0.0000076271817,0.93886566,0.021765951,0.00015117633,0.010605318],"study_design_scores_gemma":[0.0087566115,0.0005638074,0.0028169549,0.0007275764,0.00071819854,2.9552385e-7,0.000049314447,0.0012598656,0.7094998,0.27537385,0.000002454394,0.00023127664],"about_ca_topic_score_codex":0.000018029243,"about_ca_topic_score_gemma":6.9298943e-7,"teacher_disagreement_score":0.2536079,"about_ca_system_score_codex":0.000048566166,"about_ca_system_score_gemma":0.000072176124,"threshold_uncertainty_score":0.77451384},"labels":[],"label_agreement":null},{"id":"W1971685703","doi":"10.1016/j.molonc.2014.07.025","title":"Early phase clinical trials to identify optimal dosing and safety","year":2014,"lang":"en","type":"review","venue":"Molecular Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":128,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute","keywords":"Dosing; Medicine; Clinical trial; Maximum tolerated dose; Pharmacodynamics; Adverse effect; Toxicity; Drug development; Pharmacology; Intensive care medicine; Pharmacokinetics; Drug; Internal medicine","score_opus":0.798122906497753,"score_gpt":0.7487920410666263,"score_spread":0.049330865431126636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971685703","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051775212,0.4666427,0.52670586,0.00018580486,0.0022077153,0.003113917,0.0001700116,0.00009229674,0.0008299148],"genre_scores_gemma":[0.0000016605318,0.5061986,0.4922034,0.00039675133,0.00083538383,0.00017099304,0.000008804649,0.00011494326,0.000069485046],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94589794,0.0432882,0.008217496,0.0014167731,0.00047889672,0.00070070394],"domain_scores_gemma":[0.7579027,0.23768637,0.0024432712,0.0010892176,0.00015578805,0.00072265824],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0706892,0.0007428455,0.013406889,0.00026343373,0.00010779155,0.000120222045,0.00073240284,0.0022213478,0.00029369708],"category_scores_gemma":[0.4922232,0.0005898938,0.0019185429,0.00034479165,0.0004155264,0.0000314114,0.00069710606,0.0016151564,0.00029386897],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023148092,0.00036122568,2.443237e-7,0.0033471305,0.00060672464,0.0003035374,0.00001908472,1.2170906e-7,0.000006827468,0.017542798,0.0018076148,0.9757732],"study_design_scores_gemma":[0.0033451866,0.0019753675,0.0000012324755,0.003486913,0.005151945,0.00007410001,0.000003120971,0.000008798065,0.0000041319013,0.07385035,0.9115341,0.0005647888],"about_ca_topic_score_codex":0.000004586717,"about_ca_topic_score_gemma":0.0000010031296,"teacher_disagreement_score":0.9752084,"about_ca_system_score_codex":0.0002046796,"about_ca_system_score_gemma":0.00050408795,"threshold_uncertainty_score":0.99965525},"labels":[],"label_agreement":null},{"id":"W1972274720","doi":"10.1002/cjs.11209","title":"Saddlepoint approximations for rank‐invariant permutation tests and confidence intervals with interval‐censoring","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Confidence interval; Mathematics; Nonparametric statistics; Statistics; Permutation (music); Censoring (clinical trials); Log-rank test; Statistical hypothesis testing; CDF-based nonparametric confidence interval; Invariant (physics); Statistical significance; Survival analysis","score_opus":0.3316907638098913,"score_gpt":0.45296419310699587,"score_spread":0.12127342929710455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972274720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059943832,0.00003251841,0.99197847,0.0005189535,0.00036701592,0.00035354687,0.0005189453,0.000008598883,0.00022757465],"genre_scores_gemma":[0.21492347,0.0000077517525,0.78463286,0.00014821829,0.00018129582,0.000010994036,0.0000024521134,0.000029184645,0.00006378883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99791044,0.00033406998,0.0010527207,0.00018149936,0.00022213146,0.00029911293],"domain_scores_gemma":[0.97162366,0.026002405,0.00071744266,0.00019410712,0.00086226687,0.00060013554],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028473116,0.00017147396,0.0005773537,0.00018347178,0.00014457427,0.0001391987,0.00019401584,0.00008329194,0.00009192973],"category_scores_gemma":[0.100624315,0.00013922657,0.00005893612,0.00010800619,0.0002784694,0.000115403986,0.000013121032,0.00026387148,0.0000024748877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010678963,0.000029667182,0.0005753457,0.00047128645,0.00013007091,0.000053927917,0.0012146,0.000038408194,0.00008688079,0.9663004,0.00296628,0.028026292],"study_design_scores_gemma":[0.0014423669,0.00081650587,0.0018941211,0.0006183466,0.0002481523,0.00022045115,0.0003171595,0.0061982716,0.00015746566,0.9868411,0.0010345897,0.00021150704],"about_ca_topic_score_codex":0.00019358145,"about_ca_topic_score_gemma":0.002698508,"teacher_disagreement_score":0.20892908,"about_ca_system_score_codex":0.00010337093,"about_ca_system_score_gemma":0.00044214033,"threshold_uncertainty_score":0.9069515},"labels":[],"label_agreement":null},{"id":"W1974321986","doi":"10.1002/sim.4099","title":"On the three‐arm non‐inferiority trial including a placebo with a prespecified margin","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Margin (machine learning); Assay sensitivity; Placebo; Medicine; Sample size determination; Randomized controlled trial; Statistics; Clinical trial; Randomization; Fraction (chemistry); Mathematics; Computer science; Surgery; Internal medicine; Machine learning","score_opus":0.4639363371681384,"score_gpt":0.5489701146468974,"score_spread":0.08503377747875895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974321986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08610375,0.000008349808,0.8765298,0.0036788075,0.0034584184,0.004163902,0.0002977877,0.00010672192,0.02565243],"genre_scores_gemma":[0.16888502,0.00001362314,0.82836604,0.00055772054,0.0015536714,0.0002842255,0.000005399475,0.00007201712,0.0002623088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960101,0.00067465124,0.0012221882,0.00052212016,0.0010717505,0.0004991457],"domain_scores_gemma":[0.84744984,0.15096837,0.0003791941,0.00086450874,0.00016262467,0.00017545742],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009585055,0.00035280673,0.0010235676,0.00013908732,0.00016809042,0.000037752186,0.00056263304,0.0002239127,0.0028288483],"category_scores_gemma":[0.25050533,0.00019371684,0.000045767432,0.00040066586,0.0009555318,0.000031055333,0.00014388682,0.0019209024,0.000034671928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02204589,0.00032339277,0.00017456656,0.00008288733,0.000057433153,0.00010905145,0.00040657967,0.0000016048971,0.0001748635,0.95668054,0.0143877715,0.005555437],"study_design_scores_gemma":[0.03639606,0.001899746,0.00082183885,0.00030838308,0.00011263597,0.0000064136975,0.00010961912,0.0012072459,0.000078857214,0.95822054,0.00059818965,0.00024045887],"about_ca_topic_score_codex":0.00008091607,"about_ca_topic_score_gemma":0.0009988153,"teacher_disagreement_score":0.24092028,"about_ca_system_score_codex":0.00006996157,"about_ca_system_score_gemma":0.00014459687,"threshold_uncertainty_score":0.9980827},"labels":[],"label_agreement":null},{"id":"W1974830949","doi":"10.1002/sim.4435","title":"Global hypothesis testing for high‐dimensional repeated measures outcomes","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institute on Drug Abuse; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Center for Research Resources; National Institute of Neurological Disorders and Stroke; National Institute on Alcohol Abuse and Alcoholism","keywords":"Sample size determination; Type I and type II errors; Covariate; False discovery rate; Multiple comparisons problem; Computer science; Inference; Univariate; Statistical power; Statistical hypothesis testing; Statistics; Statistical inference; Nominal level; Multivariate statistics; Mathematics; Machine learning; Artificial intelligence; Confidence interval","score_opus":0.7088825096546587,"score_gpt":0.5518508889249891,"score_spread":0.15703162072966959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974830949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007512093,0.0000366042,0.98306084,0.00041975043,0.0014579999,0.0010685608,0.0015558171,0.00016346539,0.0047248495],"genre_scores_gemma":[0.05857496,0.000003977922,0.9405084,0.00043285952,0.00021965243,0.000079857185,0.0000063462358,0.00004101258,0.0001328795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99640745,0.00048920716,0.0015071151,0.00048142686,0.0006536271,0.0004611964],"domain_scores_gemma":[0.882557,0.115971684,0.00038314558,0.00045270676,0.0004568805,0.00017862667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004790977,0.0002904917,0.0011029795,0.00010002711,0.00008314819,0.00000778704,0.00029611067,0.00016566161,0.00053322996],"category_scores_gemma":[0.60342205,0.00021462202,0.00005166339,0.00037792092,0.00043519252,0.000027575363,0.00007269686,0.00020624863,0.000012339247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040537733,0.00035153076,0.0430536,0.00024559317,0.00018205147,0.0001309946,0.00023431117,0.000003011991,0.00007431789,0.8411524,0.022120094,0.09204667],"study_design_scores_gemma":[0.0022735843,0.00049441133,0.074698746,0.00020615754,0.00020439031,0.000006478888,0.00004421374,0.0003296752,0.00006490529,0.92144024,0.000025369929,0.00021183272],"about_ca_topic_score_codex":0.00038127048,"about_ca_topic_score_gemma":0.00014239275,"teacher_disagreement_score":0.5986311,"about_ca_system_score_codex":0.00011901403,"about_ca_system_score_gemma":0.00008440169,"threshold_uncertainty_score":0.8752032},"labels":[],"label_agreement":null},{"id":"W1975210746","doi":"10.1016/j.cct.2003.08.010","title":"A simple alternative confidence interval for the difference between two proportions","year":2004,"lang":"en","type":"article","venue":"Controlled Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Mathematics; Simple (philosophy); Statistics; Simplicity; Interval estimation; Interval (graph theory); Tolerance interval; Transformation (genetics); Algorithm; Combinatorics","score_opus":0.8579537961197807,"score_gpt":0.6978556411322717,"score_spread":0.160098154987509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975210746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048645395,0.00007366775,0.97816247,0.0034618366,0.0020908155,0.009124724,0.0016787266,0.00016176648,0.00038142892],"genre_scores_gemma":[0.57785887,0.000119300166,0.4072468,0.0013617374,0.008266091,0.004174502,0.000021093436,0.0000973766,0.0008542196],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98116434,0.00857008,0.008020171,0.0008992074,0.000689221,0.0006569931],"domain_scores_gemma":[0.20461786,0.7901659,0.003088499,0.0010929027,0.00064821524,0.00038661624],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07044925,0.00043040526,0.0050753797,0.0000678698,0.00033265195,0.00017329102,0.001146079,0.00033434166,0.001065988],"category_scores_gemma":[0.89306116,0.00023388007,0.0023517061,0.00023109817,0.00089178665,0.000072960815,0.00022211464,0.00084494957,0.000076767785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009730045,0.0010589581,0.0010402653,0.000083106854,0.003541862,0.000015075477,0.00012025114,0.000025363071,0.00012186065,0.8512935,0.0034787382,0.12949099],"study_design_scores_gemma":[0.05534797,0.0008710359,0.0009636597,0.00015493031,0.0016761038,0.0000013039553,0.000045680103,0.00046054166,0.00030043756,0.9387646,0.0011327044,0.00028105685],"about_ca_topic_score_codex":0.000045257195,"about_ca_topic_score_gemma":0.000034797304,"teacher_disagreement_score":0.8226119,"about_ca_system_score_codex":0.00008042886,"about_ca_system_score_gemma":0.00039277843,"threshold_uncertainty_score":0.9998472},"labels":[],"label_agreement":null},{"id":"W1975337807","doi":"10.6000/1929-6029.2012.01.02.04","title":"Generalized Augmentation for Control of the k-Familywise Error Rate","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"False discovery rate; Multiple comparisons problem; Statistical hypothesis testing; Null hypothesis; Benchmark (surveying); Null (SQL); Statistics; Set (abstract data type); Computer science; Alternative hypothesis; Algorithm; Mathematics; Artificial intelligence; Data mining; Biology","score_opus":0.6604030492929751,"score_gpt":0.6823768039884841,"score_spread":0.021973754695508996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975337807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024093006,0.00017425224,0.96800923,0.003318299,0.0032496108,0.0004915093,0.00045163254,0.0000031538857,0.00020932077],"genre_scores_gemma":[0.5047,0.00015185788,0.49374643,0.00030619756,0.00095262093,0.000028758655,0.000001995152,0.000019343557,0.00009281577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916774,0.002634375,0.0017555503,0.00011742744,0.003444598,0.0003706664],"domain_scores_gemma":[0.88195115,0.114555165,0.00068031583,0.00017772558,0.0023719755,0.00026367442],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03328015,0.00010160137,0.00046022597,0.0002426297,0.000046333047,0.00002537827,0.001026822,0.00014351621,0.0006576984],"category_scores_gemma":[0.43605644,0.00006585015,0.00014074935,0.00021534726,0.0005069484,0.00008900668,0.00013306184,0.0007888597,0.00000392905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020558152,0.00093243166,0.005931799,0.0001365681,0.00032182437,0.000043973112,0.0003950588,0.000016734833,0.0008787338,0.89645386,0.018144596,0.07468862],"study_design_scores_gemma":[0.005851477,0.00019227997,0.0076521295,0.00034263826,0.000045779285,0.000019697683,0.00013402189,0.0039825,0.0010610566,0.97901905,0.0016224323,0.00007695847],"about_ca_topic_score_codex":0.000019351239,"about_ca_topic_score_gemma":0.000011659637,"teacher_disagreement_score":0.48060697,"about_ca_system_score_codex":0.00020436598,"about_ca_system_score_gemma":0.00045204881,"threshold_uncertainty_score":0.9954415},"labels":[],"label_agreement":null},{"id":"W1975621230","doi":"10.1249/00005768-200605001-03078","title":"The Relationship between Odds Ratios and Relative Risks","year":2006,"lang":"en","type":"article","venue":"Medicine & Science in Sports & Exercise","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Relative risk; Odds ratio; Confidence interval; Confounding; Medicine; Mathematics; Linear relationship; Odds; Statistics; Logistic regression; Algebraic number; Perspective (graphical); Demography","score_opus":0.42708759592177353,"score_gpt":0.5313582441838054,"score_spread":0.10427064826203186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975621230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9752879,0.000080839665,0.014841716,0.0023032082,0.0005274641,0.00076737767,0.0000045959364,0.00005667195,0.0061302306],"genre_scores_gemma":[0.9314112,0.00004611957,0.06739652,0.000036936995,0.0003002056,0.000040785748,8.6141756e-7,0.000013804826,0.00075353874],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99658996,0.00025844024,0.0011803146,0.0004834333,0.0010634605,0.00042437608],"domain_scores_gemma":[0.9377887,0.06095969,0.00038826998,0.00054735073,0.00014770075,0.00016826337],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01622732,0.0001794588,0.00054105173,0.00017630773,0.0005379477,0.0000478814,0.0003902353,0.0001038449,0.00007123774],"category_scores_gemma":[0.11694959,0.00010732327,0.00003580719,0.0011649026,0.0033900517,0.0002469714,0.00010882481,0.0004725276,0.000007605604],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001564822,0.000022357204,0.9276527,0.000012472608,2.0862059e-7,0.000014898747,0.00033481492,0.000001442658,0.0000036055037,0.048806947,0.00058561313,0.02254926],"study_design_scores_gemma":[0.00025447548,0.00002795529,0.5077946,0.00015875755,0.00003231079,0.0000014526836,0.0001313557,0.000042771873,0.0000034148247,0.4914067,0.00007958999,0.00006657089],"about_ca_topic_score_codex":0.00016117412,"about_ca_topic_score_gemma":0.000032942145,"teacher_disagreement_score":0.44259974,"about_ca_system_score_codex":0.000076830846,"about_ca_system_score_gemma":0.000118321426,"threshold_uncertainty_score":0.9993222},"labels":[],"label_agreement":null},{"id":"W1975919614","doi":"10.3899/jrheum.121445","title":"Dr. Ajeganova and Dr. Hafström reply","year":2013,"lang":"en","type":"letter","venue":"The Journal of Rheumatology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Confounding; Diabetes mellitus; Multivariate analysis; Multivariate statistics; Gerontology; Demography; Family medicine; Internal medicine; Statistics; Endocrinology; Mathematics","score_opus":0.3455094405845345,"score_gpt":0.48784098821120875,"score_spread":0.14233154762667427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975919614","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008411623,0.0006775115,0.019478707,0.9662986,0.003685342,0.0004703921,0.00003330913,0.000040907085,0.000903623],"genre_scores_gemma":[0.0006761503,0.003993503,0.48769727,0.4982001,0.0019380301,0.000019152354,0.0000031311915,0.0003007106,0.0071719782],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922594,0.003604574,0.0027487243,0.0002652076,0.0005984296,0.00052369473],"domain_scores_gemma":[0.8798884,0.1156248,0.0031536396,0.0008049341,0.0004079998,0.00012019692],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006697467,0.00041739785,0.0023726022,0.00018704879,0.00011296142,0.000058594618,0.0010643577,0.0010800634,0.00089605903],"category_scores_gemma":[0.083351195,0.00024063718,0.00029148758,0.00013289026,0.00084560126,0.00007488279,0.00026789532,0.0044389972,0.0001016124],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086203945,0.000026674026,0.00025660312,0.00033125348,0.00040169232,0.0001057416,0.00011623823,1.1464954e-7,0.00000767868,0.005616556,0.9916111,0.001440111],"study_design_scores_gemma":[0.0007346946,0.0002670781,0.000035319685,0.00045265642,0.00048797304,0.010564732,0.000036725614,0.000012376337,0.00002139183,0.7615431,0.22561567,0.00022826197],"about_ca_topic_score_codex":0.0000719152,"about_ca_topic_score_gemma":0.0000032342273,"teacher_disagreement_score":0.76599544,"about_ca_system_score_codex":0.00004687437,"about_ca_system_score_gemma":0.00017133563,"threshold_uncertainty_score":0.9978578},"labels":[],"label_agreement":null},{"id":"W1975987260","doi":"10.1158/1538-7445.am2011-1690","title":"Abstract 1690: Definition of dose-limiting toxicity in phase I cancer clinical trials of molecularly targeted agents","year":2011,"lang":"en","type":"article","venue":"Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Toxicity; Medicine; Clinical trial; Internal medicine; Oncology; Limiting; Cancer; Grading (engineering); Phases of clinical research","score_opus":0.9503854268774826,"score_gpt":0.7368618717235832,"score_spread":0.21352355515389942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975987260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877166,0.00033791777,0.0061992933,0.00009177527,0.00047037416,0.0012514743,0.00069110247,0.000022815118,0.0032186443],"genre_scores_gemma":[0.847461,0.00069761835,0.1512609,0.000041055497,0.00022125286,0.00025911254,0.0000032429023,0.000039877796,0.000015961377],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985724,0.007695999,0.004312008,0.00053259754,0.0011381984,0.00059723237],"domain_scores_gemma":[0.93014675,0.06705253,0.0011884087,0.0005725817,0.0008023589,0.00023738111],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059077784,0.0001816097,0.001654689,0.0002880364,0.0000495716,0.000015107476,0.0005021081,0.00034893717,0.0041578277],"category_scores_gemma":[0.3005419,0.00015713915,0.0003583439,0.00069268735,0.0006035412,0.000089259476,0.00016981797,0.0010187279,0.000009660306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017564828,0.013278183,0.027288092,0.004857581,0.0014051995,0.0002838505,0.0031536166,0.000009511958,0.4266304,0.17423084,0.005025924,0.32627195],"study_design_scores_gemma":[0.006513728,0.00054932234,0.015778653,0.0009862195,0.000090023794,3.9382192e-7,0.00016447724,0.00008268501,0.20708752,0.76851785,0.000027661019,0.00020144218],"about_ca_topic_score_codex":0.0010990573,"about_ca_topic_score_gemma":0.0001268381,"teacher_disagreement_score":0.59428704,"about_ca_system_score_codex":0.0001537332,"about_ca_system_score_gemma":0.0005480435,"threshold_uncertainty_score":0.9967525},"labels":[],"label_agreement":null},{"id":"W1976776379","doi":"10.1016/j.jclinepi.2010.12.006","title":"Selecting participants that raise a clinical trial’s population attributable fraction can increase the treatment effect within the trial and reduce the required sample size","year":2011,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sample size determination; Randomized controlled trial; Medicine; Attributable risk; Population; Relative risk; Epidemiology; Clinical trial; Internal medicine; Statistics; Environmental health; Confidence interval","score_opus":0.9098661758104728,"score_gpt":0.6814465334604112,"score_spread":0.22841964235006162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976776379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9762058,0.00017051835,0.008403231,0.006513317,0.006086231,0.0024972807,0.000025596795,0.000032903117,0.000065081935],"genre_scores_gemma":[0.8907371,0.0007189848,0.10098689,0.0017297565,0.0056069847,0.00012850929,0.0000013753157,0.000044283093,0.00004609776],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8723277,0.11256974,0.012996132,0.0006986398,0.00057323725,0.00083456293],"domain_scores_gemma":[0.058307614,0.9284309,0.011420577,0.001024013,0.00028820903,0.00052867347],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26891547,0.00041414305,0.004973471,0.000044631095,0.00053005596,0.000048201564,0.00067002996,0.00074741506,0.00012544503],"category_scores_gemma":[0.9487704,0.000158995,0.0014319471,0.00024899503,0.0010544116,0.00012986234,0.00013997532,0.0022367379,0.000005785686],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6801327,0.0026121107,0.19961128,0.000047592173,0.0020465772,0.000033578082,0.0005462885,0.000020123558,0.0000063829725,0.011062288,0.003573068,0.100308],"study_design_scores_gemma":[0.11789768,0.01869971,0.07658799,0.00011566647,0.0023411696,0.000060384587,0.0001661022,0.0008007784,0.000040910356,0.7824205,0.0006450616,0.00022400686],"about_ca_topic_score_codex":0.0011331077,"about_ca_topic_score_gemma":0.0002054208,"teacher_disagreement_score":0.81586117,"about_ca_system_score_codex":0.00012076304,"about_ca_system_score_gemma":0.00034904468,"threshold_uncertainty_score":0.9717638},"labels":[],"label_agreement":null},{"id":"W1976787897","doi":"10.1208/s12248-012-9382-1","title":"Bioequivalence Requirements in the European Union: Critical Discussion","year":2012,"lang":"en","type":"review","venue":"The AAPS Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Bioequivalence; Interim; Guideline; European union; Biopharmaceutical; Biopharmaceutics; Biopharmaceutics Classification System; Risk analysis (engineering); Computer science; Medicine; Operations research; Pharmacology; Actuarial science; Management science; Drug; Mathematics; Business; Engineering; Biotechnology; Pharmacokinetics; Law; Political science; Chemistry","score_opus":0.8561965321256647,"score_gpt":0.65870973901929,"score_spread":0.19748679310637474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976787897","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.297836e-7,0.9591819,0.02676649,0.0028812506,0.0025993525,0.0007216241,0.000038539747,0.000026704269,0.0077835834],"genre_scores_gemma":[0.000028384355,0.94051236,0.05513229,0.0001444057,0.0038589244,0.0000177702,0.0000012240262,0.000080470134,0.00022418723],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9506363,0.045239504,0.0022020843,0.00028606234,0.0009910397,0.0006449859],"domain_scores_gemma":[0.9415764,0.05625949,0.000832765,0.0010459645,0.00008151729,0.00020383962],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.065459445,0.00041645867,0.0014661095,0.00009982774,0.0003472422,0.00021725157,0.0022646144,0.00019785097,0.0005358868],"category_scores_gemma":[0.070951335,0.00013470348,0.00059671997,0.0003888418,0.0004926838,0.00012316016,0.0004396517,0.0027108104,0.00032838027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004155459,0.00015213847,0.0000015588693,0.0017952356,0.00004545746,0.00009302108,0.0001470405,1.3498002e-8,1.8440964e-7,0.02134011,0.0027369268,0.97368413],"study_design_scores_gemma":[0.00017273135,0.00006002311,0.00001321325,0.009918917,0.0011945096,0.000643875,0.00006267334,5.606962e-7,1.0723808e-7,0.4626561,0.52507263,0.00020465297],"about_ca_topic_score_codex":9.167686e-7,"about_ca_topic_score_gemma":6.0452794e-7,"teacher_disagreement_score":0.9734795,"about_ca_system_score_codex":0.000108136715,"about_ca_system_score_gemma":0.000109014676,"threshold_uncertainty_score":0.99959},"labels":[],"label_agreement":null},{"id":"W1976794477","doi":"10.1007/s11912-013-0303-y","title":"Benefit and Harms of New Anti-Cancer Drugs","year":2013,"lang":"en","type":"review","venue":"Current Oncology Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Drug; Randomized controlled trial; Clinical endpoint; Intensive care medicine; Clinical trial; Biomarker; Cancer drugs; Cancer; Oncology; Pharmacology; Internal medicine","score_opus":0.816919546873807,"score_gpt":0.6846755958939144,"score_spread":0.1322439509798926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976794477","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004662406,0.99015176,0.001114292,0.000043819495,0.0059753847,0.0018025427,0.00007623473,0.00005558342,0.0007337564],"genre_scores_gemma":[4.0820697e-7,0.8808982,0.11700363,0.000011939289,0.0008222022,0.00025041096,0.000009872054,0.00006754289,0.00093579956],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942457,0.00059031544,0.003597885,0.0008269648,0.00035399242,0.00038510776],"domain_scores_gemma":[0.97329295,0.02107975,0.0042542727,0.00083774125,0.00019724795,0.00033804332],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026258845,0.0005225999,0.0057854853,0.00014394392,0.000039857136,0.000021739514,0.00025325446,0.00082838547,0.0011869323],"category_scores_gemma":[0.02421138,0.00037669812,0.0005801625,0.0002113349,0.00034353224,0.000046367863,0.00035367056,0.0008545327,0.000025825346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018192178,0.0002184604,0.0000380044,0.017868437,0.00022750805,0.000036893616,0.000040265866,1.996017e-8,2.6360973e-7,0.002842339,0.019830612,0.9588954],"study_design_scores_gemma":[0.000183586,0.000075066826,0.0000048146167,0.0073651243,0.0018458419,0.00011439654,0.0000035084024,5.697214e-7,0.000003768224,0.24217628,0.7480032,0.00022386794],"about_ca_topic_score_codex":0.00001572867,"about_ca_topic_score_gemma":9.915707e-7,"teacher_disagreement_score":0.9586715,"about_ca_system_score_codex":0.00014575524,"about_ca_system_score_gemma":0.0009507815,"threshold_uncertainty_score":0.9998685},"labels":[],"label_agreement":null},{"id":"W1977230984","doi":"10.1177/00164402062003002","title":"Pairwise Multiple Comparison Tests when Data are Nonnormal","year":2002,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Type I and type II errors; Pairwise comparison; Heteroscedasticity; Statistic; Mathematics; Statistical hypothesis testing; Test statistic; Truncated mean; Econometrics; Multiple comparisons problem; Estimator","score_opus":0.9427542988485699,"score_gpt":0.6099393060666746,"score_spread":0.3328149927818953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977230984","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4886989,0.00905558,0.16847438,0.21684323,0.018908076,0.007561861,0.0021711634,0.0011175516,0.08716925],"genre_scores_gemma":[0.6155851,0.000028673248,0.38267317,0.0006819262,0.0006948615,0.000058251262,0.000008198453,0.00001201145,0.00025780362],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99707955,0.00053804,0.0007182057,0.00062391546,0.0007601539,0.00028013872],"domain_scores_gemma":[0.987797,0.010768701,0.00024363372,0.00073356985,0.00020513956,0.00025190655],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00277651,0.0001947814,0.00041113814,0.00003528383,0.00014252224,0.0000519021,0.00048432802,0.00013344667,0.0041569006],"category_scores_gemma":[0.046842396,0.00014271865,0.000051809515,0.000099593926,0.00017251984,0.00007501017,0.00014565281,0.00029708134,0.00018381598],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001552093,0.010730999,0.13797215,0.00013238165,0.0001379626,0.0000059097515,0.0003890147,0.0000011927353,0.00016853392,0.029201614,0.7394271,0.08167792],"study_design_scores_gemma":[0.0011734465,0.00028099545,0.28521508,0.000105966166,0.000067955654,0.000012370849,0.00007983447,0.00065382593,0.000018854065,0.6973832,0.014689974,0.0003184823],"about_ca_topic_score_codex":0.000005529919,"about_ca_topic_score_gemma":0.000011692529,"teacher_disagreement_score":0.72473717,"about_ca_system_score_codex":0.000043374937,"about_ca_system_score_gemma":0.0000126521445,"threshold_uncertainty_score":0.99675345},"labels":[],"label_agreement":null},{"id":"W1977276248","doi":"10.1198/sbr.2009.0060","title":"A Mixture Distribution Approach to Assessing Medication Refill Compliance with Administrative Pharmacy Refill Records","year":2010,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pharmacy; Medicine; Data mining; Computer science; Family medicine","score_opus":0.8440390306141359,"score_gpt":0.7117385052931429,"score_spread":0.132300525320993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977276248","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02032021,0.00003180176,0.9528842,0.003252293,0.00090368796,0.002497934,0.0033595706,0.00015349338,0.016596815],"genre_scores_gemma":[0.28856468,0.000048094767,0.7101044,0.0001933698,0.00035959875,0.00032729108,0.0001140517,0.000062079256,0.0002264294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99099195,0.0026848118,0.0013709668,0.0012302058,0.0023569257,0.0013651672],"domain_scores_gemma":[0.9478282,0.048715543,0.00024333135,0.0008358099,0.0013146534,0.0010624973],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.014043117,0.0004214742,0.0008108562,0.00027635082,0.0003664064,0.00026979906,0.0008962791,0.00033412577,0.0005139626],"category_scores_gemma":[0.13379823,0.00034222208,0.00006353442,0.0018080192,0.0015083092,0.00017778967,0.00032915163,0.0045445645,0.0001163534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002057863,0.0021659483,0.0015758694,0.0008385044,0.00009959186,0.00019912921,0.00035178545,0.0000032437285,0.010592606,0.87901235,0.019482179,0.08362093],"study_design_scores_gemma":[0.0048296233,0.00072800746,0.0069482108,0.0005690756,0.0001352287,0.00007709729,0.0004503401,0.019921575,0.010963469,0.923815,0.03048532,0.00107702],"about_ca_topic_score_codex":0.00006180581,"about_ca_topic_score_gemma":0.00007054285,"teacher_disagreement_score":0.26824448,"about_ca_system_score_codex":0.00035855026,"about_ca_system_score_gemma":0.0006506892,"threshold_uncertainty_score":0.99990296},"labels":[],"label_agreement":null},{"id":"W1979098773","doi":"10.1016/j.clpt.2004.11.010","title":"Effect of NONMEM minimization status and number of replicates on bootstrap parameter distributions for population pharmacokinetic models: A case study","year":2005,"lang":"en","type":"article","venue":"Clinical Pharmacology & Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"NONMEM; Covariate; Statistics; Nonparametric statistics; Population; Mathematics; Confidence interval; Pharmacokinetics; Coverage probability; Medicine; Econometrics; Pharmacology","score_opus":0.5229012801892853,"score_gpt":0.6348841190895517,"score_spread":0.11198283890026639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979098773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9506858,0.000054260323,0.045440875,0.00036397917,0.00042728384,0.002647111,0.00030356503,0.000050370207,0.000026739739],"genre_scores_gemma":[0.9043907,0.0001575781,0.0941783,0.0007202853,0.0002664288,0.0002150039,0.00001271013,0.000043485536,0.000015493522],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942473,0.0025370086,0.0021086012,0.0005426081,0.00022047588,0.00034397087],"domain_scores_gemma":[0.9031148,0.09540986,0.00076075626,0.00035607573,0.00020162633,0.00015687884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035635147,0.00028605157,0.0011237689,0.00006212259,0.000088804765,0.000010432015,0.0001664667,0.00028172962,0.00009993253],"category_scores_gemma":[0.004021107,0.00023418556,0.00023380981,0.00017931666,0.00043094248,0.00006782721,0.000074177515,0.00038356893,0.0000024486726],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030498413,0.035146512,0.1506844,0.0021754673,0.009656432,0.00013549917,0.0015796617,0.0036173896,0.0039128065,0.009806339,0.004335595,0.7484515],"study_design_scores_gemma":[0.06969138,0.037955817,0.0076030255,0.00023451661,0.034568105,0.00022775264,0.00034597723,0.36080566,0.037626367,0.44750127,0.0016388707,0.0018012476],"about_ca_topic_score_codex":0.000009112122,"about_ca_topic_score_gemma":0.0000024441076,"teacher_disagreement_score":0.7466502,"about_ca_system_score_codex":0.00004019822,"about_ca_system_score_gemma":0.000032029453,"threshold_uncertainty_score":0.95498097},"labels":[],"label_agreement":null},{"id":"W1979337024","doi":"10.1371/journal.pone.0036677","title":"Assessment and Implication of Prognostic Imbalance in Randomized Controlled Trials with a Binary Outcome – A Simulation Study","year":2012,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Hamilton Health Sciences; Population Health Research Institute; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Confidence interval; Sample size determination; Logistic regression; Statistical power; Randomized controlled trial; Relative risk; Medicine; Outcome (game theory); Meta-analysis; Statistical inference; Absolute risk reduction; Internal medicine; Statistical significance; Coverage probability; Standard error; Mathematics","score_opus":0.6280473404291305,"score_gpt":0.5833533459721452,"score_spread":0.0446939944569853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979337024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9611118,0.000077044024,0.027103847,0.0000876041,0.000030241334,0.011415328,0.000012171636,0.000030994415,0.00013098572],"genre_scores_gemma":[0.69333655,0.00000790528,0.30547675,0.000008301766,0.000049310802,0.0010955328,7.8162867e-7,0.000013235001,0.000011630107],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99003184,0.00635773,0.0026703847,0.00021524637,0.000525012,0.00019981712],"domain_scores_gemma":[0.73746854,0.2607796,0.001251718,0.0002685331,0.00016037295,0.00007124225],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034575146,0.00015881583,0.005161463,0.00011185071,0.000021654514,0.000015540043,0.00007403634,0.00007351955,0.000038089074],"category_scores_gemma":[0.30406255,0.00009445111,0.00012836275,0.0001677226,0.00008549798,0.000076980854,0.00003862854,0.00014421386,0.0000012753216],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11932265,0.030246349,0.82797164,0.0006055479,0.0022085535,0.000002188138,0.00055245403,0.000031457428,0.0023099796,0.016392142,0.0000013753844,0.00035563868],"study_design_scores_gemma":[0.55044675,0.001045798,0.31208673,0.0004509169,0.0045110914,3.3908807e-7,0.00013388965,0.011662154,0.00019594512,0.11926388,6.264044e-8,0.00020245259],"about_ca_topic_score_codex":0.000005285724,"about_ca_topic_score_gemma":0.0000012678628,"teacher_disagreement_score":0.51588494,"about_ca_system_score_codex":0.00003759091,"about_ca_system_score_gemma":0.00003128852,"threshold_uncertainty_score":0.9941081},"labels":[],"label_agreement":null},{"id":"W1979781274","doi":"10.1002/pst.200","title":"Power and sample size considerations in clinical trials with competing risk endpoints","year":2006,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Sample size determination; Accrual; Event (particle physics); Weibull distribution; Clinical trial; Econometrics; Parametric statistics; Clinical endpoint; Sample (material); Statistics; Actuarial science; Computer science; Medicine; Economics; Mathematics; Internal medicine; Accounting","score_opus":0.6618107269419979,"score_gpt":0.6408193264275303,"score_spread":0.020991400514467684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979781274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05259555,0.000096377364,0.9373134,0.0007738231,0.0005972385,0.0015125053,0.00457074,0.00015950401,0.002380879],"genre_scores_gemma":[0.2516844,0.000079933845,0.7475139,0.0003804666,0.00023590632,0.0000343012,0.0000032724008,0.00004311347,0.00002470843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863247,0.0083031515,0.0035664402,0.0006618543,0.00054189644,0.0006019303],"domain_scores_gemma":[0.362777,0.63577366,0.0006596732,0.00029240685,0.00017397513,0.00032330232],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022997811,0.00034623445,0.0016374026,0.00006813225,0.0001828272,0.00013462326,0.00013418266,0.00021596531,0.002481508],"category_scores_gemma":[0.7308038,0.00027147512,0.000118424185,0.00021083924,0.0007889185,0.000064949956,0.0001292901,0.0010918117,0.00002632577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083221885,0.0013840463,0.11557658,0.00017629842,0.00022859962,0.0002684898,0.00011071451,0.000024114159,0.000075539225,0.8552109,0.0068674274,0.019245086],"study_design_scores_gemma":[0.00467783,0.00020588368,0.029737258,0.00006745265,0.00034698527,0.000019360798,0.000042641415,0.0030727237,0.00015133256,0.96053374,0.0007938568,0.00035091836],"about_ca_topic_score_codex":0.000092018636,"about_ca_topic_score_gemma":0.0001153098,"teacher_disagreement_score":0.70780593,"about_ca_system_score_codex":0.000056245193,"about_ca_system_score_gemma":0.000112373666,"threshold_uncertainty_score":0.9999737},"labels":[],"label_agreement":null},{"id":"W1980344160","doi":"10.1007/s00784-013-0949-8","title":"Randomization in clinical trials: stratification or minimization? The HERMES free simulation software","year":2013,"lang":"en","type":"article","venue":"Clinical Oral Investigations","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Université Paris Descartes","keywords":"Predictability; Randomization; Minification; Computer science; Clinical trial; Sample size determination; Observational study; Software; Statistics; Randomized controlled trial; Econometrics; Medicine; Medical physics; Data mining; Mathematics; Surgery; Internal medicine","score_opus":0.8513299065557994,"score_gpt":0.6597704462342981,"score_spread":0.19155946032150128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980344160","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060612213,0.000060521365,0.9058417,0.021174781,0.0030787194,0.007941079,0.0001512113,0.000508209,0.00063155947],"genre_scores_gemma":[0.109982416,0.00010749152,0.8835542,0.0031154763,0.0013439234,0.000805146,0.00007137852,0.00008466274,0.0009353038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9670319,0.021740692,0.0093470905,0.0008324741,0.0006255305,0.00042233308],"domain_scores_gemma":[0.1636284,0.82671165,0.0044538616,0.0029545731,0.0014310468,0.00082044146],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040542915,0.0003693506,0.0018693719,0.0001452074,0.00030142913,0.00028977575,0.0008638557,0.0007502462,0.0019134763],"category_scores_gemma":[0.8709212,0.00022706692,0.0006148248,0.0010814598,0.001086435,0.0005301911,0.00017737452,0.0010636167,0.00024853685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021467188,0.0041455557,0.1318828,0.00026460664,0.00069327396,0.000012136442,0.0006820638,0.011455657,0.000029423583,0.36629027,0.22729725,0.25510025],"study_design_scores_gemma":[0.0066559045,0.00019674501,0.03498246,0.000101259444,0.0002652515,9.5005646e-7,0.000108883745,0.07028825,0.000013970389,0.8860564,0.001032628,0.0002972581],"about_ca_topic_score_codex":0.000046509038,"about_ca_topic_score_gemma":0.00017560153,"teacher_disagreement_score":0.8303783,"about_ca_system_score_codex":0.00006662429,"about_ca_system_score_gemma":0.00044783243,"threshold_uncertainty_score":0.9989989},"labels":[],"label_agreement":null},{"id":"W1980718559","doi":"10.1037/1082-989x.10.3.317","title":"An Alternative to Cohen's Standardized Mean Difference Effect Size: A Robust Parameter and Confidence Interval in the Two Independent Groups Case.","year":2005,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":292,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Percentile; Confidence interval; Mathematics; Robust confidence intervals; Coverage probability; Truncated mean; Confidence distribution; CDF-based nonparametric confidence interval; Population; Standard deviation; Tolerance interval; Range (aeronautics); Measure (data warehouse); Medicine","score_opus":0.4903035578928938,"score_gpt":0.6284214039490661,"score_spread":0.13811784605617228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980718559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44307768,0.000023700744,0.5545641,0.000553954,0.00029144678,0.0010104905,0.000032706947,0.000056651003,0.00038925238],"genre_scores_gemma":[0.44892904,0.00000814065,0.54934686,0.0013043007,0.00017859357,0.00020374995,2.6889282e-7,0.000018109502,0.000010933414],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9742556,0.022199819,0.0012045504,0.0011254514,0.0006137919,0.00060075935],"domain_scores_gemma":[0.8201193,0.17839383,0.0002463637,0.0008293131,0.000091615344,0.00031955543],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.026773086,0.00045225644,0.0013050082,0.00009353076,0.00011614824,0.00020056138,0.0008736,0.00027046105,0.00038627323],"category_scores_gemma":[0.1349491,0.00025806503,0.00017693975,0.0003736835,0.00045336227,0.0001029205,0.00023170176,0.0011182677,0.000012608806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032487724,0.0014827785,0.0017536893,0.00007883898,0.00014937049,0.0014133097,0.0047373143,0.000045636087,0.0025381504,0.084259026,0.00017656518,0.90011656],"study_design_scores_gemma":[0.004365852,0.003428238,0.011922998,0.00013246314,0.0001408336,0.0007971115,0.0004047396,0.002135997,0.001445774,0.9746147,0.00007682775,0.00053448294],"about_ca_topic_score_codex":0.000043074226,"about_ca_topic_score_gemma":0.00006777177,"teacher_disagreement_score":0.8995821,"about_ca_system_score_codex":0.00008788912,"about_ca_system_score_gemma":0.000009799477,"threshold_uncertainty_score":0.9999872},"labels":[],"label_agreement":null},{"id":"W1980971305","doi":"10.1186/1471-2407-14-260","title":"The randomised clinical trial and the hazard ratio – medical research’s Emperor’s New Clothes?","year":2014,"lang":"en","type":"article","venue":"BMC Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; Hazard ratio; Statistic; Randomized controlled trial; Clinical trial; Hazard; Emperor; Internal medicine; Confidence interval; Statistics","score_opus":0.770981268210522,"score_gpt":0.6730524972166427,"score_spread":0.09792877099387931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980971305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085948296,0.0043762317,0.7201507,0.1205357,0.024062485,0.01956372,0.00006086511,0.00045269314,0.02484932],"genre_scores_gemma":[0.10931676,0.019554105,0.7156942,0.013203003,0.095467895,0.006301432,0.000003083097,0.00051226356,0.039947275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9776911,0.01767091,0.0019296176,0.0005198824,0.001645888,0.0005425599],"domain_scores_gemma":[0.41116875,0.58679146,0.00037071202,0.00097518746,0.0002110453,0.00048281904],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08763929,0.00018994854,0.0009671239,0.000028036478,0.00047856933,0.00020064042,0.0007752511,0.00033587334,0.001007188],"category_scores_gemma":[0.6824308,0.00008526837,0.00033991295,0.00017979695,0.002528007,0.00003571644,0.00028034198,0.0010951465,0.000052854386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.19158424,0.00009330901,0.0001737253,0.0000364137,0.00014228816,0.0000015312788,0.0001589821,5.265244e-7,0.0000019964662,0.45760915,0.1798987,0.17029913],"study_design_scores_gemma":[0.24076241,0.00019794118,0.00018673706,0.00007080757,0.00009943442,0.0000014283759,0.000042443553,0.0013277838,0.000015683052,0.6904161,0.06676759,0.00011166116],"about_ca_topic_score_codex":0.00015823996,"about_ca_topic_score_gemma":0.0008244564,"teacher_disagreement_score":0.59479153,"about_ca_system_score_codex":0.0000423608,"about_ca_system_score_gemma":0.0009233019,"threshold_uncertainty_score":0.999906},"labels":[],"label_agreement":null},{"id":"W1981114551","doi":"10.1016/j.jclinepi.2008.07.006","title":"Bayesian statistical inference enhances the interpretation of contemporary randomized controlled trials","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":178,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Toronto General Hospital; University of Toronto","funders":"","keywords":"Randomized controlled trial; Interpretation (philosophy); Statistical inference; Inference; Bayesian probability; Bayesian inference; Bayesian statistics; Computer science; Statistics; Econometrics; Artificial intelligence; Medicine; Machine learning; Mathematics; Internal medicine","score_opus":0.7954584011993118,"score_gpt":0.678490372859101,"score_spread":0.1169680283402108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981114551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012870123,0.0006946984,0.9766692,0.004090431,0.0028881752,0.0013429306,0.000034135235,0.000015094799,0.0013952282],"genre_scores_gemma":[0.6006829,0.0012151967,0.39622667,0.0009526445,0.00083058374,0.000030527393,6.9937937e-7,0.000014216207,0.00004653822],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6180377,0.31822675,0.061542217,0.0005703026,0.0010354759,0.0005875734],"domain_scores_gemma":[0.021892544,0.9482471,0.028058479,0.000473542,0.0010038407,0.00032451574],"candidate_categories":["metaresearch","metaepi_broad","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4546899,0.00032203196,0.030457415,0.00014155528,0.00008110636,0.000009002053,0.0007188786,0.00056469475,0.00052207883],"category_scores_gemma":[0.99292433,0.00014167809,0.0044832206,0.00015313667,0.0035400242,0.000108643864,0.00009431402,0.0015516109,0.000008721194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.48884597,0.00078711344,0.005275751,0.00012907707,0.0038630662,0.00007070564,0.00027072857,0.0000638211,0.00003338903,0.472519,0.011599673,0.016541673],"study_design_scores_gemma":[0.13457058,0.00093377696,0.0011635018,0.00023158669,0.0008302222,0.00004069316,0.00004291292,0.0077133817,0.000031887994,0.8542461,0.000078875484,0.00011651161],"about_ca_topic_score_codex":0.000013253393,"about_ca_topic_score_gemma":0.0000017965847,"teacher_disagreement_score":0.6300203,"about_ca_system_score_codex":0.000019573597,"about_ca_system_score_gemma":0.000771356,"threshold_uncertainty_score":0.9991718},"labels":[],"label_agreement":null},{"id":"W1981263734","doi":"10.1097/mlr.0b013e318068932a","title":"Designed Delays Versus Rigorous Pragmatic Trials","year":2007,"lang":"en","type":"article","venue":"Medical Care","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"National Institute on Aging","keywords":"Generalizability theory; Checklist; Clinical trial; Protocol (science); Medicine; Randomization; Randomized controlled trial; Computer science; Medical physics; Psychology; Alternative medicine","score_opus":0.6329646411933201,"score_gpt":0.6233916215225614,"score_spread":0.009573019670758631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981263734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016405595,0.0004507806,0.94916415,0.00070068956,0.0047118077,0.0012297682,0.00006885538,0.00038153533,0.026886797],"genre_scores_gemma":[0.12441323,0.000024123983,0.8729638,0.0005748818,0.0017587971,0.000057007594,0.000009320922,0.00006911821,0.0001297104],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9919745,0.0027089098,0.0022916193,0.00045926176,0.0019076269,0.000658127],"domain_scores_gemma":[0.65267515,0.34479466,0.0005270085,0.0007447549,0.0003130173,0.00094541494],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032091636,0.00027645507,0.0014150351,0.000090307316,0.0001168696,0.00003556114,0.0005482031,0.0005992391,0.0050362134],"category_scores_gemma":[0.72866863,0.00020331128,0.00034773702,0.00030491772,0.0002709317,0.000041150208,0.00014031804,0.00059898046,0.00022396186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003149024,0.00047633096,0.00017015247,0.0010024098,0.0004281749,0.0012203193,0.0022062499,7.126721e-7,0.00019424938,0.26615316,0.0227224,0.7022768],"study_design_scores_gemma":[0.013889083,0.001216982,0.00021233477,0.0004237272,0.00081750745,0.000033024873,0.0019390236,0.000112063004,0.0027517567,0.97054845,0.007342134,0.0007139017],"about_ca_topic_score_codex":0.000014041202,"about_ca_topic_score_gemma":0.00006548772,"teacher_disagreement_score":0.7043953,"about_ca_system_score_codex":0.00016109068,"about_ca_system_score_gemma":0.00023263233,"threshold_uncertainty_score":0.99666536},"labels":[],"label_agreement":null},{"id":"W1981591556","doi":"10.2165/11318040-000000000-00000","title":"Evaluation of Bioequivalence for Highly Variable Drugs with Scaled Average Bioequivalence","year":2009,"lang":"en","type":"review","venue":"Clinical Pharmacokinetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":98,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Sample size determination; Replicate; Econometrics; Sample (material); Computer science; Statistics; Medicine; Mathematics; Pharmacology; Bioavailability","score_opus":0.7578223706805757,"score_gpt":0.6614144956818232,"score_spread":0.09640787499875247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981591556","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019104338,0.82364863,0.16009195,0.0000918084,0.0027595614,0.0088424,0.0016303152,0.00020994984,0.002706309],"genre_scores_gemma":[0.000012279008,0.56762743,0.43055502,0.00010955624,0.0010395357,0.00031065068,0.00002784563,0.00012777816,0.00018990831],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98058337,0.00691065,0.0071914177,0.001701819,0.0027052897,0.00090743497],"domain_scores_gemma":[0.8532971,0.13797042,0.0041044937,0.00165705,0.0024684465,0.00050246925],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042942632,0.0010757386,0.006603289,0.00025265006,0.000113438866,0.00006692501,0.0016882693,0.0012136652,0.0005457761],"category_scores_gemma":[0.1423966,0.0007949614,0.0015125058,0.0010702135,0.0010301855,0.00010473994,0.0002763679,0.0014555565,0.000043519998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019385059,0.0010309056,0.0000011356926,0.017970178,0.0007804944,0.0000055481723,0.000012416075,0.000014612037,0.000002517342,0.011458744,0.004152772,0.9643768],"study_design_scores_gemma":[0.005954741,0.0017660821,0.0000015523185,0.017804425,0.04246612,0.000011455007,0.0000053049484,0.00229963,0.00006265448,0.4481629,0.4802573,0.0012078021],"about_ca_topic_score_codex":0.0000018266566,"about_ca_topic_score_gemma":3.0416493e-7,"teacher_disagreement_score":0.96316904,"about_ca_system_score_codex":0.00021962365,"about_ca_system_score_gemma":0.0016107035,"threshold_uncertainty_score":0.99945015},"labels":[],"label_agreement":null},{"id":"W1981725031","doi":"10.1188/08.cjon.749-755","title":"Uncertainty After Treatment for Prostate Cancer: Definition, Assessment, and Management","year":2008,"lang":"en","type":"article","venue":"Clinical journal of oncology nursing","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Centre National d’Etudes Spatiales; Oncology Nursing Society; American Cancer Society","keywords":"Medicine; Prostate cancer; Intensive care medicine; Prostate; Cancer; Management of prostate cancer; Medical physics; Internal medicine","score_opus":0.6844022541218632,"score_gpt":0.6621031271234247,"score_spread":0.0222991269984385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981725031","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74505156,0.0014199035,0.22172074,0.015514049,0.007943413,0.0028185023,0.00018695778,0.00006492731,0.0052799643],"genre_scores_gemma":[0.091946624,0.007838753,0.89862275,0.00058304355,0.00078215933,0.00010022186,8.353807e-7,0.000027392169,0.00009822702],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961262,0.0009851475,0.0020985105,0.0002760023,0.00021243637,0.00030172142],"domain_scores_gemma":[0.96394706,0.034234077,0.001069462,0.00017917273,0.0003147736,0.0002554648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003638885,0.0001841664,0.0011171504,0.00008473494,0.00014023359,0.000015796004,0.000121126606,0.00022537445,0.00005581438],"category_scores_gemma":[0.005246365,0.0001348619,0.00033119466,0.00008714902,0.0007378158,0.000067585155,0.000028043527,0.00033469158,0.000001399472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046087094,0.0034597989,0.031531785,0.00013879893,0.0008372368,0.00057005306,0.00045657845,0.00000970974,0.0000085202555,0.02542792,0.010051838,0.92289907],"study_design_scores_gemma":[0.010459085,0.006843407,0.034216233,0.0006449139,0.0011255239,0.00027427272,0.0001939348,0.00013693557,0.000013015982,0.934822,0.011072976,0.00019768246],"about_ca_topic_score_codex":0.000001334889,"about_ca_topic_score_gemma":0.000002952817,"teacher_disagreement_score":0.92270136,"about_ca_system_score_codex":0.00051216705,"about_ca_system_score_gemma":0.0004124202,"threshold_uncertainty_score":0.6280768},"labels":[],"label_agreement":null},{"id":"W1981902086","doi":"10.1007/s40262-015-0236-8","title":"Reporting Guidelines for Clinical Pharmacokinetic Studies: The ClinPK Statement","year":2015,"lang":"en","type":"article","venue":"Clinical Pharmacokinetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":172,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Memorial University of Newfoundland; St. Michael's Hospital; University of Ottawa; University of Toronto; Sunnybrook Health Science Centre; University of Waterloo; University of Manitoba; Children's & Women's Health Centre of British Columbia; Ottawa Hospital","funders":"National Medical Research Council; National Health and Medical Research Council; University of Ottawa","keywords":"Medicine; Statement (logic); Pharmacotherapy; Intensive care medicine; MEDLINE; Pharmacokinetics; Medical physics; Pharmacology; Internal medicine; Chemistry; Political science","score_opus":0.9819514435848298,"score_gpt":0.8061165991694247,"score_spread":0.1758348444154051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981902086","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07450545,0.016911766,0.6845375,0.09616826,0.09601659,0.020118073,0.00075698143,0.002227613,0.008757791],"genre_scores_gemma":[0.008401227,0.008513419,0.9461553,0.017725434,0.016174622,0.0005749264,0.000010908801,0.00023355393,0.0022105973],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9675571,0.0037751421,0.024546776,0.0015542408,0.0014482834,0.001118503],"domain_scores_gemma":[0.5948593,0.36982,0.017171744,0.0037997514,0.011908523,0.002440673],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12497096,0.00071021024,0.003134754,0.00008227797,0.000271652,0.00010567666,0.0014441209,0.0004346201,0.00017026934],"category_scores_gemma":[0.79539394,0.0004567719,0.001789691,0.000497484,0.0015460781,0.00010997926,0.00081989355,0.0015519289,0.00011633202],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007745354,0.0009626026,0.0026218076,0.00024629847,0.0016456305,0.000049643942,0.00011822622,0.00012415226,0.000014002471,0.0039138114,0.83091915,0.15861012],"study_design_scores_gemma":[0.008575973,0.0011103759,0.00017752578,0.00015685741,0.0022542276,0.000013634971,0.00040634267,0.008078618,0.0002445902,0.44969478,0.52867466,0.0006124381],"about_ca_topic_score_codex":0.000003202215,"about_ca_topic_score_gemma":0.0000012812984,"teacher_disagreement_score":0.670423,"about_ca_system_score_codex":0.00012313052,"about_ca_system_score_gemma":0.0004722393,"threshold_uncertainty_score":0.9997884},"labels":[],"label_agreement":null},{"id":"W1982070055","doi":"10.1177/0962280211436004","title":"Impact of weighted composite compared to traditional composite endpoints for the design of randomized controlled trials","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"","keywords":"Discriminative model; Composite number; Weighting; Statistics; Event (particle physics); Clinical endpoint; Sample size determination; Component (thermodynamics); Mathematics; Clinical trial; Medicine; Computer science; Econometrics; Algorithm; Artificial intelligence; Internal medicine","score_opus":0.827207652661658,"score_gpt":0.7242513774061305,"score_spread":0.10295627525552742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982070055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001213007,0.00036058578,0.9842229,0.0008861416,0.0006028701,0.01107603,0.0010807456,0.000023867284,0.00053384143],"genre_scores_gemma":[0.04953331,0.00010080273,0.9475149,0.00007887181,0.00045442284,0.002218741,0.000013709121,0.00005531492,0.000029912682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79726344,0.18429825,0.01021785,0.0007470228,0.005648953,0.0018245107],"domain_scores_gemma":[0.064326316,0.9314025,0.0010606188,0.0007064674,0.0013118023,0.0011922686],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45671725,0.0004317575,0.010750865,0.0006219715,0.00016362777,0.000043260578,0.0011633472,0.0004537111,0.0050471216],"category_scores_gemma":[0.9295541,0.00022211329,0.0015569119,0.0010599477,0.003116478,0.00006365185,0.00027845608,0.0014411467,0.00001101192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.33648917,0.0024111308,0.00012871771,0.0003698778,0.0024132342,0.000009441438,0.00041775705,0.000031824504,0.0041279765,0.5692559,0.003918586,0.08042636],"study_design_scores_gemma":[0.13795595,0.00062962744,0.0014294084,0.00042254393,0.00062051124,0.0000054979278,0.000044086257,0.04565442,0.0015875868,0.8114254,0.000022025592,0.00020295155],"about_ca_topic_score_codex":0.00008007299,"about_ca_topic_score_gemma":0.0000015669681,"teacher_disagreement_score":0.7471043,"about_ca_system_score_codex":0.00020935175,"about_ca_system_score_gemma":0.00068731495,"threshold_uncertainty_score":0.9995965},"labels":[],"label_agreement":null},{"id":"W1982378721","doi":"10.1016/j.jval.2013.08.1748","title":"Estimating Chronic Disease PREVALENCE from Claims Data: Reducing Bias by Accounting for Diseased Individuals Who Do Not Generate Claims","year":2013,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis","funders":"","keywords":"Bayes' theorem; Disease; Poisson distribution; Medicine; Statistics; Estimator; Prevalence; Sampling bias; Demography; Econometrics; Bayesian probability; Epidemiology; Mathematics; Sample size determination; Internal medicine","score_opus":0.615827141474533,"score_gpt":0.5471703359299652,"score_spread":0.06865680554456777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982378721","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6727115,0.0026929735,0.29871866,0.004421031,0.0021621862,0.0068874834,0.012078076,0.0003053944,0.000022691022],"genre_scores_gemma":[0.0987673,0.00022106376,0.89747334,0.00080755557,0.0017680103,0.0005820447,0.00018871289,0.00012786563,0.00006408663],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99173486,0.002312253,0.0026675514,0.001426921,0.00077633036,0.0010821114],"domain_scores_gemma":[0.92541546,0.07014887,0.0014447161,0.00204482,0.00016356196,0.0007825503],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010493024,0.00042946037,0.0011616088,0.000120114375,0.0003426072,0.00036087798,0.0011700533,0.00020230246,0.00029362782],"category_scores_gemma":[0.08208787,0.000395622,0.0001344593,0.00034968197,0.00016627196,0.00054608926,0.0004939474,0.00057412864,0.00004707999],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009788924,0.0039367825,0.10654836,0.06481504,0.0010366591,0.00004757541,0.0038600431,0.03508821,0.002617753,0.055068012,0.1888855,0.5371172],"study_design_scores_gemma":[0.001459525,0.000111664776,0.004496109,0.002921379,0.00012713972,3.8779646e-7,0.00002827231,0.49022865,0.00010836238,0.49997994,0.00012985306,0.00040869703],"about_ca_topic_score_codex":0.0015089433,"about_ca_topic_score_gemma":0.000006052121,"teacher_disagreement_score":0.5987547,"about_ca_system_score_codex":0.00044401808,"about_ca_system_score_gemma":0.00093649863,"threshold_uncertainty_score":0.99984956},"labels":[],"label_agreement":null},{"id":"W1982616925","doi":"10.1002/cjs.11198","title":"A semiparametric linear transformation model to estimate causal effects for survival data","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute; Program for New Century Excellent Talents in University; National Natural Science Foundation of China; National Science Foundation","keywords":"Semiparametric regression; Semiparametric model; Estimator; Transformation (genetics); Econometrics; Mathematics; Parametric statistics; Proportional hazards model; Generalized linear model; Linear regression; Estimating equations; Linear model; Statistics; Power transform; Data transformation; Applied mathematics; Computer science; Data mining","score_opus":0.5741567501406204,"score_gpt":0.5334148321011077,"score_spread":0.04074191803951266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982616925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035327172,0.000023407114,0.989632,0.0005323489,0.0009884916,0.0009456854,0.004169232,0.000011186965,0.00016490716],"genre_scores_gemma":[0.023007838,0.000005978734,0.9763218,0.00021897793,0.00026912152,0.000021999107,0.000027803037,0.00004920517,0.000077281686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997418,0.00023278945,0.0012715852,0.00021230338,0.00036778458,0.00049753656],"domain_scores_gemma":[0.96764535,0.029272392,0.00042035241,0.0004816196,0.0008637278,0.001316533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002802646,0.0002033401,0.00069817004,0.00034896415,0.00012020395,0.000117925796,0.0006801738,0.00013947864,0.00009211643],"category_scores_gemma":[0.14276417,0.00018094927,0.00007101266,0.0003218893,0.000087435,0.00024105494,0.000028628385,0.00031673748,0.000033697703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020293752,0.00017033867,0.00032979654,0.0018507807,0.00046243987,0.00015317513,0.0012648848,0.0068783076,0.00020762967,0.56064624,0.2660537,0.16177979],"study_design_scores_gemma":[0.0009620859,0.000374747,0.00024146678,0.00012683298,0.00023992054,0.00001945097,0.000028721011,0.2655286,0.00009465209,0.731451,0.00071906665,0.00021347626],"about_ca_topic_score_codex":0.00050680176,"about_ca_topic_score_gemma":0.0021699574,"teacher_disagreement_score":0.26533464,"about_ca_system_score_codex":0.00015139689,"about_ca_system_score_gemma":0.0010567995,"threshold_uncertainty_score":0.8644567},"labels":[],"label_agreement":null},{"id":"W1983518614","doi":"10.1016/j.ejca.2010.12.005","title":"Randomised controlled trials in oncology closed early for benefit: Trends in methodology, results, and interpretation","year":2011,"lang":"en","type":"review","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Cancer Care Ontario","keywords":"Interim; Interim analysis; Medicine; Accrual; Clinical trial; Sample size determination; Interpretation (philosophy); Closure (psychology); Medical physics; Oncology; Internal medicine; Statistics; Computer science","score_opus":0.827093014633824,"score_gpt":0.6594701102687771,"score_spread":0.1676229043650469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983518614","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022612252,0.94201815,0.050258208,0.00012459233,0.0019233914,0.0023263686,0.0001927842,0.000008886933,0.0031249984],"genre_scores_gemma":[0.000013063784,0.6479322,0.35103396,0.00004493132,0.000660792,0.000077684716,0.0000018058582,0.00006647974,0.00016909071],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9100717,0.072813936,0.015815524,0.000528528,0.00031193346,0.0004583871],"domain_scores_gemma":[0.6737049,0.31751606,0.008198753,0.00019730392,0.0002565962,0.00012639684],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21610527,0.0004324719,0.014269473,0.001175973,0.000020547734,0.00003489561,0.0004359218,0.00033311752,0.00010755638],"category_scores_gemma":[0.49654838,0.0002706212,0.0017695344,0.00032013134,0.00014961681,0.000064523214,0.000065487024,0.0010805855,0.0000016550445],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.059240747,0.000088675995,7.3528025e-7,0.0010425372,0.00071666663,0.000081526225,0.00047344464,6.154103e-7,0.0000010313444,0.0020446964,0.00038596833,0.93592334],"study_design_scores_gemma":[0.34321162,0.0027889984,0.000085529675,0.023278527,0.008773712,0.000049414397,0.000050395807,0.000026372325,0.0000039703846,0.14402896,0.4771149,0.00058761524],"about_ca_topic_score_codex":0.000009467576,"about_ca_topic_score_gemma":0.00005045923,"teacher_disagreement_score":0.93533576,"about_ca_system_score_codex":0.00022880702,"about_ca_system_score_gemma":0.00024358164,"threshold_uncertainty_score":0.9999746},"labels":[],"label_agreement":null},{"id":"W1983613778","doi":"10.1016/s0895-4356(99)00156-0","title":"Likelihood and clinical trials","year":2000,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bruyère; The Sisters of Charity of Ottawa","funders":"","keywords":"Bayesian probability; Orthodoxy; Statistics; Statistical hypothesis testing; Statistical theory; Econometrics; Epistemology; Medicine; Mathematics; History; Philosophy","score_opus":0.9249743914661306,"score_gpt":0.7590140087416808,"score_spread":0.1659603827244498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983613778","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7184719,0.0020236857,0.21393557,0.038360316,0.015515588,0.0012804655,0.00008166712,0.00013235571,0.010198462],"genre_scores_gemma":[0.022155583,0.009974517,0.95175815,0.006977035,0.008663894,0.0000042763604,4.2468184e-7,0.000046716457,0.0004194119],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7559032,0.18946248,0.052113444,0.0009216905,0.00060617924,0.000993001],"domain_scores_gemma":[0.03918696,0.9476937,0.010725243,0.00066578545,0.00040555588,0.0013227401],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5553469,0.0003260004,0.012803746,0.000100673824,0.00006930928,0.00001830878,0.0006156265,0.0013444766,0.0036582497],"category_scores_gemma":[0.97337884,0.00020718508,0.0029332687,0.00016217823,0.001218893,0.0001131321,0.0001090976,0.0029245345,0.00011890192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019999212,0.0007624148,0.086426094,0.000042097403,0.00068046176,0.00007101131,0.000011116189,0.0000012474793,0.0000014482019,0.038631793,0.03298678,0.83838564],"study_design_scores_gemma":[0.004399283,0.0022921343,0.06371593,0.0001424114,0.00065992185,0.00014451407,0.000013051245,0.00023709453,0.0000021995,0.90602493,0.022179717,0.00018881987],"about_ca_topic_score_codex":0.0000050085873,"about_ca_topic_score_gemma":0.0000029044434,"teacher_disagreement_score":0.86739314,"about_ca_system_score_codex":0.000019704336,"about_ca_system_score_gemma":0.0002796476,"threshold_uncertainty_score":0.99995196},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W1984151175","doi":"10.1002/sim.1271","title":"Dealing with competing risks: testing covariates and calculating sample size","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Covariate; Statistics; Econometrics; Proportional hazards model; Event (particle physics); Sample size determination; Hazard; Hazard ratio; Mathematics; Computer science; Confidence interval","score_opus":0.6075631836183745,"score_gpt":0.5529054365405092,"score_spread":0.054657747077865304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984151175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01579949,0.00012718233,0.9794321,0.00038522357,0.00020364238,0.0004329456,0.00017983158,0.00010691081,0.003332657],"genre_scores_gemma":[0.15335162,0.000037079928,0.8461185,0.00017120707,0.00024323988,0.0000127494,0.0000017777742,0.000043787386,0.0000200042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970893,0.00044594792,0.0011462462,0.00042140982,0.0004765555,0.0004205298],"domain_scores_gemma":[0.69547457,0.30365726,0.000340899,0.00022806766,0.00015818997,0.0001409874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037273997,0.0002532134,0.00083868305,0.0000804114,0.00015961318,0.00002798158,0.00013914869,0.000095710515,0.0007141073],"category_scores_gemma":[0.56665295,0.00019227805,0.000013943025,0.00034456947,0.00047697368,0.00003400992,0.00008154739,0.00049758836,0.000003925706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010722284,0.00015922688,0.07408964,0.0008965912,0.00011946858,0.00033440688,0.0024344677,0.00017287153,0.000340428,0.8043495,0.0005541065,0.11644206],"study_design_scores_gemma":[0.0023162616,0.00036036104,0.0047241542,0.0011198649,0.00013383078,0.000027033147,0.0004969165,0.0674028,0.000017293005,0.9231017,0.000038132155,0.00026162993],"about_ca_topic_score_codex":0.00047698777,"about_ca_topic_score_gemma":0.00007577204,"teacher_disagreement_score":0.5629256,"about_ca_system_score_codex":0.000044900116,"about_ca_system_score_gemma":0.000013536484,"threshold_uncertainty_score":0.7840871},"labels":[],"label_agreement":null},{"id":"W1985152499","doi":"10.1016/j.cps.2005.06.001","title":"Strategies for Nonrandomized Clinical Research in Hand Surgery","year":2005,"lang":"en","type":"review","venue":"Clinics in Plastic Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Medicine; Randomized controlled trial; Clinical study design; Research design; Variety (cybernetics); Medical physics; Evidence-based medicine; MEDLINE; Clinical trial; Intensive care medicine; Risk analysis (engineering); Surgery; Alternative medicine; Artificial intelligence; Computer science","score_opus":0.9264023149997324,"score_gpt":0.7178028726903852,"score_spread":0.20859944230934713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985152499","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011797868,0.96052074,0.012801279,0.00006299086,0.020661036,0.004773412,0.00055078906,0.000112337584,0.00039944265],"genre_scores_gemma":[0.000024493238,0.92873025,0.06517393,0.000036698013,0.0036341145,0.0019437611,0.00006160912,0.00029258934,0.00010258005],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9506918,0.025073396,0.01841605,0.0023403908,0.0013670925,0.0021112536],"domain_scores_gemma":[0.12862356,0.86667407,0.0023530684,0.001488163,0.00044843805,0.0004127109],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.19509304,0.0010900557,0.017997775,0.0024107045,0.00015928122,0.00034775157,0.0009803019,0.0032100393,0.0002507233],"category_scores_gemma":[0.8422712,0.0009170301,0.0043258835,0.002076558,0.001546205,0.00017442518,0.00040165527,0.005038331,0.00017109778],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016878353,0.0015322939,0.00023245439,0.019738508,0.000269872,0.00024093638,0.00001872421,0.0000015695263,4.5462327e-9,0.0077487947,0.020478869,0.94805014],"study_design_scores_gemma":[0.0035512745,0.00010176349,0.000022206868,0.04183437,0.0006066952,0.000012292047,0.00006526655,0.00017395262,4.209189e-8,0.40771106,0.54500693,0.00091417594],"about_ca_topic_score_codex":0.000009331309,"about_ca_topic_score_gemma":0.00009767864,"teacher_disagreement_score":0.947136,"about_ca_system_score_codex":0.00038198565,"about_ca_system_score_gemma":0.0066814437,"threshold_uncertainty_score":0.999328},"labels":[],"label_agreement":null},{"id":"W1985204469","doi":"10.1016/j.jsps.2013.05.001","title":"Study on requirements of bioequivalence for registration of pharmaceutical products in USA, Europe and Canada","year":2013,"lang":"en","type":"review","venue":"Saudi Pharmaceutical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Pharmaceutical industry; Cmax; Generic drug; Business; Government (linguistics); Medicine; Actuarial science; Pharmacology; Pharmacokinetics; Drug","score_opus":0.8514832255820811,"score_gpt":0.6603285586285363,"score_spread":0.19115466695354477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985204469","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038796116,0.96987844,0.0042636497,0.00078399654,0.0039601643,0.015070958,0.00067416695,0.00002205827,0.0014669688],"genre_scores_gemma":[0.0006011242,0.92956984,0.06879881,0.00008423463,0.0005233983,0.00014149598,0.0000025397728,0.00009028773,0.0001882614],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9908594,0.0027028252,0.0039922637,0.0006426228,0.0012310357,0.00057187834],"domain_scores_gemma":[0.9714806,0.025090836,0.0019890165,0.00044471896,0.000593185,0.0004016388],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007864642,0.0005297695,0.0029384082,0.00021499186,0.00006941154,0.00004209358,0.00059255183,0.0002247824,0.0002111838],"category_scores_gemma":[0.06384272,0.00039272374,0.00022365864,0.00043499892,0.0003548992,0.00010207542,0.00017266333,0.0014077814,0.0000048702573],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040004915,0.0023353943,0.00020267209,0.040051166,0.00073018146,0.00017954745,0.000055679175,5.6362654e-7,0.000087762564,0.011234091,0.0046261707,0.94009674],"study_design_scores_gemma":[0.014996924,0.005415471,0.00022595612,0.049474187,0.013069669,0.0005792815,0.00022879826,0.00014673044,0.0025564905,0.085711576,0.825136,0.002458892],"about_ca_topic_score_codex":0.00043966365,"about_ca_topic_score_gemma":0.0005289644,"teacher_disagreement_score":0.9376378,"about_ca_system_score_codex":0.00022926455,"about_ca_system_score_gemma":0.0013238721,"threshold_uncertainty_score":0.9998525},"labels":[],"label_agreement":null},{"id":"W1985352766","doi":"10.1016/j.jclinepi.2015.01.017","title":"The choice of the noninferiority margin in clinical trials was driven by baseline risk, type of primary outcome, and benefits of new treatment","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute for Materials Science","keywords":"Medicine; Randomized controlled trial; Baseline (sea); Clinical trial; Margin (machine learning); Population; Randomization; Vignette; Research design; Physical therapy; Surgery; Internal medicine; Psychology; Statistics","score_opus":0.9121244771619215,"score_gpt":0.7014994537019636,"score_spread":0.21062502345995782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985352766","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97523654,0.0025501077,0.0094852885,0.0077413,0.0037364159,0.0008646922,0.00018991945,0.000006336303,0.0001894267],"genre_scores_gemma":[0.22460663,0.020301351,0.75043035,0.0012665418,0.0029458406,0.000008322985,0.0000026565315,0.00006529489,0.0003729882],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.85925674,0.10220266,0.03680734,0.0005197432,0.00069629,0.000517238],"domain_scores_gemma":[0.1078478,0.8683419,0.021629041,0.00087092636,0.00077425624,0.0005360471],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30797362,0.0002738437,0.009265704,0.000066341025,0.000036495465,0.0000045913785,0.00073425256,0.0007555008,0.000035219487],"category_scores_gemma":[0.9600183,0.00012788139,0.0014828913,0.00025440814,0.0012580135,0.0000498855,0.00026680596,0.00151652,0.0000016151936],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029276574,0.0008659083,0.89499664,0.000058176698,0.00041059716,0.0000017136925,0.000030563577,0.00006456751,0.0000071757054,0.0043246616,0.007231572,0.08908075],"study_design_scores_gemma":[0.009578381,0.004075265,0.7021829,0.00024718948,0.0008213633,0.000007881816,0.0000333283,0.00038098992,0.000045455865,0.27922842,0.0032717271,0.00012709964],"about_ca_topic_score_codex":0.00019739884,"about_ca_topic_score_gemma":0.00011366781,"teacher_disagreement_score":0.76613927,"about_ca_system_score_codex":0.000066347406,"about_ca_system_score_gemma":0.0008540802,"threshold_uncertainty_score":0.71258676},"labels":[],"label_agreement":null},{"id":"W1985549752","doi":"10.1080/07474946.2010.487416","title":"Sequential Methods in Multi-Arm Clinical Trials","year":2010,"lang":"en","type":"article","venue":"Sequential Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Bayesian probability; Clinical trial; Identification (biology); Process (computing); Computer science; Early stopping; Mathematics; Econometrics; Machine learning; Risk analysis (engineering); Statistics; Medicine","score_opus":0.859529216038041,"score_gpt":0.7337854614339617,"score_spread":0.12574375460407927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985549752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031741913,0.000027893768,0.9618036,0.00040120177,0.0038472353,0.0007289881,0.00013294091,0.0001778939,0.001138338],"genre_scores_gemma":[0.068901695,0.000037314872,0.92901343,0.0002185104,0.0011548903,0.00007176825,0.000015730122,0.000058700876,0.0005279359],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9665089,0.024048667,0.0066514867,0.0012752891,0.00073826587,0.00077734765],"domain_scores_gemma":[0.87281424,0.12289963,0.0017452148,0.0016298974,0.0003334241,0.00057759363],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10853239,0.00046679936,0.0041508353,0.00079569523,0.0001222053,0.0001547069,0.00083957665,0.0009163873,0.008933929],"category_scores_gemma":[0.41005298,0.0003807577,0.0031086602,0.0024461276,0.00057435036,0.00013493346,0.00032928737,0.0019438487,0.00012631698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016541097,0.009042943,0.046544094,0.00030316363,0.026689725,0.0005227189,0.0006003268,0.0001800944,0.09684068,0.36804315,0.002596064,0.44698292],"study_design_scores_gemma":[0.0047045974,0.0001598577,0.0041872533,0.000029036133,0.012630674,0.0000062745203,0.00006751928,0.021062167,0.0074266125,0.94714254,0.0017364753,0.00084699795],"about_ca_topic_score_codex":0.00035198967,"about_ca_topic_score_gemma":0.001504231,"teacher_disagreement_score":0.57909936,"about_ca_system_score_codex":0.00006655792,"about_ca_system_score_gemma":0.00019038851,"threshold_uncertainty_score":0.99986446},"labels":[],"label_agreement":null},{"id":"W1986949593","doi":"10.1016/j.cct.2004.06.001","title":"Adjustment for baseline measurement error in randomized controlled trials induces bias","year":2004,"lang":"en","type":"article","venue":"Controlled Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Estimator; Statistics; Observational error; Baseline (sea); Context (archaeology); Randomized controlled trial; Sample size determination; Mean squared error; Reliability (semiconductor); Standard error; Mathematics; Medicine; Internal medicine; Power (physics); Physics","score_opus":0.8938245985846385,"score_gpt":0.6562920330182795,"score_spread":0.23753256556635893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986949593","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009645899,0.006682494,0.81026,0.014888882,0.01898564,0.13653506,0.0006863942,0.0004742002,0.001841424],"genre_scores_gemma":[0.1827731,0.0022886153,0.75874054,0.0037205887,0.012260802,0.039181195,0.000024915409,0.0002962895,0.00071393716],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.5052884,0.38294515,0.10029408,0.0036580532,0.00509883,0.0027154498],"domain_scores_gemma":[0.014839746,0.9651973,0.015690021,0.0015345014,0.0018563083,0.0008821049],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.8271652,0.0012608119,0.071476705,0.0006104612,0.00017975342,0.00020917901,0.0009832166,0.0014535238,0.0009656528],"category_scores_gemma":[0.99530625,0.0007128842,0.019074498,0.0005263453,0.00069090107,0.00014434596,0.00016182763,0.0012001909,0.000078124365],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.84084874,0.0037281595,0.000008854441,0.00015124827,0.0075971982,0.000017805054,0.000053946686,0.0000960046,0.00031794806,0.11994418,0.001514749,0.025721155],"study_design_scores_gemma":[0.5187935,0.0006157445,0.000010368718,0.00047398114,0.0059793065,8.2015447e-7,0.00004348002,0.00063070975,0.00021856,0.47263512,0.00022024944,0.00037813725],"about_ca_topic_score_codex":0.000033838827,"about_ca_topic_score_gemma":0.00005232835,"teacher_disagreement_score":0.58225214,"about_ca_system_score_codex":0.00044957316,"about_ca_system_score_gemma":0.0014828503,"threshold_uncertainty_score":0.9999476},"labels":[],"label_agreement":null},{"id":"W1987232265","doi":"10.2105/ajph.94.3.393","title":"Design and Analysis of Group-Randomized Trials: A Review of Recent Practices","year":2004,"lang":"en","type":"review","venue":"American Journal of Public Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":140,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"","keywords":"Randomized controlled trial; Medicine; Public health; Family medicine; MEDLINE; Sample size determination; Subgroup analysis; Meta-analysis; Internal medicine; Statistics; Pathology; Mathematics","score_opus":0.8994987648405098,"score_gpt":0.7078934704286082,"score_spread":0.19160529441190166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987232265","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2308032e-7,0.6433452,0.35316116,0.0016443082,0.00016057871,0.001589596,0.00006712285,0.000005456072,0.000026357002],"genre_scores_gemma":[1.9974345e-7,0.5326954,0.46696728,0.00020114298,0.000080074555,0.000024404524,0.0000031501645,0.000026726404,0.0000016123344],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8388642,0.13713089,0.021232568,0.0005284103,0.0016480524,0.0005958944],"domain_scores_gemma":[0.34008136,0.5358654,0.12076817,0.0008393878,0.0015708447,0.0008747817],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3141731,0.0004771956,0.037648384,0.0012398906,0.000040066167,0.000036983907,0.0006712259,0.00017030565,0.0003979254],"category_scores_gemma":[0.7977887,0.00028607118,0.0032859351,0.003964485,0.0009765684,0.00013433336,0.00008876403,0.0009538431,6.8263466e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006797586,0.00033271668,3.1969134e-7,0.101617046,0.00947887,0.0000046323025,0.000071904535,1.6428484e-7,1.4194321e-8,0.004213008,0.00022299709,0.88337857],"study_design_scores_gemma":[0.024871338,0.0042300373,0.0000016897601,0.31295034,0.11381358,0.00017650437,0.00018406552,0.00002020503,1.5910548e-7,0.06692952,0.47620183,0.0006207277],"about_ca_topic_score_codex":0.000078043115,"about_ca_topic_score_gemma":0.0000012427421,"teacher_disagreement_score":0.88275784,"about_ca_system_score_codex":0.00033085307,"about_ca_system_score_gemma":0.005697458,"threshold_uncertainty_score":0.9999592},"labels":[],"label_agreement":null},{"id":"W1987301448","doi":"10.1016/j.ejca.2007.07.031","title":"Design and conduct of phase II studies of targeted anticancer therapy: Recommendations from the task force on methodology for the development of innovative cancer therapies (MDICT)","year":2007,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Adaptive design; Clinical study design; Task force; Medicine; Task (project management); Clinical trial; Discontinuation; Research design; Clinical endpoint; Multinomial distribution; Medical physics; Risk analysis (engineering); Computer science; Internal medicine; Systems engineering; Engineering; Mathematics; Econometrics; Statistics","score_opus":0.8120928075972004,"score_gpt":0.629842277343655,"score_spread":0.18225053025354532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987301448","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17382424,0.011271841,0.81055826,0.0026246873,0.0008102654,0.00067615823,0.00018447296,0.000004650168,0.00004545955],"genre_scores_gemma":[0.19731078,0.0038516463,0.7981173,0.0003977517,0.00023463723,0.000017628157,4.8282317e-7,0.00003128317,0.000038539605],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9950578,0.002539527,0.0017930409,0.0001465686,0.00029505425,0.00016797097],"domain_scores_gemma":[0.9083727,0.087925516,0.0021472098,0.00019481483,0.0013251838,0.00003457667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017176319,0.00016695172,0.0007983472,0.00007212537,0.00014649729,0.0000056465533,0.00033118232,0.00003261177,0.0001298278],"category_scores_gemma":[0.01761553,0.00008193304,0.00009556004,0.00026838522,0.00059198984,0.000043597018,0.000065753135,0.0002459439,8.407054e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051503736,0.00035929887,0.00017636074,0.00007280311,0.0051561934,0.0000019300892,0.032578096,0.000055708446,0.096079186,0.0049285246,0.0044863396,0.8509552],"study_design_scores_gemma":[0.014567308,0.00522569,0.005777494,0.0014996378,0.0007929642,0.0000027244803,0.011358751,0.000068546855,0.76083016,0.18225497,0.017246509,0.00037522768],"about_ca_topic_score_codex":0.0000082930355,"about_ca_topic_score_gemma":0.000013584984,"teacher_disagreement_score":0.85058,"about_ca_system_score_codex":0.000046670044,"about_ca_system_score_gemma":0.00022516794,"threshold_uncertainty_score":0.99065953},"labels":[],"label_agreement":null},{"id":"W1987973071","doi":"10.1002/sim.5941","title":"Graphical assessment of internal and external calibration of logistic regression models by using loess smoothers","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":357,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Public Health Ontario; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Overfitting; Calibration; Logistic regression; Statistics; Computer science; Covariate; Loess; Econometrics; Mathematics; Artificial intelligence","score_opus":0.4241021929435487,"score_gpt":0.5779164790022724,"score_spread":0.15381428605872371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987973071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049751174,0.00008036116,0.9491192,0.00007728522,0.0002367592,0.0003428982,0.00017134583,0.000008486106,0.00021249992],"genre_scores_gemma":[0.4347288,0.00005514966,0.56509906,0.000039542905,0.000040622235,0.0000074859654,0.000002692556,0.000014576803,0.000012076779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99699086,0.00057949044,0.0014033922,0.000257527,0.00057755254,0.00019117809],"domain_scores_gemma":[0.9824188,0.016417727,0.0006209838,0.00024406666,0.00018152584,0.0001169259],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019246425,0.000172031,0.0008074914,0.00013590133,0.000021603739,0.000008488657,0.0001675667,0.00013092549,0.00035233254],"category_scores_gemma":[0.01609883,0.00012243453,0.00002708841,0.00015464702,0.0008586697,0.00007046431,0.00007646738,0.00030801483,1.3035267e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017058081,0.00049796223,0.017973794,0.0013142928,0.000097454445,0.00002710582,0.0005407127,0.00019361026,0.03140313,0.92211556,0.0037816109,0.021884194],"study_design_scores_gemma":[0.0010059485,0.00023967106,0.0015081642,0.00089317455,0.000061831655,0.0000030850517,0.00009869772,0.259879,0.00027447008,0.7359542,8.2276995e-7,0.00008094367],"about_ca_topic_score_codex":0.00046457403,"about_ca_topic_score_gemma":0.000007696043,"teacher_disagreement_score":0.38497764,"about_ca_system_score_codex":0.000040637253,"about_ca_system_score_gemma":0.00004377491,"threshold_uncertainty_score":0.992189},"labels":[],"label_agreement":null},{"id":"W1988121488","doi":"10.1177/1740774510392254","title":"Likelihood inference on the relative risk in split-cluster designs","year":2011,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Inference; Relative risk; Cluster (spacecraft); Statistics; Computer science; Medicine; Mathematics; Artificial intelligence; Confidence interval","score_opus":0.9361180592547464,"score_gpt":0.673449944718896,"score_spread":0.2626681145358505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988121488","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21833546,0.00012829123,0.6666648,0.0043425146,0.00801818,0.010106648,0.00043829455,0.00046869591,0.09149714],"genre_scores_gemma":[0.25271252,0.00029638453,0.74295145,0.002086971,0.0012212541,0.00027759507,9.700906e-7,0.00007905343,0.00037379458],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9444201,0.047467433,0.006123268,0.00085723744,0.000536738,0.00059523416],"domain_scores_gemma":[0.17880204,0.81706405,0.0021339117,0.0014897385,0.00017962756,0.00033064102],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.15688013,0.0003771383,0.002443864,0.000097973454,0.00012160408,0.000050276016,0.00084555714,0.00069604703,0.002615956],"category_scores_gemma":[0.925367,0.00021260894,0.00085371605,0.00041529498,0.00063392427,0.00010098682,0.0002590973,0.002011643,0.00094752933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026232358,0.0017353155,0.012039339,0.0000315753,0.00037078853,0.000028724864,0.00066430966,7.0645774e-7,0.000008170249,0.90623236,0.006400093,0.06986538],"study_design_scores_gemma":[0.003107848,0.00085384335,0.01296964,0.00022881046,0.00028754194,5.5537794e-7,0.00006584469,0.0001291548,0.00021221371,0.98154503,0.00032331285,0.00027617917],"about_ca_topic_score_codex":0.000029651526,"about_ca_topic_score_gemma":0.000019893509,"teacher_disagreement_score":0.7695966,"about_ca_system_score_codex":0.000053202908,"about_ca_system_score_gemma":0.00015673027,"threshold_uncertainty_score":0.99983037},"labels":[],"label_agreement":null},{"id":"W1988778209","doi":"10.1016/j.jclinepi.2010.12.019","title":"A framework for applying unfamiliar trial designs in studies of rare diseases","year":2011,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":107,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; St. Michael's Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"MEDLINE; Medicine; Computer science; Psychology; Biology","score_opus":0.9745532133838114,"score_gpt":0.7769818490013579,"score_spread":0.19757136438245348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988778209","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008855862,0.7532113,0.23842998,0.000101319216,0.005399761,0.0026463727,0.00016560334,0.000012079689,0.00002468299],"genre_scores_gemma":[0.000001149779,0.52021074,0.47694468,0.00013505212,0.002441887,0.00020317268,0.0000011031733,0.000050390765,0.000011786778],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9077554,0.052356433,0.03790985,0.0008164262,0.00037274978,0.0007891672],"domain_scores_gemma":[0.056542065,0.9135009,0.027938224,0.0008552167,0.00070309953,0.00046048197],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13347289,0.0006805238,0.03689309,0.00038375036,0.00004544479,0.0000052201044,0.0012625016,0.002578467,0.00008211458],"category_scores_gemma":[0.97968704,0.00042491208,0.00726903,0.00030147386,0.0011739493,0.00005940012,0.00027726844,0.0033647942,0.0000062105332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011032108,0.000943801,0.0001563184,0.020868547,0.0019843346,0.00003382351,0.000029353136,7.031312e-7,4.1886135e-9,0.20288807,0.0024798934,0.75958306],"study_design_scores_gemma":[0.009506418,0.002985227,0.00001787748,0.02921886,0.0045183683,0.000015802165,0.000036379977,0.000004599006,4.262469e-8,0.8490817,0.104329534,0.00028519979],"about_ca_topic_score_codex":0.0000022640052,"about_ca_topic_score_gemma":0.0000019068019,"teacher_disagreement_score":0.8611445,"about_ca_system_score_codex":0.00010111541,"about_ca_system_score_gemma":0.0010327518,"threshold_uncertainty_score":0.9998203},"labels":[],"label_agreement":null},{"id":"W1989555992","doi":"10.1080/10543400600719251","title":"Statistical Considerations for NonInferiority/Equivalence Trials in Vaccine Development","year":2006,"lang":"en","type":"review","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Victoria","keywords":"Clinical trial; Equivalence (formal languages); Medicine; Sample size determination; Statistical power; Computer science; Statistics; Mathematics; Medical physics; Internal medicine","score_opus":0.8715293489126777,"score_gpt":0.692162280269236,"score_spread":0.17936706864344176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989555992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011533147,0.36938038,0.6223258,0.00007114293,0.0014912548,0.001972293,0.0046878443,0.00002129831,0.000048870563],"genre_scores_gemma":[0.0000022578615,0.43069053,0.5682871,0.000054254873,0.00072390604,0.00008987634,0.000026067262,0.00008296419,0.00004304815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9768293,0.005742534,0.014701127,0.00064338895,0.0011621516,0.00092151435],"domain_scores_gemma":[0.639088,0.35496143,0.0043848515,0.0003221157,0.0007534434,0.00049019995],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02894105,0.00091692636,0.011039714,0.00062251545,0.00015866851,0.00019908085,0.0005825322,0.00081531296,0.00088388775],"category_scores_gemma":[0.44210547,0.0006854732,0.0009832192,0.0004517844,0.00027227734,0.00009850851,0.00017130887,0.001964766,0.000030285519],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002528655,0.00089031644,0.000007673173,0.021018188,0.000650438,0.0005980468,0.000025945687,0.0000019533345,0.0000019431286,0.18705775,0.027553238,0.7619416],"study_design_scores_gemma":[0.0025726194,0.00030560826,0.000011551002,0.0052104956,0.0038700849,0.00019211794,0.000005200402,0.00008386434,0.000013230134,0.47786292,0.50928575,0.00058653194],"about_ca_topic_score_codex":0.000003041489,"about_ca_topic_score_gemma":0.000011341625,"teacher_disagreement_score":0.7613551,"about_ca_system_score_codex":0.00064643816,"about_ca_system_score_gemma":0.0025084151,"threshold_uncertainty_score":0.9999095},"labels":[],"label_agreement":null},{"id":"W1989677836","doi":"10.1177/0013164408322027","title":"Comparing Treatment and Control Groups on Multiple Outcomes","year":2008,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of British Columbia; Simon Fraser University; University of Saskatchewan","funders":"","keywords":"Statistics; Mathematics; Normality; Type I and type II errors; Covariance; Homogeneity (statistics); Population; Statistical hypothesis testing; Treatment and control groups; Multivariate normal distribution; Analysis of covariance; A priori and a posteriori; Multivariate statistics; Econometrics","score_opus":0.8792290284703227,"score_gpt":0.5762263579324098,"score_spread":0.30300267053791285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989677836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862859,0.00014398548,0.0041505913,0.0054850215,0.0006164746,0.0005346768,0.000018130086,0.000039957114,0.0027252154],"genre_scores_gemma":[0.9464415,0.000056158795,0.05234701,0.0006906539,0.00022262527,0.00012335641,8.96718e-7,0.000008032747,0.00010978689],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983712,0.00033270515,0.0004043646,0.0003659374,0.00034336216,0.00018245362],"domain_scores_gemma":[0.98403883,0.01543065,0.00009364703,0.00017714308,0.00007906234,0.00018066051],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00091272173,0.00017545398,0.00042807023,0.000031165542,0.00017124291,0.000016123,0.00006948542,0.00007556819,0.00018571135],"category_scores_gemma":[0.015951196,0.00010871928,0.000065305256,0.000043084136,0.00017660561,0.000018605953,0.000013590617,0.00011641469,0.000021588543],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000577031,0.0063127703,0.81624925,0.000032789772,0.00025187474,0.00000665983,0.00033117135,0.0000018691303,0.00032897602,0.16112998,0.0032357317,0.011541915],"study_design_scores_gemma":[0.0020976348,0.0005521702,0.679509,0.000018794497,0.000028890265,0.000012516462,0.000014047653,0.000015739946,0.000025137226,0.3172587,0.00035504843,0.000112373964],"about_ca_topic_score_codex":0.0000066431576,"about_ca_topic_score_gemma":0.000003349827,"teacher_disagreement_score":0.1561287,"about_ca_system_score_codex":0.00006787324,"about_ca_system_score_gemma":0.000016467517,"threshold_uncertainty_score":0.9923379},"labels":[],"label_agreement":null},{"id":"W1989897941","doi":"10.1023/b:pham.0000036906.65263.da","title":"The Role of Metabolites in Bioequivalence","year":2004,"lang":"en","type":"review","venue":"Pharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"U.S. Food and Drug Administration","keywords":"Bioequivalence; Context (archaeology); Metabolite; Drug; Pharmacology; Medicine; Pharmacokinetics; Biology; Internal medicine","score_opus":0.9374920013793809,"score_gpt":0.7844228098714564,"score_spread":0.15306919150792453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989897941","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011123504,0.9934443,0.00022267309,0.00011132069,0.00021607257,0.0018014068,0.00010115687,0.000026166066,0.0040757614],"genre_scores_gemma":[0.000014354743,0.9537106,0.045457862,0.0000058688875,0.00022122821,0.0003703901,0.0000010689997,0.00007070081,0.00014790712],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9839987,0.00960303,0.0024281612,0.0006786316,0.0020237013,0.0012677647],"domain_scores_gemma":[0.67741597,0.32085148,0.00025941242,0.0008440957,0.00032162401,0.00030742402],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035237756,0.00036394954,0.0025237768,0.00034483388,0.00014374335,0.00007783792,0.0018903331,0.0004473164,0.0003597484],"category_scores_gemma":[0.33364624,0.0002090115,0.0005781157,0.0017855631,0.0018993163,0.00004145102,0.00089504826,0.003489357,0.00020558042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025320458,0.00014836593,0.0000014639462,0.009799044,0.00006558959,0.00000985193,0.000010235504,1.8772063e-8,0.0000035728444,0.37047878,0.000033503326,0.6194243],"study_design_scores_gemma":[0.00016518847,0.00002940013,2.963321e-7,0.004841611,0.00016482025,0.0000024878855,0.000012900101,0.000010592553,0.00012584856,0.5179273,0.47661343,0.00010611192],"about_ca_topic_score_codex":0.000019331743,"about_ca_topic_score_gemma":0.0000023545383,"teacher_disagreement_score":0.6193181,"about_ca_system_score_codex":0.0002599627,"about_ca_system_score_gemma":0.0009936515,"threshold_uncertainty_score":0.99880964},"labels":[],"label_agreement":null},{"id":"W1991029809","doi":"10.1016/j.ejca.2014.04.030","title":"Defining dose-limiting toxicity for phase 1 trials of molecularly targeted agents: Results of a DLT-TARGETT international survey","year":2014,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Princess Margaret Cancer Centre","funders":"","keywords":"Toxicity; Medicine; Limiting; Maximum tolerated dose; Clinical trial; Internal medicine; Oncology","score_opus":0.5609379012588367,"score_gpt":0.5792507951494835,"score_spread":0.01831289389064683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991029809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13877371,0.0003676481,0.8519902,0.0004267048,0.0023965205,0.0004223422,0.00230893,0.000015763733,0.003298162],"genre_scores_gemma":[0.45326832,0.000048791848,0.54594475,0.00011898156,0.00053123874,0.0000026367122,0.000006073649,0.000041864867,0.000037378737],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.986312,0.007922799,0.0046259947,0.00021798028,0.0006970039,0.00022427502],"domain_scores_gemma":[0.9414331,0.050981656,0.005704941,0.00025284005,0.0014890176,0.00013849398],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059867166,0.00017474945,0.0013025024,0.0001508471,0.000035648514,0.000028734574,0.00053087965,0.00005000938,0.00018465646],"category_scores_gemma":[0.5323244,0.00013892211,0.00048077357,0.00015976008,0.00010772903,0.00009173802,0.000078006546,0.00026451162,0.000001651814],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.053446215,0.0034415605,0.0033575539,0.0011326104,0.00604329,0.00013863886,0.0025332593,0.0008112402,0.15260191,0.05526656,0.048279673,0.67294747],"study_design_scores_gemma":[0.15929498,0.011883856,0.029993001,0.0065797474,0.0027628178,0.000040691037,0.00033265812,0.007061787,0.35081133,0.40196234,0.02759565,0.0016811221],"about_ca_topic_score_codex":0.000010408209,"about_ca_topic_score_gemma":0.0000043988503,"teacher_disagreement_score":0.6712664,"about_ca_system_score_codex":0.000046860387,"about_ca_system_score_gemma":0.00011230356,"threshold_uncertainty_score":0.9680646},"labels":[],"label_agreement":null},{"id":"W1991135418","doi":"10.1002/1097-0258(20001115)19:21<3017::aid-sim785>3.0.co;2-p","title":"M. D. deB. Edwardes, ‘The generalization of the odds ratio, risk ratio and risk difference tor ×k tables’.Statistics in Medicine 2000;19(14): 1901-1914","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Statistics; Generalization; Medical statistics; Odds ratio; Mathematics; Odds; Medicine; Logistic regression","score_opus":0.15515203872518482,"score_gpt":0.46718523153196945,"score_spread":0.31203319280678465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991135418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013863161,0.0008217635,0.977279,0.0012140737,0.0010062403,0.0014717013,0.0032810897,0.00003498664,0.001028006],"genre_scores_gemma":[0.0700213,0.014696521,0.910629,0.0010250442,0.00093127094,0.000153201,0.00014399571,0.000117555304,0.0022821513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913014,0.0035062365,0.002769048,0.0006391102,0.00122885,0.0005553284],"domain_scores_gemma":[0.9432147,0.054194752,0.00106234,0.0009762111,0.00033501018,0.00021698896],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007417223,0.00047855155,0.001478964,0.00018087102,0.00025783348,0.000026996353,0.00063087087,0.00026782398,0.002457183],"category_scores_gemma":[0.17916685,0.00028003892,0.000043811273,0.0009092234,0.0021128189,0.000053327087,0.00012575815,0.0010439393,0.000007248672],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076802383,0.00057553675,0.077991754,0.0010676393,0.00027771338,0.00007998557,0.008731477,0.001032115,0.0003694222,0.60669416,0.09827486,0.20413733],"study_design_scores_gemma":[0.004592647,0.00049375155,0.088467926,0.0007365143,0.0006160234,0.00001103854,0.00030007723,0.04321931,0.0000764363,0.859759,0.0013755604,0.00035172858],"about_ca_topic_score_codex":0.003156371,"about_ca_topic_score_gemma":0.0033491086,"teacher_disagreement_score":0.25306484,"about_ca_system_score_codex":0.00017944096,"about_ca_system_score_gemma":0.00023849355,"threshold_uncertainty_score":0.9999652},"labels":[],"label_agreement":null},{"id":"W1991265164","doi":"10.1007/s10637-010-9456-9","title":"A qualitative study evaluating causality attribution for serious adverse events during early phase oncology clinical trials","year":2010,"lang":"en","type":"article","venue":"Investigational New Drugs","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; St. Joseph’s Healthcare Hamilton; St Joseph's Health Care; McMaster University; Juravinski Cancer Centre","funders":"","keywords":"Causality (physics); Clinical trial; Attribution; Thematic analysis; Objectivity (philosophy); Medicine; Psychology; Qualitative research; Medical education; Internal medicine; Social psychology; Epistemology","score_opus":0.8588413857350846,"score_gpt":0.7504655684450426,"score_spread":0.10837581729004198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991265164","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94100523,0.0000035068763,0.049976584,0.0016396054,0.0021898514,0.004443353,0.0005481172,0.00013224441,0.00006153907],"genre_scores_gemma":[0.42539862,8.518499e-7,0.5718613,0.00021179336,0.0017425237,0.00043234555,0.000032756474,0.00004104629,0.00027871784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97449315,0.018033437,0.0049225627,0.0009272141,0.0011132935,0.000510332],"domain_scores_gemma":[0.6404143,0.3527565,0.0035056253,0.00088397966,0.0012966444,0.0011429649],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09192492,0.0003501179,0.0017211775,0.00010833229,0.00032246174,0.00002932265,0.00037551875,0.00048058314,0.0003010666],"category_scores_gemma":[0.59387445,0.00031631766,0.0005040406,0.0002983514,0.00042385253,0.00021107201,0.00014869378,0.0010157161,0.00006157787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01706636,0.020651009,0.015458524,0.00077937415,0.0041905707,0.00006994497,0.11855894,0.000053676737,0.051958907,0.6317368,0.0068215793,0.13265432],"study_design_scores_gemma":[0.022082303,0.0022959108,0.009058708,0.0000635197,0.0005579119,0.000004854734,0.0023237497,0.0005121591,0.0008012675,0.9617441,0.0002019103,0.00035354806],"about_ca_topic_score_codex":0.00009306557,"about_ca_topic_score_gemma":0.00005164716,"teacher_disagreement_score":0.52188474,"about_ca_system_score_codex":0.0001823188,"about_ca_system_score_gemma":0.0013366302,"threshold_uncertainty_score":0.9999289},"labels":[],"label_agreement":null},{"id":"W1991362225","doi":"10.1002/sim.3383","title":"Sample size calculation for cluster randomized cross‐over trials","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Intraclass correlation; Sample size determination; Cluster (spacecraft); Statistics; Sample (material); Cluster analysis; Cross over; Randomized controlled trial; Computer science; Correlation; External validity; Econometrics; Mathematics; Medicine; Physics; Psychometrics; Internal medicine; Thermodynamics","score_opus":0.5602429666646603,"score_gpt":0.6200809675466604,"score_spread":0.059838000882000086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991362225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002595501,0.000052218355,0.9899044,0.0005880314,0.0016712932,0.0032499065,0.0012534115,0.00005954346,0.0006256667],"genre_scores_gemma":[0.011169032,0.00013178252,0.9854928,0.00077805965,0.0012004991,0.00037505367,0.000036353085,0.00006006219,0.0007563297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9910928,0.0035442056,0.0036851359,0.0004889049,0.0007398458,0.00044909737],"domain_scores_gemma":[0.40547365,0.59304374,0.0006987997,0.00036741738,0.00028098366,0.00013539201],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033032194,0.0003020635,0.0032205132,0.00012725894,0.00013244676,0.000017041599,0.00022841588,0.00024724784,0.0017541766],"category_scores_gemma":[0.9313619,0.00021217267,0.00021651118,0.00023800677,0.0011385877,0.000050006154,0.000054444037,0.00032072267,0.000009504874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06691938,0.00023881436,0.0009717276,0.00048501298,0.00024652487,0.000036055222,0.0009053029,0.000042389678,0.00007141245,0.81520253,0.10850077,0.0063800546],"study_design_scores_gemma":[0.1902551,0.00015476887,0.0007434044,0.00011875367,0.00024190018,0.0000044177864,0.000013771387,0.008017958,0.000032314118,0.7995901,0.00063926855,0.0001882212],"about_ca_topic_score_codex":0.00012448699,"about_ca_topic_score_gemma":0.000022807622,"teacher_disagreement_score":0.89832973,"about_ca_system_score_codex":0.0001013035,"about_ca_system_score_gemma":0.00009427287,"threshold_uncertainty_score":0.9991584},"labels":[],"label_agreement":null},{"id":"W1991627202","doi":"10.1111/j.1537-2995.2007.01202.x","title":"Interventional trials: an overview of design alternatives","year":2007,"lang":"en","type":"review","venue":"Transfusion","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Blood Services; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Family medicine; Transfusion medicine; Epidemiology; Clinical epidemiology; Library science; Blood transfusion; Emergency medicine; Internal medicine","score_opus":0.95952015800169,"score_gpt":0.7278539221483648,"score_spread":0.23166623585332524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991627202","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.628829e-7,0.54293257,0.45498604,0.0000031438396,0.00048640554,0.0011931496,0.00017070115,0.00003529653,0.00019230944],"genre_scores_gemma":[9.991425e-8,0.586326,0.41323736,0.0000050323633,0.00025909793,0.00004516707,0.000010008698,0.000050503353,0.00006671477],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.978514,0.015225178,0.0047100754,0.0005754028,0.00070313114,0.00027220976],"domain_scores_gemma":[0.84876466,0.14901322,0.001401181,0.0005479309,0.00013091124,0.0001420964],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04022812,0.00046997963,0.0057855546,0.0002618425,0.000042023614,0.00002051003,0.00059203815,0.0005712569,0.002604545],"category_scores_gemma":[0.06300852,0.000325449,0.0020957452,0.00033177744,0.000160347,0.00007106536,0.000052266358,0.0005525827,0.00002753721],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008503901,0.00051107805,5.7368915e-8,0.026283076,0.0002548041,0.0000075468247,0.000040059243,1.0170664e-7,0.0000017146617,0.07503705,0.00010171107,0.8976778],"study_design_scores_gemma":[0.0008030803,0.0006294227,5.6320357e-7,0.04648206,0.0028592846,0.000010618886,0.0000067822402,0.0000134931415,0.000047670175,0.6923981,0.25637606,0.00037289655],"about_ca_topic_score_codex":0.000010490331,"about_ca_topic_score_gemma":0.0000039465963,"teacher_disagreement_score":0.8973049,"about_ca_system_score_codex":0.00006192287,"about_ca_system_score_gemma":0.00014514365,"threshold_uncertainty_score":0.9999198},"labels":[],"label_agreement":null},{"id":"W1992435907","doi":"10.1002/1097-0258(20010130)20:2<249::aid-sim641>3.0.co;2-l","title":"Statistical inferences for a twin correlation with multinomial outcomes","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multinomial distribution; Sample size determination; Statistics; Point estimation; Goodness of fit; Statistical inference; Confidence interval; Interval estimation; Computer science; Econometrics; Inference; Sample (material); Monte Carlo method; Mathematics; Artificial intelligence","score_opus":0.4665853261819578,"score_gpt":0.5871577886326694,"score_spread":0.12057246245071163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992435907","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043217707,0.000012079754,0.9905111,0.00072603044,0.00072363234,0.0010550194,0.00064839085,0.00006536082,0.0019366235],"genre_scores_gemma":[0.07072932,0.00002659812,0.9279713,0.00027762185,0.00033100674,0.00015440561,0.00005212433,0.000043699238,0.0004139162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996759,0.00041646435,0.0013064542,0.00045605307,0.00059828267,0.00046375836],"domain_scores_gemma":[0.8881183,0.11085883,0.00030936353,0.0003079979,0.00023396318,0.0001715277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028720312,0.00029252082,0.0010614758,0.00016447126,0.00008274689,0.000020512043,0.00022073403,0.00015851611,0.00089905673],"category_scores_gemma":[0.17254163,0.00019702657,0.000032182026,0.0002686697,0.00059568067,0.000050908744,0.00003907174,0.00038006573,0.000015453428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083358865,0.00022851197,0.083039105,0.00015495662,0.00006894886,0.000100843434,0.00040354527,0.000023801662,0.000008897266,0.8698447,0.009395882,0.035897236],"study_design_scores_gemma":[0.0058472627,0.0010483094,0.04438588,0.00019588448,0.00017130566,0.000012148351,0.00023058703,0.008039498,0.000004375553,0.93888336,0.0009186331,0.0002627245],"about_ca_topic_score_codex":0.00010287356,"about_ca_topic_score_gemma":0.0003428773,"teacher_disagreement_score":0.1696696,"about_ca_system_score_codex":0.000085797285,"about_ca_system_score_gemma":0.00010218245,"threshold_uncertainty_score":0.9844041},"labels":[],"label_agreement":null},{"id":"W1992970840","doi":"10.1177/1740774513490250","title":"Caution regarding the choice of standard deviations to guide sample size calculations in clinical trials","year":2013,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Sample size determination; Statistics; Clinical trial; Medicine; Medical physics; Psychology; Mathematics; Internal medicine","score_opus":0.8857924334962634,"score_gpt":0.7230755554597601,"score_spread":0.16271687803650325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992970840","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.119125254,0.00012036697,0.8300172,0.022651233,0.009375465,0.014521676,0.001273794,0.00026448246,0.0026505291],"genre_scores_gemma":[0.105684824,0.00019718801,0.8869855,0.0018449349,0.0038869458,0.00072961155,0.000008335499,0.000087905435,0.0005747809],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8619329,0.10053542,0.03385368,0.0013883283,0.0013952313,0.0008944624],"domain_scores_gemma":[0.007918655,0.98336077,0.0051089935,0.0018916467,0.0010799253,0.0006400072],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36458686,0.00041580634,0.0064221085,0.00017196189,0.00021077966,0.00015163135,0.0009151956,0.00086301804,0.0023179373],"category_scores_gemma":[0.9935464,0.00026680116,0.0022847415,0.001052938,0.0005766874,0.00018371482,0.00035927893,0.0011822678,0.00018886835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022402187,0.0023936296,0.07653305,0.00025660856,0.0016610032,0.0000074842324,0.00034875004,0.00022855838,0.00046323103,0.32356226,0.25814113,0.33416405],"study_design_scores_gemma":[0.0067031435,0.00054538663,0.056320615,0.0003434005,0.0007326657,8.1166223e-7,0.00013947449,0.0005056114,0.0001484112,0.91334397,0.020835973,0.00038055136],"about_ca_topic_score_codex":0.00042295564,"about_ca_topic_score_gemma":0.00021627637,"teacher_disagreement_score":0.8828254,"about_ca_system_score_codex":0.00016406084,"about_ca_system_score_gemma":0.0005324644,"threshold_uncertainty_score":0.9999784},"labels":[],"label_agreement":null},{"id":"W1993531603","doi":"10.1016/j.csda.2012.09.003","title":"Exact statistical power for response adaptive designs","year":2012,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Adaptive design; Markov chain; Statistical power; Mathematics; Sample size determination; Mathematical optimization; Power (physics); Applied mathematics; Computer science; Statistics","score_opus":0.7109912218851108,"score_gpt":0.5976965298666802,"score_spread":0.11329469201843057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993531603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045563225,0.00004634332,0.92460704,0.0001358325,0.00030766198,0.000555796,0.073697925,0.000081052574,0.00011274616],"genre_scores_gemma":[0.09093319,0.000005903905,0.9053898,0.00019556335,0.00023199196,0.00005121954,0.0030046236,0.00005966421,0.00012803714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9938907,0.0021022502,0.0014574182,0.00082512805,0.0009762792,0.0007482426],"domain_scores_gemma":[0.8061662,0.19139586,0.0004523746,0.0010213365,0.0005176684,0.00044657924],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00935098,0.00037663055,0.0011154587,0.00033801974,0.00025665667,0.00012004889,0.00075139507,0.00016865916,0.0018869685],"category_scores_gemma":[0.13661937,0.0003549907,0.00020249616,0.00090649864,0.0003389243,0.00028450455,0.0003877087,0.00027606366,0.00013585045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001913092,0.00069636776,0.0017285221,0.00006015863,0.0034648627,0.00001472642,0.00016022212,0.0011083196,0.000011984399,0.9088268,0.07669499,0.0053199218],"study_design_scores_gemma":[0.00078445463,0.00021041153,0.025526797,0.000011592978,0.004339288,0.0000034047891,0.000038817245,0.14930487,0.0000068061468,0.81716037,0.0021962365,0.00041694305],"about_ca_topic_score_codex":0.000028024862,"about_ca_topic_score_gemma":0.000013123601,"teacher_disagreement_score":0.18929362,"about_ca_system_score_codex":0.00014507168,"about_ca_system_score_gemma":0.00021909228,"threshold_uncertainty_score":0.9998902},"labels":[],"label_agreement":null},{"id":"W1993607274","doi":"10.1002/sim.1297","title":"The European regulatory experience","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hatch (Canada)","funders":"","keywords":"Clinical trial; Regulatory science; Margin (machine learning); Risk analysis (engineering); Work (physics); Medicine; Computer science; Management science; Economics","score_opus":0.5295102756246849,"score_gpt":0.563117157145275,"score_spread":0.033606881520590104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993607274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028269012,0.0006845947,0.7964706,0.0030764139,0.0031928166,0.0006964328,0.00009532592,0.00016078248,0.19279617],"genre_scores_gemma":[0.0859851,0.0004984218,0.90870404,0.00048939826,0.0009143717,0.00003098433,0.000001294829,0.000056473113,0.003319923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961763,0.0015756856,0.0010270189,0.0002903407,0.0005762131,0.00035442106],"domain_scores_gemma":[0.9408338,0.058120772,0.00019897804,0.0006357632,0.000085878426,0.00012478506],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006179464,0.00015967092,0.00039274874,0.00004846235,0.00015212929,0.000017768334,0.00044474474,0.000049640625,0.0011400952],"category_scores_gemma":[0.18378642,0.00009751986,0.00002443544,0.00023380651,0.0010913853,0.000022778393,0.00008874618,0.00037443696,0.00009910193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012736052,0.00005454196,0.0002974261,0.000032183318,0.000012046544,0.00012033792,0.0013974301,5.1737135e-7,0.000042208525,0.7311053,0.12360421,0.14332102],"study_design_scores_gemma":[0.00079946296,0.00010644284,0.0036098252,0.00011749074,0.000021903556,0.0000066508114,0.00037604722,0.0007400411,0.000017395085,0.98338336,0.010692265,0.0001291328],"about_ca_topic_score_codex":0.0000085137035,"about_ca_topic_score_gemma":0.000017264572,"teacher_disagreement_score":0.252278,"about_ca_system_score_codex":0.00004699483,"about_ca_system_score_gemma":0.0000073547094,"threshold_uncertainty_score":0.999773},"labels":[],"label_agreement":null},{"id":"W1994033586","doi":"10.1111/j.1537-2995.2008.01714.x","title":"The role of noninferiority designs in clinical research","year":2008,"lang":"en","type":"article","venue":"Transfusion","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Kinesiology; Library science; Citation; Psychology; Medicine; Medical education; Computer science","score_opus":0.8250701661180836,"score_gpt":0.652717478924168,"score_spread":0.1723526871939156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994033586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9667553,0.00012753159,0.023232779,0.00032301855,0.0003042199,0.0007432987,0.000009400394,0.000033910095,0.008470576],"genre_scores_gemma":[0.7700333,0.001955569,0.22770113,0.000012711905,0.0001477993,0.000025363845,1.7745327e-7,0.00001899739,0.000104933446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99376947,0.003795002,0.0012677169,0.00025432618,0.0005979096,0.00031557932],"domain_scores_gemma":[0.88795054,0.11129526,0.0000793608,0.00043472365,0.00015847551,0.00008166044],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01998691,0.00008544501,0.00043713834,0.000054880213,0.00019902956,0.000006786251,0.00032421836,0.00019323335,0.00010915977],"category_scores_gemma":[0.059645526,0.000055637847,0.00013873332,0.0003615274,0.0007301768,0.000027125318,0.000051428902,0.0007529881,0.00002216254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022445428,0.0021127774,0.12744041,0.00011794033,0.000054072785,0.00006693145,0.0019886338,0.0000021651279,0.010643617,0.48597977,0.0009443304,0.3684048],"study_design_scores_gemma":[0.00087375345,0.0003101188,0.03878014,0.000056940764,0.000009731956,0.0000034048014,0.00011573416,0.00017816846,0.005237939,0.9534353,0.0009268553,0.00007190263],"about_ca_topic_score_codex":0.0001097514,"about_ca_topic_score_gemma":0.00011532267,"teacher_disagreement_score":0.46745554,"about_ca_system_score_codex":0.000024232873,"about_ca_system_score_gemma":0.00011728908,"threshold_uncertainty_score":0.9482755},"labels":[],"label_agreement":null},{"id":"W1994303059","doi":"10.1080/00220970309602065","title":"Pairwise Multiple Comparisons: New Yardstick, New Results","year":2003,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bonferroni correction; Multiple comparisons problem; False discovery rate; Statistics; Pairwise comparison; Word error rate; Type I and type II errors; Computer science; Mathematics; Artificial intelligence; Biology","score_opus":0.5586051573696436,"score_gpt":0.5803779345219491,"score_spread":0.021772777152305522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994303059","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3668937,0.011608464,0.539537,0.013615306,0.023988416,0.002692967,0.000036190515,0.00014151011,0.041486442],"genre_scores_gemma":[0.36549705,0.000039079845,0.6316463,0.0002493696,0.0008116824,0.0000023709317,5.123666e-7,0.00002028763,0.001733354],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99698466,0.0010633676,0.0012466146,0.00011763231,0.00040512832,0.00018259988],"domain_scores_gemma":[0.9822792,0.016016025,0.00091686187,0.00035410223,0.00013214136,0.00030169493],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003277078,0.00015045836,0.00040129473,0.000058651356,0.00009118356,0.000036948855,0.00030748014,0.00007325236,0.0003723752],"category_scores_gemma":[0.058429852,0.00009917243,0.00013474067,0.00015288296,0.00008150721,0.00011098407,0.000027490818,0.00030298295,0.000038253194],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001480835,0.0019317965,0.00025141577,0.000016559803,0.00012615643,0.0000020355967,0.0048728916,0.000017814438,0.013246092,0.058425378,0.911348,0.008281017],"study_design_scores_gemma":[0.0051519517,0.00082001346,0.00053314364,0.0002754017,0.00026484104,0.00015264413,0.008985328,0.000064029315,0.14959946,0.807889,0.02596706,0.00029712354],"about_ca_topic_score_codex":0.000084901,"about_ca_topic_score_gemma":0.0000034476682,"teacher_disagreement_score":0.8853809,"about_ca_system_score_codex":0.00014239327,"about_ca_system_score_gemma":0.00091294665,"threshold_uncertainty_score":0.9495014},"labels":[],"label_agreement":null},{"id":"W1995196170","doi":"10.1177/0013164403256358","title":"Approximate Confidence Intervals for Effect Sizes","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Confidence interval; Interval (graph theory); Contrast (vision); Coverage probability; Mathematics; Population; Credible interval; Tolerance interval; Econometrics; Demography; Computer science; Combinatorics","score_opus":0.7704275307910567,"score_gpt":0.5976349069448019,"score_spread":0.17279262384625482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995196170","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12291843,0.0012594654,0.80909747,0.012569586,0.0068579395,0.0053440984,0.00010177023,0.00018878706,0.041662477],"genre_scores_gemma":[0.4791962,0.000017958506,0.51915437,0.0005466006,0.00024750756,0.0005943283,9.807452e-7,0.000012408213,0.00022964529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771386,0.00078017503,0.0004945093,0.00040311294,0.00038216473,0.00022620193],"domain_scores_gemma":[0.975208,0.024094788,0.00013133114,0.00020694615,0.0002114082,0.0001475343],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065475334,0.0001611382,0.00036790414,0.000024657498,0.00009761367,0.000037746202,0.00012845562,0.000100205194,0.00082816504],"category_scores_gemma":[0.11214416,0.00010771896,0.00010259425,0.00007100306,0.0001431431,0.000025809179,0.000013890644,0.00012772714,0.00001926902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016053309,0.00068039406,0.00055802625,0.00014898999,0.000051555417,3.36728e-7,0.00004318759,1.2774271e-7,0.0009075246,0.9791241,0.009429845,0.0088953255],"study_design_scores_gemma":[0.00082508544,0.0006506283,0.0032077893,0.0000730859,0.000044167802,0.000007808377,0.000012102889,0.000004600516,0.0011853932,0.9916546,0.002190242,0.00014454602],"about_ca_topic_score_codex":6.3792885e-7,"about_ca_topic_score_gemma":3.831762e-7,"teacher_disagreement_score":0.35627776,"about_ca_system_score_codex":0.000034496643,"about_ca_system_score_gemma":0.000026619915,"threshold_uncertainty_score":0.9067826},"labels":[],"label_agreement":null},{"id":"W1997224430","doi":"10.2310/7200.2006.023","title":"How to Randomize","year":2006,"lang":"en","type":"review","venue":"Journal of the Society for Integrative Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Randomization; Restricted randomization; Medicine; Randomized controlled trial; Medical physics; Surgery","score_opus":0.6173385711118237,"score_gpt":0.6352206030655817,"score_spread":0.017882031953758037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997224430","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.2572444e-7,0.69593567,0.29183093,0.0036133958,0.004579778,0.0028918781,0.0002692409,0.000011814965,0.0008669672],"genre_scores_gemma":[5.7001596e-8,0.45413178,0.5400146,0.00025409416,0.0015791033,0.0001169385,7.2615074e-7,0.0000487364,0.0038539239],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99357,0.002901387,0.0024611286,0.00028127816,0.00042280692,0.000363395],"domain_scores_gemma":[0.83050066,0.16361266,0.004457402,0.00039322328,0.0008883853,0.0001476547],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.009541844,0.0004976051,0.0065583806,0.00006676809,0.00013886289,0.00007124732,0.0012946726,0.0009438071,0.000033831187],"category_scores_gemma":[0.1966215,0.0002163725,0.015283597,0.0003661524,0.00034537856,0.000048914597,0.00019763864,0.0017874372,0.0000042483066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020719813,0.00016001445,4.3155783e-8,0.0021206303,0.0019394278,0.0000028901347,0.0001661073,1.6147547e-7,7.8187844e-7,0.021434871,0.43997997,0.53398794],"study_design_scores_gemma":[0.001933372,0.0005324565,2.5372103e-8,0.0033666645,0.0038065189,0.00005410571,0.00015369082,0.0000011097651,0.000003379867,0.35778186,0.6322284,0.00013845568],"about_ca_topic_score_codex":0.0000012576656,"about_ca_topic_score_gemma":0.00000659926,"teacher_disagreement_score":0.5338495,"about_ca_system_score_codex":0.0010339187,"about_ca_system_score_gemma":0.0010953966,"threshold_uncertainty_score":0.9945781},"labels":[],"label_agreement":null},{"id":"W1997610764","doi":"10.1016/j.jclinepi.2004.01.021","title":"The number needed to treat (NNT) can be adjusted for bias when the outcome is measured with error","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Number needed to treat; Outcome (game theory); Statistics; Medicine; Mathematics; Econometrics; Confidence interval; Relative risk; Mathematical economics","score_opus":0.923124085653857,"score_gpt":0.6858614348184507,"score_spread":0.2372626508354062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997610764","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09584417,0.00007674702,0.34315836,0.55533004,0.0030968762,0.0016306879,0.000118432225,0.000045843313,0.00069886865],"genre_scores_gemma":[0.04573427,0.000086962624,0.8914349,0.059415616,0.002319897,0.00007250024,7.395483e-7,0.00008028387,0.00085483573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9762203,0.011947876,0.009928926,0.00048182264,0.0005984913,0.0008225509],"domain_scores_gemma":[0.36018366,0.6324499,0.004776875,0.0009417887,0.0009820758,0.00066570885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.101660594,0.00038227762,0.00432976,0.000053868724,0.0002863385,0.000034839635,0.0012069884,0.0006042308,0.00014905419],"category_scores_gemma":[0.86416733,0.00015673901,0.001437681,0.0002304393,0.0008931976,0.000054328353,0.00013080891,0.0016054986,0.00002713833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02143816,0.0015074726,0.10544088,0.00026071002,0.0027991445,0.00010394499,0.0015414935,0.0004287441,0.000024002362,0.46774957,0.34228128,0.056424607],"study_design_scores_gemma":[0.005904447,0.0020333428,0.009498664,0.00013945739,0.000751519,0.00011773414,0.00037074523,0.000058153877,0.00006140167,0.964554,0.016278476,0.00023207604],"about_ca_topic_score_codex":0.00013817783,"about_ca_topic_score_gemma":0.00027679323,"teacher_disagreement_score":0.7625067,"about_ca_system_score_codex":0.00012037011,"about_ca_system_score_gemma":0.00047503857,"threshold_uncertainty_score":0.92502946},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W1997783552","doi":"10.2106/jbjs.l.00094","title":"Adaptive Bayesian Randomized Trials: Realizing Their Potential","year":2012,"lang":"en","type":"article","venue":"Journal of Bone and Joint Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Flexibility (engineering); Bayesian probability; Computer science; Sample size determination; Adaptive design; Randomized controlled trial; Research design; Early stopping; Clinical trial; Machine learning; Risk analysis (engineering); Artificial intelligence; Statistics; Medicine; Mathematics","score_opus":0.6452061207865782,"score_gpt":0.5068687009588742,"score_spread":0.1383374198277041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997783552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04774445,0.0037157226,0.9417749,0.0014382304,0.0035284662,0.0005287593,0.000030925883,0.00003324839,0.0012052964],"genre_scores_gemma":[0.5926939,0.0012425882,0.40310806,0.00018461062,0.002688794,0.000006362135,3.0779356e-7,0.00003133715,0.000044009605],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98737115,0.0069955713,0.0047405465,0.00012390282,0.00042381632,0.00034499576],"domain_scores_gemma":[0.74083954,0.25353593,0.004678335,0.00022325224,0.000283341,0.00043958423],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.111194186,0.00019938097,0.005125999,0.00028932566,0.000074474076,0.00004458412,0.000031913994,0.00015970698,0.0002316352],"category_scores_gemma":[0.31931353,0.000119227705,0.0016976147,0.00011340663,0.00017986698,0.00022484045,0.00005108796,0.00040647454,0.0000029004411],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.26001295,0.002544821,0.0012658522,0.0010218183,0.0065364502,0.00074486254,0.0028175027,0.0000056707527,0.0046790405,0.19078587,0.12495456,0.4046306],"study_design_scores_gemma":[0.028155932,0.00008662238,0.0004429107,0.0006580022,0.0009477144,0.00043806783,0.00050998764,0.0001382295,0.00096255814,0.9670021,0.00041029888,0.00024760378],"about_ca_topic_score_codex":0.0000056061904,"about_ca_topic_score_gemma":2.5384725e-7,"teacher_disagreement_score":0.7762162,"about_ca_system_score_codex":0.000026335674,"about_ca_system_score_gemma":0.000081250946,"threshold_uncertainty_score":0.91521263},"labels":[],"label_agreement":null},{"id":"W1998343736","doi":"10.1002/cjs.5550350107","title":"Multiple testing using the posterior probabilities of directional alternatives, with application to genomic studies","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université Laval","funders":"","keywords":"Frequentist inference; Posterior probability; Bayesian probability; Null hypothesis; Context (archaeology); Null (SQL); Multiple comparisons problem; p-value; False discovery rate; Statistical hypothesis testing; Mathematics; Statistics; Value (mathematics); Computer science; Econometrics; Bayesian inference; Data mining; Biology; Genetics","score_opus":0.5349307423524098,"score_gpt":0.506746123292269,"score_spread":0.028184619060140803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998343736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2288323,0.00008837954,0.7700109,0.000093727045,0.00025559723,0.0003207412,0.000337319,0.0000035780051,0.000057439214],"genre_scores_gemma":[0.24575113,0.0000022087227,0.75396466,0.00005652733,0.000189512,0.0000028746565,3.2115577e-7,0.000017136275,0.000015648897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982297,0.00017408698,0.00096584065,0.000119519515,0.00026951949,0.00024136282],"domain_scores_gemma":[0.9642471,0.03324254,0.0007420007,0.0001682444,0.0013148376,0.00028525802],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028359566,0.00012201896,0.00040616418,0.00014255426,0.00014139987,0.000024139763,0.00021459613,0.00003669223,0.000012466776],"category_scores_gemma":[0.067132436,0.00008147461,0.000035090612,0.00022396511,0.00037468423,0.000039783958,0.000021167867,0.00019075519,7.5277416e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018429785,0.00038042275,0.26043108,0.0022043914,0.0029610689,0.0005864058,0.024743568,0.007266443,0.029621549,0.3289058,0.003453259,0.33760303],"study_design_scores_gemma":[0.0012978977,0.0011393522,0.04737543,0.00082155573,0.00045325325,0.0004291684,0.005036732,0.0017037647,0.0033391702,0.9372785,0.0007108818,0.00041428828],"about_ca_topic_score_codex":0.00089043385,"about_ca_topic_score_gemma":0.008734569,"teacher_disagreement_score":0.6083727,"about_ca_system_score_codex":0.00028958573,"about_ca_system_score_gemma":0.0006130377,"threshold_uncertainty_score":0.9407255},"labels":[],"label_agreement":null},{"id":"W1998669587","doi":"10.1002/sim.1227","title":"Assessing the gain in diagnostic performance when combining two diagnostic tests","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McMaster University","funders":"","keywords":"Statistics; Likelihood-ratio test; Test (biology); Sensitivity (control systems); Component (thermodynamics); Score test; Diagnostic test; Computer science; Econometrics; Mathematics; Medicine","score_opus":0.44492644498609113,"score_gpt":0.5605836017274896,"score_spread":0.11565715674139843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998669587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14410478,0.0014546415,0.8170305,0.0070792916,0.004233128,0.003083987,0.00019574376,0.00023734917,0.022580601],"genre_scores_gemma":[0.543396,0.00046244063,0.45492533,0.0005803518,0.00035782464,0.000106733496,0.0000052144546,0.00004974436,0.00011635412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944042,0.001576274,0.0019966539,0.0004991109,0.00082971563,0.00069405546],"domain_scores_gemma":[0.624348,0.37467924,0.00030629267,0.00046634642,0.00008713274,0.000113044196],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008071226,0.0003448961,0.001002642,0.00021246674,0.00014145717,0.00006395525,0.0005510407,0.00013155177,0.0014013628],"category_scores_gemma":[0.7061069,0.00024028435,0.000035373727,0.00058706506,0.0007942821,0.00012709621,0.00014985073,0.0011412353,0.000070759656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044626926,0.0011764509,0.16963811,0.0010594354,0.000087133514,0.001585521,0.009117852,0.00055088056,0.00006458461,0.43639854,0.05583026,0.3244466],"study_design_scores_gemma":[0.0035716165,0.0003086621,0.033154186,0.002320473,0.00011375533,0.000020425583,0.00055722886,0.04526064,0.000018625971,0.914074,0.0002673892,0.00033300935],"about_ca_topic_score_codex":0.00012674455,"about_ca_topic_score_gemma":0.00013445382,"teacher_disagreement_score":0.69803566,"about_ca_system_score_codex":0.00012717418,"about_ca_system_score_gemma":0.000041373984,"threshold_uncertainty_score":0.9995115},"labels":[],"label_agreement":null},{"id":"W1998705404","doi":"10.1016/j.csda.2011.02.011","title":"Inference on the probability as a measurement of treatment effect under a density ratio model and random censoring","year":2011,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Censoring (clinical trials); Statistics; Inference; Econometrics; Mathematics; Random effects model; Computer science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.7377686753371127,"score_gpt":0.5290462272621571,"score_spread":0.20872244807495555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998705404","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046226785,0.000010573588,0.9513352,0.000054285698,0.000029227574,0.0005648054,0.0016476628,0.000018858374,0.000112636684],"genre_scores_gemma":[0.48678064,0.00001060727,0.5130738,0.000029631396,0.000010560003,0.000022907501,0.00005952893,0.000007069784,0.0000052595697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965587,0.0012452084,0.0008054365,0.0005210254,0.0007015198,0.00016810666],"domain_scores_gemma":[0.95110327,0.047099452,0.00038176787,0.0008600002,0.0004545802,0.000100948295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0042705564,0.000224761,0.0007864082,0.000088505454,0.00014531198,0.00003960408,0.00030151533,0.000057199384,0.00012775548],"category_scores_gemma":[0.04741522,0.00013961391,0.00010820266,0.0003206655,0.00025558082,0.000052726347,0.00019400829,0.00012327053,0.000006430977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006960349,0.0005596638,0.004596998,0.00011629064,0.0035981461,0.000004496507,0.00036345265,0.042792205,0.000023149614,0.9401231,0.00018788438,0.0069386093],"study_design_scores_gemma":[0.000605769,0.0001785914,0.007008844,0.000015954824,0.0020242834,3.306513e-7,0.0000053666363,0.39862445,0.00005734767,0.591396,8.325369e-7,0.00008224578],"about_ca_topic_score_codex":0.00029778157,"about_ca_topic_score_gemma":0.00019205143,"teacher_disagreement_score":0.44055387,"about_ca_system_score_codex":0.0001375382,"about_ca_system_score_gemma":0.00016859783,"threshold_uncertainty_score":0.9606088},"labels":[],"label_agreement":null},{"id":"W2000081466","doi":"10.1016/j.vascn.2010.06.003","title":"Non-clinical models: Validation, study design and statistical consideration in safety pharmacology","year":2010,"lang":"en","type":"editorial","venue":"Journal of Pharmacological and Toxicological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Safety pharmacology; Pharmacology; Medicine; Computer science; Reliability engineering; Computational biology; Engineering; Drug; Biology","score_opus":0.5978195212791979,"score_gpt":0.6544073368838326,"score_spread":0.05658781560463466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000081466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01147036,0.00026271777,0.6740328,0.00055678666,0.31063864,0.002743443,0.000103855215,0.00004952076,0.00014184126],"genre_scores_gemma":[0.0031637757,0.0020302925,0.85466045,0.00034351027,0.13957806,0.00011797151,0.000004157849,0.000057477428,0.000044308286],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96216524,0.028297195,0.0063237958,0.0012587098,0.0011712738,0.0007837632],"domain_scores_gemma":[0.6089408,0.38638246,0.0025713523,0.00024826755,0.00094841234,0.00090874743],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.064912535,0.0008779291,0.0046533663,0.00036704764,0.00023587326,0.00017569211,0.00070612755,0.0036077946,0.0013334015],"category_scores_gemma":[0.20724872,0.00058628304,0.00034575604,0.00036284633,0.0013613472,0.00026234202,0.0006582085,0.009235122,0.0000036693618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017148145,0.016765555,0.00054270297,0.00039242033,0.0025520495,0.0033763312,0.0003503675,0.00020435105,0.0058134077,0.006771655,0.824998,0.12108502],"study_design_scores_gemma":[0.015040189,0.012653292,0.0010012878,0.000108571854,0.0038172256,0.00010517281,0.000111009365,0.0061073666,0.0007208636,0.9438013,0.015580566,0.0009531768],"about_ca_topic_score_codex":0.0000036447605,"about_ca_topic_score_gemma":0.0000027310482,"teacher_disagreement_score":0.9370296,"about_ca_system_score_codex":0.00016031932,"about_ca_system_score_gemma":0.0005902634,"threshold_uncertainty_score":0.9996589},"labels":[],"label_agreement":null},{"id":"W2000366201","doi":"10.1214/14-ejs920rej","title":"Rejoinder of “Dynamic treatment regimes: Technical challenges and applications”","year":2014,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; University of Waterloo; National Institute on Drug Abuse; University of Michigan; National Institutes of Health; National Science Foundation","keywords":"Mathematics; Econometrics; Applied mathematics","score_opus":0.21013291329934916,"score_gpt":0.4842567246269433,"score_spread":0.2741238113275941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000366201","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096426246,0.0032357038,0.99411345,0.00034965418,0.00007157767,0.00028416925,0.000040974384,0.000015607835,0.00092460215],"genre_scores_gemma":[0.15626732,0.01374961,0.8296177,0.00002238574,0.00017809443,0.00001589401,8.95474e-7,0.000032771957,0.00011534491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975166,0.00044250843,0.001167955,0.00018809077,0.00034559853,0.00033930127],"domain_scores_gemma":[0.9769662,0.021374483,0.0009503381,0.00031492335,0.00027440977,0.00011964074],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027737787,0.00017414542,0.0007785369,0.00009885146,0.000037670878,0.0000097037055,0.00019837263,0.00012990118,0.000024469513],"category_scores_gemma":[0.012075859,0.00013234704,0.00008974238,0.00008292506,0.00023035378,0.00003534135,0.000033231016,0.0003666732,0.0000023568948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007126175,0.00019702697,0.0000069081225,0.00009028843,0.00009660548,0.0000022809072,0.000046536297,8.095854e-7,0.00024419156,0.7568845,0.00014593439,0.24221362],"study_design_scores_gemma":[0.001114361,0.0021529722,0.0003591519,0.0000666311,0.00027773945,0.00011429163,0.000058552054,0.00013085251,0.0002024948,0.99170035,0.0037042953,0.00011828839],"about_ca_topic_score_codex":9.933419e-7,"about_ca_topic_score_gemma":0.000011660598,"teacher_disagreement_score":0.24209534,"about_ca_system_score_codex":0.00018704035,"about_ca_system_score_gemma":0.00021009769,"threshold_uncertainty_score":0.99624586},"labels":[],"label_agreement":null},{"id":"W2001820849","doi":"10.1002/bimj.200290000","title":"An Empirical Comparison of Parametric and Semiparametric Cure Models","year":2002,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Memorial University of Newfoundland","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland","keywords":"Semiparametric regression; Semiparametric model; Parametric statistics; Cure rate; Econometrics; Parametric model; Estimation; Nonparametric statistics; Statistics; Mathematics; Computer science; Medicine; Economics; Internal medicine","score_opus":0.8170111462341253,"score_gpt":0.6327136137393924,"score_spread":0.1842975324947329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001820849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31305537,0.0037694625,0.6800718,0.0005594503,0.0007162888,0.0003934323,0.00006041435,0.00010240623,0.0012713751],"genre_scores_gemma":[0.53585446,0.00033316162,0.4634826,0.000060319988,0.00021647807,0.0000028826848,2.9907864e-7,0.000024890593,0.000024947625],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99435633,0.0012927362,0.002065331,0.0004564655,0.001286767,0.00054234255],"domain_scores_gemma":[0.951433,0.04605057,0.000818774,0.0004686119,0.0003625871,0.0008664534],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003664349,0.00029735628,0.0013901573,0.0031235255,0.00015413256,0.0001483389,0.00056688336,0.00044211443,0.00056739926],"category_scores_gemma":[0.08893202,0.0002268462,0.00026154122,0.009797719,0.00035868827,0.00025028273,0.000120676894,0.0010119423,0.000019528641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003055209,0.01011814,0.080336064,0.00029523272,0.00047607618,0.00011444068,0.00061114907,0.0001509698,0.00043295845,0.029117411,0.049330343,0.8287117],"study_design_scores_gemma":[0.0020669303,0.002203786,0.005039414,0.000064426706,0.0002881033,0.00022549498,0.00012210524,0.1546043,0.0005161412,0.8336316,0.00076125504,0.00047646233],"about_ca_topic_score_codex":0.0000029666228,"about_ca_topic_score_gemma":1.4559735e-7,"teacher_disagreement_score":0.8282352,"about_ca_system_score_codex":0.000092456445,"about_ca_system_score_gemma":0.00002932596,"threshold_uncertainty_score":0.9250519},"labels":[],"label_agreement":null},{"id":"W2002271480","doi":"10.1002/sim.1477","title":"Misclassification in a matched case‐control study with variable matching ratio: application to a study of c‐erbB‐2 overexpression and breast cancer","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Odds ratio; Case-control study; Breast cancer; Risk factor; Statistics; Matching (statistics); Covariate; Medicine; Breast disease; Confidence interval; Oncology; Internal medicine; Mathematics; Computer science; Cancer","score_opus":0.15994251799571924,"score_gpt":0.5014059989025446,"score_spread":0.3414634809068253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002271480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33943614,0.000012486019,0.6574149,0.00009898626,0.000056516692,0.0026740627,0.00020977837,0.000013467859,0.000083636674],"genre_scores_gemma":[0.6439562,0.000004000923,0.35563177,0.000042835458,0.000030918232,0.00030030086,0.0000010210604,0.000021864887,0.0000111180625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961388,0.0013614456,0.0012675974,0.00049554853,0.0005008704,0.00023571134],"domain_scores_gemma":[0.98494697,0.013885011,0.00040252524,0.00045169756,0.00019097238,0.00012284673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0044198,0.00021674919,0.0008667533,0.00018785016,0.00005640762,0.000013199431,0.000119404765,0.00007647241,0.00015755143],"category_scores_gemma":[0.011428999,0.00016128109,0.0000074928876,0.00056338555,0.00008692434,0.000043909455,0.00003176389,0.0002864281,7.0696785e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053995186,0.018515164,0.31200728,0.0019433309,0.000692645,0.0011860533,0.07723285,0.0022030775,0.018195631,0.49786228,0.00067339855,0.06408876],"study_design_scores_gemma":[0.022524154,0.0028518597,0.17692031,0.0010861938,0.00052874396,0.000121902776,0.03169614,0.0048958915,0.000083632556,0.75885445,0.000005486837,0.00043121478],"about_ca_topic_score_codex":0.0014126706,"about_ca_topic_score_gemma":0.0013062591,"teacher_disagreement_score":0.30452004,"about_ca_system_score_codex":0.00009610699,"about_ca_system_score_gemma":0.00006321237,"threshold_uncertainty_score":0.9968982},"labels":[],"label_agreement":null},{"id":"W2002725602","doi":"10.1136/ebmh.11.1.3-a","title":"Missing data and the trouble with LOCF","year":2008,"lang":"en","type":"article","venue":"Evidence-Based Mental Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Missing data; Drop out; Subject (documents); Data collection; Statistics; Psychology; Medicine; Computer science; Mathematics","score_opus":0.7980895649941298,"score_gpt":0.5988277908535505,"score_spread":0.19926177414057922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002725602","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058587372,0.008736812,0.6751978,0.24616623,0.001337472,0.0068489327,0.00051258114,0.0004376009,0.0021752224],"genre_scores_gemma":[0.14159274,0.00065369403,0.8519058,0.005455998,0.000205156,0.000025634783,0.0000069435055,0.000030889947,0.00012311933],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968126,0.001171053,0.00066073623,0.00046581755,0.0005353456,0.00035445398],"domain_scores_gemma":[0.9602587,0.038181387,0.00031142906,0.00097194506,0.00003503248,0.00024147965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0066573354,0.00017220374,0.00056277914,0.00003112559,0.00052085426,0.000039791033,0.00045517084,0.000050707702,0.00010220181],"category_scores_gemma":[0.013986201,0.000096351774,0.000035472665,0.0001808059,0.0008564276,0.00016548867,0.00016155769,0.00027449947,0.000011866262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027706675,0.002001947,0.010927035,0.005188108,0.00039561972,0.00017946612,0.006841401,0.000016760188,0.0001698593,0.26568174,0.19483003,0.48606136],"study_design_scores_gemma":[0.042809207,0.003919469,0.004766084,0.012131173,0.00037405198,0.00044672418,0.0014537659,0.019261325,0.00207885,0.90078974,0.010460043,0.0015095837],"about_ca_topic_score_codex":0.0001394314,"about_ca_topic_score_gemma":0.000021034544,"teacher_disagreement_score":0.635108,"about_ca_system_score_codex":0.00010540204,"about_ca_system_score_gemma":0.00055468135,"threshold_uncertainty_score":0.99431944},"labels":[],"label_agreement":null},{"id":"W2003238678","doi":"10.1111/j.1365-2230.2007.02629.x","title":"Assessing the validity of a statistical distribution: some illustrative examples from dermatological research","year":2008,"lang":"en","type":"article","venue":"Clinical and Experimental Dermatology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Goodness of fit; Quantile; Normality; Statistics; Statistic; Normal distribution; Statistical hypothesis testing; Mathematics; Test statistic; Econometrics; Normality test","score_opus":0.8432509139738495,"score_gpt":0.6603606558901906,"score_spread":0.182890258083659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003238678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9672723,0.00034757724,0.02945248,0.0012776147,0.0005488046,0.00041527042,0.0002833783,0.0000538499,0.0003487632],"genre_scores_gemma":[0.90110034,0.0001353792,0.09815933,0.00022587934,0.00027313814,0.000054655215,0.000026108371,0.000015533924,0.000009644144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9889267,0.007506893,0.0019196462,0.0006193677,0.0005240499,0.00050331576],"domain_scores_gemma":[0.8561721,0.14275919,0.00026658914,0.0004081258,0.00014894706,0.00024504706],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0029155752,0.00023911252,0.00123689,0.000029460221,0.0005159631,0.000045095647,0.00038955404,0.0004543593,0.00035728313],"category_scores_gemma":[0.046898205,0.00015092012,0.00017807145,0.00016442327,0.008866613,0.00015650349,0.0004884341,0.00094529253,0.000030036661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003582892,0.0021953122,0.08212435,0.00007294318,0.00020503688,0.0006729211,0.0005948447,1.8483621e-7,0.000623279,0.89119065,0.020412607,0.0015495793],"study_design_scores_gemma":[0.001532093,0.0002940947,0.05510494,0.00004550195,0.000052992145,0.00045129244,0.0013496319,0.00027167905,0.011498167,0.9283347,0.00083846005,0.00022645749],"about_ca_topic_score_codex":0.000034248587,"about_ca_topic_score_gemma":0.0000015164621,"teacher_disagreement_score":0.1352523,"about_ca_system_score_codex":0.000025245225,"about_ca_system_score_gemma":0.00011522843,"threshold_uncertainty_score":0.9938307},"labels":[],"label_agreement":null},{"id":"W2003470839","doi":"10.1186/1751-0147-44-s1-p44","title":"Quality and Analysis of Small Data Sets – A Statistical Point of View","year":2003,"lang":"en","type":"article","venue":"Acta veterinaria Scandinavica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ottawa Mental Health Centre","funders":"","keywords":"Outlier; Quality (philosophy); Computer science; Experimental data; Set (abstract data type); Point (geometry); Data set; Statistics; Statistical analysis; Data mining; Mathematics; Artificial intelligence","score_opus":0.7481228834294362,"score_gpt":0.5961917175534598,"score_spread":0.15193116587597644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003470839","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63145477,0.00012319096,0.35820788,0.000286001,0.00029882614,0.0007401262,0.005647398,0.000052203894,0.0031896213],"genre_scores_gemma":[0.5062246,0.000038620386,0.4936475,0.000029707608,0.000007333731,0.000006700545,0.000023318806,0.00001326998,0.000008997492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99519235,0.0019575595,0.0016184185,0.0005787667,0.00036598905,0.0002869102],"domain_scores_gemma":[0.96150154,0.035942893,0.0006572862,0.0015737343,0.00013281502,0.00019173272],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062316135,0.00021784754,0.0016148415,0.00014574172,0.000042350155,0.000022606662,0.00048678112,0.00015535958,0.00081637094],"category_scores_gemma":[0.07887867,0.00018510707,0.000129722,0.00058916357,0.00038914479,0.00006753609,0.0003794226,0.00018532595,0.0000015892583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081931654,0.0011035108,0.016708154,0.0017430274,0.0035925622,0.000046618796,0.00034836546,7.293596e-7,0.005274113,0.9515416,0.00079085235,0.018031143],"study_design_scores_gemma":[0.0014829563,0.00078217126,0.09512589,0.00016610493,0.00357294,0.000023950557,0.00009680597,0.0009827268,0.00021032107,0.89645374,0.00070352317,0.00039885895],"about_ca_topic_score_codex":0.000075747026,"about_ca_topic_score_gemma":0.000014846989,"teacher_disagreement_score":0.1354396,"about_ca_system_score_codex":0.000025858733,"about_ca_system_score_gemma":0.000055125878,"threshold_uncertainty_score":0.92888033},"labels":[],"label_agreement":null},{"id":"W2004500024","doi":"10.1007/s11606-012-2031-7","title":"Chapter 9: Options for Summarizing Medical Test Performance in the Absence of a “Gold Standard”","year":2012,"lang":"en","type":"article","venue":"Journal of General Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton General Hospital","funders":"Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Gold standard (test); Test (biology); Medicine; Index (typography); Imperfect; Sensitivity (control systems); Statistics; Computer science; Mathematics; Internal medicine","score_opus":0.43488022552912786,"score_gpt":0.5528147674902757,"score_spread":0.11793454196114783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004500024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5444979,0.0017742319,0.41828647,0.017772948,0.0072860336,0.00088483805,0.000074486736,0.000016181493,0.009406891],"genre_scores_gemma":[0.6944782,0.00042265325,0.30058894,0.0006568638,0.0034619344,0.000008794502,2.5923464e-7,0.000017340304,0.00036500575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968369,0.0002271453,0.00163285,0.00008561263,0.00096272497,0.00025477767],"domain_scores_gemma":[0.9734318,0.025091577,0.000794995,0.00017849209,0.0003143678,0.00018876758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012202428,0.00012729956,0.00065311353,0.00013354761,0.000025373967,0.0000069337157,0.0005015646,0.00009314797,0.0002918463],"category_scores_gemma":[0.08682265,0.00006615507,0.0001373105,0.00011941797,0.00027863117,0.00011403132,0.0000492046,0.0005217342,0.0000011247829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003583492,0.0019301925,0.14516124,0.0012532842,0.0005418776,0.00016368975,0.005988616,0.00002177418,0.013240704,0.6492342,0.06417985,0.11470108],"study_design_scores_gemma":[0.02059433,0.017923338,0.06451201,0.016050652,0.0008523992,0.0027522298,0.0019648392,0.0074946675,0.009914286,0.80637485,0.05071104,0.00085537735],"about_ca_topic_score_codex":0.00001357251,"about_ca_topic_score_gemma":0.000006950658,"teacher_disagreement_score":0.15714064,"about_ca_system_score_codex":0.0000437719,"about_ca_system_score_gemma":0.000049071594,"threshold_uncertainty_score":0.9208694},"labels":[],"label_agreement":null},{"id":"W2005001066","doi":"10.1245/s10434-006-9295-2","title":"Non-Inferiority Trials in Surgical Oncology","year":2007,"lang":"en","type":"review","venue":"Annals of Surgical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Clinical trial; Surgical oncology; Randomized controlled trial; Intensive care medicine; Medical physics; Oncology; Surgery; Internal medicine","score_opus":0.9027799242287069,"score_gpt":0.730008414976171,"score_spread":0.17277150925253593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005001066","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010278284,0.8605558,0.000676576,0.0013600125,0.0027205232,0.0034617486,0.0003788713,0.00010074617,0.1307354],"genre_scores_gemma":[0.0000030947851,0.92484576,0.07239979,0.00015273617,0.0018720267,0.00026751502,0.000026276906,0.00012526952,0.0003075423],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95233804,0.027612833,0.015695376,0.0015785536,0.0010432013,0.0017320005],"domain_scores_gemma":[0.5179509,0.47483367,0.005035297,0.0010277181,0.000483762,0.0006686742],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.10906246,0.0011457934,0.030292079,0.0009206846,0.00006450084,0.000025421725,0.0013080445,0.0059880316,0.0025971916],"category_scores_gemma":[0.078480534,0.00084428996,0.0044826106,0.0014196398,0.0012503499,0.000078431076,0.00068202696,0.0034246834,0.0002450923],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008461702,0.0021541792,0.000003100771,0.0070766103,0.00047156366,0.0056850845,0.000028212373,1.2826519e-7,8.721347e-8,0.04873957,0.0055325376,0.92946273],"study_design_scores_gemma":[0.0023926487,0.0015409141,0.0000012078981,0.0040822346,0.00082367286,0.00035686084,0.000010131841,0.0000020138393,0.0000049163436,0.16341029,0.826764,0.0006110911],"about_ca_topic_score_codex":0.000056790588,"about_ca_topic_score_gemma":0.000041561336,"teacher_disagreement_score":0.92885166,"about_ca_system_score_codex":0.00043522453,"about_ca_system_score_gemma":0.0022286426,"threshold_uncertainty_score":0.9994008},"labels":[],"label_agreement":null},{"id":"W2005013137","doi":"10.1002/pdi.306","title":"The value of large, robust trials: the HOPE study","year":2002,"lang":"en","type":"article","venue":"Practical Diabetes International","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Population Health Research Institute; McMaster University","funders":"","keywords":"Medicine; Ramipril; Placebo; Disease; Coronary artery disease; Diabetes mellitus; Assertion; Internal medicine; Inclusion and exclusion criteria; Randomization; Randomized controlled trial; Cardiology; Alternative medicine; Blood pressure; Pathology; Endocrinology","score_opus":0.7031186668814022,"score_gpt":0.6132725153623085,"score_spread":0.0898461515190937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005013137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25286534,0.0017125371,0.3391713,0.20946647,0.030283084,0.0116214715,0.0012811362,0.00059998024,0.15299872],"genre_scores_gemma":[0.69165194,0.00016400676,0.30387464,0.0009673475,0.0015159254,0.0002639403,0.0000018873127,0.000054981647,0.0015052983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916315,0.0048515634,0.0017000112,0.00030990425,0.0011369764,0.00037001725],"domain_scores_gemma":[0.7118562,0.286738,0.0006050617,0.0004667626,0.00026588296,0.00006812616],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023843326,0.00017214798,0.0005851605,0.000031574982,0.00021055322,0.0001445873,0.00079314614,0.00009568784,0.0030425712],"category_scores_gemma":[0.6516563,0.00008539786,0.00026386543,0.00017670721,0.00030986656,0.00013018375,0.00031499562,0.00055491016,0.00011746563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105584084,0.0025745123,0.0038829355,0.000015089449,0.00096501026,0.0000061321844,0.0001893697,0.000009625871,0.000038617207,0.93155426,0.045107152,0.015551722],"study_design_scores_gemma":[0.0018714076,0.00032926648,0.0034745513,0.000038271537,0.00041215235,0.0000024611927,0.0004214671,0.021451604,0.00033309823,0.94601613,0.02546492,0.00018464359],"about_ca_topic_score_codex":0.0000021469632,"about_ca_topic_score_gemma":0.0000026693197,"teacher_disagreement_score":0.62781304,"about_ca_system_score_codex":0.000040732473,"about_ca_system_score_gemma":0.000024463594,"threshold_uncertainty_score":0.9978688},"labels":[],"label_agreement":null},{"id":"W2005050546","doi":"10.1348/000711006x117853","title":"Robust step‐down tests for multivariate independent group designs","year":2006,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Manitoba","funders":"University of Manitoba","keywords":"Statistics; Estimator; Mathematics; Truncated mean; Multivariate statistics; Covariance; Statistic; Type I and type II errors; Sample size determination; Analysis of covariance; Test statistic; Statistical hypothesis testing; Econometrics","score_opus":0.48204144907285956,"score_gpt":0.527100397187587,"score_spread":0.04505894811472749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005050546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005416574,0.00020650192,0.99105656,0.00044839727,0.00047275733,0.0006104599,0.00036007282,0.000037362974,0.0013913013],"genre_scores_gemma":[0.040503185,0.00005387122,0.95834875,0.0002778457,0.0005638913,0.000038239727,0.0000045519873,0.00005957143,0.00015010714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948656,0.00092525856,0.0025452187,0.00048150335,0.00056213385,0.0006202771],"domain_scores_gemma":[0.94535357,0.05296318,0.00069901464,0.00023823911,0.0003581796,0.00038780007],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0052288896,0.00030765106,0.0014308968,0.00011159025,0.00015728691,0.00014056725,0.00035956575,0.00037756193,0.00073341443],"category_scores_gemma":[0.054336347,0.00027426358,0.00023268201,0.00013445188,0.0006172802,0.00010377637,0.00008251043,0.00069893297,0.000017488514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054773584,0.0019251565,0.00007355249,0.0004094517,0.00014579357,0.0006471434,0.000022056922,0.000002403588,0.00036654435,0.9056756,0.031011585,0.059172966],"study_design_scores_gemma":[0.0043350626,0.0010320626,0.00552369,0.00031045504,0.00027246663,0.0030967095,0.000024739285,0.00081637717,0.000017158802,0.98359895,0.00066442386,0.00030792443],"about_ca_topic_score_codex":0.00001540608,"about_ca_topic_score_gemma":0.000017661878,"teacher_disagreement_score":0.07792331,"about_ca_system_score_codex":0.00003883458,"about_ca_system_score_gemma":0.00004209709,"threshold_uncertainty_score":0.999971},"labels":[],"label_agreement":null},{"id":"W2005234338","doi":"10.6000/1929-6029.2014.03.01.5","title":"A Bayesian Approach for the Cox Proportional Hazards Model with Covariates Subject to Detection Limit","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Covariate; Bayesian probability; Proportional hazards model; Poisson distribution; Statistics; Computer science; Robustness (evolution); Confidence interval; Mathematics","score_opus":0.43149752995332713,"score_gpt":0.598887335163738,"score_spread":0.1673898052104109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005234338","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009966224,0.000010859944,0.9933919,0.003980468,0.00043047479,0.0005975687,0.00013631825,0.000008347381,0.0004474717],"genre_scores_gemma":[0.2683718,0.0000351527,0.7304204,0.00025056704,0.0007178102,0.000096430784,0.0000029657624,0.000026541502,0.00007829792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9916902,0.0010820857,0.001339849,0.00027779842,0.0052006305,0.00040943993],"domain_scores_gemma":[0.8930894,0.10245738,0.00037789307,0.00023131746,0.0034609742,0.00038302626],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03170451,0.00015023499,0.00045241788,0.00039135254,0.00012536538,0.0001226291,0.001156545,0.00016864367,0.00016690006],"category_scores_gemma":[0.3758404,0.00009012371,0.00008792287,0.00033524627,0.00047037398,0.00006660412,0.00015772661,0.0012921559,0.0000035342443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004811284,0.0009056434,0.00047596163,0.00014341612,0.00040619803,0.00010635377,0.0003421204,0.0046262173,0.00011168242,0.6837203,0.007850793,0.29650003],"study_design_scores_gemma":[0.0012980419,0.0006088183,0.0003394282,0.00013254261,0.000024829844,0.00006108871,0.00006717186,0.42945692,0.00013709957,0.5673676,0.00042895833,0.000077507524],"about_ca_topic_score_codex":0.000029117558,"about_ca_topic_score_gemma":0.00008444296,"teacher_disagreement_score":0.4248307,"about_ca_system_score_codex":0.00026153517,"about_ca_system_score_gemma":0.0008926082,"threshold_uncertainty_score":0.997064},"labels":[],"label_agreement":null},{"id":"W2005293181","doi":"10.1002/sim.5606","title":"A generalized Jonckheere test against ordered alternatives for repeated measures in randomized blocks","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Null hypothesis; Null (SQL); Mathematics; Statistical hypothesis testing; Statistics; Randomized controlled trial; Applied mathematics; Null distribution; Block (permutation group theory); Computer science; Econometrics; Medicine; Test statistic; Data mining; Internal medicine; Combinatorics","score_opus":0.401823268684664,"score_gpt":0.5537626732144015,"score_spread":0.15193940452973753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005293181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012039201,0.0007511696,0.9768182,0.0009811185,0.0016887501,0.003685409,0.0007999207,0.00010472078,0.0031315007],"genre_scores_gemma":[0.07784748,0.0004874383,0.91919625,0.0004930768,0.00082077994,0.0005576632,0.000048464157,0.000077382894,0.00047147242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933478,0.0020763217,0.0026458558,0.00046515276,0.00070364756,0.00076121825],"domain_scores_gemma":[0.81567925,0.18272279,0.00058091484,0.00046018665,0.0003180079,0.00023885502],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.018533079,0.0003939257,0.0026731018,0.00033149097,0.000060545422,0.000016880673,0.00033744244,0.00022198229,0.00035605178],"category_scores_gemma":[0.64158,0.00029128577,0.00011800267,0.00043790645,0.0007061819,0.000059802827,0.00007465557,0.000494086,0.0000053882527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031991526,0.0018584727,0.008075385,0.00092964986,0.0005039271,0.00013596183,0.0057386695,0.00003716706,0.0020143394,0.86003137,0.036258377,0.052425183],"study_design_scores_gemma":[0.15314813,0.0001842169,0.0004187265,0.0005775633,0.0002072462,0.0000035114126,0.00020933579,0.0047772364,0.0002856428,0.83924735,0.000615615,0.0003254382],"about_ca_topic_score_codex":0.00013022489,"about_ca_topic_score_gemma":0.0001438066,"teacher_disagreement_score":0.62304693,"about_ca_system_score_codex":0.00014566114,"about_ca_system_score_gemma":0.000081150596,"threshold_uncertainty_score":0.9999539},"labels":[],"label_agreement":null},{"id":"W2006279547","doi":"10.1016/j.jspi.2008.10.010","title":"A clarifying comparison of methods for controlling the false discovery rate","year":2008,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; False discovery rate; Statistics; Econometrics","score_opus":0.6984027215085322,"score_gpt":0.6444145945230494,"score_spread":0.05398812698548283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006279547","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022468645,0.00054019404,0.97621125,0.00015483158,0.00027891502,0.00018441785,0.00007569126,0.0000068443383,0.00007922044],"genre_scores_gemma":[0.40188226,0.000044586373,0.59790325,0.000052235642,0.00009520886,0.0000035192686,3.753856e-7,0.000008292414,0.000010299521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967352,0.0010587926,0.0016251466,0.00014566955,0.000211073,0.00022412016],"domain_scores_gemma":[0.7904743,0.20806406,0.0009391695,0.00012542853,0.0002897207,0.0001073114],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064366693,0.00014921723,0.0010587425,0.0000604582,0.0001778543,0.000051664098,0.00021092739,0.000113660615,0.00001270063],"category_scores_gemma":[0.18867312,0.00008802376,0.00011483533,0.000091296104,0.00045035288,0.00013034797,0.000048869613,0.00058499986,2.9297075e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028288243,0.00046460502,0.017735817,0.0006757882,0.0005291616,0.000046890433,0.002781221,0.0004315142,0.004240032,0.88249207,0.0033737726,0.08440033],"study_design_scores_gemma":[0.0015845993,0.00085627876,0.0046761152,0.00040413727,0.000265486,0.00004530614,0.00038887482,0.019643536,0.0009776403,0.9706914,0.00031850842,0.00014813349],"about_ca_topic_score_codex":0.0000035843527,"about_ca_topic_score_gemma":2.0267095e-7,"teacher_disagreement_score":0.3794136,"about_ca_system_score_codex":0.0000148564695,"about_ca_system_score_gemma":0.00010242281,"threshold_uncertainty_score":0.818161},"labels":[],"label_agreement":null},{"id":"W2008609509","doi":"10.1016/j.jspi.2013.08.013","title":"Simultaneous confidence bounds in monotone dose–response studies","year":2013,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Monotonic function; Confidence interval; Monotone polygon; Applied mathematics; Mathematical optimization; Homogeneous; Statistics; Combinatorics; Mathematical analysis","score_opus":0.4712425376506508,"score_gpt":0.5822010376854657,"score_spread":0.11095850003481494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008609509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49802986,0.0005826954,0.50007117,0.00050356163,0.00033769527,0.00023067124,0.00003456906,0.000019200665,0.00019058878],"genre_scores_gemma":[0.6552998,0.00009671132,0.3443737,0.00011282101,0.000060330993,0.000005569094,1.3369761e-7,0.000009071467,0.000041901705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968347,0.00082609104,0.00142185,0.00020314255,0.0004062599,0.00030797743],"domain_scores_gemma":[0.7606025,0.2380266,0.00050525257,0.000153438,0.00046255664,0.0002496882],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034920059,0.00019048566,0.00088759186,0.00013770552,0.000065555636,0.00010470147,0.00019487734,0.0001159614,0.00017117623],"category_scores_gemma":[0.36299947,0.00013920346,0.0000425684,0.00014280915,0.00048136225,0.00018105777,0.000081653234,0.0006263616,0.000015456795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010004435,0.0013593616,0.031111127,0.0013316183,0.0008164157,0.0059941267,0.010144139,0.0009147962,0.0059026685,0.77495986,0.01421037,0.14325109],"study_design_scores_gemma":[0.0009841877,0.00087807036,0.016453013,0.0006590908,0.00004894165,0.000087593085,0.0007803897,0.0039319457,0.00007694652,0.97584313,0.000072022034,0.00018465337],"about_ca_topic_score_codex":0.000017981863,"about_ca_topic_score_gemma":0.0000012098649,"teacher_disagreement_score":0.35950744,"about_ca_system_score_codex":0.000055363784,"about_ca_system_score_gemma":0.00010588339,"threshold_uncertainty_score":0.6423663},"labels":[],"label_agreement":null},{"id":"W2008661917","doi":"10.1038/nmeth.3005","title":"Analysis of variance and blocking","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":75,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Blocking (statistics); Variance (accounting); Computational biology; Computer science; Biology; Business; Computer network","score_opus":0.3803121748862196,"score_gpt":0.6438468104135495,"score_spread":0.2635346355273299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008661917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040913424,0.0001853319,0.9907588,0.00014350959,0.0003626983,0.00010134336,0.000013656161,0.00003793804,0.0043053976],"genre_scores_gemma":[0.040831506,0.000012412483,0.95869756,0.00022097025,0.00012616075,0.000004731162,4.0747366e-7,0.00001439651,0.000091844195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957362,0.0029875792,0.0005782353,0.00030808194,0.0002290431,0.00016090623],"domain_scores_gemma":[0.88289523,0.1161609,0.00028234554,0.00046330004,0.00012170848,0.00007649765],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013886463,0.00012391924,0.0009223256,0.00017587376,0.000034942954,0.000013923055,0.00018370662,0.0004055777,0.00012614652],"category_scores_gemma":[0.26038572,0.00009762405,0.00016853359,0.0008815043,0.00011822105,0.000022174148,0.00008687692,0.0005355348,5.6518206e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032318436,0.000050609644,0.0016376771,0.00010172795,0.00080862775,8.698594e-7,0.00008271682,0.0000062101262,0.0019019316,0.68978876,0.00013002538,0.30545855],"study_design_scores_gemma":[0.00026676306,0.000043063123,0.0065834136,0.000027738093,0.001901378,8.970456e-7,0.000006978797,0.0085401,0.004189191,0.9765467,0.0017749481,0.00011880412],"about_ca_topic_score_codex":0.0000028304912,"about_ca_topic_score_gemma":0.0000016865213,"teacher_disagreement_score":0.30533975,"about_ca_system_score_codex":0.0000094044035,"about_ca_system_score_gemma":0.000009965143,"threshold_uncertainty_score":0.74584436},"labels":[],"label_agreement":null},{"id":"W2009376322","doi":"10.1002/jps.22219","title":"A New Definition of Pharmaceutical Quality: Assembly of a Risk Simulation Platform to Investigate the Impact of Manufacturing/ Product Variabcpility on Clinical Performance","year":2010,"lang":"en","type":"article","venue":"Journal of Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Public Health Service; Hamilton Health Sciences Foundation","keywords":"Pharmaceutical manufacturing; Quality (philosophy); Product (mathematics); Risk analysis (engineering); Computer science; Quality by Design; Pharmaceutical industry; Process engineering; Biochemical engineering; Reliability engineering; Manufacturing engineering; Business; New product development; Medicine; Engineering; Pharmacology; Mathematics; Marketing","score_opus":0.7691639919460679,"score_gpt":0.6650675645223137,"score_spread":0.10409642742375413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009376322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98324996,0.000018835912,0.014316108,0.0005002276,0.0008397476,0.00047193564,0.00005807697,0.000010879874,0.0005342127],"genre_scores_gemma":[0.76924807,0.00005659751,0.23019233,0.00008398653,0.00040498681,0.0000016952322,1.649155e-7,0.000009827163,0.0000023566013],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925535,0.0015289884,0.0035647524,0.000358412,0.0015871151,0.00040723896],"domain_scores_gemma":[0.9235429,0.07216781,0.002677786,0.0004181478,0.000540399,0.0006529176],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03561705,0.00024920114,0.0011381498,0.000182416,0.00012487681,0.00003656039,0.0008761706,0.00017298304,0.00034323035],"category_scores_gemma":[0.13723281,0.00013714613,0.00055758806,0.0006006665,0.0013781723,0.00028133517,0.00015647725,0.0015087388,0.000005488795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016314717,0.0060476526,0.12213369,0.0011931836,0.0013688123,0.000013052351,0.0016134351,0.013225784,0.08762247,0.10904654,0.0010899815,0.6403307],"study_design_scores_gemma":[0.0027250668,0.003427121,0.14440839,0.00031250698,0.0005649446,0.00002021931,0.000052081497,0.012340074,0.26541013,0.5703557,0.00010256162,0.00028118168],"about_ca_topic_score_codex":0.00004411582,"about_ca_topic_score_gemma":0.0000034167397,"teacher_disagreement_score":0.6400495,"about_ca_system_score_codex":0.00004945134,"about_ca_system_score_gemma":0.0005913145,"threshold_uncertainty_score":0.9930352},"labels":[],"label_agreement":null},{"id":"W2009683965","doi":"10.1080/07474940802619022","title":"Discussion on “A Hybrid Selection and Testing Procedure with Curtailment for Comparative Clinical Trials” by Elena M. Buzaianu and Pinyuen Chen","year":2009,"lang":"en","type":"article","venue":"Sequential Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Chen; Selection (genetic algorithm); Bernoulli trial; Set (abstract data type); Mathematics; Sampling (signal processing); Binary number; Statistics; Computer science; Artificial intelligence; Arithmetic; Biology","score_opus":0.6773892975891347,"score_gpt":0.6170725358191327,"score_spread":0.060316761770002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009683965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4023705,0.00008395691,0.59169096,0.002720502,0.0001256405,0.0023274196,0.000264459,0.00014799112,0.0002685804],"genre_scores_gemma":[0.64175737,0.000024352395,0.35739902,0.00020644892,0.00033004847,0.000060361297,0.000024774812,0.000017575248,0.00018001904],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956293,0.0015662401,0.0014415283,0.00071961485,0.00035194014,0.00029139477],"domain_scores_gemma":[0.97895056,0.019654222,0.0007670342,0.00020636058,0.00019647123,0.00022537232],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0069118184,0.00028091192,0.0016623684,0.00013646428,0.00021117166,0.00010996132,0.00010255228,0.00013359395,0.000036058776],"category_scores_gemma":[0.03484524,0.00015700134,0.0002679426,0.00053698866,0.00013966963,0.000080790305,0.000031276737,0.0002957627,0.0000015182347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02130848,0.007219595,0.038629863,0.0011775515,0.026825191,0.000039666626,0.001774525,0.000545528,0.01973008,0.039248236,0.036163732,0.8073375],"study_design_scores_gemma":[0.008783595,0.00858264,0.0067989104,0.0004287123,0.021625316,0.000015796431,0.0002958383,0.07614546,0.013177923,0.86230624,0.000662225,0.00117737],"about_ca_topic_score_codex":0.000015069071,"about_ca_topic_score_gemma":0.000023763738,"teacher_disagreement_score":0.82305795,"about_ca_system_score_codex":0.00004791325,"about_ca_system_score_gemma":0.00005196615,"threshold_uncertainty_score":0.97328466},"labels":[],"label_agreement":null},{"id":"W2009687691","doi":"10.1177/0013164403251283","title":"The Effects of Nonnormality on Parametric, Nonparametric, and Model Comparison Approaches to Pairwise Comparisons","year":2003,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; York University","funders":"","keywords":"Type I and type II errors; Statistics; Nonparametric statistics; Statistic; Pairwise comparison; Econometrics; Mathematics; Normality; F-test of equality of variances; Parametric statistics; Levene's test; Sample size determination; Statistical hypothesis testing; Test statistic; Nominal level; Homogeneity (statistics); Confidence interval","score_opus":0.8627862254850819,"score_gpt":0.551136597639037,"score_spread":0.3116496278460449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009687691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7011124,0.0019223839,0.2688137,0.009639605,0.0018537765,0.0032744976,0.000038668077,0.00005986322,0.01328513],"genre_scores_gemma":[0.6973537,0.0000351157,0.30216214,0.00021783379,0.0000429869,0.00013764182,3.3754802e-7,0.0000067997566,0.000043439937],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681467,0.0010445876,0.0007265607,0.00042946998,0.0007259256,0.00025881708],"domain_scores_gemma":[0.9568767,0.04215392,0.00021950497,0.00034645642,0.00014337857,0.00026005547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004981774,0.00019405365,0.0004954055,0.00007839879,0.00019554101,0.000041978456,0.00017499317,0.000113097274,0.000022280208],"category_scores_gemma":[0.09427074,0.00011648184,0.000072293034,0.00037189326,0.0002521715,0.00001821822,0.000036898626,0.00027391597,0.00000737185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037638954,0.0047213132,0.008995165,0.00018655171,0.00010302754,3.3005153e-7,0.0001704752,0.00006933026,0.00007669595,0.9510098,0.01366292,0.020627977],"study_design_scores_gemma":[0.00077781203,0.0010048767,0.08364867,0.00007466653,0.00007177801,0.0000022593774,0.0000684234,0.0007818618,0.00048039985,0.91211563,0.00076238223,0.00021122066],"about_ca_topic_score_codex":0.0000026583273,"about_ca_topic_score_gemma":0.0000016618833,"teacher_disagreement_score":0.08928897,"about_ca_system_score_codex":0.00004663492,"about_ca_system_score_gemma":0.000036539208,"threshold_uncertainty_score":0.91335857},"labels":[],"label_agreement":null},{"id":"W2010355043","doi":"10.1016/j.jalz.2012.02.002","title":"Improving Alzheimer's disease phase II clinical trials","year":2012,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acuitas Therapeutics (Canada); University Health Network","funders":"","keywords":"Disease; Drug development; Government (linguistics); Clinical trial; Medicine; Drug; Phase (matter); Pharmaceutical industry; Intensive care medicine; Business; Pharmacology; Internal medicine","score_opus":0.6842459723254558,"score_gpt":0.6105036068592329,"score_spread":0.07374236546622293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010355043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043494843,0.3551822,0.53268397,0.0040551163,0.041152183,0.012095265,0.0012544331,0.0022199263,0.00786203],"genre_scores_gemma":[0.5000065,0.00008447416,0.49548924,0.0008162443,0.0033051686,0.00016471662,0.000013759821,0.00010637377,0.000013534087],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9862938,0.0064889737,0.004457039,0.0007937283,0.0008002475,0.0011661985],"domain_scores_gemma":[0.9337887,0.061235297,0.0016736112,0.0014535418,0.00019316295,0.0016556736],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040443808,0.0005368578,0.0019038554,0.000111026486,0.00038049388,0.00009463635,0.0006605789,0.00034558246,0.0036711372],"category_scores_gemma":[0.14748621,0.00044632616,0.001025637,0.00026317584,0.00035761192,0.00040401454,0.0006253862,0.0006340359,0.00043787336],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077158894,0.0049818144,0.0024242369,0.000020377789,0.026572395,0.000022635693,0.0001157725,2.3673313e-7,0.000204305,0.070309006,0.032167863,0.8624098],"study_design_scores_gemma":[0.017478196,0.0014660816,0.0022833354,0.00011466832,0.33100185,0.000008814472,0.00009084296,0.00086938706,0.006889142,0.59134537,0.046451367,0.0020009105],"about_ca_topic_score_codex":0.000017233591,"about_ca_topic_score_gemma":0.000001478931,"teacher_disagreement_score":0.86040884,"about_ca_system_score_codex":0.000007946102,"about_ca_system_score_gemma":0.00015169466,"threshold_uncertainty_score":0.99979883},"labels":[],"label_agreement":null},{"id":"W2011513835","doi":"10.1002/sim.5436","title":"Misspecification of Cox regression models with composite endpoints","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Econometrics; Estimator; Copula (linguistics); Censoring (clinical trials); Proportional hazards model; Multivariate statistics; Statistics; Context (archaeology); Regression; Mathematics","score_opus":0.530858385765817,"score_gpt":0.5711734862838657,"score_spread":0.04031510051804865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011513835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045154816,0.00015213258,0.9876018,0.00023465086,0.00037670313,0.00037802075,0.00016020265,0.00002756399,0.006553455],"genre_scores_gemma":[0.20723338,0.000088726745,0.79224074,0.00006149019,0.00020434096,0.000014332645,0.000013724354,0.000026860416,0.000116409465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972573,0.0005369225,0.0010559361,0.00021675424,0.000629615,0.00030347361],"domain_scores_gemma":[0.97418743,0.024527626,0.0004717991,0.00044371298,0.00019912631,0.00017031771],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032145209,0.00018061214,0.00074545166,0.00012355353,0.00003161884,0.0000033246472,0.00018394312,0.00010201538,0.000378092],"category_scores_gemma":[0.020838123,0.00011789231,0.000019871844,0.00025949886,0.00045741737,0.00006683611,0.000039975286,0.0002809446,0.0000073831634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004045195,0.00034999265,0.0023391321,0.0003269452,0.000035513134,0.000013346134,0.0012188093,0.0000133735075,0.0013613979,0.97646743,0.0069710165,0.010498521],"study_design_scores_gemma":[0.0017955818,0.00026540467,0.0031855267,0.000838709,0.000102209524,0.000008341745,0.00020970691,0.0018798603,0.0013300934,0.99009055,0.000146489,0.0001475006],"about_ca_topic_score_codex":0.000020457092,"about_ca_topic_score_gemma":0.000005571487,"teacher_disagreement_score":0.2027179,"about_ca_system_score_codex":0.000053958298,"about_ca_system_score_gemma":0.000026571028,"threshold_uncertainty_score":0.9874098},"labels":[],"label_agreement":null},{"id":"W2012127814","doi":"10.1002/1097-0258(20001030)19:20<2775::aid-sim545>3.0.co;2-g","title":"Numerical methods for the evaluation of individual bioequivalence criteria","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SNC-Lavalin (Canada)","funders":"","keywords":"Restricted maximum likelihood; Resampling; Fortran; Variance (accounting); Statistics; Mathematics; Bioequivalence; Computer science; Covariate; Mixed model; Maximum likelihood; Algorithm; Applied mathematics","score_opus":0.7410054186035245,"score_gpt":0.7031661636645462,"score_spread":0.03783925493897833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012127814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042085836,0.00031474073,0.99490213,0.00085633434,0.00071696687,0.0011580836,0.0003905081,0.000018066941,0.0012223044],"genre_scores_gemma":[0.01260198,0.00013023522,0.9863942,0.00024391632,0.00032800387,0.00018648659,0.000010975578,0.00002580794,0.00007837873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942953,0.00269244,0.0013942161,0.00031447728,0.0010119822,0.00029160045],"domain_scores_gemma":[0.8424781,0.1563723,0.00025589985,0.0004407403,0.00038239136,0.000070587965],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034812354,0.00016944473,0.0007063858,0.00007762773,0.00006215399,0.000010407845,0.00046880732,0.000110434456,0.006999695],"category_scores_gemma":[0.28470063,0.00010697394,0.000049416718,0.00034520729,0.00064965605,0.000026716683,0.000035138193,0.00025174208,0.000005118223],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013996588,0.00009728367,0.000037265105,0.00014666893,0.000059756912,0.0000011011632,0.000592345,0.000020815916,0.00009708463,0.13755228,0.009634491,0.851621],"study_design_scores_gemma":[0.0020075322,0.00036898078,0.0021725236,0.00014370661,0.00064430246,0.0000025410905,0.00013246581,0.042574283,0.00020159301,0.95071757,0.00092365785,0.000110867695],"about_ca_topic_score_codex":0.000027703798,"about_ca_topic_score_gemma":0.0000035709738,"teacher_disagreement_score":0.85151005,"about_ca_system_score_codex":0.000048360667,"about_ca_system_score_gemma":0.00009661407,"threshold_uncertainty_score":0.99390805},"labels":[],"label_agreement":null},{"id":"W2012298859","doi":"10.1023/b:jopa.0000008159.97748.09","title":"Estimation of Cmax and Tmax in Populations After Single and Multiple Drug Administrations","year":2003,"lang":"en","type":"article","venue":"Journal of Pharmacokinetics and Pharmacodynamics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cmax; Pharmacokinetics; Monte Carlo method; Statistics; Mathematics; Population; Distribution (mathematics); Applied mathematics; Pharmacology; Medicine; Mathematical analysis","score_opus":0.2929549838592723,"score_gpt":0.5160834613464119,"score_spread":0.2231284774871396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012298859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95233536,0.0005511109,0.046053205,0.00025103046,0.00034152356,0.00022910319,0.00008516617,0.0000052608534,0.00014826424],"genre_scores_gemma":[0.6917278,0.00039766612,0.30776054,0.00004459115,0.00004000106,0.0000021787382,6.915088e-7,0.000012934495,0.000013562874],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809736,0.00033300626,0.0010780529,0.00013794754,0.00020984658,0.00014375734],"domain_scores_gemma":[0.99460113,0.0045033903,0.0005154399,0.00007833784,0.00013483514,0.00016685425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014150235,0.00014674234,0.00040874924,0.00015727487,0.00003988826,0.00003432889,0.00006143889,0.000060886407,0.000049079765],"category_scores_gemma":[0.004788291,0.00013317369,0.000050799827,0.000156323,0.00014542046,0.00011956387,0.000031990327,0.00028449338,1.4380618e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038944494,0.008337765,0.18904573,0.005083164,0.0011286527,0.00045770628,0.0076877633,0.011355696,0.16588719,0.2771996,0.0021301543,0.32779214],"study_design_scores_gemma":[0.0073560635,0.00037742482,0.010027689,0.00027193187,0.0008049815,0.0002071372,0.00018298315,0.3348033,0.0095930025,0.63544804,0.00051802676,0.00040938827],"about_ca_topic_score_codex":0.0000033523893,"about_ca_topic_score_gemma":0.000009721205,"teacher_disagreement_score":0.35824847,"about_ca_system_score_codex":0.000022340371,"about_ca_system_score_gemma":0.000036852838,"threshold_uncertainty_score":0.5732377},"labels":[],"label_agreement":null},{"id":"W2012386044","doi":"10.1093/annonc/mdn753","title":"Stopping a trial early in oncology: for patients or for industry?","year":2009,"lang":"en","type":"letter","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Ontario Institute for Cancer Research","funders":"","keywords":"Medicine; Gemcitabine; Clinical trial; Randomized controlled trial; Internal medicine; Oncology; Tamoxifen; Breast cancer; Cancer; Letrozole; Pancreatic cancer","score_opus":0.8599858372397515,"score_gpt":0.6777961142334386,"score_spread":0.18218972300631298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012386044","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012145887,0.000054645698,0.016627995,0.9320898,0.008544333,0.021986365,0.0030157533,0.000121828925,0.005413398],"genre_scores_gemma":[0.000138124,0.000045691435,0.6306098,0.35815114,0.007669879,0.001782917,0.00007384017,0.000121098936,0.0014075148],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932014,0.0018731026,0.0029176841,0.00072988635,0.00036435726,0.00091356685],"domain_scores_gemma":[0.829951,0.16694795,0.0018701042,0.00046964118,0.00066160935,0.00009970599],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00615876,0.0004428959,0.0033617683,0.00036211434,0.0000536583,0.000017183687,0.00068262307,0.007148854,0.00013405985],"category_scores_gemma":[0.23861878,0.00037049848,0.0005892772,0.00023243339,0.0002567397,0.000055838398,0.00010971444,0.0027568955,0.0000053636227],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03387437,0.0013372593,0.000015905565,0.00039671367,0.00016707338,0.00005149846,0.00009872539,2.1627935e-7,0.0000011786393,0.0016809365,0.7924257,0.16995046],"study_design_scores_gemma":[0.03590877,0.031364586,0.00003237096,0.0001661227,0.00014398596,0.0000011410278,0.000008786929,0.0000063263747,0.00001873028,0.40806612,0.5240419,0.00024115249],"about_ca_topic_score_codex":0.000017030914,"about_ca_topic_score_gemma":0.000024112918,"teacher_disagreement_score":0.6139818,"about_ca_system_score_codex":0.00021282831,"about_ca_system_score_gemma":0.0010356097,"threshold_uncertainty_score":0.9998747},"labels":[],"label_agreement":null},{"id":"W2012397316","doi":"10.1214/14-aoas774","title":"Evaluating epoetin dosing strategies using observational longitudinal data","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medicine; Observational study; Dosing; Regimen; Kidney disease; Intensive care medicine; Proportional hazards model; Dialysis; Anemia; Marginal structural model; Randomized controlled trial; Hemodialysis; Epoetin alfa; Clinical trial; Survival analysis; Internal medicine","score_opus":0.9581370777790906,"score_gpt":0.6916552922079258,"score_spread":0.26648178557116486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012397316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03000422,0.000019661791,0.96567297,0.00027943472,0.00020650272,0.00038879164,0.0009834107,0.000045589783,0.0023993936],"genre_scores_gemma":[0.13263103,0.000012399143,0.8666702,0.00022543648,0.0003597032,0.000008474837,0.000040456576,0.000038404425,0.000013926286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996226,0.0006658548,0.0013543256,0.00045343212,0.00090662425,0.00039374945],"domain_scores_gemma":[0.9303155,0.06679905,0.0009416576,0.0014049702,0.00044540231,0.00009342547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012395255,0.0002409413,0.00066205615,0.000047415517,0.00024097854,0.00010949243,0.001010298,0.000103742364,0.00017984414],"category_scores_gemma":[0.053885277,0.00018089442,0.00005303343,0.00023564506,0.00045741972,0.00010469655,0.00047518656,0.00031350905,0.000012436393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016631848,0.00008470025,0.000051756906,0.0001834142,0.00009474265,0.0000010516203,0.0001285697,0.0010632176,0.0015790467,0.9683631,0.0022263557,0.026057713],"study_design_scores_gemma":[0.00034211442,0.00008420849,0.0010439053,0.0000704619,0.00016366248,0.00000195439,0.00015338299,0.11406103,0.0007326079,0.88304126,0.00012422429,0.00018121205],"about_ca_topic_score_codex":0.0000247145,"about_ca_topic_score_gemma":0.0000070146825,"teacher_disagreement_score":0.11299781,"about_ca_system_score_codex":0.000013144046,"about_ca_system_score_gemma":0.00018131034,"threshold_uncertainty_score":0.9540843},"labels":[],"label_agreement":null},{"id":"W2012610170","doi":"10.1177/0013164403260196","title":"The Analysis of Repeated Measurements with Mixed-Model Adjusted F Tests","year":2004,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Type I and type II errors; Statistics; Repeated measures design; Sample size determination; Mixed model; Mathematics; Covariance; Univariate; Statistic; Homogeneity (statistics); Normality; Analysis of covariance; Heteroscedasticity; Statistical hypothesis testing; Econometrics; Multivariate statistics","score_opus":0.7953401039095214,"score_gpt":0.5668979603801602,"score_spread":0.2284421435293612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012610170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8722825,0.00059951196,0.102247775,0.014646209,0.0008878165,0.0014659069,0.000080411846,0.000096141404,0.007693723],"genre_scores_gemma":[0.78469133,0.000023356508,0.2149148,0.0001581434,0.000057763755,0.0000819658,0.0000025411682,0.000008914207,0.00006116806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99712276,0.0003703196,0.00073959486,0.00040242038,0.0011345453,0.00023033816],"domain_scores_gemma":[0.99373406,0.0046805665,0.00031290913,0.0004221959,0.00069747324,0.00015281801],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040491903,0.00017497882,0.00044014197,0.00007998074,0.00017035959,0.00002774597,0.00023016983,0.00009344631,0.000093749266],"category_scores_gemma":[0.019971477,0.0000918418,0.0001195846,0.0006472842,0.00030284785,0.000025559946,0.000027833277,0.00017113479,0.000004125243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029213,0.014703297,0.048151195,0.00020887467,0.010538243,0.0000056107224,0.00083972455,0.0029397926,0.0074993656,0.84501535,0.0070757126,0.060101517],"study_design_scores_gemma":[0.0009784771,0.0002980796,0.28070447,0.00006532309,0.00087934587,0.0000026139899,0.00003933883,0.000061725674,0.00030049466,0.7164808,0.000041757095,0.0001475836],"about_ca_topic_score_codex":0.000009111795,"about_ca_topic_score_gemma":0.00005498344,"teacher_disagreement_score":0.23255327,"about_ca_system_score_codex":0.00008847867,"about_ca_system_score_gemma":0.00009708048,"threshold_uncertainty_score":0.9882837},"labels":[],"label_agreement":null},{"id":"W2013010380","doi":"10.1111/j.1541-0420.2007.00958.x","title":"Stepwise Confidence Intervals for Monotone Dose–Response Studies","year":2008,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Memorial University of Newfoundland; Acadia University","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland; Acadia University","keywords":"Monotonic function; Confidence interval; Mathematics; Statistics; Monotone polygon; Sample size determination; Applied mathematics; Medicine; Mathematical analysis","score_opus":0.8882842078628477,"score_gpt":0.6527363765385226,"score_spread":0.2355478313243251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013010380","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21175508,0.001744081,0.78104997,0.0007135888,0.0021514113,0.0017696416,0.0003536271,0.00025615768,0.00020644945],"genre_scores_gemma":[0.114715114,0.0006234127,0.8822211,0.00027414234,0.0002525771,0.00018594868,9.4606634e-7,0.000046618392,0.001680139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968066,0.00075921835,0.0011009258,0.00043997722,0.0004969809,0.00039629766],"domain_scores_gemma":[0.7850221,0.21337217,0.00034752415,0.00053365063,0.0005573265,0.00016722137],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007138255,0.0002347313,0.00089981296,0.0007671103,0.00015594163,0.000026998421,0.00040835794,0.00018185224,0.000067266716],"category_scores_gemma":[0.58946174,0.00019265579,0.00024132506,0.0023231565,0.00045695473,0.0000729462,0.00018889457,0.0001511106,0.00006764074],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018909749,0.0042693075,0.0027359058,0.003245497,0.0029595776,0.0005680001,0.005986014,0.0000048854145,0.020300403,0.48021436,0.2825387,0.17826757],"study_design_scores_gemma":[0.0027335568,0.0011355933,0.0021945587,0.00012008836,0.0001645767,0.000025511275,0.0002720737,0.0001754817,0.009174191,0.9760141,0.007535533,0.00045473667],"about_ca_topic_score_codex":0.0000036315398,"about_ca_topic_score_gemma":5.199609e-7,"teacher_disagreement_score":0.5823235,"about_ca_system_score_codex":0.00011533807,"about_ca_system_score_gemma":0.00008290775,"threshold_uncertainty_score":0.7856275},"labels":[],"label_agreement":null},{"id":"W2013102726","doi":"10.1038/bjc.2011.157","title":"Statistical issues in the use of dynamic allocation methods for balancing baseline covariates","year":2011,"lang":"en","type":"article","venue":"British Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Hospital; Ontario Clinical Oncology Group; McMaster University","funders":"","keywords":"Clinical trial; Credibility; Statistical inference; Baseline (sea); Covariate; Inference; Computer science; Medicine; Statistics; Artificial intelligence; Machine learning; Mathematics","score_opus":0.5326053452684013,"score_gpt":0.5987837027161158,"score_spread":0.0661783574477145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013102726","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036181558,0.0011782185,0.9939712,0.0002660448,0.00043194604,0.00031343172,0.00018798768,0.0000050745107,0.000027915448],"genre_scores_gemma":[0.010782507,0.0010043938,0.9877765,0.00019249534,0.00015909024,0.000027501495,0.000001201081,0.00002067846,0.000035633922],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962061,0.0018376725,0.0013867373,0.00012768486,0.0002631206,0.0001786684],"domain_scores_gemma":[0.94770986,0.050938983,0.00067619514,0.0001402096,0.00048071606,0.000054033982],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010522194,0.00009568878,0.00059249287,0.000058992366,0.000031364365,0.000038393184,0.00024985636,0.00008768996,0.00031314275],"category_scores_gemma":[0.12135776,0.00007750255,0.000113103924,0.00014071501,0.00011760154,0.000121255114,0.000021704693,0.00026746542,3.3554824e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045470477,0.00034107108,0.0004022442,0.00025676526,0.00013868058,0.000044312346,0.0005502615,0.000017913622,0.00045070407,0.04370369,0.0031129976,0.95052665],"study_design_scores_gemma":[0.0013445303,0.00025684392,0.01019105,0.0007964098,0.00027567535,0.00010598159,0.00010476633,0.0069870106,0.00074888597,0.9768525,0.0022042713,0.00013207771],"about_ca_topic_score_codex":0.00038711744,"about_ca_topic_score_gemma":0.00027706622,"teacher_disagreement_score":0.9503946,"about_ca_system_score_codex":0.000050615065,"about_ca_system_score_gemma":0.00010567732,"threshold_uncertainty_score":0.8860434},"labels":[],"label_agreement":null},{"id":"W2013383304","doi":"10.1177/1740774508093981","title":"Determining optimal sample sizes for multi-stage randomized clinical trials using value of information methods","year":2008,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Randomized controlled trial; Statistics; Sample size determination; Value (mathematics); Clinical trial; Stage (stratigraphy); Medicine; Computer science; Mathematics; Internal medicine; Biology","score_opus":0.9543317968023223,"score_gpt":0.7614272996126612,"score_spread":0.19290449718966107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013383304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023836996,0.00009340208,0.96045953,0.00011659987,0.006043451,0.008032414,0.0011209307,0.00018966616,0.00010700446],"genre_scores_gemma":[0.0027084479,0.0005019255,0.9931689,0.00047597554,0.0025555212,0.00038173108,0.000024436844,0.00010128714,0.00008176158],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.5738138,0.34648946,0.074518874,0.0019193573,0.0016601897,0.0015983059],"domain_scores_gemma":[0.029287778,0.9512555,0.016301094,0.0014087581,0.0010503983,0.00069644634],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6663435,0.00071795634,0.019225178,0.00030166912,0.00031273556,0.00010303673,0.00092655193,0.0016420915,0.00054213987],"category_scores_gemma":[0.992816,0.00052449724,0.008058362,0.0004395029,0.0020989743,0.00046600154,0.00037507864,0.0010978244,0.000019410081],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24490222,0.0032786687,0.0015530578,0.0013875739,0.0057019694,0.000018821695,0.0007694986,0.00051374955,0.0006189508,0.10715325,0.002511107,0.63159114],"study_design_scores_gemma":[0.40460193,0.0012276762,0.00021216429,0.000460822,0.0046141143,0.000011934482,0.00019590315,0.24260935,0.0029894,0.33961254,0.0024683909,0.0009957651],"about_ca_topic_score_codex":0.000026471094,"about_ca_topic_score_gemma":8.745818e-7,"teacher_disagreement_score":0.6305953,"about_ca_system_score_codex":0.000066602275,"about_ca_system_score_gemma":0.0007832056,"threshold_uncertainty_score":0.99972063},"labels":[],"label_agreement":null},{"id":"W2013520562","doi":"10.1158/1078-0432.ccr-14-0521","title":"Design of Phase I Combination Trials: Recommendations of the Clinical Trial Design Task Force of the NCI Investigational Drug Steering Committee","year":2014,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Center for Advancing Translational Sciences; National Cancer Institute; National Institutes of Health","keywords":"Clinical trial; Medicine; Regimen; Drug development; Clinical study design; Clinical endpoint; Pharmacodynamics; Combination therapy; Phases of clinical research; Pharmacology; Intensive care medicine; Medical physics; Oncology; Drug; Pharmacokinetics; Internal medicine","score_opus":0.9658311449296211,"score_gpt":0.7722733089490966,"score_spread":0.19355783598052445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013520562","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017757124,0.36636722,0.57119834,0.0044666813,0.01482,0.04017327,0.0023145028,0.00008287941,0.00039950112],"genre_scores_gemma":[0.00026944184,0.7912688,0.20366259,0.00010231116,0.002079498,0.0017750557,0.000019138373,0.00017446114,0.00064868253],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8086574,0.16880392,0.017784853,0.0010605329,0.0029785214,0.0007147825],"domain_scores_gemma":[0.25739965,0.7278359,0.009622315,0.0026878696,0.0021305515,0.00032371806],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28279766,0.0005278689,0.008029955,0.00025347574,0.00031888994,0.000050061484,0.003501273,0.0011736482,0.0003286808],"category_scores_gemma":[0.7000216,0.00029795125,0.0031610942,0.0016860509,0.004260525,0.000080351405,0.001302834,0.004211872,0.000011238687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0080314865,0.0035070714,0.000023478473,0.010815332,0.0013507163,6.6302925e-7,0.000083926665,0.00001994757,0.000004244558,0.061173912,0.055103187,0.85988605],"study_design_scores_gemma":[0.044966202,0.0030514197,0.00001459865,0.024532942,0.0035481704,0.0000012373044,0.000039879258,0.000856867,0.00012386857,0.8146475,0.107710645,0.0005066787],"about_ca_topic_score_codex":0.000031114832,"about_ca_topic_score_gemma":0.00000862899,"teacher_disagreement_score":0.85937935,"about_ca_system_score_codex":0.00024281046,"about_ca_system_score_gemma":0.0050460673,"threshold_uncertainty_score":0.99994725},"labels":[],"label_agreement":null},{"id":"W2013625279","doi":"10.1016/j.jmir.2012.03.002","title":"Inferential Statistics for Radiation Scientists: A Brief Guide to Better Statistical Interpretations","year":2012,"lang":"en","type":"article","venue":"Journal of medical imaging and radiation sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute","funders":"","keywords":"Statistical inference; Statistics; Statistical hypothesis testing; Computer science; Variance (accounting); Statistical analysis; Probability and statistics; Test (biology); Monte Carlo method; Econometrics; Data science; Psychology; Mathematics","score_opus":0.21386837563390945,"score_gpt":0.5731599187610802,"score_spread":0.3592915431271707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013625279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005259819,0.00027671002,0.98188555,0.009260193,0.0028348318,0.00020061627,0.00013125835,0.000013476192,0.00013751771],"genre_scores_gemma":[0.08723878,0.000105263345,0.9092884,0.0017012125,0.0016123031,0.000010281138,0.0000027152364,0.000011392649,0.000029664343],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962542,0.00044130773,0.0012485685,0.0001991934,0.0014975694,0.00035917823],"domain_scores_gemma":[0.96759534,0.030754149,0.00054501457,0.000100789985,0.00032165562,0.00068305375],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012916069,0.0001243585,0.00039296286,0.00027379833,0.00024648706,0.00022509266,0.00032031853,0.00007409176,0.00028341447],"category_scores_gemma":[0.18788078,0.00009171428,0.000066893896,0.00030429388,0.0005520044,0.00040176464,0.0000649726,0.00023191831,0.00000521959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004007443,0.00015961642,0.006028687,0.000057351084,0.000039736893,0.0000044269864,0.0007563887,0.000005592775,0.000054701253,0.18941726,0.1798938,0.62354237],"study_design_scores_gemma":[0.0038469601,0.0006152646,0.0246746,0.00042019575,0.00043051605,0.00022983373,0.0012390232,0.04958662,0.00029511424,0.81267023,0.10547097,0.00052068057],"about_ca_topic_score_codex":0.000008065416,"about_ca_topic_score_gemma":0.0000020727384,"teacher_disagreement_score":0.623253,"about_ca_system_score_codex":0.000060912655,"about_ca_system_score_gemma":0.0002900144,"threshold_uncertainty_score":0.8189601},"labels":[],"label_agreement":null},{"id":"W2014489208","doi":"10.1002/cjs.11140","title":"Interim analysis of clinical trials based on urn models","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interim; Interim analysis; Estimator; Statistics; Computer science; Statistical hypothesis testing; Gaussian; Econometrics; Clinical trial; Mathematics; Medicine; Law","score_opus":0.8794529496569852,"score_gpt":0.6534883635396405,"score_spread":0.2259645861173447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014489208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052798507,0.0000565145,0.9877902,0.00017845123,0.002168258,0.0001945601,0.0026707612,0.000004574003,0.0016568295],"genre_scores_gemma":[0.42050982,0.000010509687,0.5786889,0.00029793073,0.00043034978,0.0000014229837,0.000004555159,0.000023965884,0.00003253695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9862888,0.005638197,0.0067432337,0.00018362027,0.000665505,0.0004806598],"domain_scores_gemma":[0.83153194,0.1613399,0.0039934,0.0005407662,0.00087349425,0.0017205281],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05204334,0.00023016306,0.003367621,0.00088328525,0.00005592058,0.000040822648,0.0004748697,0.00026258174,0.0020156156],"category_scores_gemma":[0.4694603,0.00017783883,0.0009664534,0.00064328645,0.00033734122,0.0000996944,0.000016358821,0.000673727,0.000009890228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084714417,0.00084050465,0.027154967,0.00019798063,0.0059498916,0.0001957244,0.00053964765,0.0035111941,0.000016639802,0.7918039,0.080008164,0.08893426],"study_design_scores_gemma":[0.0023382797,0.0010932137,0.012301798,0.00025043858,0.009447892,0.000008781188,0.00015563576,0.07228445,0.00008885298,0.90004313,0.0016039859,0.00038352038],"about_ca_topic_score_codex":0.00022946001,"about_ca_topic_score_gemma":0.00077847036,"teacher_disagreement_score":0.41741696,"about_ca_system_score_codex":0.000120702745,"about_ca_system_score_gemma":0.0012691927,"threshold_uncertainty_score":0.99889666},"labels":[],"label_agreement":null},{"id":"W2014561143","doi":"10.1016/j.chemosphere.2014.10.051","title":"Comments on “A simple method for estimating in vitro air-tissue and in vivo blood–tissue partition coefficients” by Abraham, Gala, Ibrahim, Acree and Liu","year":2014,"lang":"en","type":"letter","venue":"Chemosphere","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Partition (number theory); In vivo; In vitro; Simple (philosophy); Partition coefficient; Chemistry; Mathematics; Chromatography; Biology; Biochemistry; Philosophy; Biotechnology; Combinatorics","score_opus":0.1805369005959504,"score_gpt":0.48490721829816846,"score_spread":0.30437031770221806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014561143","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026839357,0.00024202908,0.89638406,0.09385508,0.0006352507,0.0037565362,0.0012559815,0.0001367133,0.0010503797],"genre_scores_gemma":[0.0005694812,0.000015187112,0.9031041,0.0943164,0.00083759316,0.0003816896,0.000136025,0.0001609571,0.00047855565],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950385,0.0010363301,0.0015722606,0.0011234869,0.0004663657,0.00076307455],"domain_scores_gemma":[0.9466435,0.051844306,0.0006360377,0.0006430509,0.00007772497,0.00015538362],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032845198,0.00064884673,0.0018415096,0.000051940657,0.000115250645,0.000109434965,0.00035192055,0.0013115007,0.00031797925],"category_scores_gemma":[0.029392462,0.00063559535,0.00009118918,0.00021148894,0.00020293244,0.00007500891,0.00020811571,0.0014460437,0.000007889171],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024870585,0.00044623873,0.00005544366,0.0027753033,0.000080302314,0.00005789808,0.00016369905,0.000010304363,0.0026293988,0.00018534585,0.9378467,0.055500623],"study_design_scores_gemma":[0.010857667,0.0011328901,0.00001795781,0.002417028,0.0005770007,0.00002933709,0.000108622364,0.019131673,0.16024879,0.40685916,0.39679208,0.0018277977],"about_ca_topic_score_codex":0.00008635488,"about_ca_topic_score_gemma":0.000023495204,"teacher_disagreement_score":0.54105467,"about_ca_system_score_codex":0.00009837876,"about_ca_system_score_gemma":0.000032607026,"threshold_uncertainty_score":0.999985},"labels":[],"label_agreement":null},{"id":"W2015295476","doi":"10.1093/biostatistics/kxt054","title":"Efficient panel designs for longitudinal recurrent event studies recording panel counts","year":2013,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control; Western University","funders":"Western Canada Research Grid; Compute Canada","keywords":"Panel data; Covariate; Computer science; Outcome (game theory); Event (particle physics); Econometrics; Panel analysis; Statistics; Set (abstract data type); Piecewise; Mathematics","score_opus":0.8361934892466871,"score_gpt":0.5864674015450662,"score_spread":0.24972608770162097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015295476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023360054,0.00024958112,0.9915536,0.00029602146,0.0030656806,0.0013257671,0.0006560192,0.00009661726,0.0004207124],"genre_scores_gemma":[0.0394834,0.00009901745,0.9591258,0.00008245968,0.00038534313,0.00022461299,0.0000073131982,0.000045980745,0.00054603274],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978374,0.00024075527,0.0008270253,0.00037497445,0.0003263344,0.0003934579],"domain_scores_gemma":[0.9633168,0.03548335,0.0002915278,0.00031950243,0.00045083463,0.00013796313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001459043,0.00022749553,0.0005538985,0.000054133252,0.00013167257,0.0000481551,0.00018364041,0.00010688106,0.0004347356],"category_scores_gemma":[0.073611304,0.00018578263,0.00010954003,0.000119134,0.00015969657,0.000015438161,0.00008561476,0.0001536803,0.00033811777],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013441891,0.0006155354,0.00029730168,0.0011767156,0.0004598675,0.000016287313,0.0003251653,0.000040919072,0.0002261718,0.4520864,0.36398947,0.18063179],"study_design_scores_gemma":[0.00069260976,0.00037127562,0.00059220725,0.00023765856,0.00024437776,0.000005301514,0.00018722525,0.010324947,0.00015174258,0.98389345,0.0029338705,0.00036530336],"about_ca_topic_score_codex":0.000006101,"about_ca_topic_score_gemma":0.0000014281827,"teacher_disagreement_score":0.5318071,"about_ca_system_score_codex":0.00012836981,"about_ca_system_score_gemma":0.00005208861,"threshold_uncertainty_score":0.93419206},"labels":[],"label_agreement":null},{"id":"W2015323027","doi":"10.3758/bf03195460","title":"More power to you: Simple power calculations for treatment effects with one degree of freedom","year":2002,"lang":"en","type":"article","venue":"Behavior Research Methods, Instruments, & Computers","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Calculator; Computer science; Simple (philosophy); Desk; Power (physics); Degree (music); Software; Computer program; Reliability engineering; Industrial engineering; Theoretical computer science; Programming language; Engineering","score_opus":0.7590410932523416,"score_gpt":0.6387111954867275,"score_spread":0.12032989776561409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015323027","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23885547,0.000028038292,0.7530654,0.00052194804,0.0005242801,0.006244066,0.00030067092,0.000106812055,0.0003533393],"genre_scores_gemma":[0.0431503,0.0000095682935,0.9548501,0.000070962116,0.00009787573,0.0014486285,0.000009682607,0.00010810702,0.00025479277],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923683,0.0030527234,0.0012274348,0.0009244902,0.001369415,0.0010576347],"domain_scores_gemma":[0.9475886,0.04948869,0.00028840255,0.0013274337,0.00067519816,0.00063165696],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0049755997,0.00044008778,0.0013159349,0.0005013009,0.00029553357,0.00009924614,0.00070479617,0.00023246423,0.00039906704],"category_scores_gemma":[0.02304187,0.00035371076,0.00033473963,0.0008992681,0.0005506375,0.00011786196,0.00035828658,0.0003455107,0.000022854978],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094192475,0.007613472,0.005272664,0.00040672487,0.0009506585,0.00007310442,0.0022446376,0.000078495344,0.006226213,0.033606503,0.0066685244,0.9359171],"study_design_scores_gemma":[0.08293718,0.104426764,0.13613574,0.004740518,0.0053403266,0.00017159911,0.0033885525,0.024095515,0.15601288,0.42450914,0.05030584,0.007935947],"about_ca_topic_score_codex":0.00014690572,"about_ca_topic_score_gemma":0.000015368676,"teacher_disagreement_score":0.92798114,"about_ca_system_score_codex":0.0004399399,"about_ca_system_score_gemma":0.0000918093,"threshold_uncertainty_score":0.99989146},"labels":[],"label_agreement":null},{"id":"W2015562215","doi":"10.1517/17530059.2012.634797","title":"Bioinformatics advances for clinical biomarker development","year":2011,"lang":"en","type":"article","venue":"Expert Opinion on Medical Diagnostics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada); University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Biomarker; Biomarker discovery; Standardization; Bioinformatics; Clinical Practice; Medicine; Computer science; Data science; Computational biology; Biology; Proteomics","score_opus":0.7448562009410405,"score_gpt":0.6231279349601743,"score_spread":0.12172826598086628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015562215","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033909283,0.0015702075,0.9762645,0.0011411593,0.011940447,0.0014657918,0.00008035212,0.0003203197,0.0068781334],"genre_scores_gemma":[0.0003340282,0.018573703,0.9755287,0.0039610458,0.0011173086,0.0003523816,0.000018862629,0.00006567343,0.000048303627],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944658,0.0005377477,0.002664124,0.0005118472,0.001222191,0.00059828634],"domain_scores_gemma":[0.865793,0.13206695,0.00047251608,0.00060103135,0.00023372867,0.0008327884],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006102989,0.0003684836,0.00090662786,0.0001049945,0.0001714005,0.000026323882,0.00069145166,0.0006185,0.0015385335],"category_scores_gemma":[0.45672506,0.00027813212,0.00027812735,0.00018968227,0.00050265284,0.00009875168,0.00019672875,0.00046602753,0.00023483175],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032667277,0.0015642137,0.000665083,0.00014292855,0.00011613194,0.000014512984,0.00062808854,4.641747e-8,3.522907e-7,0.10423592,0.16273582,0.7295702],"study_design_scores_gemma":[0.0030281842,0.00094211503,0.0018537497,0.00077881996,0.000017052327,0.0000065354116,0.00020328532,0.0009688325,0.00042582318,0.30571356,0.6854519,0.00061008125],"about_ca_topic_score_codex":0.0000015122101,"about_ca_topic_score_gemma":0.0000015199496,"teacher_disagreement_score":0.72896016,"about_ca_system_score_codex":0.000055924727,"about_ca_system_score_gemma":0.00029429072,"threshold_uncertainty_score":0.9999671},"labels":[],"label_agreement":null},{"id":"W2016473862","doi":"10.1067/mhj.2001.112501","title":"Should all trials have a Data Safety and Monitoring Committee?","year":2001,"lang":"en","type":"article","venue":"American Heart Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Clinical trial; Safety monitoring; Data monitoring committee; Food and drug administration; Intensive care medicine; Warrant; Agency (philosophy); Phases of clinical research; Medical physics; Risk analysis (engineering); Bioinformatics; Internal medicine","score_opus":0.867095559889939,"score_gpt":0.6564620144721711,"score_spread":0.2106335454177679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016473862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.218665,0.0016536852,0.71638083,0.047030546,0.006281595,0.0022417894,0.0007177655,0.00044811412,0.0065806657],"genre_scores_gemma":[0.036853842,0.0019699554,0.95719117,0.0009922693,0.002746756,0.0000048557963,0.0000015615237,0.00005354324,0.00018601851],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934412,0.003358916,0.0017639999,0.00038832115,0.0005655465,0.0004819999],"domain_scores_gemma":[0.91848534,0.07931432,0.00072065083,0.0008768784,0.000111949346,0.00049085956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01914051,0.00022859882,0.0016081122,0.00008870241,0.00022168522,0.00016726827,0.0005259568,0.00008693689,0.00033832536],"category_scores_gemma":[0.14494286,0.0001766864,0.00016185621,0.00018030294,0.00041924312,0.00017316877,0.0003527602,0.0009016646,0.000019391011],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022092885,0.0005964081,0.15335712,0.00006883405,0.0011554364,0.00049826514,0.0006385752,0.000005935296,0.0012339606,0.004831531,0.08211943,0.7532852],"study_design_scores_gemma":[0.004329564,0.0012613011,0.029952904,0.00045994724,0.0010434488,0.003373614,0.001979074,0.0009928715,0.0003669203,0.6396422,0.3155695,0.0010286698],"about_ca_topic_score_codex":0.000071810435,"about_ca_topic_score_gemma":0.000005848837,"teacher_disagreement_score":0.7522566,"about_ca_system_score_codex":0.000056433837,"about_ca_system_score_gemma":0.00007036836,"threshold_uncertainty_score":0.8622596},"labels":[],"label_agreement":null},{"id":"W2016790303","doi":"10.1208/s12248-013-9499-x","title":"International Guidelines for Bioequivalence of Systemically Available Orally Administered Generic Drug Products: A Survey of Similarities and Differences","year":2013,"lang":"en","type":"review","venue":"The AAPS Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":117,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Health Canada; World Health Organization","keywords":"Bioequivalence; Medicine; Biopharmaceutics; Generic drug; Pharmacology; Product (mathematics); Drug; Pharmacokinetics; Actuarial science; Marketing; Business; Mathematics","score_opus":0.9036359667159596,"score_gpt":0.6148576475444002,"score_spread":0.2887783191715594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016790303","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013588375,0.98763555,0.0074271886,0.0004143946,0.0015342559,0.0015666292,0.0011690503,0.00001409775,0.00010294482],"genre_scores_gemma":[0.000011057931,0.6619986,0.33667567,0.000018250936,0.00045751384,0.000053985357,0.0000047163394,0.000032823973,0.0007473529],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924821,0.0025514986,0.0037663067,0.00033343176,0.00060728134,0.0002593361],"domain_scores_gemma":[0.9439027,0.0482577,0.0038871947,0.0005524818,0.0032932784,0.0001066521],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012468468,0.00036615593,0.0028856443,0.00012713275,0.000083326304,0.000117364914,0.0013272536,0.00019283182,0.00023756422],"category_scores_gemma":[0.19128886,0.00019058392,0.00032650525,0.00019888439,0.0004954102,0.00007720724,0.00029569294,0.00042102116,0.000004343064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003302656,0.0004166573,0.00014743595,0.16919127,0.0028996246,0.0000075509524,0.000241866,2.9700965e-7,0.000067684305,0.006700804,0.12432339,0.69567317],"study_design_scores_gemma":[0.0030329938,0.0016319896,0.00011623175,0.17147896,0.008505394,0.0012003792,0.0003477704,0.00040482706,0.00015339117,0.4675809,0.3435826,0.001964538],"about_ca_topic_score_codex":0.000032698426,"about_ca_topic_score_gemma":0.0000041146586,"teacher_disagreement_score":0.6937086,"about_ca_system_score_codex":0.00003700264,"about_ca_system_score_gemma":0.0004943349,"threshold_uncertainty_score":0.81552327},"labels":[],"label_agreement":null},{"id":"W2016845295","doi":"10.1111/j.0006-341x.2004.172_6.x","title":"Modern Medical Statistics. A Practical Guide.","year":2004,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Citation; Library science; Computer science; Psychology; Information retrieval","score_opus":0.7097786706050814,"score_gpt":0.6479915868720674,"score_spread":0.061787083733014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016845295","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073447713,0.0000721037,0.99124795,0.002173906,0.0010205758,0.00030937517,0.00022693665,0.00019999396,0.0040147053],"genre_scores_gemma":[0.0050481185,0.00011529352,0.99311894,0.0007339966,0.00047897335,0.000023743345,0.0000048591196,0.000057051173,0.00041902222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995228,0.0004061344,0.0013144173,0.00050539634,0.0020088598,0.0005372057],"domain_scores_gemma":[0.93007326,0.067997955,0.00029915958,0.00063152844,0.00033126518,0.0006668208],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057149683,0.00024518132,0.0006566536,0.00058971724,0.00008973276,0.00007436759,0.00042749417,0.00045994474,0.001257239],"category_scores_gemma":[0.6521127,0.00020440311,0.00012768454,0.0025266723,0.00032566622,0.00007982999,0.00024457884,0.00051852094,0.00040792857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043814725,0.0008041715,0.000074745236,0.00009580656,0.00007718792,0.0003708167,0.000048205813,9.892773e-7,0.00005443405,0.8725552,0.03572282,0.0901518],"study_design_scores_gemma":[0.0015934522,0.00021387015,0.00016086981,0.00004453473,0.00008757323,0.000061341125,0.000014838925,0.00054814265,0.0002477483,0.98839086,0.008373393,0.00026334467],"about_ca_topic_score_codex":0.000030014691,"about_ca_topic_score_gemma":0.000006447446,"teacher_disagreement_score":0.64639777,"about_ca_system_score_codex":0.00020267678,"about_ca_system_score_gemma":0.00059617695,"threshold_uncertainty_score":0.9996557},"labels":[],"label_agreement":null},{"id":"W2017034538","doi":"10.2307/3315939","title":"Testing the equality of multinomial populations ordered by increasing convexity under the alternative","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multinomial distribution; Convexity; Statistic; Null (SQL); Mathematics; Test statistic; Likelihood-ratio test; Null hypothesis; Null distribution; Statistics; Alternative hypothesis; Econometrics; Applied mathematics; Combinatorics; Mathematical economics; Statistical hypothesis testing; Computer science; Economics","score_opus":0.6838467639401864,"score_gpt":0.5232818070246364,"score_spread":0.16056495691554995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017034538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13006566,0.00005351361,0.86549795,0.0011889205,0.00073868164,0.00027472188,0.0018367425,0.000005058401,0.00033875287],"genre_scores_gemma":[0.5216163,0.0000018198594,0.47803837,0.00017113228,0.00014908629,0.000001242823,0.0000016299527,0.00001392597,0.0000065011855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99667543,0.0011739327,0.001364384,0.00012174223,0.00037146246,0.00029302243],"domain_scores_gemma":[0.9481714,0.048863485,0.0013971622,0.00030013683,0.00090873963,0.00035908888],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047954023,0.0001510088,0.00045827022,0.00006148807,0.0003304369,0.000065266875,0.00046522374,0.00008430107,0.000093437746],"category_scores_gemma":[0.1418638,0.00009330371,0.00008242399,0.00023820366,0.0007504337,0.00005697895,0.000029020106,0.00054008764,0.0000022270722],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079735015,0.00008623615,0.0062908386,0.00006389473,0.00021315317,0.00004186602,0.0012163019,0.0010595958,0.0003021576,0.98146814,0.0033407582,0.005837304],"study_design_scores_gemma":[0.00094084686,0.00010768179,0.018133488,0.00011277272,0.00016963106,0.00004942951,0.00055574125,0.00047018193,0.00017715953,0.97907627,0.0000950194,0.00011178567],"about_ca_topic_score_codex":0.020006398,"about_ca_topic_score_gemma":0.009103991,"teacher_disagreement_score":0.39155063,"about_ca_system_score_codex":0.0002386532,"about_ca_system_score_gemma":0.0012642915,"threshold_uncertainty_score":0.98651946},"labels":[],"label_agreement":null},{"id":"W2017316498","doi":"10.1164/ajrccm.176.5.522","title":"On the Correct Statistical Analysis of Exacerbation Rates in Clinical Trials","year":2007,"lang":"en","type":"letter","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Exacerbation; Clinical trial; Statistical analysis; Intensive care medicine; MEDLINE; Statistics; Internal medicine","score_opus":0.5224597351453603,"score_gpt":0.6187961233821117,"score_spread":0.09633638823675139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017316498","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0925132,0.004438787,0.4150547,0.4766687,0.006050968,0.0020355063,0.0011087651,0.00004713594,0.002082243],"genre_scores_gemma":[0.20526683,0.0004055621,0.071867816,0.7108239,0.011405375,0.000029675606,0.000024124218,0.00014818607,0.00002854329],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9694547,0.021163426,0.006956661,0.00046625442,0.0015332226,0.00042570182],"domain_scores_gemma":[0.53802246,0.45849803,0.0021364696,0.00038990684,0.00074308756,0.00021007474],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057266586,0.0004192436,0.005936114,0.00095193397,0.00005928193,0.000020866208,0.00042170324,0.00056784553,0.000755902],"category_scores_gemma":[0.6831158,0.00022985676,0.0007114503,0.001183474,0.0050417045,0.000038497656,0.000057750447,0.0042103385,0.0000016191653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041482276,0.00043912636,0.009435192,0.0010252021,0.0036398119,0.002568223,0.0008411389,0.0000042661522,0.00002625842,0.1104624,0.5632122,0.30419797],"study_design_scores_gemma":[0.010039913,0.07329548,0.023789408,0.0078110634,0.05869889,0.00010122,0.013638036,0.00020135779,0.00022009292,0.716189,0.09405907,0.001956419],"about_ca_topic_score_codex":0.000018803747,"about_ca_topic_score_gemma":0.0000073335746,"teacher_disagreement_score":0.6258492,"about_ca_system_score_codex":0.00009361076,"about_ca_system_score_gemma":0.00024162598,"threshold_uncertainty_score":0.998087},"labels":[],"label_agreement":null},{"id":"W2017440455","doi":"10.1016/j.spl.2008.08.001","title":"Multiple rank-based testing for ordered alternatives with incomplete data","year":2008,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Rank (graph theory); Variance (accounting); Statistics; Combinatorics; Multiple comparisons problem; Algorithm; Applied mathematics","score_opus":0.7289355504940511,"score_gpt":0.5138852413554094,"score_spread":0.21505030913864176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017440455","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0380187,0.0000049109262,0.9504351,0.0011080921,0.0002365033,0.0023106972,0.0076215216,0.00020239425,0.00006208797],"genre_scores_gemma":[0.018518828,9.60088e-7,0.97973585,0.0010270487,0.00021883224,0.00022434314,0.0001736869,0.00008650425,0.000013928919],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99553496,0.00085623586,0.0012316495,0.0010990723,0.00064524537,0.0006328211],"domain_scores_gemma":[0.8639901,0.13323848,0.0005052355,0.0016230572,0.0004542753,0.0001888099],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003015497,0.00040493687,0.00090013247,0.000071662704,0.00035581805,0.000056977857,0.00096590386,0.00009510708,0.000060213504],"category_scores_gemma":[0.24355605,0.00033575704,0.00006954835,0.0002928194,0.0011104341,0.00013023909,0.00024020771,0.0003576998,0.000009590179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010641941,0.005991787,0.2901751,0.010552122,0.002070463,0.0007419377,0.0020394626,0.00082109496,0.013307305,0.48215565,0.10981061,0.07169252],"study_design_scores_gemma":[0.0043852613,0.00047851013,0.0047339518,0.00012467631,0.00017282611,0.0000120109,0.00000448027,0.027992062,0.00030328042,0.96079767,0.0004601931,0.0005350937],"about_ca_topic_score_codex":0.00009050443,"about_ca_topic_score_gemma":0.00010467494,"teacher_disagreement_score":0.478642,"about_ca_system_score_codex":0.00011224985,"about_ca_system_score_gemma":0.0002438356,"threshold_uncertainty_score":0.99990946},"labels":[],"label_agreement":null},{"id":"W2019266571","doi":"10.1016/j.ejps.2014.10.001","title":"The impact of new partial AUC parameters for evaluating the bioequivalence of prolonged-release formulations","year":2014,"lang":"en","type":"article","venue":"European Journal of Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BioPhage Pharma (Canada); Université de Montréal; Université du Québec","funders":"","keywords":"Bioequivalence; Equivalence (formal languages); Pharmacokinetics; Medicine; Area under the curve; Pharmacology; Guideline; Mathematics; Steady state (chemistry); Econometrics; Statistics; Chemistry; Pathology","score_opus":0.7961630982966539,"score_gpt":0.6656719182816906,"score_spread":0.1304911800149633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019266571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5507696,0.00013800287,0.44506654,0.0021695073,0.00054016575,0.0005721493,0.00001731937,0.000009153085,0.0007175553],"genre_scores_gemma":[0.72037894,0.0000221765,0.279311,0.000040951498,0.00022235514,0.0000014852698,3.3152112e-8,0.000008591062,0.0000144598225],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942361,0.0031101308,0.0014424798,0.00015253799,0.0007390921,0.00031967668],"domain_scores_gemma":[0.9326633,0.065330006,0.0012587453,0.00020686121,0.00031597563,0.00022510436],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03505331,0.0001223054,0.00035990716,0.000043127526,0.00029101057,0.00006153371,0.0009435945,0.000020356694,0.00005348043],"category_scores_gemma":[0.15186243,0.000052703803,0.00038558966,0.0003065764,0.0012830117,0.000110309855,0.000094663985,0.0002607145,0.0000023246416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020451131,0.00043835994,0.002069578,0.00014551221,0.00038389547,0.0000037906898,0.0010760471,0.0053498866,0.019619305,0.10929439,0.003375075,0.856199],"study_design_scores_gemma":[0.0027830019,0.008375211,0.0038434656,0.0002693959,0.00059072516,0.00002530176,0.0001426968,0.1593616,0.0146966865,0.80906874,0.0006348157,0.00020834334],"about_ca_topic_score_codex":0.000003508371,"about_ca_topic_score_gemma":3.0247745e-7,"teacher_disagreement_score":0.8559907,"about_ca_system_score_codex":0.000019540947,"about_ca_system_score_gemma":0.0002102188,"threshold_uncertainty_score":0.9936157},"labels":[],"label_agreement":null},{"id":"W2019370408","doi":"10.1080/00949650412331299102","title":"On binary longitudinal mixed models in adaptive clinical trials","year":2005,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Random effects model; Longitudinal data; Adaptive design; Statistics; Longitudinal study; Estimation; Repeated measures design; Mixed model; Set (abstract data type); Clinical trial; Binary number; Treatment effect; Binary data; Fixed effects model; Econometrics; Computer science; Medicine; Panel data; Data mining; Meta-analysis; Arithmetic","score_opus":0.7844613853038903,"score_gpt":0.6455522159241195,"score_spread":0.13890916937977082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019370408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08247576,0.000027760227,0.9161284,0.00042723204,0.00038818264,0.00028760947,0.00004268164,0.000014047074,0.00020831208],"genre_scores_gemma":[0.54321384,0.000014247321,0.456374,0.00012852544,0.00025062697,0.0000013231888,0.0000014086457,0.000010574172,0.000005443847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99090105,0.004398156,0.0036678188,0.0002600392,0.0005828584,0.0001900793],"domain_scores_gemma":[0.8050252,0.1932037,0.0011476022,0.00008645664,0.00033379826,0.00020321457],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017497394,0.0001818086,0.0012234934,0.0002481032,0.00005541162,0.000051230727,0.00009101056,0.00019008985,0.00009692485],"category_scores_gemma":[0.11824823,0.00014169162,0.00016632905,0.0001789058,0.00014411312,0.00022974946,0.000031092117,0.00058316934,0.000008158616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022628244,0.00058307825,0.00024512794,0.000027401527,0.00006620493,0.00004128872,0.00008902384,0.47861755,0.0000036322144,0.33535415,0.0009941342,0.18171561],"study_design_scores_gemma":[0.0019586463,0.0006590582,0.0057910495,0.000061955616,0.000058731923,0.0000043940413,0.000017664554,0.4882617,0.0000018611275,0.503094,0.000014025934,0.00007690385],"about_ca_topic_score_codex":0.0000015387478,"about_ca_topic_score_gemma":0.0000028789198,"teacher_disagreement_score":0.4607381,"about_ca_system_score_codex":0.00008533133,"about_ca_system_score_gemma":0.00007342179,"threshold_uncertainty_score":0.8891791},"labels":[],"label_agreement":null},{"id":"W2019447419","doi":"10.1111/j.1467-9469.2009.00661.x","title":"Estimating Optimal Dynamic Regimes: Correcting Bias under the Null","year":2009,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Estimator; Mathematics; Covariate; Inference; Null hypothesis; Null (SQL); Parametric statistics; Interval estimation; Econometrics; Statistics; Applied mathematics; Confidence interval; Computer science; Artificial intelligence","score_opus":0.36824768129523855,"score_gpt":0.5205440633546159,"score_spread":0.15229638205937734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019447419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021926995,0.00009845779,0.97419494,0.0008773576,0.002010298,0.0002239229,0.000107461434,0.000033154003,0.0005274266],"genre_scores_gemma":[0.21218167,0.000018566112,0.786834,0.00026303972,0.00042778678,0.0000013714827,0.0000011353609,0.000033498192,0.00023892394],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957724,0.00086403283,0.0018874259,0.00023362481,0.0007656546,0.00047681382],"domain_scores_gemma":[0.9587394,0.038205042,0.0019064811,0.00039655686,0.0004987927,0.00025372262],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005329151,0.00028926844,0.0008307055,0.00012468554,0.00029643494,0.0001675783,0.0005893766,0.00013355937,0.00020039518],"category_scores_gemma":[0.06456393,0.00019099988,0.00019729623,0.00033121597,0.00027719207,0.000121234676,0.00005166666,0.0009861757,0.00001556668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009014725,0.0007564543,0.0009552075,0.00028715422,0.0006059213,0.0009913334,0.0025451854,0.0061331266,0.00021625128,0.4205843,0.045009807,0.5210138],"study_design_scores_gemma":[0.0010198182,0.00092294824,0.0017816047,0.00064000953,0.0003274396,0.00073190406,0.00096703006,0.018505076,0.000068559864,0.9747405,0.000040396266,0.00025471023],"about_ca_topic_score_codex":0.000003249725,"about_ca_topic_score_gemma":0.0000017422951,"teacher_disagreement_score":0.55415624,"about_ca_system_score_codex":0.00017778328,"about_ca_system_score_gemma":0.00015459766,"threshold_uncertainty_score":0.9433156},"labels":[],"label_agreement":null},{"id":"W2019885781","doi":"10.1016/j.spl.2004.08.008","title":"Missing responses in adaptive allocation design","year":2004,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Imputation (statistics); Mathematics; Adaptive design; Skew; Statistics; Standard error; Econometrics; Mathematical optimization; Computer science; Clinical trial","score_opus":0.5461531378756146,"score_gpt":0.5082145035147081,"score_spread":0.0379386343609065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019885781","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017031774,0.000009891964,0.9774291,0.0037456148,0.00025353575,0.0011796711,0.00015960589,0.000101568156,0.000089238754],"genre_scores_gemma":[0.022962056,0.0000038877597,0.97587174,0.0009308752,0.00008070225,0.00009393895,0.0000038778885,0.000039746883,0.000013199551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99501437,0.0022322724,0.001186023,0.00060932594,0.0004805034,0.00047750544],"domain_scores_gemma":[0.9512723,0.047599364,0.0002733603,0.00056148216,0.00014939714,0.00014407061],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005832156,0.0002668023,0.0005659901,0.000118306976,0.00009732722,0.000059466714,0.00027254212,0.00013814904,0.00007362561],"category_scores_gemma":[0.13350572,0.0002606832,0.000066962,0.00032247033,0.00047179832,0.000099612706,0.00006866204,0.00042642094,0.00003460651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008536818,0.00043529464,0.00031690276,0.00017091307,0.000039115515,0.000077225726,0.00072111964,0.00022665151,0.0032609366,0.9787946,0.0010415933,0.014061989],"study_design_scores_gemma":[0.0011647149,0.00017994242,0.00245164,0.00013751506,0.000048418144,0.000004130221,0.000010324304,0.0002955493,0.0015199053,0.99388963,0.000020577412,0.0002776352],"about_ca_topic_score_codex":0.00008069853,"about_ca_topic_score_gemma":0.00005223097,"teacher_disagreement_score":0.12767355,"about_ca_system_score_codex":0.0005474809,"about_ca_system_score_gemma":0.0002471446,"threshold_uncertainty_score":0.99998456},"labels":[],"label_agreement":null},{"id":"W2019978533","doi":"10.1002/pst.244","title":"Assessment of the Gould‐Shih procedure for sample size re‐estimation","year":2006,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Standard deviation; Sample size determination; Statistics; Mathematics; Estimator; Standard error; Nominal level; Confidence interval","score_opus":0.5327868823583967,"score_gpt":0.6279960254321367,"score_spread":0.09520914307374007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019978533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021048314,0.000015051841,0.9894403,0.00085212855,0.0005780656,0.0016636336,0.004128759,0.00007066782,0.0011465662],"genre_scores_gemma":[0.18614449,0.000006491156,0.81298804,0.00028506477,0.00021858081,0.0001528095,0.000011004025,0.000041969568,0.00015156779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967411,0.00050751434,0.001276417,0.0003667678,0.0006734951,0.0004347018],"domain_scores_gemma":[0.8578741,0.1408698,0.00044243952,0.00038094085,0.0003096705,0.0001230626],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021249305,0.00024522436,0.00059336046,0.000025555402,0.00016490747,0.000042839307,0.00037751414,0.0001527416,0.00051321514],"category_scores_gemma":[0.17033862,0.00017476738,0.00016473542,0.00026011403,0.00035364466,0.00004308192,0.00012204,0.00036098112,0.000004111914],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008968214,0.00055026263,0.0023984932,0.0009819178,0.000063057305,0.0000015383426,0.00001923898,0.00013613656,0.00074030133,0.968522,0.020024404,0.0064729718],"study_design_scores_gemma":[0.00130002,0.00010154367,0.010135794,0.0000676439,0.00036868243,0.000001821217,0.000009164891,0.09176667,0.0021197624,0.89227957,0.0016586871,0.00019064028],"about_ca_topic_score_codex":0.000024674975,"about_ca_topic_score_gemma":0.000013188455,"teacher_disagreement_score":0.18403965,"about_ca_system_score_codex":0.00011276527,"about_ca_system_score_gemma":0.0001700215,"threshold_uncertainty_score":0.83664995},"labels":[],"label_agreement":null},{"id":"W2020401994","doi":"10.6000/1929-6029.2013.02.04.1","title":"Progression and Death as Competing Risks in Ovarian Cancer","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Proportional hazards model; Ovarian cancer; Econometrics; Gray (unit); Complement (music); Statistics; Statistical model; Computer science; Medicine; Cancer; Mathematics; Internal medicine; Biology","score_opus":0.7015313884885316,"score_gpt":0.7235348038349219,"score_spread":0.022003415346390276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020401994","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.703909,0.0006675041,0.26117644,0.023376752,0.003025819,0.0013046755,0.00016311924,0.00001798848,0.006358712],"genre_scores_gemma":[0.4776875,0.0010762995,0.52057004,0.00015254234,0.0004351957,0.000032230542,8.3741327e-7,0.000017151178,0.000028170703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9921332,0.0017557105,0.001516704,0.00021455486,0.0039970274,0.00038282396],"domain_scores_gemma":[0.91299814,0.08441487,0.00037491848,0.00012713947,0.0016574016,0.00042754342],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018216666,0.000114700466,0.00044759014,0.0004980927,0.000039800605,0.0001112906,0.00070927525,0.00018860686,0.003410922],"category_scores_gemma":[0.35380563,0.00008736848,0.00003494876,0.00023773685,0.00033534042,0.0001079405,0.0003194638,0.0019426388,0.000020198073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033490613,0.00054042996,0.07095958,0.00009739641,0.000085792555,0.0019860133,0.0004300311,0.0000047082003,0.00016302486,0.39058656,0.0019508302,0.53286076],"study_design_scores_gemma":[0.0018356591,0.00018255209,0.05561477,0.0014883484,0.0000059215713,0.000072268755,0.00018558948,0.0031123299,0.000102948325,0.9371245,0.00019111643,0.00008403214],"about_ca_topic_score_codex":0.0009291418,"about_ca_topic_score_gemma":0.00012376445,"teacher_disagreement_score":0.54653794,"about_ca_system_score_codex":0.00025477563,"about_ca_system_score_gemma":0.00051999814,"threshold_uncertainty_score":0.9975001},"labels":[],"label_agreement":null},{"id":"W2020953180","doi":"10.1177/0962280210391443","title":"A Bayesian destructive weighted Poisson cure rate model and an application to a cutaneous melanoma data","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Markov chain Monte Carlo; Poisson distribution; Bayesian inference; Bayesian probability; Mathematics; Statistics; Cure rate; Applied mathematics; Medicine; Surgery","score_opus":0.5453015859287329,"score_gpt":0.6948447323734955,"score_spread":0.14954314644476263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020953180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006384726,0.000014197655,0.98590904,0.0035096975,0.0002643053,0.001605599,0.00068525574,0.000096457305,0.0015306886],"genre_scores_gemma":[0.022421509,0.00004324741,0.97621584,0.00038074976,0.00043125649,0.0003152872,0.000036977537,0.000093748116,0.000061364226],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97760093,0.014639412,0.001690862,0.002070038,0.0026028308,0.0013959401],"domain_scores_gemma":[0.6042627,0.3879208,0.00020759417,0.0033128941,0.00073464506,0.003561376],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059343524,0.0003863122,0.0011580101,0.00043629674,0.00024345776,0.00014845925,0.0020786463,0.0008505868,0.0015147462],"category_scores_gemma":[0.66302735,0.00032192844,0.000041313877,0.0011740575,0.0017316856,0.00017130644,0.0016192851,0.0044140047,0.000037280355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004125734,0.0003003688,0.000087988534,0.00010534637,0.00002230502,0.0001821712,0.00017819116,0.0000011937051,0.002232832,0.46742418,0.0008237386,0.5282291],"study_design_scores_gemma":[0.0005424804,0.00029407753,0.00026495202,0.000061443796,0.000026545174,0.000046166217,0.0000694608,0.3684995,0.0001730421,0.6292839,0.0005151573,0.00022328451],"about_ca_topic_score_codex":0.00018029372,"about_ca_topic_score_gemma":0.0005545572,"teacher_disagreement_score":0.6036838,"about_ca_system_score_codex":0.000105549734,"about_ca_system_score_gemma":0.0006523604,"threshold_uncertainty_score":0.9999233},"labels":[],"label_agreement":null},{"id":"W2021382870","doi":"10.1097/mlr.0b013e318215d90d","title":"N-of-1 Trials in the Medical Literature","year":2011,"lang":"en","type":"review","venue":"Medical Care","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Clinical trial; Medicine; Population; Randomization; Medical physics; Internal medicine","score_opus":0.8591717291981216,"score_gpt":0.6998938575083188,"score_spread":0.15927787168980279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021382870","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.7520777e-7,0.9904303,0.0015914341,0.00028692957,0.0015804096,0.0015709309,0.00031698876,0.000038674687,0.0041838572],"genre_scores_gemma":[0.0000015732687,0.9597266,0.037887793,0.0003447038,0.001584097,0.0003019343,0.00004070588,0.000067566245,0.000045063724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96102494,0.02796863,0.0063968487,0.00067729736,0.0034138274,0.0005184308],"domain_scores_gemma":[0.57753897,0.41850835,0.0017260129,0.0014325981,0.00022953305,0.0005645446],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06213558,0.0005631667,0.008790208,0.00020460234,0.000036367015,0.000035419325,0.0026115938,0.003172626,0.006880996],"category_scores_gemma":[0.83948004,0.00026066063,0.0019430706,0.000870452,0.00050927367,0.000022895196,0.00033520113,0.0036289252,0.00005021092],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013106801,0.00012176418,0.0000010041573,0.033977356,0.00009387497,0.0004770678,0.00078805065,2.2335926e-10,8.124283e-10,0.0783012,0.005476014,0.88075054],"study_design_scores_gemma":[0.00050122157,0.00009626008,6.4670263e-7,0.05133805,0.00091050495,0.00008392886,0.00007948442,4.1643648e-7,1.1575472e-7,0.17934537,0.76741546,0.00022852638],"about_ca_topic_score_codex":0.000009823618,"about_ca_topic_score_gemma":0.000026204618,"teacher_disagreement_score":0.880522,"about_ca_system_score_codex":0.00006450816,"about_ca_system_score_gemma":0.001270957,"threshold_uncertainty_score":0.99998456},"labels":[],"label_agreement":null},{"id":"W2022284177","doi":"10.1177/0272989x06288684","title":"Implications of Cancer Staging Uncertainties in Radiation Therapy Decisions","year":2006,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Breast cancer; Radiation therapy; Medicine; Medical physics; Cancer; Intensive care medicine; Value of information; Computer science; Surgery; Artificial intelligence; Internal medicine","score_opus":0.429800335296527,"score_gpt":0.6046876730360619,"score_spread":0.17488733773953485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022284177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21917185,0.00054923166,0.77647054,0.001195689,0.00051457767,0.00037894727,0.000037780894,0.00005547073,0.0016258826],"genre_scores_gemma":[0.6156088,0.00045260278,0.3834051,0.00022481436,0.00019909083,0.000061525185,0.0000012422223,0.000022027481,0.000024775014],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963512,0.00041539996,0.0015569085,0.00033999403,0.0010486504,0.00028785062],"domain_scores_gemma":[0.9087763,0.090220526,0.00034551098,0.00041782693,0.00014809135,0.000091759735],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003932885,0.00015087068,0.0005506576,0.00023095794,0.000076416356,0.000026273428,0.00041257092,0.0002112031,0.0017905455],"category_scores_gemma":[0.10852484,0.00011726332,0.00012480762,0.0006631389,0.0001661643,0.000061088285,0.00010542029,0.00030649867,0.000007370953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007039202,0.00015911054,0.020109758,0.000009645748,0.000010337541,0.0000049437035,0.000046027453,0.00008184119,0.00009089507,0.11956537,0.0019791008,0.8578726],"study_design_scores_gemma":[0.0009067973,0.00003033421,0.091982454,0.0005453045,0.000011497839,9.846401e-7,0.000025150537,0.0019108139,0.0001583723,0.903423,0.00089311425,0.00011218752],"about_ca_topic_score_codex":0.00013104048,"about_ca_topic_score_gemma":0.00018298942,"teacher_disagreement_score":0.85776037,"about_ca_system_score_codex":0.00010541915,"about_ca_system_score_gemma":0.00015520168,"threshold_uncertainty_score":0.99912196},"labels":[],"label_agreement":null},{"id":"W2022569477","doi":"10.1097/ede.0b013e31821d09cd","title":"Future Cases as Present Controls to Adjust for Exposure Trend Bias in Case-only Studies","year":2011,"lang":"en","type":"article","venue":"Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Environmental Health Sciences; Agency for Healthcare Research and Quality","keywords":"Odds ratio; Confounding; Crossover study; Confidence interval; Pharmacoepidemiology; Crossover; Case-control study; Medicine; Odds; Statistics; Computer science; Mathematics; Internal medicine; Logistic regression","score_opus":0.9005140709931115,"score_gpt":0.6476807596992679,"score_spread":0.2528333112938437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022569477","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.863898,0.008696326,0.075834595,0.028301368,0.00895533,0.00840084,0.00136401,0.00040218903,0.004147391],"genre_scores_gemma":[0.08976261,0.00017256146,0.9032159,0.0032408056,0.0021104496,0.0007917748,0.0000032600763,0.000050798077,0.00065186975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922724,0.0044142166,0.0019086599,0.0006309345,0.00009816314,0.0006756498],"domain_scores_gemma":[0.66657484,0.3322004,0.00038492904,0.0005092849,0.00011910686,0.0002114175],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011221413,0.00029790972,0.0021121195,0.0001288321,0.00007533953,0.000003934382,0.0002474746,0.0003840654,0.00028171076],"category_scores_gemma":[0.6122108,0.00021681843,0.00024357619,0.00016506283,0.00023009077,0.000036299232,0.00014766234,0.00031704016,0.000040819083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025139814,0.0006754006,0.028913613,0.0004871724,0.00074129447,0.003505083,0.0037280796,0.0000122373285,0.000024668048,0.7667079,0.10675076,0.08593983],"study_design_scores_gemma":[0.0017924245,0.0018233749,0.0032373453,0.00007697327,0.00016538583,0.0008013707,0.0018460735,0.000035964003,0.000065545755,0.98173654,0.008149441,0.0002695804],"about_ca_topic_score_codex":0.0002492754,"about_ca_topic_score_gemma":0.0015694418,"teacher_disagreement_score":0.82738125,"about_ca_system_score_codex":0.00006212534,"about_ca_system_score_gemma":0.000050781728,"threshold_uncertainty_score":0.88415986},"labels":[],"label_agreement":null},{"id":"W2023584100","doi":"10.2174/1381612023393099","title":"The Design of Clinical Trials for New Molecularly Targeted Compounds: Progress and New Initiatives","year":2002,"lang":"en","type":"review","venue":"Current Pharmaceutical Design","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; Queen's University","funders":"","keywords":"Clinical trial; Clinical study design; Medicine; Clinical endpoint; Discontinuation; Endpoint Determination; Medical physics; Drug development; Randomized controlled trial; Surrogate endpoint; Computer science; Pharmacology; Internal medicine; Drug","score_opus":0.9702097865430614,"score_gpt":0.7440994896269888,"score_spread":0.22611029691607265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023584100","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3325645e-8,0.5009511,0.49049622,0.000093750095,0.0015612778,0.006674996,0.0001396553,0.000060204024,0.000022742734],"genre_scores_gemma":[3.467642e-7,0.561427,0.43673104,0.000026727099,0.0012440627,0.00039435213,0.000007849749,0.000106097155,0.00006251367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9449779,0.041669205,0.0100114355,0.001354837,0.00097475626,0.0010118573],"domain_scores_gemma":[0.4404253,0.55323213,0.0038756002,0.0008687723,0.0003503358,0.0012478882],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051310416,0.0011059922,0.009310959,0.000163774,0.00023027742,0.00026258218,0.001272586,0.000920734,0.00015776348],"category_scores_gemma":[0.42838475,0.0006665454,0.0021711919,0.0005288839,0.0013513094,0.00012790493,0.00029584608,0.0019241346,0.000028312505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005622144,0.00049151614,6.1240365e-7,0.008543742,0.0011995761,0.000005674944,0.000027030024,2.7871184e-7,7.446687e-7,0.030507497,0.036728714,0.9219324],"study_design_scores_gemma":[0.0035394488,0.0007093897,5.3791774e-7,0.006969236,0.007753438,0.0000087254775,0.000003917734,0.0015974985,0.000029007664,0.3407529,0.6379958,0.0006401347],"about_ca_topic_score_codex":3.9027393e-7,"about_ca_topic_score_gemma":3.3488643e-8,"teacher_disagreement_score":0.92129225,"about_ca_system_score_codex":0.00006847044,"about_ca_system_score_gemma":0.0014166927,"threshold_uncertainty_score":0.9995786},"labels":[],"label_agreement":null},{"id":"W2024015933","doi":"10.1002/pst.294","title":"Sequential design approaches for bioequivalence studies with crossover designs","year":2007,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Theratechnologies (Canada)","funders":"","keywords":"Sample size determination; Bioequivalence; Crossover; Variance (accounting); Crossover study; Statistics; Type I and type II errors; Statistical power; Clinical study design; A priori and a posteriori; Computer science; Mathematics; Econometrics; Clinical trial; Medicine; Machine learning; Placebo; Pharmacology; Pharmacokinetics","score_opus":0.9499294280480977,"score_gpt":0.6769455700599387,"score_spread":0.27298385798815894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024015933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005018375,0.00023853769,0.99548227,0.00019111783,0.0006009637,0.0018031155,0.0007165315,0.00017295188,0.0002926923],"genre_scores_gemma":[0.026120493,0.00009018419,0.9723901,0.00038403887,0.0005180414,0.00015318145,0.0000060646285,0.00009516204,0.00024274185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957122,0.0005995682,0.0011907405,0.0007026183,0.00073203206,0.0010628321],"domain_scores_gemma":[0.87751573,0.1209517,0.0002961455,0.00036706903,0.0004354459,0.00043390825],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007773739,0.00044040784,0.0008799425,0.00007936053,0.00028330684,0.00009160008,0.0003865692,0.00018391006,0.00016793206],"category_scores_gemma":[0.060723636,0.00033103136,0.00011392797,0.0002938384,0.0012387057,0.0000778929,0.00013350644,0.00043333616,0.000026839789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047788313,0.0006209284,0.00013829129,0.0010390279,0.00078845734,0.0001395825,0.00032404324,0.00009763594,0.00060947187,0.902356,0.008539382,0.080568306],"study_design_scores_gemma":[0.0033620347,0.0007173656,0.000050896087,0.0000796646,0.0009265163,0.000022952372,0.0001257416,0.008321926,0.0192227,0.9645975,0.0020009943,0.0005717041],"about_ca_topic_score_codex":0.0000017270233,"about_ca_topic_score_gemma":0.0000048496267,"teacher_disagreement_score":0.120352134,"about_ca_system_score_codex":0.00016858298,"about_ca_system_score_gemma":0.00012017925,"threshold_uncertainty_score":0.99991417},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2024918973","doi":"10.1081/bip-100102502","title":"ON THE TIMING OF A FUTILITY ANALYSIS IN CLINICAL TRIALS","year":2000,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"Virginia Commonwealth University","keywords":"Interim; Interim analysis; Clinical trial; Medicine; Early stopping; Medical physics; Statistics; Actuarial science; Computer science; Mathematics; Internal medicine; Law; Artificial intelligence; Political science","score_opus":0.861676975374754,"score_gpt":0.7038348345033432,"score_spread":0.1578421408714108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024918973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43375677,0.00018927199,0.55828494,0.002282367,0.0010775395,0.0009899338,0.0012218053,0.000022590195,0.002174783],"genre_scores_gemma":[0.5336867,0.0004065421,0.46493706,0.0005546087,0.0003268004,0.000004014684,9.0788416e-7,0.000021717075,0.000061625775],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9800781,0.010882597,0.007367906,0.00027425107,0.0010286529,0.0003684959],"domain_scores_gemma":[0.6809143,0.31628677,0.0017944904,0.00039719293,0.00031412553,0.0002931704],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06526349,0.00023865131,0.0026170919,0.00023773503,0.000053136453,0.000034673358,0.00055615656,0.00024003537,0.009980463],"category_scores_gemma":[0.36509734,0.00013881597,0.0009313463,0.0010290751,0.000580761,0.000043671105,0.00005119332,0.0013567171,0.00002497723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0087996395,0.0044017634,0.006076988,0.00025221467,0.0043564895,0.00037395576,0.00022783937,0.00020345152,0.00024022444,0.38224187,0.013069224,0.5797563],"study_design_scores_gemma":[0.0027899141,0.00066821335,0.013065625,0.00013022462,0.003528041,0.000010176168,0.00004590139,0.014607342,0.0006000571,0.963729,0.00062822126,0.00019723436],"about_ca_topic_score_codex":0.000005500439,"about_ca_topic_score_gemma":0.000003892977,"teacher_disagreement_score":0.5814872,"about_ca_system_score_codex":0.00006972696,"about_ca_system_score_gemma":0.00013699039,"threshold_uncertainty_score":0.99092454},"labels":[],"label_agreement":null},{"id":"W2025258436","doi":"10.1159/000346247","title":"Incomplete Data in Randomized Dermatology Trials: Consequences and Statistical Methodology","year":2013,"lang":"en","type":"article","venue":"Dermatology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Amgen (Canada); University of Waterloo","funders":"","keywords":"Context (archaeology); Medicine; Psychological intervention; Clinical trial; Randomized controlled trial; Intensive care medicine; MEDLINE; Medical physics; Surgery; Pathology","score_opus":0.8350191092730128,"score_gpt":0.6257504249756319,"score_spread":0.20926868429738088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025258436","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024415663,0.0006628576,0.9482387,0.020610644,0.0010992925,0.003017952,0.00033560392,0.0001676918,0.0014516496],"genre_scores_gemma":[0.1424438,0.00016802369,0.85582304,0.001105928,0.00006670228,0.00032082302,0.000028115574,0.000030778152,0.000012803941],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9468204,0.047506988,0.0037891315,0.0009159631,0.00024207892,0.00072544045],"domain_scores_gemma":[0.48111257,0.5168702,0.0007177531,0.0009722329,0.00010891047,0.00021830283],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017912023,0.00035806655,0.0058112154,0.00028206554,0.00007658036,0.000055652017,0.0007981269,0.00055972976,0.0015576921],"category_scores_gemma":[0.5872273,0.0002696991,0.00012009119,0.00020705107,0.0043784063,0.0001676654,0.0007077443,0.0005976112,0.00015166948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033513117,0.00010071676,0.0008932631,0.00020908887,0.00021951807,0.0004148,0.00014267878,1.422993e-7,0.0001990232,0.98005694,0.0069300174,0.007482516],"study_design_scores_gemma":[0.04223269,0.000025300138,0.00027126918,0.000030677114,0.0002107158,0.0020075508,0.00011779853,0.0033557985,0.00021104416,0.9507782,0.00049663463,0.00026230924],"about_ca_topic_score_codex":0.00038356218,"about_ca_topic_score_gemma":0.00010771309,"teacher_disagreement_score":0.56931525,"about_ca_system_score_codex":0.000021249627,"about_ca_system_score_gemma":0.00013529824,"threshold_uncertainty_score":0.9999755},"labels":[],"label_agreement":null},{"id":"W2026001276","doi":"10.1093/annonc/mdj088","title":"Reply to the Letter to the Editor on ‘Cost-opportunity analysis in clinical oncology: from the “wild far-west” to a correct integration of the disciplines, avoiding the “war of the worlds”’, by D. Tassinari et al. (Ann Oncol 2006; 17: 876)","year":2005,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Clinical Oncology; Oncology; Library science; Family medicine; Internal medicine; Cancer","score_opus":0.4971506705477903,"score_gpt":0.590347943849948,"score_spread":0.09319727330215777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026001276","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07640996,0.000078004785,0.012839089,0.90015984,0.004512352,0.0037428017,0.0009565239,0.00002234977,0.0012790535],"genre_scores_gemma":[0.36503288,0.00022090427,0.027315121,0.59958595,0.006017439,0.0007834583,0.000018705587,0.00008015602,0.0009453516],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97696817,0.017095003,0.0035989233,0.0007373021,0.0010250785,0.00057552406],"domain_scores_gemma":[0.8343685,0.16001825,0.002179343,0.0026409053,0.0005864241,0.00020653564],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03726709,0.00040740336,0.0017657522,0.00013434132,0.0004063551,0.000039118684,0.002926026,0.0004266712,0.0002109229],"category_scores_gemma":[0.1868005,0.00015084393,0.0009031081,0.0019880785,0.0009011688,0.000075538315,0.0011135078,0.0022699512,0.000028090906],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089082855,0.0010831167,0.0015591305,0.0000055154733,0.00043156728,0.0000016778823,0.002977951,0.00067457586,0.00020706253,0.0011250941,0.9263959,0.06464756],"study_design_scores_gemma":[0.00084292475,0.0020246308,0.025733162,0.00020461141,0.0008356696,0.0000019458048,0.0019158093,0.0007095809,0.00113921,0.012600215,0.9537453,0.0002469158],"about_ca_topic_score_codex":0.0009559023,"about_ca_topic_score_gemma":0.014866234,"teacher_disagreement_score":0.3005739,"about_ca_system_score_codex":0.00020524205,"about_ca_system_score_gemma":0.0006837864,"threshold_uncertainty_score":0.9913361},"labels":[],"label_agreement":null},{"id":"W2026010070","doi":"10.1080/03610910500415928","title":"Selecting the Optimal Transformation of a Continuous Covariate in Cox's Regression: Implications for Hypothesis Testing","year":2006,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université de Montréal; The Quebec Population Health Research Network; McGill University; Montreal General Hospital","funders":"","keywords":"Covariate; Type I and type II errors; Parametric statistics; Statistics; Mathematics; A priori and a posteriori; Proportional hazards model; Econometrics","score_opus":0.680644217753717,"score_gpt":0.5902146463542108,"score_spread":0.09042957139950614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026010070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027088225,0.0000571967,0.97032166,0.00063789805,0.00004737911,0.00115951,0.00022175327,0.000039337945,0.00042702208],"genre_scores_gemma":[0.5043114,0.000009645127,0.49550802,0.000017432263,0.000015929303,0.00009482204,0.000026626201,0.000011578405,0.0000045434786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730796,0.00071820006,0.0014396765,0.00020686365,0.0001471267,0.00018015016],"domain_scores_gemma":[0.89187974,0.10667646,0.00057357823,0.00040097587,0.00044350102,0.000025737634],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002298442,0.0001473934,0.00037832305,0.00018011582,0.0002625969,0.000055329616,0.00026915586,0.00010316507,0.0000035058404],"category_scores_gemma":[0.02316006,0.00012871213,0.00003797531,0.00064001326,0.00020474469,0.000107816115,0.00006370646,0.00020824192,5.275153e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112314316,0.00039716653,0.0066108713,0.00018012279,0.000021405218,2.4734507e-7,0.0012444949,0.17078646,0.0002339682,0.63487667,0.00010719494,0.1854291],"study_design_scores_gemma":[0.00070648256,0.000036845526,0.029165737,0.00007622489,0.000029304232,0.0000010685197,0.000118421594,0.47449106,0.000017670036,0.49525577,0.000024469527,0.00007696795],"about_ca_topic_score_codex":0.00010429747,"about_ca_topic_score_gemma":0.00016216376,"teacher_disagreement_score":0.4772232,"about_ca_system_score_codex":0.00007105015,"about_ca_system_score_gemma":0.00006243772,"threshold_uncertainty_score":0.98506826},"labels":[],"label_agreement":null},{"id":"W2026405046","doi":"10.1177/0013164404268675","title":"Effect Sizes and their Intervals: The Two-Level Repeated Measures Case","year":2005,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Mathematics; Confidence interval; Estimator; Sample size determination; Variance (accounting); Coverage probability; Population; Econometrics; Demography","score_opus":0.7635696793982186,"score_gpt":0.5823470726920558,"score_spread":0.18122260670616286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026405046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9256414,0.0025128247,0.021136852,0.040997174,0.0014839127,0.0016638513,0.0000829389,0.00012341862,0.006357629],"genre_scores_gemma":[0.9143822,0.000047929825,0.08349995,0.0010084955,0.00075727026,0.00015587355,7.6556586e-7,0.000013065066,0.00013442128],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99650425,0.0018370539,0.0005730296,0.00044909134,0.00040603004,0.00023053485],"domain_scores_gemma":[0.97552556,0.023634866,0.00014428042,0.0003198123,0.00020458446,0.00017089813],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009215028,0.0002309397,0.00037529823,0.000030120258,0.0002311203,0.00007041399,0.00016591416,0.000098117736,0.00044519745],"category_scores_gemma":[0.042521466,0.00011111319,0.00008988933,0.00010307269,0.0003096977,0.000038384176,0.00006129594,0.00029826292,0.000019209192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004990446,0.0014405194,0.0010901979,0.00009404421,0.00026442343,0.000018727886,0.00093001145,0.000001460859,0.0013680826,0.06585635,0.011805338,0.9166318],"study_design_scores_gemma":[0.0019002794,0.0009764268,0.014591875,0.00014486167,0.0001341725,0.0009421635,0.00018458204,0.000063118474,0.0011221208,0.97500366,0.0045872717,0.00034945933],"about_ca_topic_score_codex":0.000010618051,"about_ca_topic_score_gemma":0.000020457997,"teacher_disagreement_score":0.91628236,"about_ca_system_score_codex":0.000046801357,"about_ca_system_score_gemma":0.00002138285,"threshold_uncertainty_score":0.9655438},"labels":[],"label_agreement":null},{"id":"W2026726213","doi":"10.1016/j.pain.2014.05.025","title":"Research designs for proof-of-concept chronic pain clinical trials: IMMPACT recommendations","year":2014,"lang":"en","type":"review","venue":"Pain","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Clinical trial; Medicine; Clinical study design; Sample size determination; Research design; Chronic pain; Proof of concept; Population; Medical physics; Intensive care medicine; Physical therapy; Computer science; Statistics; Mathematics; Internal medicine","score_opus":0.969877637237985,"score_gpt":0.7863547361162134,"score_spread":0.1835229011217716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026726213","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3084416e-9,0.40933466,0.58263755,0.00024429205,0.0009779424,0.0060334164,0.0005063163,0.000050618793,0.00021519532],"genre_scores_gemma":[2.7170117e-7,0.48588577,0.5075426,0.00005262659,0.004032843,0.0018725236,0.00007226065,0.00015018058,0.0003909262],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.39096045,0.58899117,0.015521188,0.0017695224,0.001230418,0.001527281],"domain_scores_gemma":[0.12396749,0.8700022,0.0034624138,0.0015974679,0.00058370153,0.0003867449],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.773358,0.00064331497,0.010208788,0.00039494512,0.00021258036,0.00008792527,0.0013117593,0.001566333,0.0011275775],"category_scores_gemma":[0.96503526,0.00046535482,0.0033807608,0.0007737005,0.0006876719,0.000044482495,0.00022728831,0.0022232027,0.000047303052],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033172215,0.0003157857,1.7393263e-7,0.021808371,0.00044755088,9.92061e-7,0.0000173722,1.4682449e-7,5.5350693e-8,0.02097136,0.13431251,0.82209253],"study_design_scores_gemma":[0.0005574883,0.0011057992,1.6773624e-8,0.01387557,0.0009199775,6.96648e-7,0.000015486818,0.000438374,0.000004130371,0.3605521,0.6222305,0.00029981794],"about_ca_topic_score_codex":0.0000061133846,"about_ca_topic_score_gemma":0.0000068972768,"teacher_disagreement_score":0.82179266,"about_ca_system_score_codex":0.000418723,"about_ca_system_score_gemma":0.001941877,"threshold_uncertainty_score":0.99978554},"labels":[],"label_agreement":null},{"id":"W2028238637","doi":"10.1186/1471-2288-11-95","title":"A comparison of a new multinomial stopping rule with stopping rules of fleming and gehan in single arm phase II cancer clinical trials","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Ontario Clinical Oncology Group; McMaster University; Juravinski Hospital; Juravinski Cancer Centre","funders":"","keywords":"Early stopping; Clinical trial; Medicine; Statistics; Internal medicine; Mathematics; Computer science; Artificial intelligence","score_opus":0.9873198587340849,"score_gpt":0.8050490733946936,"score_spread":0.18227078533939134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028238637","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5894919,0.00039652706,0.40857166,0.00015769244,0.00028892167,0.0007670432,0.000024820272,0.000020164112,0.0002812615],"genre_scores_gemma":[0.12675728,0.00018100966,0.8723948,0.00003702178,0.00046391555,0.000073450916,0.0000011977125,0.000038171074,0.0000531508],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.893865,0.09427879,0.00719501,0.0011355255,0.0022848663,0.0012408274],"domain_scores_gemma":[0.22763677,0.76835597,0.0016865929,0.00071442453,0.000532055,0.0010741878],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23238027,0.0002731299,0.0042969524,0.0004853364,0.00010432164,0.00001118003,0.0006776627,0.0007735499,0.0014366535],"category_scores_gemma":[0.8835946,0.00020080364,0.00024889142,0.0004610848,0.0024700298,0.000063381696,0.00072141545,0.0018338797,0.0000019438291],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014180636,0.007214798,0.02485406,0.0014392401,0.00032986785,0.000057523797,0.007049658,0.0000020484538,0.0072501223,0.030073509,0.00043504368,0.9071135],"study_design_scores_gemma":[0.041279722,0.01939569,0.0076124542,0.0056630163,0.00050856586,0.000029949375,0.00505005,0.0068178247,0.041299764,0.87120074,0.00040568528,0.000736541],"about_ca_topic_score_codex":0.0015176802,"about_ca_topic_score_gemma":0.0009899318,"teacher_disagreement_score":0.90637696,"about_ca_system_score_codex":0.000081575046,"about_ca_system_score_gemma":0.0018829255,"threshold_uncertainty_score":0.9994762},"labels":[],"label_agreement":null},{"id":"W2029114449","doi":"10.1016/j.arthro.2003.09.023","title":"Practical aspects of randomization and blinding in randomized clinical trials","year":2003,"lang":"en","type":"article","venue":"Arthroscopy The Journal of Arthroscopic and Related Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fowler Kennedy Sport Medicine Clinic; Western University","funders":"","keywords":"Blinding; Randomization; Restricted randomization; Randomized controlled trial; Clinical trial; Medicine; Research design; Clinical study design; Computer science; Medical physics; Statistics; Mathematics; Surgery; Internal medicine","score_opus":0.4801915977814985,"score_gpt":0.5800980758949988,"score_spread":0.09990647811350034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029114449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8642736,0.004091125,0.122437984,0.001944099,0.0040600616,0.0015663503,0.0000048807347,0.000020045003,0.0016018185],"genre_scores_gemma":[0.87472403,0.020312099,0.104682714,0.00009777341,0.00011486799,0.0000051345573,2.534531e-7,0.000027979146,0.000035150773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96012115,0.03249165,0.0064665847,0.0002149746,0.00042849692,0.00027715488],"domain_scores_gemma":[0.5936765,0.40270072,0.0030981458,0.0002035185,0.00016907373,0.0001520255],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16072819,0.00021431874,0.003836733,0.00023367854,0.00010042947,0.00003272459,0.0000777402,0.00034037925,0.00017625558],"category_scores_gemma":[0.5885319,0.000119467986,0.0004834704,0.0003170417,0.0010971056,0.00018322522,0.000037440073,0.0008324682,0.0000015738424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15213366,0.0020802838,0.044893514,0.00064010767,0.004166412,0.00026793042,0.0027018315,0.0000470953,0.0012321679,0.773619,0.0034670848,0.0147509305],"study_design_scores_gemma":[0.10864302,0.00024046481,0.00043727446,0.001023205,0.0010524706,0.0002653133,0.0003319056,0.00025668152,0.0016183621,0.88588184,0.00007452048,0.000174955],"about_ca_topic_score_codex":0.0000025185082,"about_ca_topic_score_gemma":0.0000021806477,"teacher_disagreement_score":0.42780375,"about_ca_system_score_codex":0.000015556838,"about_ca_system_score_gemma":0.00028009183,"threshold_uncertainty_score":0.86420697},"labels":[],"label_agreement":null},{"id":"W2029302922","doi":"10.1016/j.csda.2009.03.002","title":"Group sequential testing of homogeneity in genetic linkage analysis","year":2009,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linkage (software); Homogeneity (statistics); Sample size determination; Genetic linkage; Statistics; Multiple comparisons problem; Monte Carlo method; Mathematics; Computer science; Genetics; Biology; Gene","score_opus":0.5488176037055619,"score_gpt":0.549484249912318,"score_spread":0.0006666462067561607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029302922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031652898,0.00005135943,0.95822054,0.000045371256,0.000059394795,0.00020197267,0.0096455505,0.000039737086,0.000083148014],"genre_scores_gemma":[0.33394155,0.000011817558,0.664418,0.000057281846,0.000067055626,0.0000036084807,0.0014813547,0.000011798173,0.000007575686],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994653,0.0010015769,0.0021710207,0.000877207,0.00093707134,0.00036011921],"domain_scores_gemma":[0.96492064,0.03241389,0.00084188604,0.0012117198,0.00044480726,0.00016708393],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031152472,0.00027962166,0.0014758557,0.0009830093,0.00009605651,0.00007265445,0.00088087446,0.0001383099,0.00036512286],"category_scores_gemma":[0.039778396,0.00028626263,0.0002729283,0.0062312805,0.00018766588,0.00010825463,0.00029419526,0.00027735846,0.000009029894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015998168,0.0022287357,0.29680628,0.0002460031,0.016199615,0.00027586662,0.00017640418,0.28455085,0.00015684059,0.2798186,0.0014754678,0.11790539],"study_design_scores_gemma":[0.00025337335,0.000044463774,0.24439915,0.00000928391,0.00646364,6.7808674e-7,0.0000033316492,0.33502406,0.000004093405,0.41365412,0.0000048024385,0.00013900359],"about_ca_topic_score_codex":0.00041380184,"about_ca_topic_score_gemma":0.0005078972,"teacher_disagreement_score":0.30228865,"about_ca_system_score_codex":0.00007750906,"about_ca_system_score_gemma":0.00010909232,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W2029950934","doi":"10.1002/cjs.10053","title":"Contaminated normal modeling with application to microarray data analysis","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistics; Gamma distribution; Mathematics; BETA (programming language); Data mining; Computer science","score_opus":0.3112712227147943,"score_gpt":0.46936735986178596,"score_spread":0.15809613714699167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029950934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017643463,0.0000074079885,0.9788311,0.000266188,0.0003058207,0.00019761003,0.0025369595,0.000007278611,0.00020414774],"genre_scores_gemma":[0.2901932,0.0000015911099,0.7094272,0.0001347251,0.00016486984,0.0000022632933,0.000024490078,0.000022046179,0.000029620574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979476,0.0001523482,0.0009916063,0.0002569886,0.0003127552,0.00033870604],"domain_scores_gemma":[0.9916854,0.0050665326,0.00045875678,0.0008129271,0.00088117033,0.0010952079],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002587964,0.0001596456,0.0006070111,0.0004076151,0.00011274992,0.000091024485,0.0008134291,0.00011689051,0.00027851938],"category_scores_gemma":[0.02791417,0.00013268301,0.000051458614,0.00064886647,0.0001264446,0.00010073183,0.000035427744,0.0005806807,0.000013092376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070887676,0.00032428995,0.018356588,0.00030749035,0.0055622524,0.0013525813,0.0019506974,0.009202438,0.00507623,0.76364183,0.037322197,0.15619451],"study_design_scores_gemma":[0.00262052,0.00080009317,0.004253652,0.00014606188,0.007512646,0.00026009785,0.0004864455,0.32328656,0.0005096387,0.652385,0.006622638,0.0011166574],"about_ca_topic_score_codex":0.0017196838,"about_ca_topic_score_gemma":0.08932492,"teacher_disagreement_score":0.3140841,"about_ca_system_score_codex":0.00006501081,"about_ca_system_score_gemma":0.00088658754,"threshold_uncertainty_score":0.98027414},"labels":[],"label_agreement":null},{"id":"W2030157325","doi":"10.1002/sim.4018","title":"A Bayesian approach to simultaneously adjusting for verification and reference standard bias in diagnostic test studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Covariate; Statistics; Bayesian probability; Test (biology); Independence (probability theory); Sensitivity (control systems); Conditional independence; Selection bias; Computer science; Econometrics; Mathematics","score_opus":0.5507579548728604,"score_gpt":0.5716683765821122,"score_spread":0.020910421709251836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030157325","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009851074,0.00009754871,0.98576,0.00060612924,0.00049057166,0.001675938,0.0007573266,0.00004364061,0.00071781094],"genre_scores_gemma":[0.21622568,0.00014652635,0.7829665,0.00014584092,0.00020510837,0.00022636709,0.00001273928,0.00003082268,0.00004043553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971097,0.00027323523,0.0013300031,0.00052613975,0.00039152932,0.0003694081],"domain_scores_gemma":[0.63449806,0.36443228,0.000244703,0.00034329423,0.00032038617,0.00016129701],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006316659,0.00023420919,0.00091415684,0.00019030618,0.00006961088,0.00001801057,0.00019933506,0.00014664681,0.00002457684],"category_scores_gemma":[0.8895271,0.00018981945,0.00001412243,0.0003579237,0.00041346328,0.000027634813,0.00007629684,0.0005589609,0.0000019221359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005341268,0.0005714521,0.009367628,0.0030516277,0.000066072054,0.00010689942,0.0070179044,0.000115487106,0.0012052758,0.7913573,0.0071904617,0.17941579],"study_design_scores_gemma":[0.0023257649,0.00080150145,0.002258011,0.0006641737,0.000102321115,0.000008042478,0.0015313167,0.010791085,0.00005538273,0.9806556,0.0005401146,0.00026669767],"about_ca_topic_score_codex":0.000043683303,"about_ca_topic_score_gemma":0.00047265273,"teacher_disagreement_score":0.8832104,"about_ca_system_score_codex":0.0000751409,"about_ca_system_score_gemma":0.00006189044,"threshold_uncertainty_score":0.77406126},"labels":[],"label_agreement":null},{"id":"W2030272349","doi":"10.1155/2014/585687","title":"Exploring Population Pharmacokinetic Modeling with Resampling Visualization","year":2014,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Shandong Agricultural University; Shandong University","keywords":"Resampling; Outlier; Computer science; Visualization; Population; Multivariate statistics; Data mining; Data visualization; Multidimensional scaling; Statistics; Machine learning; Artificial intelligence; Medicine; Mathematics","score_opus":0.9451424330423583,"score_gpt":0.6951659736697268,"score_spread":0.24997645937263158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030272349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14465456,0.0000042073134,0.85117984,0.00054380076,0.001082941,0.0003084006,0.000012353205,0.000109160595,0.002104768],"genre_scores_gemma":[0.6538639,0.00002465781,0.34457913,0.000027041531,0.0012330321,0.000115112816,0.000018987625,0.000035503414,0.000102603124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962074,0.000915276,0.00056739897,0.00038627273,0.0015445577,0.00037904957],"domain_scores_gemma":[0.98735267,0.011438228,0.00011061983,0.00024939433,0.00069755124,0.00015154103],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00742219,0.00012419056,0.00021580518,0.00048050177,0.00016573831,0.00011927486,0.00036321065,0.00006413036,0.00024038358],"category_scores_gemma":[0.043464504,0.00010088413,0.00004687197,0.00049409334,0.00009515013,0.00023608934,0.00013796544,0.00031006272,0.00003536427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061606185,0.00030198917,0.0010691264,0.00015619512,0.00016416072,0.00000846731,0.000233664,0.0025778355,0.0054702368,0.92072505,0.00066828984,0.068008944],"study_design_scores_gemma":[0.00091009773,0.00011701134,0.00047367552,0.00017710554,0.00001348891,0.0000033265171,0.000046936497,0.50206125,0.0010986298,0.49388224,0.0010700498,0.00014618879],"about_ca_topic_score_codex":0.000055403558,"about_ca_topic_score_gemma":0.0000049637592,"teacher_disagreement_score":0.5092094,"about_ca_system_score_codex":0.00016124763,"about_ca_system_score_gemma":0.000027667591,"threshold_uncertainty_score":0.9645928},"labels":[],"label_agreement":null},{"id":"W2030375608","doi":"10.1016/j.csda.2013.05.015","title":"A hierarchical Bayes model for biomarker subset effects in clinical trials","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Bayes' theorem; Biomarker; Bayes factor; Bayesian probability; Statistics; Computer science; Mathematics; Econometrics; Computational biology; Artificial intelligence; Medicine; Biology; Genetics","score_opus":0.7677535222997305,"score_gpt":0.6494448756109211,"score_spread":0.11830864668880936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030375608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017617152,0.000033433473,0.9759405,0.00044638594,0.00024655467,0.0015962564,0.01988255,0.00005911796,0.0000334799],"genre_scores_gemma":[0.031107485,0.000025930853,0.9637155,0.00038557994,0.0001951473,0.00027898658,0.0041606417,0.00004809044,0.00008266107],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.987754,0.005215692,0.0044844593,0.0012195962,0.00080517196,0.00052106543],"domain_scores_gemma":[0.6251937,0.3719737,0.00090102875,0.0011208869,0.0004740923,0.0003365759],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025118202,0.00036578134,0.0026121899,0.00048145425,0.00012664769,0.00020687621,0.0009668024,0.0002902574,0.00048682626],"category_scores_gemma":[0.41732585,0.00031256158,0.0005358726,0.0010783757,0.00034416528,0.00020654043,0.00047034203,0.00042365523,0.000067733155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004327577,0.0014624981,0.011219104,0.00044622415,0.0057513965,0.000026565336,0.000081278224,0.017787647,0.000008395764,0.6492281,0.14416787,0.16938816],"study_design_scores_gemma":[0.0010548431,0.00003784103,0.018461348,0.000017616618,0.001616369,3.8612433e-7,0.0000021149128,0.49133468,3.6278675e-7,0.48726267,0.000036285048,0.00017548409],"about_ca_topic_score_codex":0.00009998612,"about_ca_topic_score_gemma":0.00014519517,"teacher_disagreement_score":0.47354704,"about_ca_system_score_codex":0.00006557824,"about_ca_system_score_gemma":0.00023862533,"threshold_uncertainty_score":0.99993265},"labels":[],"label_agreement":null},{"id":"W2030706697","doi":"10.1002/pst.368","title":"The Rheumatoid Arthritis Drug Development Model: a case study in Bayesian clinical trial simulation","year":2009,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes","funders":"AstraZeneca","keywords":"Drug development; Clinical trial; Medicine; Rheumatoid arthritis; Bayesian probability; Outcome (game theory); Population; Intensive care medicine; Drug; Risk analysis (engineering); Medical physics; Computer science; Internal medicine; Pharmacology; Artificial intelligence; Mathematics","score_opus":0.6679110266087562,"score_gpt":0.6478830317170668,"score_spread":0.020027994891689382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030706697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12408167,0.00009341335,0.8708831,0.00036447617,0.000908428,0.0032089127,0.00008994668,0.00014474404,0.00022530717],"genre_scores_gemma":[0.5625781,0.00016527722,0.43669572,0.00023673712,0.00016926172,0.000081675455,0.0000021625335,0.000032865868,0.00003822729],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9902754,0.0032720088,0.0039317664,0.000742495,0.0009548604,0.00082350173],"domain_scores_gemma":[0.89799815,0.10033352,0.00041833165,0.00055466907,0.00020748546,0.0004878668],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013298714,0.00041505106,0.0010448612,0.00008379267,0.0004608106,0.00018736842,0.00043221394,0.00018729574,0.00011085986],"category_scores_gemma":[0.08118486,0.00031804314,0.00013892245,0.00035193822,0.00029217472,0.00009065886,0.00014956052,0.0011870265,0.000037318383],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011894642,0.0058337376,0.000813237,0.000031980177,0.00014383483,0.0041026613,0.001161354,0.0016623886,9.4883615e-7,0.08434432,0.001950173,0.88806075],"study_design_scores_gemma":[0.034659326,0.0004839977,0.00016657733,0.000044922206,0.00006126784,0.00005927126,0.00025160707,0.42453104,0.0000103126395,0.538469,0.0008897886,0.0003729073],"about_ca_topic_score_codex":0.000014386698,"about_ca_topic_score_gemma":0.0002250095,"teacher_disagreement_score":0.8876878,"about_ca_system_score_codex":0.00016687972,"about_ca_system_score_gemma":0.0002828459,"threshold_uncertainty_score":0.99992716},"labels":[],"label_agreement":null},{"id":"W2030743452","doi":"10.1002/bimj.200710376","title":"Estimation and Confidence Regions for Multi‐Dimensional Effective Dose","year":2007,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Navy; University of Wisconsin-Madison; Wisconsin Sea Grant Institute, University of Wisconsin; Ryerson University; National Oceanic and Atmospheric Administration; National Science Foundation","keywords":"Univariate; Confidence interval; Logistic regression; Statistics; Range (aeronautics); Mathematics; Confidence region; Multivariate statistics; Computer science; Econometrics; Engineering","score_opus":0.6342267285278458,"score_gpt":0.6205889763961734,"score_spread":0.013637752131672398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030743452","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009799916,0.00014341781,0.9884801,0.00030510646,0.0005934008,0.0005682286,0.000022535976,0.000032878543,0.00005441075],"genre_scores_gemma":[0.11641355,0.00001492688,0.88302916,0.00013991953,0.00031934172,0.000012753172,5.755938e-7,0.000016639447,0.00005310993],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99792355,0.0002967169,0.0007833614,0.00024315488,0.00042505583,0.00032816152],"domain_scores_gemma":[0.8942643,0.10458906,0.00033074798,0.00013257837,0.00029852946,0.0003848164],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007537011,0.00014382479,0.00040678072,0.0005879541,0.00021575927,0.000072938514,0.00013325112,0.00018270685,0.00003704979],"category_scores_gemma":[0.23866424,0.00010834275,0.00013824666,0.00093855435,0.00020962754,0.000085356325,0.000056944937,0.0003339865,0.000009179988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074014487,0.00056693197,0.00023698389,0.000089596884,0.00014074033,0.00006819493,0.00006700423,0.0000032870066,0.0016743221,0.47822896,0.0040179887,0.5141659],"study_design_scores_gemma":[0.0025276055,0.00048504927,0.0074643744,0.00007891945,0.00010042358,0.00023525298,0.00001842344,0.008446002,0.0013435668,0.97885084,0.0002851563,0.00016438281],"about_ca_topic_score_codex":0.0000019755882,"about_ca_topic_score_gemma":5.6093927e-7,"teacher_disagreement_score":0.5140015,"about_ca_system_score_codex":0.00009275081,"about_ca_system_score_gemma":0.000040188468,"threshold_uncertainty_score":0.76774883},"labels":[],"label_agreement":null},{"id":"W2031364987","doi":"10.1007/s00362-008-0165-9","title":"Inference on effect size indices from several two-armed experiments","year":2008,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Bootstrapping (finance); Estimator; Statistics; Mathematics; Bivariate analysis; Sample size determination; Confidence interval; Inference; Null hypothesis; Statistical hypothesis testing; Homogeneity (statistics); Monte Carlo method; Series (stratigraphy); Computer science; Econometrics; Artificial intelligence","score_opus":0.3938085268102587,"score_gpt":0.5614108691675798,"score_spread":0.16760234235732108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031364987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7314113,0.000048294503,0.16241644,0.0003746408,0.0031393091,0.0021715674,0.0028005948,0.000730861,0.096907035],"genre_scores_gemma":[0.5623484,0.00001067203,0.43653637,0.00055527734,0.0002259925,0.00006994272,0.000010672153,0.00004016574,0.00020250295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953371,0.0015325194,0.0008936653,0.0007280345,0.0009126756,0.0005959492],"domain_scores_gemma":[0.7973142,0.20163836,0.00017760944,0.00045525117,0.000044344033,0.0003702109],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000925707,0.00041488354,0.0009657219,0.000045845165,0.00021226381,0.000041921674,0.00038184854,0.0002042068,0.0061393487],"category_scores_gemma":[0.17674592,0.0003255316,0.00013738358,0.00016761007,0.00066286104,0.00006018755,0.00012405362,0.000572597,0.00053011783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006079083,0.002568324,0.016548147,0.0003705642,0.0013018999,0.0022519247,0.0027366031,0.00003667503,0.012028535,0.84443104,0.026764223,0.08488299],"study_design_scores_gemma":[0.0055990806,0.0015421187,0.030910168,0.0001685556,0.00018124074,0.0000073019214,0.00006140242,0.00029806505,0.0040614232,0.9558071,0.0005892318,0.00077435176],"about_ca_topic_score_codex":0.000106034655,"about_ca_topic_score_gemma":0.000007336223,"teacher_disagreement_score":0.2741199,"about_ca_system_score_codex":0.00010518139,"about_ca_system_score_gemma":0.000082437014,"threshold_uncertainty_score":0.99991965},"labels":[],"label_agreement":null},{"id":"W2031651171","doi":"10.1371/journal.pone.0016237","title":"Estimating the Power of Indirect Comparisons: A Simulation Study","year":2011,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Ottawa","funders":"Canadian Institutes of Health Research; Pfizer Canada; Pfizer","keywords":"Confidence interval; Fragility; Interval estimation; Statistics; Estimation; Statistical hypothesis testing; Medicine; Econometrics; Mathematics; Economics","score_opus":0.8370309769443626,"score_gpt":0.5575910182431496,"score_spread":0.27943995870121296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031651171","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8924293,0.000009592668,0.103243515,0.000022928592,0.00008779176,0.0010170769,0.000010779654,0.00006875872,0.0031102777],"genre_scores_gemma":[0.5157631,1.208634e-7,0.48415446,0.000012421658,0.000027568973,0.000018483524,7.982721e-8,0.000009709064,0.0000140061975],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781126,0.00076187146,0.0007145072,0.00015928582,0.0004232276,0.00012982663],"domain_scores_gemma":[0.96173203,0.037281826,0.00036160744,0.0004461731,0.000140191,0.000038182458],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028550604,0.00009458276,0.0005234357,0.00003218378,0.000055939465,0.000009081745,0.00021394863,0.000052068488,0.0004443562],"category_scores_gemma":[0.09485886,0.000062645275,0.000049711303,0.00015332148,0.00008598289,0.00003062021,0.000082129176,0.0001799673,0.000023970792],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022562165,0.2837392,0.47821498,0.0022301704,0.010826518,0.000046161935,0.1123603,0.0008480349,0.002860916,0.087053254,0.0012376962,0.01832655],"study_design_scores_gemma":[0.0012238325,0.0012689898,0.035665322,0.00035703156,0.001005752,2.347064e-7,0.0008832222,0.054760974,0.0049653985,0.89965904,0.000001150547,0.00020905536],"about_ca_topic_score_codex":0.000010504441,"about_ca_topic_score_gemma":0.0000026855946,"teacher_disagreement_score":0.8126058,"about_ca_system_score_codex":0.000011466384,"about_ca_system_score_gemma":0.000013582933,"threshold_uncertainty_score":0.9127655},"labels":[],"label_agreement":null},{"id":"W2032559340","doi":"10.1186/1471-2407-11-426","title":"Early mortality and overall survival in oncology phase I trial participants: can we improve patient selection?","year":2011,"lang":"en","type":"article","venue":"BMC Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Logistic regression; Internal medicine; Surgical oncology; Univariate; Multivariate analysis; Univariate analysis; Oncology; Prospective cohort study; Multivariate statistics","score_opus":0.7419150106956403,"score_gpt":0.6049455771107186,"score_spread":0.13696943358492164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032559340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920151,0.00003868047,0.0039524673,0.00006514315,0.0019457218,0.0009885514,0.00016524759,0.000041436724,0.00078760623],"genre_scores_gemma":[0.88362736,0.000073883995,0.11485929,0.00012992568,0.0005540982,0.00061101257,5.943982e-7,0.00003301267,0.00011080265],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970331,0.0010319876,0.00090438576,0.00039694237,0.00023052389,0.0004030496],"domain_scores_gemma":[0.99168587,0.0075238487,0.0002921379,0.00023351812,0.00007775141,0.0001868614],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017561575,0.00016681607,0.00064618373,0.000046315203,0.00003962319,0.000016609729,0.00009824287,0.00018449752,0.0007063039],"category_scores_gemma":[0.01492961,0.00014324464,0.00007489323,0.00012649072,0.00013512655,0.000051331193,0.00006942444,0.00026653713,0.0000039277156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.182142,0.016701004,0.23878647,0.000993024,0.0011636798,0.0001429296,0.020476896,0.000009976211,0.0025959073,0.19032025,0.002837797,0.34383005],"study_design_scores_gemma":[0.07463282,0.0041302666,0.026765373,0.00007837723,0.0003028365,0.0000011073723,0.00016427465,0.00042261815,0.0019163863,0.8906303,0.00052233133,0.0004333226],"about_ca_topic_score_codex":0.004435041,"about_ca_topic_score_gemma":0.009733731,"teacher_disagreement_score":0.70031005,"about_ca_system_score_codex":0.00022224819,"about_ca_system_score_gemma":0.0003242632,"threshold_uncertainty_score":0.993368},"labels":[],"label_agreement":null},{"id":"W2032742414","doi":"10.1016/j.cct.2004.06.003","title":"Incorporating the sampling variation of the disease prevalence when calculating the sample size in a study to determine the diagnostic accuracy of a test","year":2004,"lang":"en","type":"article","venue":"Controlled Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Confidence interval; Statistics; Sample size determination; Gold standard (test); Sampling (signal processing); Population; Mathematics; Test (biology); Standard deviation; Coefficient of variation; Incidence (geometry); Sample (material); Standard error; Medicine; Computer science; Biology","score_opus":0.6374061872251882,"score_gpt":0.5979579653594067,"score_spread":0.03944822186578145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032742414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8352465,0.00018474697,0.12458147,0.011280372,0.0014011591,0.02683812,0.00036573538,0.000052119827,0.000049796832],"genre_scores_gemma":[0.910885,0.000020923057,0.0868874,0.0006231157,0.0006832369,0.0008517345,2.794363e-7,0.00003471458,0.000013648422],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9632037,0.025293037,0.009277395,0.0006568058,0.0011270021,0.00044204717],"domain_scores_gemma":[0.010834082,0.9814327,0.005173044,0.0019525393,0.0004356469,0.00017203153],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11427878,0.00034539812,0.0027305125,0.000043099746,0.00033606964,0.00009999801,0.0016756682,0.00014331797,0.000074608186],"category_scores_gemma":[0.9932164,0.00013369632,0.0009879237,0.00067319185,0.00052619696,0.00007354075,0.00062841544,0.00079343596,0.0000034983645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.034216933,0.026356889,0.6343405,0.0016965037,0.003557261,0.000047913105,0.021401653,0.01939407,0.0027533756,0.14292333,0.00017207196,0.11313946],"study_design_scores_gemma":[0.018835792,0.0005685589,0.18946727,0.0007350999,0.0014164065,6.0023024e-7,0.000406885,0.0017521121,0.00003196919,0.7866137,0.0000041696535,0.00016744937],"about_ca_topic_score_codex":0.0001966504,"about_ca_topic_score_gemma":0.0001587265,"teacher_disagreement_score":0.9561396,"about_ca_system_score_codex":0.00006783383,"about_ca_system_score_gemma":0.00047038886,"threshold_uncertainty_score":0.91203636},"labels":[],"label_agreement":null},{"id":"W2032918102","doi":"10.1016/j.jclinepi.2012.11.006","title":"Increased statistical power with combined independent randomization tests used with multiple-baseline design","year":2013,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children","funders":"VMware; NetApp","keywords":"Randomization; Statistics; Mathematics; Statistical power; Power (physics); Multiple baseline design; Sample size determination; Subject (documents); Medicine; Computer science; Reliability engineering; Randomized controlled trial; Internal medicine; Engineering","score_opus":0.594019471434238,"score_gpt":0.5827935140556644,"score_spread":0.01122595737857357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032918102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09453429,0.000022294196,0.90091485,0.0026649227,0.00054589304,0.0011672422,0.000024129218,0.000044297696,0.000082059625],"genre_scores_gemma":[0.36606422,0.000028373051,0.63211924,0.001317301,0.00036373173,0.000032391545,0.0000029708663,0.000047639693,0.00002414215],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9483006,0.039879035,0.009767684,0.0005874311,0.0007815495,0.0006836715],"domain_scores_gemma":[0.19559674,0.7951064,0.0062728566,0.0006037493,0.0014420839,0.0009781296],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09210947,0.0004447327,0.0059270374,0.00016342888,0.000082241226,0.0000331973,0.00052637415,0.0006724668,0.0012747705],"category_scores_gemma":[0.8592876,0.00024436117,0.00042875356,0.00025935445,0.0009569526,0.00018540157,0.00007864792,0.001831513,0.00006210337],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11416931,0.006128764,0.7391141,0.00024534276,0.0028574625,0.00066445576,0.000103593615,0.0019315211,0.00016037429,0.08314678,0.03243806,0.019040264],"study_design_scores_gemma":[0.059073463,0.011787893,0.16346808,0.0003784696,0.00070026505,0.00021443416,0.000042893087,0.011053827,0.000059320348,0.75262547,0.0001236259,0.00047226623],"about_ca_topic_score_codex":0.000039624523,"about_ca_topic_score_gemma":0.000016625021,"teacher_disagreement_score":0.7671782,"about_ca_system_score_codex":0.00006376651,"about_ca_system_score_gemma":0.00055287563,"threshold_uncertainty_score":0.9996382},"labels":[],"label_agreement":null},{"id":"W2034513653","doi":"10.1016/j.spl.2005.07.014","title":"Orthogonal multiple contrast test for testing monotone on the average","year":2005,"lang":"en","type":"article","venue":"Statistics & Probability Letters","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Acadia University","funders":"","keywords":"Mathematics; Contrast (vision); Monotone polygon; Statistics; Combinatorics; Likelihood-ratio test; Statistical hypothesis testing; Poisson distribution; Applied mathematics; Discrete mathematics; Artificial intelligence; Computer science; Geometry","score_opus":0.4311857186526139,"score_gpt":0.46555941136084605,"score_spread":0.03437369270823215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034513653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038877584,0.0000032282655,0.94684285,0.0073400512,0.00028093826,0.0027328758,0.003430007,0.00014873738,0.00034375122],"genre_scores_gemma":[0.07783377,9.816795e-7,0.9165802,0.0044223345,0.0005794134,0.00045756038,0.000014151568,0.000061961764,0.000049646176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961785,0.0006665132,0.0012835105,0.0006759733,0.00053794804,0.0006575319],"domain_scores_gemma":[0.7092175,0.2894626,0.0003188728,0.000619096,0.00024416,0.00013781234],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0048015234,0.00036612098,0.00064275326,0.00004068656,0.00034434997,0.00010341391,0.00044245846,0.0001252143,0.00017232903],"category_scores_gemma":[0.45745715,0.0002654195,0.00015061717,0.00016328656,0.0005570298,0.000057610974,0.00009263946,0.00053703325,0.000060897655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023649192,0.00073418254,0.0032907627,0.00023590185,0.00008206123,0.000007960543,0.00015035002,0.00007520947,0.00326853,0.9466877,0.017756345,0.027474487],"study_design_scores_gemma":[0.0012812238,0.00026641163,0.002426309,0.00006806628,0.000089169305,0.0000031322127,0.0000033057406,0.008870716,0.0007253655,0.9846601,0.0012757396,0.0003304546],"about_ca_topic_score_codex":0.000010420295,"about_ca_topic_score_gemma":0.000040586216,"teacher_disagreement_score":0.45265564,"about_ca_system_score_codex":0.00018309332,"about_ca_system_score_gemma":0.00008283801,"threshold_uncertainty_score":0.9999798},"labels":[],"label_agreement":null},{"id":"W2034778756","doi":"10.1177/009286150103500409","title":"Blinded Sample Size Adjustment","year":2001,"lang":"en","type":"article","venue":"Drug Information Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"Sample size determination; Variance (accounting); Statistics; Sample (material); Mathematics; Sample variance; Analysis of variance; Econometrics; Medicine","score_opus":0.4047541854108013,"score_gpt":0.5229688361768974,"score_spread":0.11821465076609605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034778756","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023182102,0.000022484694,0.94548786,0.0028889352,0.0029025225,0.0004661249,0.00007023218,0.00015087212,0.024828844],"genre_scores_gemma":[0.01636673,0.00013540327,0.980937,0.0015230459,0.000776423,0.000012040749,0.0000016332484,0.00001212056,0.00023557572],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974476,0.00030130785,0.0013389182,0.00006917983,0.0005671653,0.00027584672],"domain_scores_gemma":[0.96944976,0.029135384,0.000633451,0.00023141396,0.00030110162,0.00024889674],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003435301,0.00013358501,0.0003012572,0.00009430498,0.00017084854,0.00015235439,0.00023667648,0.00008060644,0.0040026433],"category_scores_gemma":[0.12807758,0.000105016894,0.00013967256,0.00020227893,0.00004748872,0.0007299056,0.000048276703,0.0004240646,0.0003141178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049186824,0.00029651978,0.0008088988,0.00010420094,0.00018416664,0.000018878185,0.0031160568,0.00009818142,0.000018970644,0.20037961,0.16570455,0.6287781],"study_design_scores_gemma":[0.0017855963,0.000051911582,0.0013058205,0.00004099772,0.000040722076,0.00015328289,0.00044749063,0.00055320165,0.00009461197,0.9397013,0.05567456,0.00015049668],"about_ca_topic_score_codex":0.0000030887593,"about_ca_topic_score_gemma":9.597348e-7,"teacher_disagreement_score":0.7393217,"about_ca_system_score_codex":0.0000920797,"about_ca_system_score_gemma":0.00007913021,"threshold_uncertainty_score":0.99690783},"labels":[],"label_agreement":null},{"id":"W2035208070","doi":"10.4236/am.2014.51013","title":"A New Maximum Test via the Dependent Samples t-Test and the Wilcoxon Signed-Ranks Test","year":2014,"lang":"en","type":"article","venue":"Applied Mathematics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Bonferroni correction; Wilcoxon signed-rank test; Mathematics; Statistics; Test (biology); Monte Carlo method; Sign test; Mann–Whitney U test","score_opus":0.19623606107558414,"score_gpt":0.41689893239564463,"score_spread":0.2206628713200605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035208070","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070519326,0.000077088196,0.97453046,0.0022205657,0.00022145876,0.0021687574,0.000060165166,0.00023643937,0.019779895],"genre_scores_gemma":[0.07750818,0.00005247779,0.9200063,0.0008474126,0.000673949,0.00024424723,0.0000020544214,0.00012567319,0.0005397241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962345,0.0002661703,0.0015154138,0.000557002,0.0008282721,0.00059864065],"domain_scores_gemma":[0.65089554,0.34678814,0.0006288456,0.0013756355,0.000087324996,0.00022453221],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007299196,0.00051935785,0.0011767958,0.000050225615,0.00039684912,0.00024996695,0.0009775782,0.00028374942,0.00030795913],"category_scores_gemma":[0.14070712,0.00027559552,0.00018013193,0.00027425142,0.0007783866,0.000046761757,0.00045942076,0.0006452182,0.00020533231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056896566,0.0005709256,0.000092012895,0.00045150498,0.000096802265,0.000002837877,0.0011686577,0.00000212785,0.0016775185,0.93134207,0.0057054046,0.058833234],"study_design_scores_gemma":[0.0027569768,0.00014534213,0.00006437069,0.00009920018,0.00047447038,0.00003581087,0.00024781254,0.0019870456,0.0015139132,0.99123204,0.0010771365,0.0003658731],"about_ca_topic_score_codex":0.000020953668,"about_ca_topic_score_gemma":0.000031560947,"teacher_disagreement_score":0.34652197,"about_ca_system_score_codex":0.00004065302,"about_ca_system_score_gemma":0.00006259483,"threshold_uncertainty_score":0.9999696},"labels":[],"label_agreement":null},{"id":"W2035260443","doi":"10.1198/016214501753208546","title":"Multiple Test Procedures for Identifying the Maximum Safe Dose","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pairwise comparison; Monotonic function; Computer science; Multiple comparisons problem; Monte Carlo method; Mathematics; Sequence (biology); Statistics; Reliability engineering; Algorithm; Engineering","score_opus":0.3033497489109927,"score_gpt":0.5236922743536984,"score_spread":0.22034252544270566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035260443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04314935,0.000032042804,0.9436031,0.010384095,0.0012228811,0.0008586997,0.00035921787,0.000029604596,0.0003609946],"genre_scores_gemma":[0.35689342,0.000057603927,0.640642,0.0009481191,0.0009537799,0.000029285913,9.3315083e-7,0.000037895934,0.00043694777],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99628913,0.000925969,0.0013267052,0.00017485487,0.0009084924,0.00037485597],"domain_scores_gemma":[0.8025315,0.19303608,0.0033949013,0.00028173623,0.00063104625,0.00012473649],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00560262,0.00017090852,0.00068061176,0.000047994337,0.00028340594,0.000115713854,0.00055748574,0.0000697563,0.00006274501],"category_scores_gemma":[0.55463207,0.000091484384,0.00030342935,0.0003958629,0.00024292087,0.000089540816,0.00009016028,0.00048515934,0.000010602837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036874935,0.002928751,0.26102087,0.0005014798,0.0019472691,0.00006763757,0.001284437,0.000101015394,0.0054562786,0.1295376,0.3448339,0.24863327],"study_design_scores_gemma":[0.0011085897,0.000351645,0.094919555,0.000079997866,0.00039666012,0.00003070639,0.0002574559,0.00071775255,0.00014321013,0.89955616,0.0022980247,0.0001402321],"about_ca_topic_score_codex":0.000018961942,"about_ca_topic_score_gemma":0.000029862435,"teacher_disagreement_score":0.7700186,"about_ca_system_score_codex":0.00037032712,"about_ca_system_score_gemma":0.00015260495,"threshold_uncertainty_score":0.44911945},"labels":[],"label_agreement":null},{"id":"W2035324238","doi":"10.1177/1740774512469312","title":"Central statistical monitoring: Detecting fraud in clinical trials","year":2013,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"Canadian Institutes of Health Research; British Heart Foundation; Medical Research Council; Australian Government","keywords":"Medicine; Clinical trial; Multicenter study; Risk assessment; Statistics; Cutoff; Missing data; Statistical model; Computer science; Data mining; Randomized controlled trial; Internal medicine; Mathematics","score_opus":0.9255815327318341,"score_gpt":0.7339168505663992,"score_spread":0.19166468216543486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035324238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41492704,0.00042696876,0.514247,0.0035299745,0.046350673,0.014276939,0.0005590525,0.0010829597,0.0045993826],"genre_scores_gemma":[0.2621369,0.00047117224,0.7217322,0.0005482969,0.014127714,0.0004919837,0.000006219561,0.00017746039,0.0003080442],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75443375,0.18892457,0.048992727,0.0030088515,0.0019234467,0.0027166465],"domain_scores_gemma":[0.03129462,0.9578483,0.00623011,0.002018574,0.0005248141,0.0020835525],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.41966522,0.0008520088,0.01183752,0.0002622334,0.00018024318,0.0003901251,0.00123616,0.0021353513,0.005753752],"category_scores_gemma":[0.979388,0.00064919156,0.0029253913,0.0006956147,0.0010142236,0.00029616882,0.00050689257,0.0038842862,0.0010284894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016460438,0.002795413,0.11252406,0.00020361219,0.0007543957,0.00013593023,0.00008145305,0.000005129828,0.00015545872,0.040772595,0.022164434,0.81876147],"study_design_scores_gemma":[0.010824888,0.0008913197,0.090126954,0.000410163,0.0006047466,0.000005939297,0.00017476386,0.0007278666,0.00032342275,0.89337337,0.0017322525,0.0008043075],"about_ca_topic_score_codex":0.00009051193,"about_ca_topic_score_gemma":0.00000960968,"teacher_disagreement_score":0.85260075,"about_ca_system_score_codex":0.0001684415,"about_ca_system_score_gemma":0.00046434344,"threshold_uncertainty_score":0.9997493},"labels":[],"label_agreement":null},{"id":"W2036036016","doi":"10.1002/sim.1014","title":"Selection effects in randomized trials with count data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Count data; Selection (genetic algorithm); Selection bias; Sample size determination; Statistics; Clinical trial; Econometrics; Computer science; Population; Sample (material); Medicine; Mathematics; Internal medicine; Artificial intelligence","score_opus":0.6251665613778234,"score_gpt":0.5981809771304896,"score_spread":0.026985584247333883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036036016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005186047,0.00023849783,0.9926437,0.00072282756,0.0007685649,0.0023248324,0.0002517779,0.000055545333,0.002475659],"genre_scores_gemma":[0.014258414,0.00041615652,0.9841069,0.00030574124,0.00047278637,0.00014705375,0.000029502713,0.00004593853,0.00021751174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98802036,0.0074006743,0.0027237472,0.0006073599,0.0008318195,0.00041601597],"domain_scores_gemma":[0.6571437,0.34149277,0.0005499589,0.0006012167,0.00010843151,0.000103905746],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041726157,0.00027750028,0.0036837123,0.000266453,0.000036113852,0.000017572598,0.00041212022,0.00015794403,0.0014893584],"category_scores_gemma":[0.7270354,0.00017499819,0.00003871095,0.0006091167,0.0005596824,0.00006388569,0.00008490997,0.00059063465,0.000022472615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02747482,0.00075230363,0.00092980504,0.0012073928,0.000329548,0.00047527402,0.0009689398,0.000017950226,0.0000717389,0.80526096,0.098663345,0.063847944],"study_design_scores_gemma":[0.14344306,0.00034521078,0.00020589025,0.0008189803,0.00038395938,0.000009296461,0.000037869268,0.0325002,0.000018100636,0.82179517,0.00025109897,0.00019115927],"about_ca_topic_score_codex":0.00013200431,"about_ca_topic_score_gemma":0.00029371673,"teacher_disagreement_score":0.68530923,"about_ca_system_score_codex":0.00011263498,"about_ca_system_score_gemma":0.000040564093,"threshold_uncertainty_score":0.99942344},"labels":[],"label_agreement":null},{"id":"W2036536239","doi":"10.1177/0962280213480576","title":"An adaptive clinical trials procedure for a sensitive subgroup examined in the multiple sclerosis context","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"University of British Columbia","keywords":"Context (archaeology); Multiple sclerosis; Biomarker; Medicine; Clinical trial; Subgroup analysis; Oncology; Statistical power; Internal medicine; Outcome (game theory); Statistics; Meta-analysis; Immunology; Mathematics","score_opus":0.9252194452879065,"score_gpt":0.7518419097395197,"score_spread":0.17337753554838675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036536239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008650542,0.000071491995,0.9765431,0.0040533547,0.00054972083,0.008905694,0.00041809637,0.00006749361,0.0007404562],"genre_scores_gemma":[0.18661493,0.00008825471,0.8074244,0.0011787058,0.0007870584,0.0037659241,0.000013870081,0.00008278321,0.000044040135],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76078594,0.22284827,0.0072129425,0.002126001,0.004573914,0.0024529323],"domain_scores_gemma":[0.051490314,0.94392973,0.000519397,0.001284971,0.0013600253,0.0014155791],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42447096,0.0005199531,0.0032758552,0.00046102956,0.00026132842,0.00023269224,0.0017697742,0.0012768201,0.002269217],"category_scores_gemma":[0.9691238,0.00032813952,0.00037965257,0.001548517,0.0034197366,0.0001964018,0.00035419487,0.0049077827,0.000081475206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00215964,0.0017350498,0.00047875728,0.00018250756,0.00007218963,0.00009366578,0.0006428978,3.1134377e-7,0.00019526327,0.3287201,0.005873401,0.6598462],"study_design_scores_gemma":[0.005922207,0.002685414,0.021611953,0.0005262938,0.000064169246,0.0000090773365,0.0045400606,0.053698406,0.00022452594,0.9100258,0.0003070672,0.0003850455],"about_ca_topic_score_codex":0.0005719239,"about_ca_topic_score_gemma":0.00054378016,"teacher_disagreement_score":0.72108144,"about_ca_system_score_codex":0.00023380945,"about_ca_system_score_gemma":0.00089113065,"threshold_uncertainty_score":0.9999171},"labels":[],"label_agreement":null},{"id":"W2036548314","doi":"10.5539/ijsp.v1n2p43","title":"On the Existence of Constant Accrual Rates in Clinical Trials and Direction for Future Research","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Center for Research Resources; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Georgia Clinical and Translational Science Alliance","keywords":"Accrual; Constant (computer programming); Econometrics; Point (geometry); Computer science; Mathematics; Economics; Accounting","score_opus":0.8093774077781707,"score_gpt":0.6841256012407814,"score_spread":0.12525180653738932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036548314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7849014,0.0005910412,0.2017687,0.005040385,0.0041850843,0.0015686689,0.0014957682,0.000005565062,0.00044337971],"genre_scores_gemma":[0.53961885,0.0005007446,0.45909414,0.00005375813,0.00070219743,0.000013670907,7.8807255e-7,0.0000067712676,0.000009067406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9932767,0.0038400746,0.002066237,0.00013218092,0.00053471624,0.00015005618],"domain_scores_gemma":[0.7522128,0.24576612,0.0007865649,0.0001011537,0.0010467988,0.00008653358],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.077621855,0.000083475745,0.00058289466,0.000077560406,0.000043569748,0.000037609556,0.00018014002,0.000096997916,0.00004860683],"category_scores_gemma":[0.40132955,0.00004830042,0.00008368661,0.0000705502,0.000505656,0.00006338092,0.0000611694,0.0004419379,2.4840742e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013988542,0.0003641176,0.009734762,0.000070982634,0.00009307965,0.0000018045722,0.0002121466,3.497738e-7,0.00003645023,0.92437476,0.00090345455,0.06280924],"study_design_scores_gemma":[0.00094883254,0.00043535366,0.022244753,0.00012202422,0.000031987456,0.0000100150655,0.00018703156,0.00013229017,0.00013707143,0.9753473,0.00035681506,0.00004655546],"about_ca_topic_score_codex":0.0000057523434,"about_ca_topic_score_gemma":0.000008374059,"teacher_disagreement_score":0.3237077,"about_ca_system_score_codex":0.000044758883,"about_ca_system_score_gemma":0.00009152803,"threshold_uncertainty_score":0.94978243},"labels":[],"label_agreement":null},{"id":"W2036701577","doi":"10.1348/000711009x475853","title":"Detecting a lack of association: An equivalence testing approach","year":2009,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Association (psychology); Type I and type II errors; Equivalence (formal languages); Sample size determination; Test (biology); Association test; Statistics; Statistical hypothesis testing; Econometrics; Independence (probability theory); Statistical power; Sample (material); Psychology; Computer science; Mathematics","score_opus":0.6273935671893198,"score_gpt":0.5794021805264894,"score_spread":0.047991386662830426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036701577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050041,0.0001287223,0.94175744,0.00028244243,0.00015759014,0.00019707806,0.000062297775,0.00002900707,0.0073444094],"genre_scores_gemma":[0.21469206,0.000034627014,0.7847619,0.00025903594,0.00020294501,0.0000021509486,4.0767253e-7,0.0000161372,0.00003070758],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99528325,0.0011410421,0.002213082,0.00032131936,0.0006260123,0.00041530936],"domain_scores_gemma":[0.9584871,0.039306086,0.0011359315,0.00020630335,0.00051755086,0.00034704703],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073548737,0.00018924473,0.0012455139,0.00008063737,0.000090371424,0.000067428424,0.0003231706,0.00026838318,0.00024923962],"category_scores_gemma":[0.20284313,0.00017614766,0.000114196555,0.00024028774,0.00030360516,0.00012843951,0.0000449117,0.0007477421,0.00000421721],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003153898,0.0027646914,0.00043642038,0.0006081299,0.00015814113,0.00050139474,0.00022776668,0.0000022408651,0.001058298,0.51734704,0.0016880403,0.47489247],"study_design_scores_gemma":[0.0012253802,0.0015315952,0.004767342,0.00033859926,0.00015967102,0.0034263874,0.000067187895,0.0009956433,0.000043924578,0.9872526,0.000014260201,0.00017744167],"about_ca_topic_score_codex":0.0000019254471,"about_ca_topic_score_gemma":3.8010688e-7,"teacher_disagreement_score":0.47471502,"about_ca_system_score_codex":0.000034383756,"about_ca_system_score_gemma":0.000042011063,"threshold_uncertainty_score":0.80387163},"labels":[],"label_agreement":null},{"id":"W2037611498","doi":"10.1111/j.1365-2753.2005.00619.x","title":"Summarizing the probability of wait‐list events*","year":2005,"lang":"en","type":"letter","venue":"Journal of Evaluation in Clinical Practice","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Epidemiology; Sobolev space; Marie curie; Sociology; Library science; Medicine; Mathematics; Computer science","score_opus":0.746332153457936,"score_gpt":0.6720165708617646,"score_spread":0.07431558259617144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037611498","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016937339,0.00045772982,0.012502625,0.9699668,0.00659416,0.0023762502,0.00005540842,0.00001558243,0.0063376855],"genre_scores_gemma":[0.0011981248,0.00046160983,0.81843483,0.16401005,0.0155344615,0.000042856114,0.000004810055,0.0000819816,0.00023128398],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9247147,0.051214114,0.0167757,0.0007300613,0.0060117273,0.00055372255],"domain_scores_gemma":[0.36657533,0.6116685,0.015756486,0.0011901215,0.004690454,0.0001190757],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2356845,0.00037985222,0.0022528588,0.00020545852,0.000076131946,0.000058762038,0.0010562369,0.0015772233,0.0011582868],"category_scores_gemma":[0.9243283,0.00024797514,0.0010705366,0.00048794472,0.00049760396,0.0004844186,0.00021626179,0.0099239675,0.000023385062],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011758878,0.0019109887,0.0011151038,0.00054689683,0.0007581365,0.00012405356,0.00014626833,0.00008344144,0.0000031515058,0.0037388387,0.9272482,0.063149035],"study_design_scores_gemma":[0.0021373392,0.00050850504,0.001129793,0.0007070701,0.0023079768,0.000087514665,0.000059210382,0.0004715006,0.000005553957,0.73962384,0.2527415,0.00022019987],"about_ca_topic_score_codex":0.00001868468,"about_ca_topic_score_gemma":0.000014460896,"teacher_disagreement_score":0.8059568,"about_ca_system_score_codex":0.00042889226,"about_ca_system_score_gemma":0.0012897814,"threshold_uncertainty_score":0.99999726},"labels":[],"label_agreement":null},{"id":"W2037636378","doi":"10.1177/1740774508098413","title":"Optimal sample size determinations from an industry perspective based on the expected value of information","year":2008,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation","funders":"","keywords":"Sample size determination; Bayesian probability; Value of information; Profit (economics); Econometrics; Time horizon; Statistics; Sample (material); Expected utility hypothesis; Expected value; Robustness (evolution); Actuarial science; Computer science; Economics; Mathematics; Microeconomics; Mathematical optimization; Artificial intelligence","score_opus":0.7750729232342143,"score_gpt":0.6449265610705023,"score_spread":0.130146362163712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037636378","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7301983,0.000007694994,0.25754094,0.0035004325,0.0015909575,0.0023383861,0.0022497808,0.00020449501,0.0023690106],"genre_scores_gemma":[0.3632128,0.000009963705,0.6347357,0.0011078041,0.00079606776,0.000087544584,0.00000918331,0.000023376577,0.000017536244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9797942,0.014304161,0.004476505,0.00041749422,0.00073312013,0.00027454534],"domain_scores_gemma":[0.21244559,0.7834963,0.0020232797,0.0011448711,0.00062682806,0.00026313472],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025742456,0.0002585478,0.0016896654,0.00008227416,0.00020115357,0.000043924323,0.0005849958,0.00084046205,0.0020429823],"category_scores_gemma":[0.9292617,0.00016965732,0.00063660246,0.00036533477,0.0006992233,0.00020663391,0.000086966844,0.0011633037,0.00004161594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009618251,0.009384344,0.009697063,0.00010535843,0.0013097146,0.000040837655,0.005208985,0.0016071378,0.0003457208,0.90758365,0.020554122,0.034544785],"study_design_scores_gemma":[0.0046427106,0.0011674723,0.01703243,0.000117220945,0.00032286023,0.0000012003479,0.0010319708,0.0116064325,0.0013982565,0.9621604,0.0002108686,0.00030819623],"about_ca_topic_score_codex":0.00008282694,"about_ca_topic_score_gemma":0.0000023254606,"teacher_disagreement_score":0.9035193,"about_ca_system_score_codex":0.00007577852,"about_ca_system_score_gemma":0.0003418649,"threshold_uncertainty_score":0.9988693},"labels":[],"label_agreement":null},{"id":"W2038387558","doi":"10.5414/cpp43485","title":"The bioequivalence of highly variable drugs and drug products","year":2005,"lang":"en","type":"review","venue":"International Journal of Clinical Pharmacology and Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Bioequivalence; Cmax; Confidence interval; Statistics; Mathematics; Replicate; Population; Pharmacology; Drug; Pharmacokinetics; Geometric mean; Medicine; Econometrics","score_opus":0.5790763290199263,"score_gpt":0.6584686201810384,"score_spread":0.07939229116111202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038387558","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000097695105,0.98600507,0.0011848878,0.0029321285,0.009056793,0.00040375208,0.000077055236,0.000009506167,0.00023309978],"genre_scores_gemma":[0.000079032114,0.917527,0.077747285,0.000558878,0.0038401186,0.0000066522407,6.829957e-7,0.000030193869,0.00021012648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917728,0.002795677,0.0043538366,0.00029895172,0.0005574938,0.00022129901],"domain_scores_gemma":[0.8683439,0.12645446,0.0039312057,0.00019480825,0.0009382105,0.00013745225],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013141359,0.00029754892,0.002274392,0.00011336393,0.00007781734,0.00004553356,0.001019118,0.0003917353,0.00006326366],"category_scores_gemma":[0.016399104,0.00017204684,0.00041334255,0.0001326513,0.001205033,0.00008423638,0.00027392377,0.001495869,0.0000030945444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030292763,0.00030610876,0.000013244326,0.00079906965,0.002722391,0.000015965306,0.00004277333,1.5483359e-7,0.0000029588496,0.02529117,0.00201031,0.9684929],"study_design_scores_gemma":[0.0010167337,0.00017569585,0.000005284047,0.0011797354,0.0026010245,0.00009223662,0.0000112654025,0.000011276391,0.000011174952,0.20306031,0.79170257,0.00013268288],"about_ca_topic_score_codex":8.156529e-7,"about_ca_topic_score_gemma":2.4051064e-7,"teacher_disagreement_score":0.96836025,"about_ca_system_score_codex":0.000032200252,"about_ca_system_score_gemma":0.0005139959,"threshold_uncertainty_score":0.9918862},"labels":[],"label_agreement":null},{"id":"W2039114218","doi":"10.1016/j.jclinepi.2008.09.017","title":"Uncertainty in the minimum event risk to justify treatment was evaluated","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Event (particle physics); Medicine; Confidence interval; Intervention (counseling); Adverse effect; Computer science; Statistics; Mathematics; Internal medicine","score_opus":0.8411022187661521,"score_gpt":0.7152376648877102,"score_spread":0.12586455387844186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039114218","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.772109,0.0002930611,0.09306616,0.1283061,0.0038394344,0.0013578401,0.000046948215,0.000030864496,0.0009506175],"genre_scores_gemma":[0.4819973,0.0011847221,0.50147575,0.012760105,0.0024546066,0.000017385708,8.2476646e-7,0.000020687376,0.000088629226],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9278708,0.05740718,0.012906766,0.0005242062,0.0005689069,0.00072215527],"domain_scores_gemma":[0.40262845,0.5917767,0.004160149,0.0006776484,0.00030659873,0.00045040558],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17207013,0.00030789923,0.0044839405,0.00014436159,0.00006697319,0.000011390853,0.00082044513,0.0005685283,0.00019782741],"category_scores_gemma":[0.8801907,0.0001558471,0.0012709539,0.0003475919,0.00024435137,0.00004020228,0.000051167677,0.0016072142,0.000058498637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066260668,0.0058189286,0.03412032,0.00003906574,0.00062540197,0.00037359115,0.00069659494,0.007203818,0.00001933825,0.11928102,0.05464314,0.7705527],"study_design_scores_gemma":[0.0031560934,0.007844105,0.11754551,0.000114635186,0.00040446882,0.00004853278,0.00009656139,0.0023570985,0.0000037263333,0.8626383,0.005640952,0.00015004762],"about_ca_topic_score_codex":0.000034917528,"about_ca_topic_score_gemma":0.00003301499,"teacher_disagreement_score":0.77040267,"about_ca_system_score_codex":0.00015744797,"about_ca_system_score_gemma":0.000275167,"threshold_uncertainty_score":0.85252804},"labels":[],"label_agreement":null},{"id":"W2039658745","doi":"10.1177/1740774510368301","title":"Trends in the application of dynamic allocation methods in multi-arm cancer clinical trials","year":2010,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; London Health Sciences Centre; McMaster University","funders":"","keywords":"Clinical trial; Medicine; Internal medicine","score_opus":0.9049874966009664,"score_gpt":0.7889799673320202,"score_spread":0.1160075292689462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039658745","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07195098,0.00027908475,0.90456754,0.0062702657,0.009479264,0.0061653396,0.00032674617,0.00013860941,0.00082213955],"genre_scores_gemma":[0.15478848,0.0005156786,0.8417144,0.0005749208,0.0013102642,0.00090371765,0.000014905294,0.00006368581,0.00011397271],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6730031,0.27320483,0.048247486,0.002736235,0.0015730233,0.0012353619],"domain_scores_gemma":[0.13394107,0.85568815,0.007352823,0.002330936,0.0003716945,0.00031529317],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5943893,0.00044573622,0.0065743383,0.00041390234,0.00005914222,0.000057394143,0.0013863975,0.0015797481,0.0007090577],"category_scores_gemma":[0.88196534,0.00028649936,0.001921443,0.001420329,0.0008679511,0.00010793806,0.00017910091,0.0028484743,0.00002657666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089733937,0.0032808725,0.006887821,0.00007057163,0.0001569614,0.000003322769,0.000121589364,0.0000050152794,0.0019421596,0.032254063,0.000634016,0.95374626],"study_design_scores_gemma":[0.016683899,0.00055521436,0.103607535,0.0001909488,0.0008975397,0.0000025187237,0.00015574749,0.016533837,0.0005650284,0.85679054,0.0034377573,0.00057941437],"about_ca_topic_score_codex":0.00015461307,"about_ca_topic_score_gemma":0.001017698,"teacher_disagreement_score":0.95316684,"about_ca_system_score_codex":0.000063699226,"about_ca_system_score_gemma":0.00027889566,"threshold_uncertainty_score":0.9999587},"labels":[],"label_agreement":null},{"id":"W2040188371","doi":"10.1080/03610918.2011.552824","title":"Interval Estimation for the Difference of Two Independent Variances","year":2011,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Health and Medical Research Council; Stony Brook University","keywords":"Mathematics; Statistics; Kurtosis; Interval estimation; Confidence interval; Sample size determination; Interval (graph theory); Estimation; Combinatorics","score_opus":0.7899799295406142,"score_gpt":0.6385617845523684,"score_spread":0.1514181449882458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040188371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028949336,0.0000554046,0.9956662,0.00008318386,0.00014469039,0.0006961759,0.00012294608,0.000024744762,0.00031173226],"genre_scores_gemma":[0.49942303,0.000023041437,0.50045246,0.000018107165,0.000007879947,0.000049248523,0.000011869165,0.0000069003254,0.000007457733],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981735,0.0004992738,0.00087915227,0.00016711392,0.00017262035,0.000108341024],"domain_scores_gemma":[0.9447473,0.054031394,0.00043261712,0.00047372453,0.00028330393,0.000031657124],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015421828,0.00011043842,0.00026384337,0.00009241918,0.000146993,0.000029207493,0.0003496341,0.00005937426,0.000021479007],"category_scores_gemma":[0.012080214,0.00009068161,0.000033134536,0.00019229598,0.00028315745,0.00006837507,0.00014251827,0.00015400884,0.0000011648784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007405916,0.00019284648,0.0012106964,0.00007146758,0.000029157625,1.3473894e-7,0.0014215227,0.011889999,0.000009998334,0.74827135,0.000017794564,0.23681098],"study_design_scores_gemma":[0.0004575501,0.000043853113,0.015135696,0.00003221772,0.00003851339,3.0054886e-7,0.00006671004,0.49185702,0.000015313703,0.4922994,0.000004792657,0.000048614642],"about_ca_topic_score_codex":0.000057893143,"about_ca_topic_score_gemma":0.00008727855,"teacher_disagreement_score":0.4965281,"about_ca_system_score_codex":0.000029812752,"about_ca_system_score_gemma":0.000034045996,"threshold_uncertainty_score":0.99624145},"labels":[],"label_agreement":null},{"id":"W2040312310","doi":"10.1002/bimj.200800233","title":"Response Adaptive Designs with a Variance‐penalized Criterion","year":2009,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Memorial University of Newfoundland","funders":"","keywords":"Adaptive design; Variance (accounting); Mathematics; Statistics; Optimal design; Mathematical optimization; Computer science; Clinical trial; Medicine","score_opus":0.6829663816665612,"score_gpt":0.5744816967948589,"score_spread":0.10848468487170226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040312310","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010371354,0.00011087381,0.9857567,0.0022744946,0.00032233857,0.00028944216,0.000020140911,0.00008159413,0.00077308726],"genre_scores_gemma":[0.11557842,0.000029897843,0.8830003,0.0007458471,0.0003973176,0.000005447124,2.0170091e-7,0.000024960978,0.00021761392],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99424577,0.0029339003,0.0010118808,0.00034158697,0.00095599686,0.0005108468],"domain_scores_gemma":[0.95215434,0.046140764,0.00046120654,0.0003234117,0.000374643,0.0005456372],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008333539,0.0002522493,0.0007455851,0.00088747626,0.00019530352,0.00019248904,0.0003997743,0.00021116469,0.0006243325],"category_scores_gemma":[0.130693,0.00016450549,0.00019959954,0.0030777869,0.00015928994,0.00014475394,0.000039326245,0.0006461342,0.000049093484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13029626,0.004762924,0.00029426935,0.00005178951,0.00082862383,0.004615685,0.0005126181,0.000006488127,0.037178773,0.18705025,0.049951542,0.5844508],"study_design_scores_gemma":[0.004526571,0.006721955,0.0064542145,0.00018224891,0.00017188441,0.0008342548,0.000041937346,0.0001951656,0.0013011567,0.97623897,0.002936215,0.00039541037],"about_ca_topic_score_codex":0.000001061894,"about_ca_topic_score_gemma":8.614753e-8,"teacher_disagreement_score":0.78918874,"about_ca_system_score_codex":0.00019274458,"about_ca_system_score_gemma":0.00018196917,"threshold_uncertainty_score":0.87662953},"labels":[],"label_agreement":null},{"id":"W2040330324","doi":"10.1002/sim.4486","title":"Optimal allocation of participants for the estimation of selection, preference and treatment effects in the two‐stage randomised trial design","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Preference; Selection (genetic algorithm); Randomized controlled trial; Sample size determination; Treatment and control groups; Treatment effect; Clinical trial; Medicine; Statistics; Mathematics; Computer science; Internal medicine","score_opus":0.5865424133203638,"score_gpt":0.5720278292840314,"score_spread":0.014514584036332434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040330324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03763472,0.00008524211,0.9579216,0.000116560484,0.00023583903,0.003935093,0.00004319194,0.0000049659834,0.000022756383],"genre_scores_gemma":[0.4581502,0.000044460154,0.5412119,0.000014423988,0.00008657244,0.00047294187,0.000002854277,0.000007089656,0.000009575392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99680823,0.0015626447,0.0009899647,0.00013451205,0.00028388025,0.00022078096],"domain_scores_gemma":[0.8314808,0.16788512,0.00034855903,0.00016828746,0.00008031556,0.000036900557],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009890106,0.00012560815,0.00057597883,0.00006179747,0.0000379469,0.00000456682,0.00011089456,0.0000566418,0.000025938441],"category_scores_gemma":[0.13589546,0.000064290354,0.000023181476,0.00018259569,0.000268288,0.000031418003,0.000011513077,0.00010261707,2.2864388e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11418138,0.0020275158,0.0013873052,0.00133985,0.00030846937,0.0000024989067,0.015573524,0.0070446953,0.00090591353,0.7264287,0.0009496802,0.12985048],"study_design_scores_gemma":[0.2100211,0.0045614676,0.0051896833,0.00033917656,0.00083748624,0.0000012778122,0.0004941357,0.21611862,0.002813692,0.5594702,0.000013111306,0.00014004913],"about_ca_topic_score_codex":0.00006949833,"about_ca_topic_score_gemma":0.000030920874,"teacher_disagreement_score":0.42051548,"about_ca_system_score_codex":0.000043931865,"about_ca_system_score_gemma":0.000051853447,"threshold_uncertainty_score":0.87138325},"labels":[],"label_agreement":null},{"id":"W2040991114","doi":"10.1037/a0017737","title":"Testing multiple outcomes in repeated measures designs.","year":2010,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Canadian Institutes of Health Research; Manitoba Health Research Council","keywords":"Bonferroni correction; Multiple comparisons problem; Type I and type II errors; Statistics; Statistical power; Permutation (music); Monte Carlo method; Mathematics; Outcome (game theory); Variable (mathematics); Statistical hypothesis testing; Repeated measures design; Computer science","score_opus":0.8871628882891909,"score_gpt":0.695675757748921,"score_spread":0.1914871305402699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040991114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23679656,0.000014951533,0.7484806,0.00043215454,0.002014949,0.00077010726,0.000013227229,0.00046027754,0.011017137],"genre_scores_gemma":[0.13614382,0.0000021915382,0.86303675,0.000403986,0.00016170317,0.00012123603,3.5828074e-7,0.000040328785,0.000089645364],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9909475,0.0056214933,0.0015259075,0.0008765792,0.00039293154,0.0006355746],"domain_scores_gemma":[0.76781654,0.23050685,0.0003227081,0.0009273684,0.00016816508,0.0002583422],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021954468,0.0003471878,0.0011759442,0.00014027834,0.00008924834,0.00005350847,0.0006302576,0.0006050398,0.00057962694],"category_scores_gemma":[0.7586523,0.00023952386,0.00020957628,0.00069487194,0.00033403825,0.0000580514,0.00014111829,0.0015617388,0.000048399706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020978248,0.0014157537,0.13758561,0.000032683714,0.000051342657,0.00007605069,0.000072618255,0.0000015932296,0.13295756,0.027750133,0.00032641878,0.69952047],"study_design_scores_gemma":[0.0011773857,0.0001947154,0.18683285,0.000023619748,0.000029313638,0.0000152155835,0.000013300533,0.00026088726,0.0030266535,0.8078861,0.00024788213,0.0002920512],"about_ca_topic_score_codex":0.000018355,"about_ca_topic_score_gemma":0.000012779107,"teacher_disagreement_score":0.780136,"about_ca_system_score_codex":0.000025770132,"about_ca_system_score_gemma":0.00001541619,"threshold_uncertainty_score":0.97674996},"labels":[],"label_agreement":null},{"id":"W2042003034","doi":"10.1037/a0025810","title":"Many tests of significance: New methods for controlling type I errors.","year":2011,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Multiple comparisons problem; Control (management); Computer science; Mathematics; Statistics; False discovery rate; Artificial intelligence","score_opus":0.8514252015725781,"score_gpt":0.7047830235817717,"score_spread":0.14664217799080637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042003034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011177775,0.0002858948,0.98372865,0.00014795459,0.0022284791,0.0014237679,0.000024074832,0.00019120506,0.010852195],"genre_scores_gemma":[0.0021159016,0.000046376725,0.9961085,0.00042772284,0.00041203303,0.00014392106,8.442401e-7,0.00006932189,0.00067537813],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99035716,0.005887685,0.0019578296,0.0008972952,0.00025333712,0.0006466775],"domain_scores_gemma":[0.866086,0.13142188,0.0007961415,0.00094896415,0.0003605051,0.00038652506],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021005796,0.00039688873,0.0018206182,0.00011477494,0.000077671284,0.000018241513,0.00080556964,0.0005889914,0.0018985223],"category_scores_gemma":[0.28623438,0.00029065288,0.0004995556,0.00056979794,0.0004063963,0.000057469628,0.000115275376,0.0005260089,0.000020609847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017543568,0.000748754,0.00014847577,0.00013367283,0.00017280594,0.0000040569244,0.00019753778,6.4664437e-7,0.027907142,0.3135695,0.001739751,0.65362334],"study_design_scores_gemma":[0.002012898,0.0015762842,0.0017832353,0.00005641779,0.00027079633,0.000006008866,0.00003957027,0.00026920944,0.017872458,0.97311485,0.0026504367,0.00034785407],"about_ca_topic_score_codex":0.0000130482895,"about_ca_topic_score_gemma":4.7419002e-7,"teacher_disagreement_score":0.65954536,"about_ca_system_score_codex":0.000027520557,"about_ca_system_score_gemma":0.000055553737,"threshold_uncertainty_score":0.9999546},"labels":[],"label_agreement":null},{"id":"W2042225280","doi":"10.1016/j.jclinepi.2010.05.009","title":"Aggregating single patient (n-of-1) trials in populations where recruitment and retention was difficult: The case of palliative care","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":84,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Medicine; Clinical trial; Sample size determination; Psychological intervention; Population; Intervention (counseling); Palliative care; Research design; Gold standard (test); Consolidated Standards of Reporting Trials; N of 1 trial; Statistics; Surgery; Internal medicine; Nursing; Environmental health","score_opus":0.9581004386805326,"score_gpt":0.7348378265606642,"score_spread":0.22326261211986842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042225280","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005639499,0.97988075,0.007325975,0.0005986375,0.0034043093,0.0028124978,0.0002717402,0.0000070471733,0.000059555685],"genre_scores_gemma":[0.000360025,0.6435103,0.35547838,0.00004186633,0.0005310271,0.000040531137,0.0000040549075,0.000029276696,0.000004564191],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8654653,0.094308846,0.0389001,0.0005638181,0.0003506969,0.00041127144],"domain_scores_gemma":[0.25150156,0.7030457,0.04385502,0.0005715547,0.000831669,0.0001944645],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.121984266,0.0004234903,0.018338548,0.00019712825,0.0000659501,0.000009254647,0.00038903463,0.0015926776,0.00005298512],"category_scores_gemma":[0.92858595,0.00021828963,0.0028920674,0.00032168778,0.00071765314,0.000043624954,0.00020111905,0.0030621395,8.840694e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012915916,0.00035009024,0.00072574115,0.005338521,0.00033035735,0.00010798729,0.00021153674,0.000003557703,5.4567e-7,0.012078591,0.00022447213,0.98049945],"study_design_scores_gemma":[0.0029116871,0.004146638,0.00079371524,0.057976294,0.006989342,0.00045687557,0.0007854972,0.000078575096,0.0000028627646,0.86288744,0.06247452,0.00049655244],"about_ca_topic_score_codex":0.00004907109,"about_ca_topic_score_gemma":0.00020667768,"teacher_disagreement_score":0.9800029,"about_ca_system_score_codex":0.00009782119,"about_ca_system_score_gemma":0.00033113998,"threshold_uncertainty_score":0.99970347},"labels":[],"label_agreement":null},{"id":"W2042319973","doi":"10.1002/pst.443","title":"On assessing the presence of evaluation‐time bias in progression‐free survival in randomized trials","year":2010,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Randomized controlled trial; Computer science; Test (biology); Log-rank test; Randomized experiment; Progression-free survival; Statistics; Econometrics; Overall survival; Survival analysis; Medical physics; Medicine; Oncology; Mathematics; Internal medicine","score_opus":0.7951823931859413,"score_gpt":0.6931044078284545,"score_spread":0.1020779853574868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042319973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17779215,0.00026012867,0.7785403,0.0053504845,0.0069778403,0.01784914,0.0017224479,0.0001791767,0.011328334],"genre_scores_gemma":[0.29913732,0.0000406067,0.6999807,0.00014562906,0.00022656798,0.0003756092,0.000007167492,0.00004655996,0.000039832237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9601973,0.03132057,0.0046239374,0.00063134066,0.0025479055,0.0006789388],"domain_scores_gemma":[0.37889385,0.61894983,0.0009234143,0.00069591036,0.00036143692,0.00017556973],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13138388,0.0003142049,0.0025338796,0.00016629064,0.00007550101,0.00009401798,0.0006438875,0.00023427875,0.0023130036],"category_scores_gemma":[0.9009176,0.00018939546,0.00022792659,0.0005426999,0.0010259817,0.00008533974,0.00023398551,0.0014394823,0.00002843375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012166324,0.0013026465,0.0006157302,0.00021919556,0.00012264351,0.000037753787,0.00021418954,0.00007227167,0.0014537188,0.8917318,0.0019757925,0.09008792],"study_design_scores_gemma":[0.05567032,0.000048562182,0.0005783744,0.00016962721,0.00031124233,0.0000017829238,0.000016376835,0.11085637,0.001538857,0.83057266,0.000054186035,0.00018163478],"about_ca_topic_score_codex":0.000020660711,"about_ca_topic_score_gemma":0.000027629207,"teacher_disagreement_score":0.7695337,"about_ca_system_score_codex":0.000066122644,"about_ca_system_score_gemma":0.0002725744,"threshold_uncertainty_score":0.998599},"labels":[],"label_agreement":null},{"id":"W2042378780","doi":"10.1186/1745-6215-10-27","title":"Design, analysis, and presentation of crossover trials","year":2009,"lang":"en","type":"review","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Simon Fraser University","funders":"","keywords":"Sample size determination; Crossover study; Medicine; Crossover; Clinical trial; Randomized controlled trial; Research design; MEDLINE; Drug trial; Clinical study design; Medical physics; Alternative medicine; Statistics; Internal medicine; Computer science; Pathology","score_opus":0.9412843850960871,"score_gpt":0.7413113448083124,"score_spread":0.19997304028777474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042378780","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.946206e-7,0.68771064,0.30667686,0.000011759522,0.0003442795,0.004624931,0.00040383943,0.00004180153,0.00018556723],"genre_scores_gemma":[2.2420923e-7,0.59267557,0.40649772,0.000010274488,0.0004423149,0.00012605682,0.000014981403,0.000034309942,0.00019856154],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9320394,0.053003523,0.012907181,0.00084926625,0.00082003325,0.00038064635],"domain_scores_gemma":[0.46820724,0.52217555,0.008446282,0.00082887826,0.00018619996,0.00015585127],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11902371,0.0006031622,0.024042431,0.00060433376,0.000053997417,0.00011921839,0.0004213574,0.00089629804,0.0008979549],"category_scores_gemma":[0.7056667,0.00039327063,0.0030912168,0.0012072081,0.0001943197,0.00006560372,0.00009634906,0.00037945167,0.000020017453],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025847775,0.00012739286,3.9443566e-7,0.0065464983,0.0051849894,0.000004335746,0.000023785238,6.9318526e-7,0.0000029323446,0.008759883,0.002062255,0.97702837],"study_design_scores_gemma":[0.0022399125,0.00021882706,0.0000035339801,0.0045233825,0.10196352,0.0000031179607,0.0000036745896,0.000008406782,0.00009641207,0.80739063,0.08306613,0.00048245565],"about_ca_topic_score_codex":0.000010889158,"about_ca_topic_score_gemma":0.000001067195,"teacher_disagreement_score":0.97654593,"about_ca_system_score_codex":0.000051139104,"about_ca_system_score_gemma":0.00025444964,"threshold_uncertainty_score":0.99985194},"labels":[],"label_agreement":null},{"id":"W2042803707","doi":"10.1016/j.jclinepi.2007.07.016","title":"Early stopping of randomized clinical trials for overt efficacy is problematic","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Medical Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Interim; Early stopping; Randomized controlled trial; Medicine; Clinical trial; Continuation; Value (mathematics); Psychology; Statistics; Surgery; Computer science; Internal medicine; Political science; Mathematics; Law","score_opus":0.963934586630097,"score_gpt":0.7795635393828945,"score_spread":0.18437104724720255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042803707","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002139534,0.6702763,0.31413242,0.0009336229,0.007410335,0.0068416013,0.00019869317,0.00003061171,0.00015505854],"genre_scores_gemma":[0.0000014111537,0.5460726,0.44883034,0.00051719893,0.0042666,0.00010844005,0.0000028952543,0.00010511843,0.00009538569],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.30308783,0.49084848,0.20126371,0.0018387692,0.0014218617,0.0015393535],"domain_scores_gemma":[0.024681605,0.8570171,0.11421407,0.0014648046,0.0016477159,0.00097470713],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.71168005,0.0012354929,0.14248423,0.0005452954,0.000098875724,0.000020797499,0.0021128294,0.0051066605,0.00033191164],"category_scores_gemma":[0.9957683,0.00071207306,0.051658355,0.00043878204,0.0028708577,0.000110454246,0.00034227813,0.0057865637,0.00003912541],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.024808617,0.0015121293,0.000046489935,0.019875143,0.010028985,0.000030924286,0.000033753073,9.856021e-7,2.9889485e-8,0.038898118,0.032505743,0.8722591],"study_design_scores_gemma":[0.08905655,0.001991956,0.00002519243,0.027665671,0.014934036,0.00015718698,0.0000031979496,0.00009459011,1.2009987e-7,0.67508525,0.19049455,0.0004917021],"about_ca_topic_score_codex":0.000004255064,"about_ca_topic_score_gemma":2.392182e-7,"teacher_disagreement_score":0.8717674,"about_ca_system_score_codex":0.00009119835,"about_ca_system_score_gemma":0.002384023,"threshold_uncertainty_score":0.99984276},"labels":[],"label_agreement":null},{"id":"W2042805913","doi":"10.1136/bmj.39136.682083.ae","title":"Problems with use of composite end points in cardiovascular trials: systematic review of randomised controlled trials","year":2007,"lang":"en","type":"review","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":456,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Canadian College of Naturopathic Medicine; Western University; McMaster University","funders":"Canadian Institutes of Health Research; Mayo Foundation for Medical Education and Research","keywords":"Medicine; End point; Randomized controlled trial; Relative risk; Clinical trial; Clinical endpoint; Internal medicine; Confidence interval; Mathematics","score_opus":0.7630812926026873,"score_gpt":0.6042377862803687,"score_spread":0.15884350632231858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042805913","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8068758e-7,0.8830435,0.030586721,0.000018222863,0.00033123425,0.085346006,0.0003696768,0.000030699655,0.00027371824],"genre_scores_gemma":[1.3411824e-7,0.7385631,0.25712693,0.000033354532,0.00018151084,0.003917456,0.000014694486,0.00010361803,0.00005918387],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8078439,0.14503583,0.043076582,0.0009414972,0.0025180427,0.0005841406],"domain_scores_gemma":[0.36129466,0.6138863,0.02175382,0.0022329332,0.0006648492,0.00016742427],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.4148709,0.0010141345,0.116446435,0.0005540444,0.000022981776,0.000040147657,0.0006475005,0.0007690542,0.00018196898],"category_scores_gemma":[0.88566136,0.0005163375,0.013428551,0.00092865253,0.00025496326,0.000065835695,0.00011539613,0.00066990475,0.000012024006],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031483376,0.00027584247,1.6037913e-7,0.94580555,0.017751044,0.00004194452,0.000016060432,0.000001376871,2.7589186e-7,0.0011468678,0.00031232028,0.031500217],"study_design_scores_gemma":[0.06113948,0.00015130233,7.129068e-8,0.82777977,0.0986993,0.00003546726,0.0000032093328,0.000005440244,0.0000031419404,0.0062759407,0.0054837484,0.0004230999],"about_ca_topic_score_codex":0.000020874471,"about_ca_topic_score_gemma":0.0000022714617,"teacher_disagreement_score":0.47079045,"about_ca_system_score_codex":0.00013480528,"about_ca_system_score_gemma":0.0005417927,"threshold_uncertainty_score":0.9997288},"labels":[],"label_agreement":null},{"id":"W2043211096","doi":"10.1080/10503300902926554","title":"Evaluating clinical significance through equivalence testing: Extending the normative comparisons approach","year":2009,"lang":"en","type":"article","venue":"Psychotherapy Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University; York University","funders":"","keywords":"Normative; Equivalence (formal languages); Psychology; Psychotherapist; Epistemology; Social psychology; Philosophy; Linguistics","score_opus":0.970118849444943,"score_gpt":0.7776482322961681,"score_spread":0.1924706171487749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043211096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014477771,0.0006464655,0.9169038,0.005200191,0.0006696606,0.0032578458,0.000029955576,0.0002741865,0.058540158],"genre_scores_gemma":[0.051031813,0.0004910358,0.9458891,0.0008194574,0.0010285729,0.0002162691,8.360505e-7,0.00005318082,0.00046969898],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98195285,0.01182931,0.001885629,0.0009797683,0.0022157475,0.0011367253],"domain_scores_gemma":[0.8055859,0.19153897,0.00046302486,0.0014157435,0.000779459,0.00021689989],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055515587,0.00031403892,0.0008680986,0.00009728956,0.00083492894,0.00023355409,0.0016570039,0.00024040774,0.00032844735],"category_scores_gemma":[0.0961549,0.00020557434,0.00024240637,0.001619478,0.0012722958,0.00017020438,0.000066069624,0.002439642,0.000109510496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012064675,0.002664556,0.0018634343,0.00013407585,0.00020313018,0.000009300002,0.0026418157,0.000049119295,0.0029708976,0.4604308,0.036980405,0.490846],"study_design_scores_gemma":[0.0013017574,0.001406098,0.003276544,0.00015985042,0.00002413942,0.000007097863,0.00040086068,0.011449353,0.0002134397,0.98016983,0.0013262377,0.00026481363],"about_ca_topic_score_codex":0.00001533455,"about_ca_topic_score_gemma":0.0000013410204,"teacher_disagreement_score":0.51973903,"about_ca_system_score_codex":0.0000836499,"about_ca_system_score_gemma":0.00021150649,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W2043994334","doi":"10.1021/pr200021n","title":"Biospecimen Reporting for Improved Study Quality (BRISQ)","year":2011,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":331,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute; National Institutes of Health","keywords":"Quality (philosophy); Consistency (knowledge bases); Data science; Biorepository; Computer science; Medicine; Risk analysis (engineering); Biobank; Bioinformatics; Biology","score_opus":0.9770253359502199,"score_gpt":0.7704332796433205,"score_spread":0.20659205630689936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043994334","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7387249,0.00007150882,0.24483974,0.0011831375,0.0009674861,0.009730117,0.000040770592,0.0000566016,0.0043857563],"genre_scores_gemma":[0.14628118,0.000006146064,0.8524747,0.000010845233,0.0006806771,0.000119804645,7.1425e-8,0.000037239122,0.00038932808],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9893446,0.003454744,0.005034415,0.00032002528,0.0012478295,0.00059838186],"domain_scores_gemma":[0.9462683,0.044410974,0.0046413373,0.0007018389,0.0036261606,0.000351364],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1367559,0.00014557086,0.0010447287,0.000274568,0.00017838439,0.000066548666,0.00063227944,0.00014615337,0.00036146367],"category_scores_gemma":[0.6178582,0.00010289794,0.00031676327,0.00042333984,0.00018790909,0.00012853007,0.00022545781,0.0011233317,0.000008598132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.032318696,0.03845994,0.05152575,0.005406156,0.006018117,0.001543208,0.01824725,6.204118e-7,0.37102166,0.19861558,0.023175348,0.25366768],"study_design_scores_gemma":[0.0020995638,0.003910783,0.0073016533,0.00009776951,0.000057847243,0.000023099581,0.0011908691,0.000024873814,0.014175097,0.9708483,0.00013535233,0.00013474881],"about_ca_topic_score_codex":0.00004155448,"about_ca_topic_score_gemma":0.000004584798,"teacher_disagreement_score":0.7722328,"about_ca_system_score_codex":0.00014655238,"about_ca_system_score_gemma":0.00029991157,"threshold_uncertainty_score":0.88889146},"labels":[],"label_agreement":null},{"id":"W2044932116","doi":"10.1007/s40273-013-0123-9","title":"Survival Modeling for the Estimation of Transition Probabilities in Model-Based Economic Evaluations in the Absence of Individual Patient Data: A Tutorial","year":2013,"lang":"en","type":"article","venue":"PharmacoEconomics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":143,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton; Programs for Assessment of Technology in Health Research Institute","funders":"","keywords":"Computer science; Parametric statistics; Statistics; Statistical model; Parametric model; Logistic regression; Data mining; Econometrics; Machine learning; Mathematics","score_opus":0.585087396856932,"score_gpt":0.5634263158170457,"score_spread":0.021661081039886287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044932116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48233354,0.000011007854,0.5141474,0.0004641229,0.00037273337,0.0018827897,0.00076004624,0.000005690539,0.000022668099],"genre_scores_gemma":[0.7570214,0.000009071254,0.24237993,0.00006676463,0.0000832228,0.0004045395,0.000023718381,0.000011001593,3.3645642e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977695,0.0004591647,0.0012510305,0.0002280915,0.00014226788,0.00014998073],"domain_scores_gemma":[0.97086364,0.028275004,0.00033577788,0.00043187066,0.00007221266,0.000021499682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063431077,0.00011180025,0.00034852803,0.00006467512,0.00003682551,0.000030860992,0.0005256536,0.000059197933,0.00003828258],"category_scores_gemma":[0.0049678604,0.00008171819,0.00006996073,0.000051958785,0.00011073223,0.00022974449,0.000048158065,0.00014151716,0.0000016117739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010829421,0.00014543705,0.000017839615,0.00011188764,0.000024841911,2.2131486e-8,0.0016039567,0.9674618,0.000042344072,0.020707846,0.00008602287,0.00968969],"study_design_scores_gemma":[0.00084263703,0.00002892581,0.000016809592,0.000016979815,0.00004579289,6.820541e-8,0.0002432789,0.60495543,0.00018889812,0.39361078,0.0000011739551,0.00004921243],"about_ca_topic_score_codex":0.00012868042,"about_ca_topic_score_gemma":0.00006257739,"teacher_disagreement_score":0.37290293,"about_ca_system_score_codex":0.00008490276,"about_ca_system_score_gemma":0.00022499125,"threshold_uncertainty_score":0.5947352},"labels":[],"label_agreement":null},{"id":"W2045199830","doi":"10.1186/1472-6947-11-31","title":"PKreport: report generation for checking population pharmacokinetic model assumptions","year":2011,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Computer science; Scripting language; Population; Web application; Data mining; Class (philosophy); Software; Python (programming language); Information retrieval; World Wide Web; Programming language; Artificial intelligence","score_opus":0.7592022736181914,"score_gpt":0.6016217230420324,"score_spread":0.15758055057615894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045199830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0803097,0.000018366929,0.91711324,0.000007563001,0.0005911408,0.00053594285,0.000014043577,0.00008151492,0.001328486],"genre_scores_gemma":[0.13545328,0.000029231629,0.86385643,0.0002459289,0.00028308915,0.000071345334,0.000011096423,0.00002349775,0.000026083184],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959019,0.0000896768,0.0025357269,0.00024153486,0.0009504225,0.0002807833],"domain_scores_gemma":[0.98385274,0.014400014,0.0008695914,0.00040002543,0.00021911248,0.00025851335],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0065511423,0.00019547902,0.0004963664,0.00013793993,0.00020932748,0.0000776106,0.00018274898,0.00027123225,0.00029099878],"category_scores_gemma":[0.06378648,0.00015729808,0.00014138647,0.00013735701,0.00007408911,0.00021599812,0.00015057084,0.00022485766,0.0000058814117],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028234383,0.00028525497,0.0017454316,0.0008230989,0.000086251624,0.00004428024,0.0010225108,0.0013414205,0.000039952498,0.16443543,0.0049649356,0.8249291],"study_design_scores_gemma":[0.00047186526,0.000023991104,0.00016507805,0.00016287356,0.00006129494,0.00006417206,0.000032538905,0.56552005,0.000018026087,0.43333557,0.000030120089,0.00011439103],"about_ca_topic_score_codex":0.000002891795,"about_ca_topic_score_gemma":0.000012082002,"teacher_disagreement_score":0.8248147,"about_ca_system_score_codex":0.00003684525,"about_ca_system_score_gemma":0.000111669964,"threshold_uncertainty_score":0.94409966},"labels":[],"label_agreement":null},{"id":"W2045476400","doi":"10.1016/j.cct.2010.09.009","title":"Phase II cancer clinical trials with a one-sample log-rank test and its corrections based on the Edgeworth expansion","year":2010,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Log-rank test; Sample size determination; Medicine; Clinical trial; Statistics; Rank (graph theory); Clinical endpoint; Sample (material); Type I and type II errors; Survival analysis; Mathematics; Internal medicine; Combinatorics","score_opus":0.8780922722693723,"score_gpt":0.6676386266436244,"score_spread":0.21045364562574786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045476400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58693916,0.0012150788,0.22781786,0.078767456,0.046507403,0.03715484,0.0118566975,0.0018132658,0.007928225],"genre_scores_gemma":[0.82171154,0.0008187057,0.15765505,0.0073200576,0.010023474,0.0014539692,0.00003943463,0.00023889777,0.00073890144],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94043946,0.04259502,0.013231705,0.0018446016,0.0011579869,0.0007312021],"domain_scores_gemma":[0.062685885,0.9277734,0.0054917107,0.0021264933,0.0007654946,0.0011569831],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.23737752,0.00080396084,0.006985375,0.00018986182,0.00075447076,0.00021645268,0.00088669406,0.0013556618,0.0023723086],"category_scores_gemma":[0.9453274,0.00045570647,0.0016706894,0.00066337385,0.0013905969,0.00020277489,0.00029522067,0.0036974342,0.000060262122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.055963054,0.057282332,0.0299117,0.0004722916,0.0033649013,0.00014114137,0.00022219786,0.000009969003,0.0028652777,0.07877491,0.1412982,0.62969404],"study_design_scores_gemma":[0.1390585,0.0412815,0.003552882,0.0027817853,0.004796912,0.0000104524315,0.00018930009,0.012028482,0.0030275101,0.7067869,0.08355418,0.0029316484],"about_ca_topic_score_codex":0.00004805886,"about_ca_topic_score_gemma":0.000083878294,"teacher_disagreement_score":0.8851784,"about_ca_system_score_codex":0.000032745123,"about_ca_system_score_gemma":0.0014803924,"threshold_uncertainty_score":0.9999408},"labels":[],"label_agreement":null},{"id":"W2045717403","doi":"10.1016/j.ejps.2011.09.010","title":"Harmonization of Regulatory Approaches for Evaluating Therapeutic Equivalence and Interchangeability of Multisource Drug Products: Workshop summary report","year":2011,"lang":"en","type":"article","venue":"European Journal of Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada; Apotex (Canada); BioPhage Pharma (Canada)","funders":"","keywords":"Interchangeability; Harmonization; Bioequivalence; Regulatory science; Risk analysis (engineering); Business; Equivalence (formal languages); Pharmaceutical industry; Management science; Pharmacology; Computer science; Medicine; Economics; Pharmacokinetics; Mathematics","score_opus":0.8796313223735304,"score_gpt":0.5833190707002008,"score_spread":0.29631225167332953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045717403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6041647,0.0012318861,0.3913944,0.0005801013,0.000611692,0.0007748007,0.000013369285,0.000019485264,0.0012095527],"genre_scores_gemma":[0.5597655,0.000037979364,0.4400606,0.000020997628,0.00007992392,0.000001547467,7.964495e-8,0.000010517635,0.000022862321],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943878,0.0026913448,0.0017387506,0.0003233962,0.0006318068,0.00022692142],"domain_scores_gemma":[0.98503965,0.012507826,0.0015430994,0.00023140274,0.00053141685,0.00014657766],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040609304,0.00014158603,0.0005066157,0.00009293756,0.00008248776,0.000018525081,0.0004979546,0.00002901512,0.000049561735],"category_scores_gemma":[0.07208721,0.000099311976,0.00011838083,0.0003229352,0.0016483824,0.00018035447,0.00017122897,0.00024248658,2.9512287e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001993338,0.0016971279,0.012091467,0.00296428,0.0003453317,0.000061400766,0.011638173,0.000055358138,0.03931435,0.025312556,0.00033402877,0.90419257],"study_design_scores_gemma":[0.005451464,0.0041046236,0.026943605,0.0032019308,0.0016993044,0.00040786326,0.005768218,0.033099715,0.3208122,0.5972308,0.0003648052,0.00091547164],"about_ca_topic_score_codex":8.246378e-7,"about_ca_topic_score_gemma":1.1519452e-7,"teacher_disagreement_score":0.9032771,"about_ca_system_score_codex":0.000020822592,"about_ca_system_score_gemma":0.00008473914,"threshold_uncertainty_score":0.9878946},"labels":[],"label_agreement":null},{"id":"W2045769757","doi":"10.5539/ijsp.v4n1p33","title":"Dose Finding Method in Joint Modeling of Efficacy and Safety Endpoints in Phase II Studies","year":2014,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health","keywords":"Clinical trial; Clinical endpoint; Medicine; Drug development; Selection (genetic algorithm); Phase (matter); Confirmatory factor analysis; Efficacy; Estimation; Surrogate endpoint; Computer science; Joint (building); Phases of clinical research; Medical physics; Drug; Reliability engineering; Pharmacology; Structural equation modeling; Internal medicine; Machine learning; Engineering; Chemistry","score_opus":0.48332612197477565,"score_gpt":0.57762695267772,"score_spread":0.09430083070294437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045769757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34122297,0.00008206945,0.6578308,0.00026736513,0.0002558357,0.00016450507,0.0001154868,0.0000022397537,0.00005874232],"genre_scores_gemma":[0.42131615,0.00017295234,0.5784372,0.000017119844,0.00004746164,0.0000016152371,4.6592766e-7,0.000005179679,0.0000018731189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965263,0.000784499,0.001969319,0.00019395014,0.00039488732,0.00013105052],"domain_scores_gemma":[0.9728702,0.025719255,0.00067783106,0.00010996512,0.0005448245,0.000077967066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011146003,0.0001266574,0.000751652,0.00017238705,0.000029409437,0.000018624933,0.00014819266,0.000065305816,0.000022883994],"category_scores_gemma":[0.112420484,0.000102013146,0.000044939607,0.000077892226,0.00015020187,0.00007480758,0.00016872537,0.00031597915,1.1032032e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034003754,0.002201493,0.003770531,0.0006997422,0.00039157894,0.000060754326,0.0038817567,0.0027421396,0.0005609475,0.5950249,0.000056095727,0.38720968],"study_design_scores_gemma":[0.0047037886,0.00048446958,0.0023825585,0.00043459114,0.000037444705,0.000017298677,0.00008329554,0.06090195,0.00011283311,0.9307429,0.000013101248,0.00008577593],"about_ca_topic_score_codex":0.00001554719,"about_ca_topic_score_gemma":0.000025118321,"teacher_disagreement_score":0.38712388,"about_ca_system_score_codex":0.00007540953,"about_ca_system_score_gemma":0.00004983234,"threshold_uncertainty_score":0.89505595},"labels":[],"label_agreement":null},{"id":"W2045797278","doi":"10.2106/jbjs.k.01287","title":"Use and Interpretation of Composite End Points in Orthopaedic Trials","year":2012,"lang":"en","type":"article","venue":"Journal of Bone and Joint Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Institute for Work & Health","funders":"","keywords":"Interpretation (philosophy); Event (particle physics); Orthopedic surgery; Randomized controlled trial; Computer science; Medicine; Medical physics; Pathology; Surgery; Physics","score_opus":0.5715509204029665,"score_gpt":0.4999385976207019,"score_spread":0.07161232278226459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045797278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848032,0.0007208119,0.013542886,0.00024484482,0.0005343116,0.00010715771,0.000012328065,0.0000032291855,0.000031234045],"genre_scores_gemma":[0.8465779,0.0005809402,0.15256365,0.00008335632,0.00017581825,0.0000010270361,2.495511e-7,0.000009786643,0.000007288848],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994632,0.0017266945,0.0031490307,0.000077101344,0.00026151587,0.00015366974],"domain_scores_gemma":[0.8998977,0.09767382,0.0020524096,0.00009440801,0.00012850558,0.00015316738],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030987203,0.00010060738,0.0018157754,0.00035045418,0.000014915762,0.000022613724,0.0000139339445,0.000088523426,0.000055735072],"category_scores_gemma":[0.17828587,0.00007287082,0.0002772792,0.00010448477,0.00009794803,0.00030346127,0.000036096586,0.00022073406,5.939059e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045016496,0.0015088265,0.6688848,0.001774648,0.0006043685,0.00018997284,0.0026576398,0.00000207683,0.020369772,0.010672303,0.004952658,0.28388125],"study_design_scores_gemma":[0.0026332657,0.00028614877,0.5516857,0.0033511664,0.00052355335,0.0004442192,0.00022245054,0.00021233528,0.005936861,0.4342173,0.00018309506,0.00030391008],"about_ca_topic_score_codex":0.000006292571,"about_ca_topic_score_gemma":0.0000012931068,"teacher_disagreement_score":0.423545,"about_ca_system_score_codex":0.00001442215,"about_ca_system_score_gemma":0.000032718704,"threshold_uncertainty_score":0.9978026},"labels":[],"label_agreement":null},{"id":"W2045852813","doi":"10.1016/j.cmpb.2014.12.006","title":"Assessment of health status over time by Prevalence and Weighted Prevalence functions: Interface in R","year":2015,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut pour la Recherche en Santé Publique; Terry Fox Research Institute","keywords":"Descriptive statistics; Medicine; Statistics; Confidence interval; Quality of life (healthcare); Survival analysis; Event (particle physics); Computer science; Mathematics","score_opus":0.4045250897444877,"score_gpt":0.5868299005714225,"score_spread":0.18230481082693478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045852813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054229423,0.0057135336,0.93801385,0.00038877936,0.000445963,0.0010654611,0.00003640738,0.000040920997,0.000065667904],"genre_scores_gemma":[0.007753477,0.0009508513,0.9909745,0.00009699357,0.000065921864,0.00004756844,0.00000433285,0.000016861484,0.00008951243],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99428165,0.0032250823,0.0013082267,0.00050473417,0.0003172485,0.0003630465],"domain_scores_gemma":[0.9887908,0.010164413,0.00037844872,0.00032225152,0.0000896785,0.00025441998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014781969,0.00020636151,0.0009232868,0.00016840464,0.000022072029,0.00002378522,0.00015589579,0.0001231176,0.000038632203],"category_scores_gemma":[0.0033617318,0.00015714805,0.0000286686,0.00050806574,0.00046052682,0.00006968603,0.00023123376,0.00029803134,5.1899497e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005887382,0.0004885923,0.06301199,0.0018547436,0.00003187174,0.0000023561518,0.0005357476,3.194725e-7,0.00014036172,0.0010067151,0.0008817091,0.9319867],"study_design_scores_gemma":[0.0130565595,0.010942215,0.22130503,0.007906243,0.00018619097,0.00002931671,0.0002515423,0.081552826,0.00016228964,0.65600604,0.007730187,0.0008715728],"about_ca_topic_score_codex":0.000060503917,"about_ca_topic_score_gemma":0.0000018973657,"teacher_disagreement_score":0.93111515,"about_ca_system_score_codex":0.000084556654,"about_ca_system_score_gemma":0.00009242632,"threshold_uncertainty_score":0.6408312},"labels":[],"label_agreement":null},{"id":"W2045862988","doi":"10.1002/sim.1696","title":"A non‐parametric procedure for evaluating treatment effect in the meta‐analysis of survival data","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Statistics; Hazard ratio; Censoring (clinical trials); Mathematics; Logarithm; Confidence interval; Multiplicative function; Contrast (vision); Econometrics; Computer science; Artificial intelligence","score_opus":0.769066250341494,"score_gpt":0.6656981586317418,"score_spread":0.10336809170975225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045862988","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011205524,0.00043968236,0.98048705,0.0008943176,0.0003030289,0.003483579,0.0028379848,0.000016885286,0.00033195835],"genre_scores_gemma":[0.115227275,0.00006571983,0.88393414,0.00011444846,0.000103703685,0.0003691786,0.00013705407,0.000026704438,0.000021774162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953143,0.0012736177,0.0016348986,0.00054940296,0.0008856151,0.0003421747],"domain_scores_gemma":[0.805255,0.19303441,0.00045510606,0.0010552924,0.00014198381,0.000058233003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022447215,0.00027967826,0.0027024325,0.00054288196,0.000041322244,0.000010853579,0.0007069028,0.00011142962,0.00011111567],"category_scores_gemma":[0.29689956,0.00014565741,0.00018290001,0.0024960542,0.00026553264,0.000028982082,0.00008202344,0.00024584902,0.0000012673871],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022965893,0.004457432,0.007822698,0.005075217,0.13001418,0.00023780981,0.009437209,0.005695797,0.0002126406,0.7853789,0.0027168395,0.046654686],"study_design_scores_gemma":[0.005449199,0.0026298556,0.002443835,0.0000870026,0.12284311,0.0000010434693,0.0003071697,0.022927364,0.0000475516,0.843097,0.000011011437,0.00015585449],"about_ca_topic_score_codex":0.00037311311,"about_ca_topic_score_gemma":0.0009161824,"teacher_disagreement_score":0.27445236,"about_ca_system_score_codex":0.00011985253,"about_ca_system_score_gemma":0.00014202985,"threshold_uncertainty_score":0.7779802},"labels":[],"label_agreement":null},{"id":"W2046126869","doi":"10.1007/s11017-010-9170-9","title":"Statistical decisions and the interim analyses of clinical trials","year":2011,"lang":"en","type":"article","venue":"Metamedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Erasmus+; Canadian Institutes of Health Research; Erasmus Universiteit Rotterdam","keywords":"Interim; Clinical trial; Philosophy of medicine; Interim analysis; Data monitoring committee; Management science; Medicine; Engineering ethics; Computer science; Medical physics; Alternative medicine; Law; Political science; Economics; Engineering","score_opus":0.975303311264481,"score_gpt":0.7753018544398078,"score_spread":0.20000145682467318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046126869","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016190507,0.0003930811,0.9746989,0.00067802257,0.0012250195,0.000689605,0.00008820713,0.000035404646,0.0060012257],"genre_scores_gemma":[0.2074374,0.00033745894,0.7913733,0.0003453744,0.00034077588,0.000022606522,9.4090603e-7,0.000017467426,0.00012468155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98237026,0.011642585,0.004883665,0.000356418,0.0005306027,0.00021644362],"domain_scores_gemma":[0.44712296,0.5504956,0.0011904467,0.0007339902,0.00020123937,0.00025574391],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0777152,0.0001760492,0.0031458898,0.00007872716,0.000044410594,0.000008516121,0.0003140789,0.00014285976,0.0022280675],"category_scores_gemma":[0.8598069,0.00007798074,0.00033707125,0.00020404632,0.0023900005,0.000026058657,0.00016999635,0.0004088267,0.00001297541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030799627,0.00041185087,0.0009055286,0.00005454198,0.0009307065,0.000023006225,0.00040332487,2.1803263e-8,0.00012391685,0.76948595,0.006609769,0.21797143],"study_design_scores_gemma":[0.005855354,0.00042974972,0.0059043113,0.000114599774,0.0020907933,0.000006997741,0.00018235238,0.00017696944,0.00047026598,0.9842563,0.00042549102,0.00008676469],"about_ca_topic_score_codex":0.000070684575,"about_ca_topic_score_gemma":0.0000051588186,"teacher_disagreement_score":0.7820917,"about_ca_system_score_codex":0.000004500775,"about_ca_system_score_gemma":0.000047876092,"threshold_uncertainty_score":0.99868405},"labels":[],"label_agreement":null},{"id":"W2046562703","doi":"10.2307/3315066","title":"Mixed‐scale models for survival/sacrifice experiments","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Waterloo","funders":"","keywords":"Occult; Interim; Econometrics; Statistics; Sacrifice; Statistical model; Scale (ratio); Computer science; Mathematics; Medicine; Pathology; Geography","score_opus":0.6241144059244803,"score_gpt":0.5061750010814996,"score_spread":0.11793940484298071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046562703","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041425745,0.00013122974,0.9860365,0.00020240089,0.0018598845,0.0003300011,0.002955166,0.000011124813,0.0043311114],"genre_scores_gemma":[0.022014307,0.00004189049,0.9759557,0.000187967,0.0004715012,0.0000108832555,0.0000046169907,0.00006066076,0.0012524261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99730664,0.00033351502,0.0012980277,0.00019846168,0.00035166345,0.000511688],"domain_scores_gemma":[0.9832094,0.014519854,0.00038712504,0.00029495597,0.0005436169,0.0010450982],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002120256,0.00020408309,0.000701997,0.0001270722,0.00015899408,0.00008418741,0.00041713615,0.00015018099,0.0019785375],"category_scores_gemma":[0.014829381,0.0001909866,0.0001505898,0.00013343559,0.0002018222,0.00011375887,0.0000073598076,0.00028611682,0.000024689429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026974152,0.00015384672,0.0001393063,0.00019945824,0.00026811575,0.00023069457,0.00097522384,0.00034500394,0.000054776232,0.6577472,0.20416245,0.13545416],"study_design_scores_gemma":[0.0011258028,0.00027144866,0.00007856917,0.00008362574,0.00015028317,0.000028357612,0.00020046595,0.0018258228,0.00023562009,0.9804211,0.015355852,0.00022302674],"about_ca_topic_score_codex":0.00035450282,"about_ca_topic_score_gemma":0.0020021047,"teacher_disagreement_score":0.3226739,"about_ca_system_score_codex":0.00015496484,"about_ca_system_score_gemma":0.0007852396,"threshold_uncertainty_score":0.9989338},"labels":[],"label_agreement":null},{"id":"W2047186977","doi":"10.1007/s40273-014-0145-y","title":"Methods for Adjusting for Bias Due to Crossover in Oncology Trials","year":2014,"lang":"en","type":"article","venue":"PharmacoEconomics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TransCanada (Canada)","funders":"Pfizer","keywords":"Crossover; Crossover study; Censoring (clinical trials); Medicine; Randomized controlled trial; Treatment effect; Computer science; Statistics; Intensive care medicine; Mathematics; Internal medicine; Machine learning","score_opus":0.8723868667747371,"score_gpt":0.7400603947834757,"score_spread":0.13232647199126135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047186977","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008907406,0.000027545319,0.98192674,0.0015618628,0.0029480795,0.0029735344,0.00025911536,0.00006425558,0.001331464],"genre_scores_gemma":[0.002153224,0.00001044397,0.9910405,0.0036506897,0.0016460696,0.0012380366,0.0000034334043,0.00007956144,0.00017800619],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99347955,0.0028490783,0.0024735983,0.0005741427,0.000056108547,0.0005674998],"domain_scores_gemma":[0.56905276,0.42960656,0.0006969459,0.00029877535,0.000116875366,0.00022810501],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057752516,0.00024852256,0.002025834,0.00014514108,0.00008112354,0.000060092843,0.000382957,0.00022856027,0.00021825898],"category_scores_gemma":[0.47692102,0.00023824016,0.00038198588,0.00009956257,0.000060017635,0.0000739989,0.00012468302,0.00021848794,0.000029027537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016590983,0.00016789917,0.000022538794,0.00024572024,0.00010417968,7.230942e-7,0.00017905075,0.00010098658,0.0020343345,0.16033998,0.011108625,0.82403684],"study_design_scores_gemma":[0.0062789256,0.0002602714,0.000011707856,0.000022636317,0.00017830865,0.000002137614,0.000024271616,0.028944321,0.01775009,0.7844038,0.16186595,0.00025757193],"about_ca_topic_score_codex":0.000009016582,"about_ca_topic_score_gemma":0.0000126780715,"teacher_disagreement_score":0.8237793,"about_ca_system_score_codex":0.00024248565,"about_ca_system_score_gemma":0.00011588633,"threshold_uncertainty_score":0.9715152},"labels":[],"label_agreement":null},{"id":"W2047326688","doi":"10.1002/cjs.5550360404","title":"Doubly adaptive biased coin designs with delayed responses","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Science Foundation","keywords":"Adaptive design; Function (biology); Computer science; Control theory (sociology); Computerized adaptive testing; Mathematics; Statistics; Medicine; Artificial intelligence; Biology; Clinical trial","score_opus":0.6755917334017751,"score_gpt":0.48008572076501277,"score_spread":0.19550601263676237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047326688","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02495639,0.00007338224,0.9715266,0.00022324488,0.00041189333,0.00024820588,0.0018800304,0.000013693444,0.00066656346],"genre_scores_gemma":[0.18338138,0.000024079989,0.8158169,0.00022572443,0.00019209381,0.0000032702876,0.0000017281778,0.000046733483,0.00030811987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968389,0.00084535725,0.0011539845,0.00019035039,0.00049013906,0.00048126152],"domain_scores_gemma":[0.9615575,0.035209235,0.00074614875,0.00028550727,0.0009840311,0.0012175514],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019263853,0.00023573182,0.0007390544,0.00030319422,0.00024572236,0.000041844527,0.00034543843,0.00013825824,0.0005229851],"category_scores_gemma":[0.057300877,0.00018658255,0.00008772913,0.00031000134,0.00070008775,0.00008638045,0.00001066385,0.00053247425,0.000021131813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009263902,0.00033361054,0.006061707,0.00014901493,0.0015230066,0.04494674,0.00358208,0.00022341529,0.0002345867,0.57453936,0.34356254,0.015580018],"study_design_scores_gemma":[0.0049014916,0.005072573,0.006566935,0.0003596677,0.0005986123,0.003012941,0.00043795927,0.00041241586,0.00065688527,0.9739086,0.003357782,0.00071413367],"about_ca_topic_score_codex":0.00082513446,"about_ca_topic_score_gemma":0.005916263,"teacher_disagreement_score":0.3993692,"about_ca_system_score_codex":0.00022727088,"about_ca_system_score_gemma":0.0039751846,"threshold_uncertainty_score":0.9506399},"labels":[],"label_agreement":null},{"id":"W2049564589","doi":"10.1002/pst.289","title":"Comparing two independent incidence rates using conditional and unconditional exact tests","year":2007,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western Forest Products","funders":"","keywords":"Exact statistics; Mathematics; Statistics; Exact test; Wald test; Type I and type II errors; Score test; Poisson distribution; Likelihood-ratio test; Binomial distribution; p-value; Chi-square test; Negative binomial distribution; Binomial test; Nominal level; Statistic; Test statistic; Statistical hypothesis testing; Confidence interval","score_opus":0.7041238095391115,"score_gpt":0.6470359725829649,"score_spread":0.05708783695614661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049564589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12058225,0.000045505203,0.876714,0.000070888986,0.0004295484,0.00035842348,0.0010205854,0.000083693325,0.0006950882],"genre_scores_gemma":[0.49563912,0.00000807852,0.503669,0.00034520123,0.00026092303,0.0000060858347,0.000030673036,0.000025027311,0.000015888943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99637544,0.00041306778,0.0011595647,0.00050396926,0.0009048405,0.0006431212],"domain_scores_gemma":[0.93898284,0.059767816,0.00028658463,0.00019614398,0.00027867034,0.00048792822],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039730743,0.00031051273,0.0006097646,0.00010588361,0.00025534813,0.00010316459,0.00022115314,0.00012812152,0.0011634314],"category_scores_gemma":[0.031299066,0.0002991394,0.000059353977,0.00021204635,0.0006694726,0.00013716918,0.00023396485,0.0006834608,0.0000465216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002475749,0.00035300417,0.07414464,0.00018944492,0.00014146938,0.00029079808,0.000048153994,0.000060664188,0.001491235,0.9166765,0.0015749811,0.004781505],"study_design_scores_gemma":[0.0020539118,0.000061728024,0.045733564,0.00006911553,0.00021607352,0.0001280046,0.000024442994,0.025550656,0.0023302708,0.92314535,0.00031558014,0.00037129447],"about_ca_topic_score_codex":0.00002650529,"about_ca_topic_score_gemma":0.000027892629,"teacher_disagreement_score":0.37505686,"about_ca_system_score_codex":0.00018403276,"about_ca_system_score_gemma":0.000109228364,"threshold_uncertainty_score":0.99994606},"labels":[],"label_agreement":null},{"id":"W2049721389","doi":"10.2527/jas.2009-1908","title":"Statistical power calculations: Comment","year":2009,"lang":"en","type":"letter","venue":"Journal of Animal Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Null (SQL); Statistical power; Null hypothesis; Power (physics); Mathematics; Phenomenon; Conditional probability; Statistical hypothesis testing; Statistics; Null model; Computer science; Physics; Combinatorics; Data mining; Thermodynamics","score_opus":0.5086509141920409,"score_gpt":0.5829699785113726,"score_spread":0.07431906431933166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049721389","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048682975,0.00005623124,0.15032728,0.84311944,0.0016975752,0.0003349408,0.00012149384,0.000027219734,0.0038289973],"genre_scores_gemma":[0.001105428,0.000012192923,0.6978585,0.29894453,0.001993233,0.0000012342805,5.1299537e-7,0.000019817493,0.00006457348],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941127,0.0005806503,0.0019140366,0.0003564568,0.0024749464,0.0005612141],"domain_scores_gemma":[0.95989823,0.037166942,0.0014718304,0.00038135398,0.00081575674,0.00026586128],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008068141,0.00027110623,0.0010184611,0.00028041372,0.00017197154,0.00019448741,0.0011695653,0.00039479873,0.00071401545],"category_scores_gemma":[0.12965825,0.00019439751,0.00024873597,0.00048523126,0.0010191872,0.00020045416,0.0001367356,0.0024775674,0.00003429089],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006781526,0.00010128997,0.000011866074,0.000029954503,0.000025334128,0.0005996191,0.000028080844,3.4136028e-7,0.0003255079,0.042029798,0.9554063,0.0013741083],"study_design_scores_gemma":[0.00039709982,0.0019210529,0.000949425,0.00025076035,0.00015917959,0.00020570453,0.000013051421,0.00004564069,0.00012962369,0.7229553,0.27270204,0.00027114034],"about_ca_topic_score_codex":0.0000029200937,"about_ca_topic_score_gemma":2.0173854e-7,"teacher_disagreement_score":0.68270427,"about_ca_system_score_codex":0.00030730467,"about_ca_system_score_gemma":0.000598935,"threshold_uncertainty_score":0.99982375},"labels":[],"label_agreement":null},{"id":"W2050464419","doi":"10.1016/j.jval.2013.03.153","title":"Modelling drug class effects in bayesian multiple treatment comparison meta-analysis: Applications in early and advanced parkinson's disease","year":2013,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Drug class; Drug; Medicine; Random effects model; Parkinson's disease; Class (philosophy); Pharmacology; Disease; Internal medicine; Computer science; Meta-analysis; Artificial intelligence","score_opus":0.4652705594039648,"score_gpt":0.5116672727313282,"score_spread":0.04639671332736339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050464419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4414352,0.0021850704,0.5499641,0.0011855231,0.000051760853,0.005033686,0.00006453044,0.000052311752,0.00002783959],"genre_scores_gemma":[0.5904666,0.000092406786,0.4079313,0.00005273883,0.000013674469,0.0014109508,0.0000031681416,0.000016930906,0.000012218094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99479955,0.002459126,0.001461255,0.00059944333,0.00024956636,0.00043105494],"domain_scores_gemma":[0.9578192,0.04092507,0.00034664065,0.0005317617,0.00003134066,0.00034596285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002270046,0.00024806111,0.0018501424,0.00032972993,0.00005475485,0.000036377314,0.00014624045,0.000081813865,0.000017054894],"category_scores_gemma":[0.003820179,0.00019784574,0.0002468055,0.00075934804,0.0000581172,0.0000825153,0.00003931157,0.000266038,0.000006896084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019474879,0.003024486,0.24185283,0.0013201936,0.0032937515,0.000014531146,0.0030801073,0.6847629,0.0000036551507,0.052477084,0.000025031733,0.009950672],"study_design_scores_gemma":[0.0010660802,0.00006827646,0.014187052,0.000037807233,0.0019227645,4.4887333e-8,0.00006852679,0.6379082,0.000006484946,0.3445453,0.000053487107,0.0001359492],"about_ca_topic_score_codex":0.008650179,"about_ca_topic_score_gemma":0.00089683576,"teacher_disagreement_score":0.2920682,"about_ca_system_score_codex":0.0002780516,"about_ca_system_score_gemma":0.000083722305,"threshold_uncertainty_score":0.9979513},"labels":[],"label_agreement":null},{"id":"W2050518819","doi":"10.1097/01.inf.0000050666.26000.34","title":"Need for equivalence testing of efficacy of alternative antibiotics for treatment of pertussis","year":2003,"lang":"en","type":"letter","venue":"The Pediatric Infectious Disease Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Clarithromycin; Erythromycin; Medicine; Regimen; Clinical trial; Adverse effect; Randomized controlled trial; Internal medicine; Confidence interval; Antibiotics; Equivalence (formal languages); Mathematics; Biology; Helicobacter pylori; Microbiology","score_opus":0.408313969471973,"score_gpt":0.4986371202766193,"score_spread":0.09032315080464626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050518819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31204098,0.0016485834,0.62968385,0.02703003,0.0077458634,0.011320359,0.0099234395,0.00010372352,0.00050315907],"genre_scores_gemma":[0.06816808,0.002392692,0.8939473,0.007316343,0.027350497,0.000090458365,0.000019987161,0.000375041,0.00033960954],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955962,0.00092555536,0.0021385131,0.00029924372,0.00059375487,0.0004467895],"domain_scores_gemma":[0.8450317,0.14962472,0.003649102,0.0004777937,0.0010765973,0.00014013184],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00212807,0.00040902282,0.0015814184,0.00027486682,0.00015994748,0.000024954054,0.00041382888,0.00031804162,0.000043816337],"category_scores_gemma":[0.1576477,0.00025992235,0.0011247508,0.0003496442,0.00025884793,0.00003512211,0.000045804332,0.0004351647,6.543383e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008856847,0.021022383,0.15626879,0.053697437,0.013571577,0.00032113923,0.0024437374,0.0019645449,0.00041419637,0.013310824,0.6701253,0.0580032],"study_design_scores_gemma":[0.009984551,0.0053508184,0.000959513,0.0005199143,0.018855968,0.000062724714,0.000054938293,0.0011148688,0.00075105554,0.96062654,0.0010565502,0.0006625255],"about_ca_topic_score_codex":0.000011041471,"about_ca_topic_score_gemma":2.714666e-7,"teacher_disagreement_score":0.94731575,"about_ca_system_score_codex":0.0001618158,"about_ca_system_score_gemma":0.0005740051,"threshold_uncertainty_score":0.9999853},"labels":[],"label_agreement":null},{"id":"W2050644751","doi":"10.1016/j.ejca.2011.05.019","title":"Early stopping rules in oncology: Considerations for clinicians","year":2011,"lang":"en","type":"review","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McMaster University; Juravinski Cancer Centre","funders":"","keywords":"Clinical trial; Harm; Medicine; Clinical Practice; Intensive care medicine; Clinical Oncology; Medical physics; Cancer; Oncology; Family medicine; Internal medicine; Psychology","score_opus":0.866584728659454,"score_gpt":0.6631963191333864,"score_spread":0.20338840952606763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050644751","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004975416,0.9711198,0.018902909,0.00015496444,0.0024454568,0.00074243173,0.00020608919,0.000013934808,0.0064094183],"genre_scores_gemma":[0.0000012226207,0.60570794,0.39274508,0.000102744125,0.0012037638,0.000017610995,2.6902893e-7,0.00007298754,0.00014835694],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990269,0.0051777996,0.0038337004,0.00024520542,0.00019910405,0.00027518606],"domain_scores_gemma":[0.9282258,0.067747384,0.003246569,0.00026633838,0.00036981134,0.00014410191],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012370713,0.00029149937,0.0029683502,0.00023688514,0.000055550787,0.000042399122,0.00039402785,0.0001687019,0.00041323103],"category_scores_gemma":[0.09884424,0.00021598901,0.0008354751,0.00011169988,0.00014065475,0.000061061415,0.00006857308,0.0010812135,0.000034508736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000337298,0.00009236216,0.0000021463889,0.001979925,0.00027011096,0.00015635834,0.00019602219,2.6104775e-7,7.975569e-8,0.016353408,0.005733855,0.97518176],"study_design_scores_gemma":[0.0007294742,0.0003687172,0.000012682041,0.012637898,0.001114045,0.000034781253,0.000012386791,5.087331e-7,1.952015e-7,0.20585088,0.7790585,0.00017993661],"about_ca_topic_score_codex":0.0000030605343,"about_ca_topic_score_gemma":0.000014523585,"teacher_disagreement_score":0.9750018,"about_ca_system_score_codex":0.00020392193,"about_ca_system_score_gemma":0.0008805554,"threshold_uncertainty_score":0.9087466},"labels":[],"label_agreement":null},{"id":"W2051778548","doi":"10.1016/j.ejca.2011.03.016","title":"Heterogeneity in the definition of dose-limiting toxicity in phase I cancer clinical trials of molecularly targeted agents: A review of the literature","year":2011,"lang":"en","type":"review","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute","keywords":"Toxicity; Medicine; Limiting; Clinical trial; Maximum tolerated dose; Oncology; Internal medicine","score_opus":0.8118245039593,"score_gpt":0.6537769044671239,"score_spread":0.15804759949217606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051778548","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006303104,0.99476707,0.0009738254,0.00009826422,0.00087051076,0.0014087898,0.0008299723,0.000002636047,0.00041861454],"genre_scores_gemma":[0.00031207982,0.970837,0.027912827,0.00038131166,0.00046179726,0.000027573411,0.0000026998891,0.000061019793,0.0000037200498],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9122388,0.071577996,0.014609426,0.0003575133,0.0009253833,0.000290895],"domain_scores_gemma":[0.9516775,0.0294406,0.017269764,0.0007585563,0.0007569148,0.00009667815],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08438427,0.00040413789,0.0063548763,0.0001878173,0.000022305732,0.00001828744,0.0013575777,0.00021346849,0.00025040586],"category_scores_gemma":[0.2063113,0.00020165043,0.0026822626,0.0009420593,0.00027829732,0.00007339847,0.00016182591,0.0018337568,7.857742e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034774552,0.0009899031,0.00006107693,0.08454215,0.0007640629,0.00010851492,0.0003612577,6.1486975e-7,0.000024009816,0.0016977276,0.00092316413,0.9101798],"study_design_scores_gemma":[0.00522769,0.0008131956,0.00034027253,0.90058553,0.005944732,0.00004798927,0.000027251765,0.0000020503007,0.00018449781,0.022775223,0.06363264,0.00041891198],"about_ca_topic_score_codex":0.0000097681195,"about_ca_topic_score_gemma":0.000011511693,"teacher_disagreement_score":0.9097609,"about_ca_system_score_codex":0.00009487111,"about_ca_system_score_gemma":0.00056607026,"threshold_uncertainty_score":0.94281906},"labels":[],"label_agreement":null},{"id":"W2051978677","doi":"10.1016/j.jval.2012.03.279","title":"PMS90 the Influence of ‘Weak Links' on Comparative Treatment Effects in Multiple Treatment Comparison Meta-Analysis: A Simulation Study","year":2012,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McMaster University","funders":"","keywords":"Meta-analysis; Spurious relationship; Statistics; Cluster (spacecraft); Treatment effect; Confidence interval; Treatment and control groups; Multiple comparisons problem; Medicine; Econometrics; Mathematics; Computer science; Internal medicine","score_opus":0.8576107612714143,"score_gpt":0.6472244818715237,"score_spread":0.21038627939989063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051978677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907921,0.00049465836,0.0037511762,0.00018321835,0.000094485105,0.0045751217,0.00004126042,0.000024331715,0.000043652257],"genre_scores_gemma":[0.94970626,0.000014362735,0.049660157,0.000059456182,0.00004365675,0.0004853531,0.0000019919623,0.000014974515,0.000013790351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9878067,0.008958008,0.0019755678,0.0003760873,0.00046115127,0.00042251364],"domain_scores_gemma":[0.86422557,0.13421199,0.00074352266,0.0006404758,0.000049293274,0.0001291644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054290113,0.00030612075,0.0029172353,0.00025021136,0.00007777522,0.000012720807,0.00016946955,0.00012259536,0.000019471961],"category_scores_gemma":[0.010611228,0.00017037876,0.00042961902,0.00085069926,0.000081504855,0.000053740092,0.000033139837,0.000285703,0.000012901883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033279505,0.013549867,0.12339442,0.000102733604,0.0099987155,0.0000017949181,0.018623173,0.82729405,0.0000028876543,0.005863128,0.0000044461726,0.00083197514],"study_design_scores_gemma":[0.009135355,0.014114069,0.54110974,0.00012735299,0.037242964,3.780286e-7,0.0027344562,0.340041,0.00034462838,0.05462462,0.00006581949,0.0004596248],"about_ca_topic_score_codex":0.004625303,"about_ca_topic_score_gemma":0.0009547141,"teacher_disagreement_score":0.48725304,"about_ca_system_score_codex":0.0005983798,"about_ca_system_score_gemma":0.00008266838,"threshold_uncertainty_score":0.9977228},"labels":[],"label_agreement":null},{"id":"W2052404934","doi":"10.1177/0962280214553330","title":"On the analysis of composite measures of quality in medical research","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Health Canada; Partenariat Canadien Contre Le Cancer; Heart and Stroke Foundation of Canada","keywords":"Binomial regression; Statistics; Logistic regression; Generalized linear model; Mathematics; Generalized estimating equation; Poisson regression; Marginal model; Regression analysis; Negative binomial distribution; Overdispersion; Quasi-likelihood; Linear regression; Gee; Econometrics; Poisson distribution; Medicine; Population","score_opus":0.89062208648722,"score_gpt":0.7857866714285195,"score_spread":0.10483541505870042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052404934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027486425,0.000069582304,0.95076215,0.0074082823,0.00022724114,0.0009815294,0.00019239206,0.000022165279,0.012850252],"genre_scores_gemma":[0.24993728,0.00012338352,0.7493024,0.00026812768,0.000116491334,0.00015686522,0.0000044213384,0.00004080367,0.00005020802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7226506,0.24497475,0.0061843847,0.0014826737,0.022604099,0.002103493],"domain_scores_gemma":[0.106773086,0.8885837,0.00034527932,0.0017336005,0.0015106633,0.0010536611],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50820994,0.00030946673,0.0029188546,0.0020578597,0.00015374339,0.00003690338,0.002580996,0.0009275924,0.0104591735],"category_scores_gemma":[0.964639,0.00019902387,0.0003130263,0.00818005,0.007796699,0.000033930195,0.0010466818,0.0066502416,0.00002372492],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006335776,0.0009938073,0.001312478,0.0002795913,0.00021583503,0.000047225705,0.00020176082,0.0000042237016,0.00020722978,0.70625705,0.00081075315,0.28903648],"study_design_scores_gemma":[0.0011646968,0.00048723796,0.027862562,0.0006502027,0.00008730845,0.0000011289513,0.00022550105,0.02209767,0.00087631587,0.94610924,0.00025894077,0.00017921855],"about_ca_topic_score_codex":0.0012833021,"about_ca_topic_score_gemma":0.0008060411,"teacher_disagreement_score":0.643609,"about_ca_system_score_codex":0.00023219924,"about_ca_system_score_gemma":0.00085135346,"threshold_uncertainty_score":0.99564147},"labels":[],"label_agreement":null},{"id":"W2054641956","doi":"10.1016/j.cct.2011.11.015","title":"Dose-finding designs in pediatric phase I clinical trials: Comparison by simulations in a realistic timeline framework","year":2012,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer","keywords":"Medicine; Maximum tolerated dose; Accrual; Clinical trial; Duration (music); Toxicity; Timeline; Oncology; Internal medicine; Statistics","score_opus":0.960724625125865,"score_gpt":0.7587921475871148,"score_spread":0.2019324775387502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054641956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21168056,0.0081081595,0.7358407,0.0036191565,0.018403001,0.015968893,0.0030012121,0.00072879903,0.0026495424],"genre_scores_gemma":[0.74905974,0.0006691553,0.24159977,0.00065508846,0.0074940748,0.00019205966,0.000089420646,0.00013667678,0.00010399786],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.75722504,0.18632267,0.050763637,0.0022057388,0.0015510764,0.0019318267],"domain_scores_gemma":[0.05388327,0.9339093,0.008595179,0.0017954364,0.00027249506,0.0015442977],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.42599466,0.00088103244,0.012036513,0.00061350054,0.00014746778,0.00015806765,0.0010465148,0.0025015774,0.0010863584],"category_scores_gemma":[0.95359886,0.00073905557,0.0020409643,0.0017331045,0.00052486034,0.00047809997,0.0003347078,0.0039574453,0.00021093877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013036977,0.028843166,0.6951343,0.00039184155,0.0006242123,0.00010448725,0.00041169193,0.000048849088,0.00006275224,0.030993043,0.15147838,0.07887034],"study_design_scores_gemma":[0.06462024,0.0023622327,0.011713156,0.0010188154,0.0016132046,0.0000031292561,0.00020150426,0.009063624,0.000070021066,0.8999842,0.0074854456,0.001864475],"about_ca_topic_score_codex":0.00004533997,"about_ca_topic_score_gemma":0.00001272254,"teacher_disagreement_score":0.86899114,"about_ca_system_score_codex":0.000173274,"about_ca_system_score_gemma":0.00069145503,"threshold_uncertainty_score":0.9998268},"labels":[],"label_agreement":null},{"id":"W2054642506","doi":"10.1016/j.jspi.2007.11.002","title":"Asymptotically efficient estimation in response adaptive trials","year":2007,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Estimator; Asymptotically optimal algorithm; Applied mathematics; Upper and lower bounds; Dependency (UML); Statistics; Efficiency; Maximum likelihood; Set (abstract data type); Mathematical optimization; Artificial intelligence; Computer science; Mathematical analysis","score_opus":0.5270702011956881,"score_gpt":0.5913568089307135,"score_spread":0.06428660773502537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054642506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12784214,0.00005337869,0.87117934,0.0001377217,0.00023533822,0.00014640775,0.00003370117,0.000011084481,0.0003608776],"genre_scores_gemma":[0.5021778,0.00000369264,0.4977166,0.00003948411,0.00004927169,8.3118334e-7,2.1184798e-7,0.000006703997,0.0000054022557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99435765,0.0019258413,0.0026118814,0.0001998778,0.000575806,0.00032896685],"domain_scores_gemma":[0.68115497,0.31734714,0.00083702913,0.00011935696,0.0002618422,0.00027966703],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04089888,0.00016854495,0.0010487242,0.0002509747,0.00005157592,0.000053803575,0.00014363807,0.00016193393,0.000078005],"category_scores_gemma":[0.5538511,0.00012342427,0.000070540074,0.00020213122,0.00024321087,0.00007186733,0.000047084937,0.00064818363,0.0000044823523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022743734,0.0006754165,0.003532564,0.00013843123,0.00013539079,0.0011836978,0.0012768556,0.0019097833,0.0009492575,0.85795516,0.0007456992,0.10875399],"study_design_scores_gemma":[0.0018646409,0.0013737577,0.073897846,0.0007248992,0.00010367109,0.00006859618,0.00023766175,0.020790558,0.00017280389,0.9005533,0.000023445991,0.0001888346],"about_ca_topic_score_codex":0.0000030494016,"about_ca_topic_score_gemma":6.9318315e-7,"teacher_disagreement_score":0.51295227,"about_ca_system_score_codex":0.000077079974,"about_ca_system_score_gemma":0.0001429114,"threshold_uncertainty_score":0.98759645},"labels":[],"label_agreement":null},{"id":"W2055353237","doi":"10.1002/sim.3092","title":"Comparison of algorithms to generate event times conditional on time‐dependent covariates","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Covariate; Computer science; Toolbox; Event (particle physics); Algorithm; Stability (learning theory); Calibration; Flexibility (engineering); Binomial (polynomial); Statistics; Data mining; Mathematics; Machine learning","score_opus":0.37609532417178737,"score_gpt":0.6061969173828708,"score_spread":0.23010159321108348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055353237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023088462,0.000029898327,0.9920363,0.00046939123,0.00074903213,0.00054728065,0.00096840074,0.000030086025,0.0028607962],"genre_scores_gemma":[0.08163392,0.000008102229,0.91669124,0.00043670804,0.00045748812,0.00001766764,0.000061763916,0.000032866283,0.000660266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958531,0.00043587622,0.0019268948,0.0003735875,0.0010326328,0.0003778712],"domain_scores_gemma":[0.94478315,0.05398894,0.00040216744,0.00033731494,0.00026338192,0.00022503694],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007309828,0.00023217253,0.0010957808,0.00025021122,0.00004527417,0.0000066412276,0.00025289145,0.00013317312,0.0029549648],"category_scores_gemma":[0.07066413,0.00018861954,0.00003846339,0.0002952687,0.0002831786,0.00001503604,0.00007042045,0.00036152283,0.00013238045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045749277,0.0008084173,0.0007088476,0.00014672297,0.00010716976,0.00009986819,0.0006677555,0.00040644585,0.0015913906,0.91365886,0.06272773,0.018619291],"study_design_scores_gemma":[0.0018955471,0.0013489425,0.0028321932,0.00029903016,0.00009155739,0.000003126577,0.00015546294,0.0051121674,0.0052539497,0.98247975,0.0003168366,0.00021144167],"about_ca_topic_score_codex":0.000030827177,"about_ca_topic_score_gemma":0.000017232782,"teacher_disagreement_score":0.07932507,"about_ca_system_score_codex":0.00011767205,"about_ca_system_score_gemma":0.00005673924,"threshold_uncertainty_score":0.99795645},"labels":[],"label_agreement":null},{"id":"W2055909840","doi":"10.1002/sim.4343","title":"Comparison of alternative models for linking drug exposure with adverse effects","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"A priori and a posteriori; Model selection; Metric (unit); Computer science; Information Criteria; Statistics; Econometrics; Mathematics; Data mining; Machine learning","score_opus":0.5145667783424172,"score_gpt":0.5664642533495956,"score_spread":0.05189747500717845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055909840","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064186803,0.000059746948,0.9894896,0.000035352212,0.000528353,0.0010566687,0.00016298762,0.000027446524,0.0022211398],"genre_scores_gemma":[0.32332817,0.000013139314,0.6763416,0.000044308115,0.00012252128,0.000065672335,0.0000066784064,0.000030951356,0.00004696628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99724793,0.00042668567,0.0012101821,0.00032705755,0.0004949597,0.0002932072],"domain_scores_gemma":[0.940815,0.05783952,0.0005848808,0.00034861016,0.00030438742,0.00010763063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025840928,0.00022322581,0.0012145886,0.00013136123,0.0000359152,0.0000022003533,0.0002717034,0.00009424423,0.00008520339],"category_scores_gemma":[0.036003172,0.00015899523,0.000038608603,0.0001843048,0.00047716804,0.00004326682,0.00005014659,0.0003233407,0.000001406381],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008559056,0.00042682103,0.0046961783,0.0016144397,0.00014417448,0.000043907843,0.01107642,0.00012822692,0.000056152185,0.96955305,0.0015730277,0.0098316865],"study_design_scores_gemma":[0.004051947,0.0015449272,0.0005953895,0.0013371558,0.00024240941,0.0000011286527,0.00071098015,0.019121679,0.0017405746,0.9704746,0.000010994001,0.00016821022],"about_ca_topic_score_codex":0.00006603195,"about_ca_topic_score_gemma":0.00007456,"teacher_disagreement_score":0.31690946,"about_ca_system_score_codex":0.00004316368,"about_ca_system_score_gemma":0.000046046614,"threshold_uncertainty_score":0.972117},"labels":[],"label_agreement":null},{"id":"W2057634318","doi":"10.1093/annonc/mdt211","title":"Spin and bias: the tip of the iceberg","year":2013,"lang":"en","type":"letter","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Clinical endpoint; Selection bias; Scopus; Perspective (graphical); End point; Publication bias; Point (geometry); Clinical trial; MEDLINE; Internal medicine; Meta-analysis; Pathology; Law; Computer science","score_opus":0.8134681196420586,"score_gpt":0.622572782676002,"score_spread":0.19089533696605654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057634318","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024247814,0.00031115618,0.0005113199,0.9790701,0.0013593781,0.00094040757,0.00016562136,0.000015308817,0.015201913],"genre_scores_gemma":[0.00090698135,0.00065948436,0.14503822,0.8456531,0.003503851,0.00011506305,0.0000030647802,0.00008522109,0.004035006],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99482286,0.002978685,0.0012664292,0.00027637658,0.00035538644,0.0003002521],"domain_scores_gemma":[0.8838527,0.11352817,0.0014201015,0.00086078746,0.00030269005,0.000035526835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003996783,0.00022191985,0.0012939721,0.00004894023,0.000045782042,0.000010062471,0.00079164247,0.0011056628,0.0005048346],"category_scores_gemma":[0.08948043,0.0001079567,0.00028875296,0.00013101354,0.0011993985,0.000018640767,0.0003695491,0.0013620434,0.000022251867],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017786246,0.00006035,0.00003058434,0.0003002088,0.00019220727,0.00000778921,0.00007616791,6.7703006e-8,0.000019530107,0.013161103,0.961922,0.024212217],"study_design_scores_gemma":[0.00019512096,0.00036468348,0.00022798662,0.000101951424,0.0001389527,0.0000070415817,0.000012034923,0.0000042673078,0.00032424636,0.55280143,0.44574454,0.00007771565],"about_ca_topic_score_codex":0.00006198646,"about_ca_topic_score_gemma":0.000008894255,"teacher_disagreement_score":0.53964037,"about_ca_system_score_codex":0.000011131078,"about_ca_system_score_gemma":0.0001486863,"threshold_uncertainty_score":0.9181893},"labels":[],"label_agreement":null},{"id":"W2057648481","doi":"10.1002/cncr.29084","title":"Assessing benefit in trials: Are we making progress in assessing progression in cancer clinical trials?","year":2014,"lang":"en","type":"letter","venue":"Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Ontario Institute for Cancer Research","funders":"National Institutes of Health","keywords":"Medicine; Clinical trial; Intensive care medicine; Endpoint Determination; Cancer; Medical physics; Internal medicine","score_opus":0.9052111927268044,"score_gpt":0.7439559206187487,"score_spread":0.16125527210805568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057648481","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023728704,0.04060535,0.02124462,0.85596955,0.037180834,0.018347861,0.0007577661,0.0006709324,0.001494384],"genre_scores_gemma":[0.01520155,0.0064992886,0.73602587,0.16283818,0.06524027,0.012491186,0.00006760825,0.0012334931,0.000402574],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93754953,0.04102487,0.015003006,0.0026739587,0.0018311134,0.0019175087],"domain_scores_gemma":[0.76790625,0.22185288,0.008575731,0.0011903298,0.00029159078,0.00018321826],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.10757505,0.001183887,0.010739949,0.0009799912,0.000104604835,0.0008955766,0.0011386427,0.0045738257,0.00080233946],"category_scores_gemma":[0.27225482,0.00094075064,0.0010646355,0.0012301459,0.00053750223,0.0004952609,0.00039873787,0.008923591,0.000009797439],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044035653,0.00048399213,0.0845291,0.003710229,0.00018787259,0.0010325387,0.000153837,0.000025423235,0.000004687623,0.00035792944,0.107324004,0.80175],"study_design_scores_gemma":[0.021176957,0.00026223942,0.026391331,0.19818203,0.0015758923,0.0000137214665,0.00034811092,0.0045142923,0.000090199115,0.57294774,0.17054334,0.003954167],"about_ca_topic_score_codex":0.00009940428,"about_ca_topic_score_gemma":0.00060833234,"teacher_disagreement_score":0.79779583,"about_ca_system_score_codex":0.0016505336,"about_ca_system_score_gemma":0.0011570558,"threshold_uncertainty_score":0.9993043},"labels":[],"label_agreement":null},{"id":"W2057677543","doi":"10.1006/rtph.2001.1415","title":"Reply to Comment","year":2000,"lang":"en","type":"article","venue":"Regulatory Toxicology and Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cantox Health Sciences International","funders":"","keywords":"Endocrinology; Internal medicine; Alkaline phosphatase; Toxicity; Chemistry; Body weight; Tap water; Creatinine; Animal science; Biology; Medicine; Biochemistry","score_opus":0.3338266178407151,"score_gpt":0.5470417684210886,"score_spread":0.21321515058037355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057677543","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9220389,0.00013737667,0.0031848904,0.060481235,0.0020123646,0.0012063095,0.000041496718,0.00023921828,0.01065821],"genre_scores_gemma":[0.20754844,0.000116586205,0.4989549,0.28491685,0.0011590677,0.0002978756,0.0000016213033,0.000066432294,0.006938253],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99736196,0.0011829144,0.0005465508,0.00041900226,0.00010973229,0.0003798473],"domain_scores_gemma":[0.98645616,0.012862086,0.000078350975,0.00026049773,0.00003489817,0.00030800328],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018115353,0.00017135285,0.0005256889,0.00006215432,0.0001314393,0.00000790639,0.00019011377,0.00022809705,0.027101472],"category_scores_gemma":[0.0017186851,0.00015784828,0.00006134052,0.000093134506,0.0003154613,0.000027796626,0.00008588415,0.0002776854,0.00020671437],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008117876,0.00045455297,0.0003102072,0.00006670443,0.00018814678,0.000066605535,0.00028076727,0.000007564861,0.00819522,0.13341464,0.7497289,0.10647488],"study_design_scores_gemma":[0.0011533394,0.0004533103,0.0012712755,0.0000074982095,0.00010684409,0.000031768952,0.000007749045,0.00004116643,0.008169918,0.510512,0.4780737,0.00017143918],"about_ca_topic_score_codex":0.0000024271194,"about_ca_topic_score_gemma":9.5045095e-7,"teacher_disagreement_score":0.7144905,"about_ca_system_score_codex":0.00004226112,"about_ca_system_score_gemma":0.00003405174,"threshold_uncertainty_score":0.9737879},"labels":[],"label_agreement":null},{"id":"W2058047353","doi":"10.1016/j.urolonc.2010.06.010","title":"Advanced topics in evidence-based urologic oncology: Surrogate endpoints","year":2011,"lang":"en","type":"review","venue":"Urologic Oncology Seminars and Original Investigations","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Poznańskie Centrum Superkomputerowo-Sieciowe","keywords":"Surrogate endpoint; Clinical endpoint; Context (archaeology); Endpoint Determination; Medicine; Clinical trial; Intensive care medicine; Medical physics; Internal medicine","score_opus":0.6405611199299064,"score_gpt":0.570225369675923,"score_spread":0.07033575025398342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058047353","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005458313,0.98760724,0.0010056155,0.0021879382,0.0015879682,0.0025179707,0.00015232112,0.00022675775,0.004168378],"genre_scores_gemma":[0.0000017781456,0.53666764,0.46145773,0.00078517484,0.00019979314,0.00052849576,0.00001543721,0.000039093487,0.0003048475],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9887962,0.0060109426,0.002622022,0.0013773435,0.00028326828,0.0009102657],"domain_scores_gemma":[0.92287934,0.074016646,0.0016642064,0.00081460236,0.0001282353,0.00049699197],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0064256066,0.0008898677,0.004450839,0.000512355,0.00023282102,0.000041067142,0.000866842,0.0025001068,0.00053954276],"category_scores_gemma":[0.072669305,0.00069357286,0.00046816192,0.0008255918,0.0021146694,0.00017359035,0.00031008266,0.002475111,0.0001164628],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015124178,0.0006395259,0.0011961269,0.0034191525,0.00013062952,0.00060768495,0.00012314502,0.000004297103,5.269044e-7,0.12170415,0.002347304,0.86967623],"study_design_scores_gemma":[0.0006026297,0.0018587153,0.000007159091,0.0027033982,0.0009431451,0.00008491331,0.000014783629,0.000032673797,0.0000019562308,0.35964003,0.6337155,0.00039505315],"about_ca_topic_score_codex":0.00002350583,"about_ca_topic_score_gemma":0.00006652199,"teacher_disagreement_score":0.8692812,"about_ca_system_score_codex":0.00059019116,"about_ca_system_score_gemma":0.002058244,"threshold_uncertainty_score":0.9998262},"labels":[],"label_agreement":null},{"id":"W2058080345","doi":"10.1016/j.cct.2009.03.010","title":"An analysis of current pharmaceutical industry practices for making clinical trial results publicly accessible","year":2009,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"QUAD Engineering (Canada)","funders":"","keywords":"Medicine; Clinical trial; Gefitinib; Family medicine; Varenicline; Pharmacology; Internal medicine; Cancer","score_opus":0.9761767828606797,"score_gpt":0.8061697989041927,"score_spread":0.17000698395648695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058080345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4213517,0.002862049,0.4536744,0.01998966,0.040983006,0.035160698,0.009144322,0.0016898257,0.015144341],"genre_scores_gemma":[0.76045424,0.00028636132,0.22918071,0.0014242439,0.008167343,0.0001933065,0.00010367041,0.00007488313,0.00011523824],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92031085,0.046856225,0.027815036,0.0025519961,0.0015119036,0.00095397624],"domain_scores_gemma":[0.27375156,0.69598037,0.024339238,0.003065477,0.0014382178,0.0014251122],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2814229,0.00069494493,0.008918848,0.00063366257,0.00018828952,0.00036818744,0.0019425084,0.002364152,0.00034270342],"category_scores_gemma":[0.90284777,0.0005447372,0.004513891,0.0018735207,0.00075295166,0.0009480448,0.0002261513,0.0031595419,0.000011259005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.36116534,0.01634151,0.013254743,0.00020212658,0.0057778535,0.000027682841,0.00005787932,0.000008209977,0.000039946695,0.055827666,0.03459775,0.5126993],"study_design_scores_gemma":[0.2647428,0.015112148,0.009194598,0.00056440436,0.018417662,0.0000018389668,0.00018044401,0.009269606,0.0002839669,0.6249669,0.05575572,0.001509936],"about_ca_topic_score_codex":0.000009479142,"about_ca_topic_score_gemma":0.000006005662,"teacher_disagreement_score":0.64912415,"about_ca_system_score_codex":0.00005738063,"about_ca_system_score_gemma":0.0012813803,"threshold_uncertainty_score":0.9997004},"labels":[],"label_agreement":null},{"id":"W2058388133","doi":"10.1007/s13311-013-0221-6","title":"Designing Clinical Trials for Dystonia","year":2013,"lang":"en","type":"review","venue":"Neurotherapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dystonia Medical Research Foundation Canada; Toronto Western Hospital","funders":"National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; National Institutes of Health; Dystonia Coalition; Dystonia Medical Research Foundation","keywords":"Clinical trial; Dystonia; Tolerability; Clinical study design; Medicine; Medical physics; Psychology; Intensive care medicine; Alternative medicine; Psychiatry; Pathology","score_opus":0.9729653065478591,"score_gpt":0.7536013271799333,"score_spread":0.21936397936792573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058388133","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.683994e-8,0.6305251,0.3576579,0.00004766417,0.0030617237,0.007889723,0.000255301,0.00020064489,0.00036188684],"genre_scores_gemma":[5.6579252e-9,0.5235724,0.47241175,0.00035200105,0.0016791114,0.0010796337,0.0000044192197,0.00026547967,0.0006351961],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9676426,0.021343349,0.008585908,0.0011652015,0.0005172116,0.0007457162],"domain_scores_gemma":[0.48167005,0.51294965,0.003491664,0.0013166497,0.0002497818,0.00032223095],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03889813,0.00097293686,0.011452583,0.00018084318,0.0001418108,0.0001961813,0.0010828301,0.001766312,0.0004908408],"category_scores_gemma":[0.33608496,0.00068238244,0.0039596935,0.00030705176,0.0002960934,0.00005168282,0.00010048765,0.0015505183,0.00029160787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027637765,0.00018045817,3.2618377e-7,0.010643199,0.0006706064,0.0000049028504,0.0000070481838,2.3947669e-8,0.0000010400867,0.020057937,0.0069291783,0.96147764],"study_design_scores_gemma":[0.0007330034,0.00033334453,5.94455e-8,0.0028801851,0.004637791,0.00001019785,0.0000020461932,0.000023223369,0.0000042687043,0.28158453,0.70932424,0.00046713994],"about_ca_topic_score_codex":7.3477355e-7,"about_ca_topic_score_gemma":2.8230704e-7,"teacher_disagreement_score":0.9610105,"about_ca_system_score_codex":0.00007554866,"about_ca_system_score_gemma":0.00048000077,"threshold_uncertainty_score":0.99956274},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2058899694","doi":"10.1002/sim.4011","title":"Nonparametric sequential monitoring of longitudinal trials","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Nonparametric statistics; Computer science; Simple (philosophy); Applied mathematics; Monte Carlo method; Statistics; Longitudinal data; Mathematics; Algorithm; Data mining","score_opus":0.6279650322204489,"score_gpt":0.6259249707736588,"score_spread":0.0020400614467900313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058899694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09149694,0.00007097444,0.89728796,0.00022116398,0.0078091957,0.0007223982,0.00037240898,0.000051608153,0.0019673656],"genre_scores_gemma":[0.23108704,0.000053142387,0.7674971,0.000012879345,0.0012211035,0.000021049806,0.0000033112535,0.000028077064,0.000076263714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945468,0.0010595358,0.0027829893,0.0003816373,0.00086000393,0.00036906105],"domain_scores_gemma":[0.85187846,0.14629577,0.00082718325,0.000538111,0.00029147335,0.00016896652],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018957302,0.00023076803,0.0018333473,0.0003933041,0.000037968657,0.000010713697,0.00036244636,0.00022262176,0.0015764185],"category_scores_gemma":[0.60937965,0.00017713635,0.00008446279,0.00071622955,0.00066150626,0.000035367746,0.00008439827,0.00090399454,0.000011852615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031698062,0.0003654207,0.05156487,0.0005261687,0.00014718957,0.00012259875,0.00029711096,0.0000035351313,0.01038496,0.87594384,0.005015174,0.05531215],"study_design_scores_gemma":[0.002374745,0.00029698334,0.018906489,0.00023091205,0.00022771386,0.000007303632,0.000075695694,0.0001803968,0.0025795747,0.9748288,0.0001234328,0.00016794597],"about_ca_topic_score_codex":0.000088633664,"about_ca_topic_score_gemma":0.000027451773,"teacher_disagreement_score":0.59042233,"about_ca_system_score_codex":0.00003822436,"about_ca_system_score_gemma":0.000086619926,"threshold_uncertainty_score":0.9993363},"labels":[],"label_agreement":null},{"id":"W2058914942","doi":"10.1191/1740774505cn084oa","title":"A critical history of individual and collective ethics in the lineage of Lellouch and Schwartz","year":2005,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Exposition (narrative); Normative; Dilemma; Epistemology; Sociology; Collective action; Meta-ethics; Engineering ethics; Information ethics; Law; Political science; Philosophy","score_opus":0.9186973067652314,"score_gpt":0.7038480207878172,"score_spread":0.21484928597741426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058914942","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8692304,0.010124039,0.06300734,0.024876032,0.005855672,0.008672856,0.0012551645,0.00016030611,0.016818194],"genre_scores_gemma":[0.37517107,0.00068023935,0.6210712,0.0016462116,0.0010465244,0.000056294382,0.0000010828236,0.000035693884,0.00029169067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9692016,0.023931935,0.005347834,0.0005084948,0.0007273592,0.00028273207],"domain_scores_gemma":[0.28277504,0.7154534,0.00090207654,0.00045282952,0.00026846144,0.00014819938],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14276224,0.00019521869,0.0023254545,0.00010458411,0.000038438913,0.000020659634,0.00036239272,0.00071544526,0.00015956702],"category_scores_gemma":[0.88441825,0.00013106405,0.00028311124,0.00020521379,0.0023652937,0.00006743804,0.00019810801,0.0014362752,0.000002544949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004171803,0.0058754184,0.006979978,0.0017153793,0.0007355898,0.000041308405,0.019448765,0.000001861368,0.0006015884,0.77070177,0.04098216,0.1487444],"study_design_scores_gemma":[0.0056609567,0.0011978647,0.0060794163,0.00032907818,0.00061287556,0.000007544732,0.00048452156,0.00018330722,0.0005102478,0.9809004,0.0037986534,0.00023515536],"about_ca_topic_score_codex":0.000005989191,"about_ca_topic_score_gemma":0.000008822939,"teacher_disagreement_score":0.741656,"about_ca_system_score_codex":0.000053636,"about_ca_system_score_gemma":0.0005258962,"threshold_uncertainty_score":0.88270664},"labels":[],"label_agreement":null},{"id":"W2059417084","doi":"10.1016/j.ijrobp.2008.06.1095","title":"Inter- and Intra-observer Agreement in Clinical Target Volumes for Post-prostatectomy Patients","year":2008,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario","funders":"","keywords":"Medicine; Prostatectomy; Intraclass correlation; Prostate; Nuclear medicine; Urology; Contouring; Seminal vesicle; Confidence interval; Observer (physics); Radiation therapy; Prostate cancer; Radiology; Internal medicine; Cancer","score_opus":0.22720845791068314,"score_gpt":0.5049850959441553,"score_spread":0.2777766380334722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059417084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84774107,0.00008092295,0.14461826,0.0017721537,0.0047213077,0.0006297816,0.0002867591,0.00002289201,0.0001268568],"genre_scores_gemma":[0.6090633,0.00035248624,0.3874913,0.0012130038,0.0017459983,0.00003145176,0.000034187167,0.000033123397,0.00003517771],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956594,0.0010253837,0.0024150924,0.00032873443,0.0002907215,0.00028067024],"domain_scores_gemma":[0.9792708,0.017295454,0.0017563674,0.00016537555,0.001355399,0.00015660116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033636887,0.00022398554,0.00088901655,0.0001462388,0.000064304346,0.00002268445,0.00047467762,0.00033989412,0.00008445212],"category_scores_gemma":[0.037513155,0.0001929325,0.0002960705,0.00011345909,0.00040293526,0.00023341825,0.00013309442,0.00059202965,0.000011270602],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011097845,0.0013661743,0.7832533,0.000022932947,0.00043276738,0.00002985113,0.0004066301,0.000018977747,0.000069790265,0.022962293,0.0031298262,0.18719769],"study_design_scores_gemma":[0.015577591,0.0035153767,0.1536698,0.000091195856,0.00009663762,0.000028634291,0.00006160771,0.0019881467,0.00035796408,0.81258404,0.011719439,0.0003095592],"about_ca_topic_score_codex":0.000009082961,"about_ca_topic_score_gemma":0.0000063976345,"teacher_disagreement_score":0.7896218,"about_ca_system_score_codex":0.00035011,"about_ca_system_score_gemma":0.00029458114,"threshold_uncertainty_score":0.9705943},"labels":[],"label_agreement":null},{"id":"W2059469444","doi":"10.1016/j.pain.2008.06.025","title":"Analyzing multiple endpoints in clinical trials of pain treatments: IMMPACT recommendations","year":2008,"lang":"en","type":"review","venue":"Pain","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":219,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Centre for Global Health Research; University of Toronto","funders":"Allergan; National Institutes of Health; University of Rochester; U.S. Department of Veterans Affairs","keywords":"Clinical trial; Medicine; Type I and type II errors; Clinical endpoint; Intensive care medicine; Gatekeeping; Randomized controlled trial; Medical physics; Statistics; Internal medicine","score_opus":0.8869929090371754,"score_gpt":0.7068485700059751,"score_spread":0.1801443390312003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059469444","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012650601,0.74241424,0.25210732,0.00009361305,0.0006954628,0.0030622077,0.0011583923,0.00007509762,0.00039243733],"genre_scores_gemma":[0.0000015112998,0.62789756,0.37134758,0.000033173248,0.00029079145,0.00020025045,0.000069145506,0.00007116112,0.0000888116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.69210565,0.28690457,0.018535351,0.0011925844,0.00053342583,0.00072840485],"domain_scores_gemma":[0.3027395,0.69181246,0.0042226296,0.0009259381,0.000084690924,0.00021476563],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2927062,0.0006528515,0.010975563,0.0004818782,0.00006274988,0.000024004916,0.00055516977,0.0009404628,0.0007850831],"category_scores_gemma":[0.93373,0.00048277102,0.0031557933,0.00078941445,0.00020544397,0.000053248907,0.00012997902,0.0010445245,0.000052824314],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031524534,0.0008657665,0.00015674916,0.0034970758,0.00076949334,0.000023302753,0.00003085318,9.686043e-8,9.31408e-8,0.0006295983,0.006313343,0.9876821],"study_design_scores_gemma":[0.0036603084,0.0005526339,0.000024930041,0.042328767,0.0032462059,0.000010783412,0.000060890958,0.0005172467,0.000002382243,0.21292707,0.7356059,0.0010628799],"about_ca_topic_score_codex":0.000038004917,"about_ca_topic_score_gemma":0.000023914175,"teacher_disagreement_score":0.98661923,"about_ca_system_score_codex":0.00027118978,"about_ca_system_score_gemma":0.0003884599,"threshold_uncertainty_score":0.9997624},"labels":[],"label_agreement":null},{"id":"W2060337608","doi":"10.1080/03610918.2014.920877","title":"Permutation Methods for Comparing the Accuracy of Nested Prediction Models in Survival Analysis","year":2014,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Permutation (music); Resampling; Covariate; Computer science; Sample size determination; Computation; Data mining; Statistics; Algorithm; Artificial intelligence; Machine learning; Mathematics","score_opus":0.7745191346689994,"score_gpt":0.6710572868435637,"score_spread":0.10346184782543566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060337608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012015485,0.00004547228,0.9864941,0.00015194541,0.00010375646,0.0008304509,0.00009665975,0.000031930165,0.00023017894],"genre_scores_gemma":[0.5061777,0.000020929358,0.49362084,0.000013944877,0.000010569152,0.00005616137,0.000087896544,0.000009283356,0.0000026619637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99498963,0.002984418,0.0014307791,0.00025103346,0.00019558793,0.00014854176],"domain_scores_gemma":[0.85695785,0.1414812,0.0005744389,0.00056242716,0.0003876759,0.000036392452],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006100773,0.00014243058,0.00056190445,0.00036391025,0.0001593923,0.000052056763,0.00030643496,0.00010395346,0.000004257717],"category_scores_gemma":[0.03549384,0.00013004777,0.00006734962,0.0009793999,0.00020250735,0.00014964254,0.00011807387,0.00021305482,3.1237292e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050734707,0.00011221892,0.0040637893,0.00005880859,0.00005257838,2.5542459e-8,0.0008588394,0.56226385,0.000012177403,0.35641065,0.000005311665,0.07611105],"study_design_scores_gemma":[0.0005901821,0.000026413485,0.021982502,0.000022453829,0.00014535223,9.6598775e-8,0.00012159956,0.51770324,0.0000036297342,0.45933267,0.000013208105,0.000058671023],"about_ca_topic_score_codex":0.000058703972,"about_ca_topic_score_gemma":0.00021249363,"teacher_disagreement_score":0.49416223,"about_ca_system_score_codex":0.000065071414,"about_ca_system_score_gemma":0.00003414218,"threshold_uncertainty_score":0.9726306},"labels":[],"label_agreement":null},{"id":"W2060897239","doi":"10.1080/03610918.2012.674599","title":"Weighted Multiple Testing Correction for Correlated Binary Endpoints","year":2013,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Population Health Research Institute; University of Calgary","funders":"","keywords":"Bonferroni correction; Multiple comparisons problem; Type I and type II errors; Statistics; Binary number; Sequence (biology); Mathematics; False discovery rate; Correlation; Statistical hypothesis testing; Statistical power; Computer science; Biology; Genetics; Arithmetic","score_opus":0.6562664388264549,"score_gpt":0.5881034977318212,"score_spread":0.06816294109463361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060897239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021801237,0.00003870284,0.9753172,0.00015942217,0.0004521299,0.0015560207,0.00010838349,0.0001467288,0.00042022215],"genre_scores_gemma":[0.46588764,0.00001141982,0.53370595,0.000044766814,0.000022343485,0.0001527114,0.00009763763,0.000020864856,0.00005664309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751097,0.0006851508,0.001097443,0.0003062118,0.000183202,0.00021703346],"domain_scores_gemma":[0.8867483,0.11161844,0.00040557733,0.00046766418,0.0006754851,0.00008452888],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010610952,0.00018545667,0.00035415284,0.00020513595,0.00031717887,0.000103559294,0.0002278978,0.00015635708,0.000045429573],"category_scores_gemma":[0.04683588,0.00019772328,0.000034903656,0.00047345395,0.0001846132,0.00018320106,0.00014222022,0.0002820314,0.000022059516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017383926,0.0009245906,0.012887103,0.00022904274,0.00007931602,0.0000015580712,0.001160084,0.0609473,0.0003368958,0.08878715,0.0040498213,0.8304233],"study_design_scores_gemma":[0.0008668467,0.000065670996,0.010372495,0.000059005495,0.000026143207,0.0000010413881,0.00007208082,0.5760922,0.000008165893,0.41224092,0.0000726056,0.00012285843],"about_ca_topic_score_codex":0.00006246352,"about_ca_topic_score_gemma":0.000029156232,"teacher_disagreement_score":0.83030045,"about_ca_system_score_codex":0.00009726454,"about_ca_system_score_gemma":0.00004448162,"threshold_uncertainty_score":0.961193},"labels":[],"label_agreement":null},{"id":"W2061828617","doi":"10.1080/10629360500109023","title":"Comprehensive study of tests for normality and symmetry: extending the Spiegelhalter test","year":2006,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normality; Normality test; Mathematics; Statistics; Symmetry (geometry); Statistical hypothesis testing; Sample size determination; Asymptotic distribution; Test (biology); Inference; Nominal level; Statistical inference; Econometrics; Confidence interval; Computer science; Artificial intelligence; Geometry; Estimator","score_opus":0.40329186801925937,"score_gpt":0.5630034197151369,"score_spread":0.15971155169587753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061828617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38111508,0.00002593064,0.6182979,0.00007007529,0.00008325066,0.00034442527,0.000040386043,0.0000045496317,0.000018411736],"genre_scores_gemma":[0.678814,0.0000024615183,0.32103845,0.000026609123,0.000105099745,0.0000019367058,0.0000012903143,0.0000073882334,0.0000027780507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978615,0.0003940051,0.0011771793,0.00013177135,0.00032586665,0.000109656605],"domain_scores_gemma":[0.891458,0.10720932,0.0006624328,0.00006692236,0.0005464886,0.00005687683],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013770757,0.00011105057,0.0004525183,0.00007717861,0.000112037786,0.000049129903,0.000056357203,0.00005050537,0.000007991435],"category_scores_gemma":[0.019566782,0.00007386469,0.000040710296,0.0001132445,0.00013496687,0.00008125586,0.000030416519,0.00014919249,1.8250815e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023624734,0.005405342,0.09135644,0.0018296277,0.00045003838,0.000048931775,0.001851123,0.080627844,0.0009760744,0.55362266,0.0014859949,0.25998345],"study_design_scores_gemma":[0.0018378039,0.00096241035,0.20848048,0.00003431167,0.00014458876,0.000008571723,0.0001989517,0.17902346,0.000011306648,0.6092104,0.000022129427,0.000065628716],"about_ca_topic_score_codex":0.000009859253,"about_ca_topic_score_gemma":0.0000031843038,"teacher_disagreement_score":0.29769892,"about_ca_system_score_codex":0.000018179355,"about_ca_system_score_gemma":0.000016494818,"threshold_uncertainty_score":0.9886918},"labels":[],"label_agreement":null},{"id":"W2061870174","doi":"10.1155/2012/852384","title":"Cutting Edge PBPK Models and Analyses: Providing the Basis for Future Modeling Efforts and Bridges to Emerging Toxicology Paradigms","year":2012,"lang":"en","type":"article","venue":"Journal of Toxicology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Physiologically based pharmacokinetic modelling; Human health; Computer science; Risk assessment; Risk analysis (engineering); Process (computing); Data science; Biochemical engineering; Management science; Computational biology; Bioinformatics; Medicine; Biology; Engineering; Pharmacokinetics; Environmental health","score_opus":0.583268262767895,"score_gpt":0.5725538369461494,"score_spread":0.010714425821745643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061870174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45874688,0.00080245617,0.5348358,0.0039874935,0.0010526186,0.00048059205,0.000010329659,0.000012639815,0.0000711516],"genre_scores_gemma":[0.5596997,0.00011779258,0.4377895,0.00068700215,0.0016384923,0.000027184786,1.1430489e-7,0.00002626552,0.00001394957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969853,0.0006906813,0.0012945641,0.0002434501,0.00021677837,0.00056921673],"domain_scores_gemma":[0.9748421,0.023716707,0.000703263,0.00021244875,0.00019839758,0.00032713506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0068253344,0.00022514736,0.000983266,0.00018415262,0.0002553945,0.00005641153,0.00025231374,0.00027203592,0.000016526914],"category_scores_gemma":[0.027503423,0.00014783385,0.00018096901,0.00014662034,0.0001086162,0.00024171882,0.00018006058,0.00044634985,4.8666647e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028357552,0.0013755953,0.0052126455,0.0016100644,0.002632693,0.000080323196,0.018319132,0.021252805,0.029836878,0.6071257,0.006161117,0.30355728],"study_design_scores_gemma":[0.0018035128,0.001410475,0.00044069404,0.00023602127,0.0012179834,0.0006731896,0.002937119,0.16426234,0.0033137011,0.82200634,0.0012487757,0.00044985762],"about_ca_topic_score_codex":0.0000023261177,"about_ca_topic_score_gemma":0.0000049917576,"teacher_disagreement_score":0.3031074,"about_ca_system_score_codex":0.000078983154,"about_ca_system_score_gemma":0.00006485218,"threshold_uncertainty_score":0.98068833},"labels":[],"label_agreement":null},{"id":"W2063146817","doi":"10.1002/cjs.10002","title":"Log‐rank permutation tests for trend: saddlepoint<i>p</i>‐values and survival rate confidence intervals","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Statistics; Confidence interval; Permutation (music); Statistic; Censoring (clinical trials); Computation; Log-rank test; Rank (graph theory); Test statistic; Statistical hypothesis testing; Combinatorics; Survival analysis; Algorithm","score_opus":0.3827156616167734,"score_gpt":0.499844750703545,"score_spread":0.11712908908677161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063146817","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014277679,0.00021277902,0.9806034,0.0012002941,0.0011821527,0.00035645254,0.0018416052,0.000012980152,0.00031266644],"genre_scores_gemma":[0.2105854,0.00006579869,0.7882746,0.00048743206,0.00037517672,0.0000033286797,0.0000062860736,0.000028055423,0.00017393842],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972937,0.00054151844,0.0013207145,0.0002101406,0.00024090317,0.00039301935],"domain_scores_gemma":[0.96523845,0.03251591,0.0007415391,0.00018694882,0.0005766486,0.0007404922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038047137,0.00021255505,0.0007457547,0.00019736297,0.00014088968,0.0001368926,0.00024228328,0.00012749045,0.00013906267],"category_scores_gemma":[0.11484183,0.0001909153,0.000101033635,0.00012596819,0.00027624692,0.00012285139,0.000008864467,0.00029716073,0.0000031698148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040282813,0.0001098244,0.0011394804,0.00036927318,0.0002509921,0.00062294013,0.0022096892,0.000027953107,0.0006666344,0.77158165,0.062948264,0.1596705],"study_design_scores_gemma":[0.0011695822,0.0009360529,0.005661598,0.00021885238,0.00022276472,0.00008682938,0.0002133799,0.00047685477,0.00018157449,0.9901125,0.00050917675,0.00021082348],"about_ca_topic_score_codex":0.00013853014,"about_ca_topic_score_gemma":0.0027239379,"teacher_disagreement_score":0.21853088,"about_ca_system_score_codex":0.00010794995,"about_ca_system_score_gemma":0.00056636473,"threshold_uncertainty_score":0.89261425},"labels":[],"label_agreement":null},{"id":"W2063301308","doi":"10.1080/02664760802124455","title":"Statistical inference for start-up demonstration tests with rejection of units upon observing<i>d</i>failures","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Chinese University of Hong Kong; University of Hong Kong","keywords":"Inference; Estimator; Statistical inference; Likelihood function; Computer science; Bayesian probability; Statistics; Bayesian inference; Maximum likelihood; Expectation–maximization algorithm; Mathematics; Sample (material); Econometrics; Artificial intelligence","score_opus":0.4423127721272717,"score_gpt":0.48979964912010265,"score_spread":0.04748687699283094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063301308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028973684,0.000012487558,0.96877635,0.00005723766,0.00036267107,0.000561097,0.00093774876,0.000023543562,0.00029518298],"genre_scores_gemma":[0.27911782,0.000051267765,0.7205358,0.000031484018,0.00017723853,0.0000147100955,0.000010984896,0.00003556344,0.00002511396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963699,0.00023885479,0.0019828896,0.00024493545,0.0008390332,0.00032440058],"domain_scores_gemma":[0.9474825,0.048539326,0.0017670748,0.00028357882,0.0017137275,0.00021377091],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019493944,0.0002688427,0.0009840882,0.00014914564,0.00015162832,0.000030032157,0.00026983547,0.00017905829,0.00007294675],"category_scores_gemma":[0.048974473,0.00021199272,0.00006206309,0.00037243386,0.00033505473,0.00010192151,0.000037652844,0.000465807,0.0000022719075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003911419,0.00045437284,0.00080534583,0.0007397482,0.00028491355,0.00006399924,0.00069572974,0.0003933906,0.0028226196,0.9599333,0.01035032,0.019544845],"study_design_scores_gemma":[0.0031910092,0.0023451755,0.0031245209,0.00021172002,0.00045683797,0.000098268734,0.00026528517,0.0017201417,0.004451612,0.9833026,0.0005237523,0.00030911184],"about_ca_topic_score_codex":0.000008866031,"about_ca_topic_score_gemma":0.000049238042,"teacher_disagreement_score":0.25014415,"about_ca_system_score_codex":0.000086212756,"about_ca_system_score_gemma":0.0006458579,"threshold_uncertainty_score":0.9590364},"labels":[],"label_agreement":null},{"id":"W2063486572","doi":"10.1007/s10985-009-9132-6","title":"Confidence intervals for the first crossing point of two hazard functions","year":2009,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Proportional hazards model; Hazard ratio; Event (particle physics); Hazard; Confidence interval; Statistics; Nonparametric statistics; Monte Carlo method; Mathematics; Power transform; Smoothing; Econometrics; Computer science; Artificial intelligence","score_opus":0.49486301611838934,"score_gpt":0.5662854192028375,"score_spread":0.07142240308444814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063486572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035542544,0.00008265947,0.99258655,0.0036147225,0.00015029653,0.00034093307,0.0025572423,0.000041183754,0.0002710056],"genre_scores_gemma":[0.10980561,0.000017813209,0.8884326,0.0008257404,0.00035434292,0.000024057194,0.000113044014,0.000016696522,0.0004100502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99754983,0.00027283668,0.0011506095,0.00046876806,0.0003244368,0.00023353974],"domain_scores_gemma":[0.94124097,0.0556062,0.0005067142,0.002363225,0.00020336696,0.00007950459],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005211808,0.00015772374,0.00081871374,0.000115399234,0.0002839771,0.0001689364,0.0011389632,0.000072579074,0.00077245396],"category_scores_gemma":[0.07960883,0.000105679355,0.00041302523,0.0007992119,0.00031330614,0.00014175479,0.00024411627,0.00015592865,0.000025746976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010104275,0.0018034468,0.003999902,0.00046444035,0.019398956,0.000014798329,0.0010977912,0.0014369532,0.0008963254,0.53248334,0.32523194,0.112161666],"study_design_scores_gemma":[0.0007921439,0.00014273715,0.0018297497,0.0000908263,0.010962231,0.0000015069645,0.00009843278,0.07606088,0.00040761544,0.90523976,0.00415242,0.00022168155],"about_ca_topic_score_codex":0.00007037372,"about_ca_topic_score_gemma":0.00013350979,"teacher_disagreement_score":0.3727564,"about_ca_system_score_codex":0.000018723222,"about_ca_system_score_gemma":0.000044813405,"threshold_uncertainty_score":0.92814404},"labels":[],"label_agreement":null},{"id":"W2063974614","doi":"10.1191/0962280205sm0391oa","title":"On group sequential procedures under variance heterogeneity","year":2005,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variance (accounting); Group (periodic table); Statistics; Econometrics; Computer science; Mathematics; Economics","score_opus":0.7225271869331464,"score_gpt":0.7272749290543858,"score_spread":0.004747742121239407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063974614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022374673,0.00008034224,0.9820144,0.0044765635,0.00059959706,0.0009621779,0.00011018962,0.00012562862,0.009393622],"genre_scores_gemma":[0.034033705,0.00010505913,0.9627651,0.0014405723,0.0009977554,0.0003233798,0.0000050134554,0.00009193564,0.0002374541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9629804,0.026176767,0.00219012,0.0015061134,0.005217883,0.0019287525],"domain_scores_gemma":[0.6050908,0.392111,0.00015361268,0.0009689937,0.00033222625,0.0013433344],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071765244,0.0004259197,0.0012464799,0.00041650803,0.00025122572,0.00011756535,0.0012963124,0.000820916,0.012496996],"category_scores_gemma":[0.75534326,0.00034266774,0.00016216128,0.0011561692,0.002169226,0.00009805984,0.00062914396,0.0040892432,0.00034917652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041500686,0.00084582646,0.000040287243,0.00018462942,0.0000397303,0.00014942093,0.000035704117,0.0000057521643,0.00019920275,0.7040132,0.004419881,0.2896513],"study_design_scores_gemma":[0.0017048,0.0005139346,0.0011460958,0.00036796342,0.000023492554,0.00002091103,0.000038002683,0.005522822,0.0007655932,0.9871373,0.002409252,0.0003498385],"about_ca_topic_score_codex":0.000047058427,"about_ca_topic_score_gemma":0.00019461286,"teacher_disagreement_score":0.683578,"about_ca_system_score_codex":0.00047982627,"about_ca_system_score_gemma":0.0006879122,"threshold_uncertainty_score":0.99990255},"labels":[],"label_agreement":null},{"id":"W2064023586","doi":"10.6000/1929-6029.2012.01.01.07","title":"Modified McNemar Test","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"McNemar's test; Statistic; Statistics; Test statistic; Test (biology); Control (management); Mathematics; Econometrics; Statistical hypothesis testing; Computer science; Biology; Artificial intelligence","score_opus":0.7547346477049882,"score_gpt":0.7089670191742586,"score_spread":0.045767628530729576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064023586","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02259429,0.00029431895,0.94826305,0.0065110545,0.0065011205,0.00038277198,0.00035202628,0.000021263066,0.015080106],"genre_scores_gemma":[0.41058037,0.00044632648,0.58622086,0.00021403897,0.002299632,0.0000088482375,0.0000016733228,0.000027044654,0.00020120307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.988869,0.0016081766,0.0018864025,0.00016278024,0.00684585,0.00062776636],"domain_scores_gemma":[0.76489556,0.23134229,0.0004241753,0.00022977657,0.0023201092,0.0007880976],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03852961,0.00013358834,0.00051580026,0.0005587632,0.000045156925,0.000058943908,0.0013802955,0.00023421875,0.003121738],"category_scores_gemma":[0.7245656,0.00010510316,0.00009139256,0.00034157882,0.0005584641,0.0001509065,0.000318913,0.0021106014,0.00007089456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032304923,0.0017911502,0.009366643,0.000061466395,0.00012749058,0.0011065707,0.00030537852,0.0000033081083,0.000079695725,0.7963296,0.04231831,0.1481873],"study_design_scores_gemma":[0.0016145057,0.000217493,0.004459886,0.00036242927,0.000013964941,0.00015728774,0.00011598726,0.0009258038,0.00014545156,0.9879487,0.003925915,0.00011254282],"about_ca_topic_score_codex":0.000021572778,"about_ca_topic_score_gemma":0.0000106133675,"teacher_disagreement_score":0.68603605,"about_ca_system_score_codex":0.00031457073,"about_ca_system_score_gemma":0.0004895939,"threshold_uncertainty_score":0.99778956},"labels":[],"label_agreement":null},{"id":"W2064381090","doi":"10.1002/pst.111","title":"Carry‐over in cross‐over trials in bioequivalence: theoretical concerns and empirical evidence","year":2004,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pfizer (Canada)","funders":"","keywords":"Carry (investment); Bioequivalence; Estimator; Context (archaeology); Econometrics; Computer science; Test (biology); Order (exchange); Mathematics; Statistics; Economics; Medicine; Pharmacology","score_opus":0.8455461255403379,"score_gpt":0.7076831575087411,"score_spread":0.1378629680315968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064381090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42672777,0.00094682485,0.5627643,0.0030187927,0.0014217236,0.002486307,0.0017102435,0.00016771775,0.00075632334],"genre_scores_gemma":[0.6306677,0.00079295726,0.366963,0.0010624039,0.00036165435,0.00007459628,0.0000028443053,0.000055269073,0.000019559922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9898248,0.0038446705,0.003238529,0.0010005736,0.0010429933,0.0010484448],"domain_scores_gemma":[0.8341656,0.16442251,0.00032052232,0.00041174522,0.00012344927,0.0005562234],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016531724,0.0004893036,0.0019703815,0.0001801216,0.00008295218,0.00017889374,0.00046601694,0.00043261354,0.0026091062],"category_scores_gemma":[0.37030193,0.00040756527,0.00016455693,0.00057943666,0.0024278834,0.00019456203,0.0003571604,0.0013221377,0.00004917832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011848004,0.0005418724,0.04391392,0.00039073237,0.000049111095,0.00040528283,0.00032255726,0.00003067122,0.0002566106,0.94390523,0.00074283377,0.00825638],"study_design_scores_gemma":[0.006882178,0.00022031067,0.022565752,0.0004481715,0.00018732174,0.0000120126515,0.000027104512,0.0033033588,0.00076033466,0.9647604,0.00033264112,0.00050041603],"about_ca_topic_score_codex":0.00006921551,"about_ca_topic_score_gemma":0.000042776286,"teacher_disagreement_score":0.3537702,"about_ca_system_score_codex":0.00039279717,"about_ca_system_score_gemma":0.00027343785,"threshold_uncertainty_score":0.99983764},"labels":[],"label_agreement":null},{"id":"W2064554092","doi":"10.1002/sim.2885","title":"Non‐inferiority trial design for recurrent events","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample size determination; Statistics; Poisson distribution; Robustness (evolution); Null hypothesis; Econometrics; Computer science; Event (particle physics); Marginal distribution; Random effects model; Mathematics; Medicine; Random variable; Meta-analysis; Internal medicine","score_opus":0.6391600063244661,"score_gpt":0.6329558923146955,"score_spread":0.0062041140097706116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064554092","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012426054,0.00003050844,0.9901071,0.00024801758,0.0044067125,0.0029069025,0.00023217413,0.000042923635,0.00078303553],"genre_scores_gemma":[0.0072534876,0.00004580872,0.99058247,0.00017666181,0.0015599917,0.00013405686,0.000013782363,0.000045839442,0.00018793004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959036,0.00044847128,0.0019376162,0.0004486806,0.0006713061,0.000590301],"domain_scores_gemma":[0.8821255,0.11661376,0.00038170177,0.00041027536,0.0002425019,0.00022624018],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021215882,0.00026284775,0.0010528488,0.00016942945,0.00007271914,0.0000074837876,0.00030308543,0.00020917895,0.00033912572],"category_scores_gemma":[0.28007862,0.00021283118,0.00006554313,0.00029095248,0.00025434198,0.000027162552,0.000056209945,0.00044723577,0.00001328087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09075569,0.0011360234,0.0003486436,0.0007057457,0.000124186,0.000111442445,0.0006665135,0.000003843292,0.00012247308,0.65088826,0.07853328,0.17660388],"study_design_scores_gemma":[0.04351987,0.003831127,0.0006546496,0.00025472778,0.00013038218,0.0000018072157,0.00006892767,0.0007737258,0.00011776167,0.94948685,0.00094577746,0.00021438194],"about_ca_topic_score_codex":0.000015889567,"about_ca_topic_score_gemma":0.000051372488,"teacher_disagreement_score":0.2985986,"about_ca_system_score_codex":0.00015831909,"about_ca_system_score_gemma":0.000103322694,"threshold_uncertainty_score":0.8679003},"labels":[],"label_agreement":null},{"id":"W2066131559","doi":"10.3109/13697137.2012.656004","title":"NNT, number needed to treat: does it have any real value?","year":2012,"lang":"en","type":"article","venue":"Climacteric","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Number needed to treat; Medicine; Number needed to harm; Statistician; Intervention (counseling); Harm; Adverse effect; Absolute risk reduction; Value (mathematics); Intensive care medicine; Relative risk; Confidence interval; Statistics; Internal medicine; Psychiatry; Psychology","score_opus":0.4833032056294667,"score_gpt":0.5752640351015744,"score_spread":0.09196082947210771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066131559","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8316627,0.0000103031225,0.013947402,0.0027828745,0.0029487025,0.00097004673,0.00022749472,0.000338387,0.14711206],"genre_scores_gemma":[0.23052065,0.000058910427,0.75910723,0.0026686087,0.0020561093,0.00012189484,0.000005448093,0.00010807019,0.0053530494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968589,0.000712678,0.0009057642,0.0003866038,0.000345895,0.00079014094],"domain_scores_gemma":[0.97914714,0.01924795,0.00022324792,0.00071885216,0.0000879553,0.0005748321],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021560118,0.00029783626,0.00076771213,0.000059502916,0.00009392652,0.000065597946,0.00031267898,0.00021755775,0.0029847755],"category_scores_gemma":[0.028174967,0.00020608299,0.00020241112,0.00024406878,0.000112492315,0.00014048666,0.00020657867,0.00025328918,0.0015796685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021345522,0.005239941,0.13048404,0.0016144229,0.0005833601,0.00012629606,0.012524575,0.0000016078264,0.03780852,0.4005094,0.30970675,0.09926654],"study_design_scores_gemma":[0.0023924634,0.0003243202,0.035059027,0.00020993254,0.00059011043,0.000038374685,0.0010377478,0.000035787773,0.01016667,0.92834365,0.020637041,0.0011648429],"about_ca_topic_score_codex":0.000080975595,"about_ca_topic_score_gemma":0.0000056799586,"teacher_disagreement_score":0.74515986,"about_ca_system_score_codex":0.00010828662,"about_ca_system_score_gemma":0.000026807023,"threshold_uncertainty_score":0.9991977},"labels":[],"label_agreement":null},{"id":"W2066815258","doi":"10.1097/jto.0b013e31821b10ab","title":"Biostatistics Primer: What a Clinician Ought to Know: Hazard Ratios","year":2011,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":104,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Medicine; Biostatistics; Primer (cosmetics); Hazard; Hazard ratio; Medical physics; Internal medicine; Epidemiology; Confidence interval","score_opus":0.5000480710161161,"score_gpt":0.6300492098192128,"score_spread":0.1300011388030966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066815258","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04518644,0.000575672,0.91614085,0.009258149,0.016635528,0.0012867089,0.00007894095,0.00009025863,0.010747438],"genre_scores_gemma":[0.011676288,0.00033904237,0.98419803,0.001965819,0.0012539024,0.000011714424,4.2562039e-7,0.000051055387,0.0005036919],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934827,0.0023972273,0.0028546257,0.00030305109,0.0005066216,0.00045578327],"domain_scores_gemma":[0.963823,0.032328524,0.0019742977,0.00050305726,0.00082010153,0.0005509748],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008971442,0.00026537987,0.001538774,0.00027184596,0.00008298503,0.00006461742,0.00067717675,0.00041784017,0.0010260611],"category_scores_gemma":[0.104607716,0.00020897527,0.00032364877,0.00034163104,0.00022388711,0.00027552314,0.00018538638,0.0008430241,0.00023151746],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030723584,0.0015037879,0.00047959344,0.00013779382,0.0003679365,0.0007879913,0.0019509018,0.0000015529428,0.0005053036,0.035262886,0.06031378,0.8956161],"study_design_scores_gemma":[0.0008791065,0.005572874,0.00088903884,0.00044471284,0.0007280694,0.00031084087,0.00089930464,0.0000357256,0.004700632,0.9163087,0.068881705,0.00034930283],"about_ca_topic_score_codex":0.0000029243388,"about_ca_topic_score_gemma":0.000024381654,"teacher_disagreement_score":0.89526683,"about_ca_system_score_codex":0.00021668604,"about_ca_system_score_gemma":0.0005270483,"threshold_uncertainty_score":0.9998871},"labels":[],"label_agreement":null},{"id":"W2067180843","doi":"10.1118/1.1711415","title":"TCP isoeffect analysis using a heterogeneous distribution of radiosensitivity","year":2004,"lang":"en","type":"letter","venue":"Medical Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Regional Cancer Foundation; Carleton University","funders":"","keywords":"Confidence interval; Population; Statistics; Distribution (mathematics); Mathematics; Nuclear medicine; Value (mathematics); Homogeneous; Medicine; Mathematical analysis; Combinatorics","score_opus":0.3214441492235482,"score_gpt":0.5051126053896587,"score_spread":0.18366845616611055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067180843","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031376767,0.000030490646,0.975574,0.01881249,0.0006979381,0.00045623738,0.001136849,0.00008995823,0.0000643153],"genre_scores_gemma":[0.21307144,0.00010095849,0.42787027,0.31616017,0.03983631,0.00010278365,0.002119488,0.0006014583,0.00013711606],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99302685,0.0019811015,0.0014852589,0.0007047529,0.0022390569,0.0005629978],"domain_scores_gemma":[0.9557803,0.041905127,0.0009218843,0.00094675965,0.00022253614,0.00022337289],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0029031078,0.0004998949,0.0028332362,0.00008532476,0.000070493836,0.000024116973,0.0004609433,0.0016511967,0.00026189658],"category_scores_gemma":[0.06573278,0.00042998148,0.0014126325,0.00096569094,0.0007081377,0.000033114597,0.00020143493,0.0024673683,0.000015214809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005007911,0.004378865,0.00043443576,0.015051016,0.036086615,0.011565187,0.00034120918,0.0010801102,0.00027436568,0.014921546,0.80065364,0.11471224],"study_design_scores_gemma":[0.0010519226,0.00017541845,0.000027723116,0.00069128495,0.0087085925,0.00003020422,0.0000010703926,0.0035680218,0.0034775399,0.979591,0.002018904,0.0006583276],"about_ca_topic_score_codex":0.000066107124,"about_ca_topic_score_gemma":0.0000025948384,"teacher_disagreement_score":0.96466947,"about_ca_system_score_codex":0.00031579618,"about_ca_system_score_gemma":0.00033598734,"threshold_uncertainty_score":0.999834},"labels":[],"label_agreement":null},{"id":"W2067306560","doi":"10.1002/qaj.294","title":"Conducting portions of GLP studies in GMP laboratories","year":2004,"lang":"en","type":"article","venue":"The Quality Assurance Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada); Purdue Pharma (Canada)","funders":"","keywords":"Good laboratory practice; Good manufacturing practice; Clinical Practice; Overhead (engineering); Risk analysis (engineering); Engineering; Computer science; Engineering ethics; Management science; Medicine; Operations management; Nursing; Electrical engineering","score_opus":0.89577125109756,"score_gpt":0.6918572440235644,"score_spread":0.20391400707399554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067306560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9495189,0.0007423069,0.041742295,0.0057046465,0.0015023146,0.00024560574,0.00005214802,0.000030395438,0.00046138518],"genre_scores_gemma":[0.6866222,0.0002065927,0.31270584,0.00010340999,0.00031630322,0.000006292544,7.430178e-8,0.000011015891,0.000028284228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99535227,0.0020031412,0.0017998222,0.00012975905,0.0004835262,0.0002314639],"domain_scores_gemma":[0.9465381,0.05088864,0.0014154743,0.00039972426,0.0006830373,0.00007504767],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019560892,0.00011864531,0.0007017168,0.000042708754,0.00016934234,0.000025935913,0.00027307612,0.00007016289,0.00004098154],"category_scores_gemma":[0.24211787,0.00007486825,0.000110199006,0.00041080842,0.000432578,0.00012522392,0.00005014079,0.00060753024,0.000004415573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002075875,0.00049564434,0.0065813144,0.0005312303,0.00041286263,0.000043257485,0.010636087,0.00036035548,0.003382832,0.9738011,0.0008167669,0.0027310003],"study_design_scores_gemma":[0.0008911785,0.000051166673,0.003794653,0.0003547402,0.000040102892,0.000027767075,0.006090126,0.0000014233194,0.0033187997,0.9852965,0.0000409067,0.00009262877],"about_ca_topic_score_codex":0.000022634174,"about_ca_topic_score_gemma":0.0000682089,"teacher_disagreement_score":0.27096355,"about_ca_system_score_codex":0.00009131262,"about_ca_system_score_gemma":0.00018028244,"threshold_uncertainty_score":0.7642661},"labels":[],"label_agreement":null},{"id":"W2068795211","doi":"10.1200/jco.2005.06.679","title":"Comparison of Outcomes of Phase II Studies and Subsequent Randomized Control Studies Using Identical Chemotherapeutic Regimens","year":2005,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Phase (matter); Internal medicine; Chemistry","score_opus":0.8477716970268385,"score_gpt":0.7455523759788565,"score_spread":0.10221932104798204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068795211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95579904,0.0071303966,0.029106509,0.005728034,0.0014963577,0.0006488895,0.000010251061,0.000010074858,0.00007047225],"genre_scores_gemma":[0.6207306,0.0012507405,0.37718794,0.0004019333,0.00038482854,0.00000361729,3.487245e-8,0.000015553862,0.000024753232],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9810069,0.005584952,0.012208411,0.00025187802,0.0006612052,0.00028665518],"domain_scores_gemma":[0.6288532,0.35912997,0.009968068,0.00030019286,0.001503538,0.0002450319],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037418168,0.0002630651,0.011792016,0.00013844702,0.00006417705,0.0000057322472,0.00027231858,0.00038481454,0.000044338376],"category_scores_gemma":[0.4272853,0.00016087176,0.0011344971,0.000118161304,0.002860699,0.00009262351,0.00016192146,0.00078636885,8.435096e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.44637084,0.04034541,0.028426478,0.0020475914,0.074875645,0.00015517695,0.0070985723,0.00014108764,0.003310831,0.12949038,0.0027060567,0.26503193],"study_design_scores_gemma":[0.4378372,0.010996971,0.00060777215,0.00047986943,0.00846293,0.00004113546,0.0013011787,0.0021172757,0.0012724595,0.5363933,0.00026649874,0.00022342],"about_ca_topic_score_codex":0.0000017256691,"about_ca_topic_score_gemma":0.000005016121,"teacher_disagreement_score":0.40690288,"about_ca_system_score_codex":0.000114495575,"about_ca_system_score_gemma":0.0003155994,"threshold_uncertainty_score":0.99985296},"labels":[],"label_agreement":null},{"id":"W2069283580","doi":"10.1177/0962280212469682","title":"A cure rate survival model under a hybrid latent activation scheme","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Unobservable; Poisson distribution; Carcinogenesis; Survival analysis; Statistics; Mathematics; Biology; Econometrics; Cancer; Genetics","score_opus":0.853355063546163,"score_gpt":0.7394206970475853,"score_spread":0.11393436649857769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069283580","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003848191,0.00006179825,0.9852623,0.0036903657,0.0007407828,0.0009091844,0.00011139978,0.000110235276,0.0052657966],"genre_scores_gemma":[0.033220775,0.00010256311,0.9646643,0.00049148424,0.0007081718,0.00029676806,0.000010525016,0.00010575761,0.00039966565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95748496,0.031830564,0.0022502944,0.0010468819,0.004766077,0.0026212283],"domain_scores_gemma":[0.5229411,0.47319135,0.00020596688,0.0009826466,0.00059250905,0.002086401],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12751694,0.0004211615,0.0013445569,0.00042801673,0.00022262294,0.00008673055,0.0009244824,0.0006373098,0.0063979886],"category_scores_gemma":[0.75748354,0.00034072745,0.0001573301,0.0011708377,0.0015495435,0.0002146618,0.0007980264,0.0043164887,0.00016232443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038171213,0.0009649861,0.00038496093,0.0002427557,0.00006308455,0.00004999048,0.00011426516,0.0000089756295,0.0010393701,0.8769533,0.0046525695,0.115144044],"study_design_scores_gemma":[0.0013445136,0.00013693185,0.0019635707,0.00024410854,0.00002634858,0.0000073142833,0.000101776175,0.08675495,0.0012156388,0.90722686,0.0006352507,0.00034270843],"about_ca_topic_score_codex":0.00006281424,"about_ca_topic_score_gemma":0.000007755167,"teacher_disagreement_score":0.62996656,"about_ca_system_score_codex":0.00044252953,"about_ca_system_score_gemma":0.0007093268,"threshold_uncertainty_score":0.99990445},"labels":[],"label_agreement":null},{"id":"W2069593790","doi":"10.1002/cjs.5550360113","title":"Nonparametric tests of hypotheses for umbrella alternatives","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Nonparametric statistics; Null hypothesis; Statistic; Statistical hypothesis testing; Alternative hypothesis; Null (SQL); Test statistic; Class (philosophy); Econometrics; Mathematics; Statistics; Computer science; Data mining; Artificial intelligence","score_opus":0.6372626154125042,"score_gpt":0.518261751457429,"score_spread":0.11900086395507514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069593790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032486297,0.00026728841,0.962249,0.000110520996,0.001004538,0.00031882673,0.0026889157,0.0000057408547,0.0008689211],"genre_scores_gemma":[0.20855696,0.00008566964,0.79086185,0.000062262654,0.00020539593,0.0000028038182,8.281484e-7,0.000030738312,0.00019348282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765867,0.00022336752,0.0013316103,0.00013494023,0.00032549855,0.00032592702],"domain_scores_gemma":[0.9344817,0.06273471,0.0010028773,0.00020684792,0.0009815966,0.00059228775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014426365,0.00015730926,0.00076095725,0.00039689444,0.00009993346,0.000017937607,0.00037776414,0.00009984988,0.00019949982],"category_scores_gemma":[0.21819745,0.00013761454,0.00014821063,0.00029658526,0.00050515524,0.000050869978,0.000011427638,0.00023324507,0.0000044779044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031579,0.0003636434,0.01636468,0.0009332673,0.00078003644,0.0012126617,0.0014684906,0.0000790107,0.000415799,0.7624368,0.121591665,0.09403818],"study_design_scores_gemma":[0.0010656848,0.00071870757,0.0058747446,0.00014994592,0.00014915087,0.00017158748,0.00006737625,0.00018547109,0.00086357235,0.98863393,0.0019419973,0.00017784926],"about_ca_topic_score_codex":0.0002914484,"about_ca_topic_score_gemma":0.0005534934,"teacher_disagreement_score":0.22619714,"about_ca_system_score_codex":0.000094970914,"about_ca_system_score_gemma":0.0012459798,"threshold_uncertainty_score":0.788388},"labels":[],"label_agreement":null},{"id":"W2069688121","doi":"10.1002/1097-0258(20001030)19:20<2867::aid-sim551>3.0.co;2-j","title":"Properties of the estimated variance component for subject-by-formulation interaction in studies of individual bioequivalence","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Variance (accounting); Statistics; Restricted maximum likelihood; Econometrics; Variance components; Component (thermodynamics); Mathematics; Maximum likelihood; Medicine; Economics; Pharmacology","score_opus":0.6061784706403508,"score_gpt":0.5724391072053919,"score_spread":0.03373936343495887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069688121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6958108,0.000833666,0.29697153,0.00093517493,0.001187613,0.0026889418,0.0012922158,0.000030688163,0.000249405],"genre_scores_gemma":[0.660035,0.00018762989,0.3395981,0.00003806207,0.000035059995,0.000045526092,0.000006542782,0.000011741438,0.00004233425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973805,0.0004332048,0.0014039138,0.00018841194,0.0004251602,0.00016880539],"domain_scores_gemma":[0.97946477,0.01963897,0.0004416491,0.00023400107,0.00019615966,0.000024477009],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031785327,0.00013251431,0.0006823751,0.00008271094,0.000029852792,0.0000032106373,0.00022925284,0.00006934507,0.00009011101],"category_scores_gemma":[0.06627908,0.00008317119,0.000026759773,0.00029317688,0.0005024502,0.00004159514,0.000043884193,0.00018736444,6.0879034e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053853644,0.0025929983,0.016151229,0.0128018465,0.0007124398,0.000013204174,0.026038488,0.001285325,0.06082845,0.57486355,0.018436365,0.2808907],"study_design_scores_gemma":[0.0031177776,0.00055048417,0.012524598,0.003888399,0.00017460417,0.0000019792742,0.0007476367,0.01014641,0.0111889,0.9574587,0.000046320103,0.00015419134],"about_ca_topic_score_codex":0.00007161493,"about_ca_topic_score_gemma":0.000044809738,"teacher_disagreement_score":0.38259512,"about_ca_system_score_codex":0.00006619347,"about_ca_system_score_gemma":0.000035123958,"threshold_uncertainty_score":0.941586},"labels":[],"label_agreement":null},{"id":"W2070009349","doi":"10.1515/sagmb-2013-0003","title":"Simple estimators of false discovery rates given as few as one or two p-values without strong parametric assumptions","year":2013,"lang":"en","type":"article","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; False discovery rate; Prior probability; Nonparametric statistics; Parametric statistics; Bayes' theorem; Generality; Simple (philosophy)","score_opus":0.1952700356856978,"score_gpt":0.5447426637159445,"score_spread":0.3494726280302467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070009349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18229286,0.00018343072,0.81540394,0.00012819638,0.00003422585,0.0012009289,0.00042558063,0.000023191957,0.00030763302],"genre_scores_gemma":[0.45035484,0.00013959233,0.5489141,0.000061567574,0.000021783513,0.00041574996,0.000038814702,0.000023431383,0.000030104848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735606,0.00051721674,0.0010073506,0.0005534485,0.00018865308,0.0003772679],"domain_scores_gemma":[0.9846549,0.014195635,0.00026131293,0.0005272445,0.00016704554,0.00019384487],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005988909,0.00024619492,0.0007199027,0.00017023286,0.00008127269,0.00005461562,0.00026776077,0.00019583564,0.00028411165],"category_scores_gemma":[0.015726045,0.00019921744,0.00006206827,0.00041784908,0.00082368666,0.000030933206,0.00020629607,0.00023824793,0.00003864176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036526748,0.0004078904,0.008506908,0.00009156366,0.000093269584,0.0000028367515,0.000022045035,0.000023637887,0.0046487357,0.96976787,0.00007261889,0.01632612],"study_design_scores_gemma":[0.0006736972,0.0004117796,0.0059990995,0.000023354882,0.00013873931,0.000004261906,0.00007389746,0.0018315007,0.0032142377,0.9872182,0.00017965927,0.00023156106],"about_ca_topic_score_codex":0.00020879583,"about_ca_topic_score_gemma":0.000020956977,"teacher_disagreement_score":0.268062,"about_ca_system_score_codex":0.000029569359,"about_ca_system_score_gemma":0.0001016904,"threshold_uncertainty_score":0.9925649},"labels":[],"label_agreement":null},{"id":"W2070196328","doi":"10.1007/s10985-005-7221-8","title":"Implications of Model Misspecification in Robust Tests for Recurrent Events","year":2006,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal model; Estimator; Econometrics; Censoring (clinical trials); Marginal structural model; Marginal distribution; Statistics; Null hypothesis; Statistical hypothesis testing; Computer science; Mathematics; Regression analysis; Causal inference; Random variable","score_opus":0.7080364433530821,"score_gpt":0.5838627304641274,"score_spread":0.12417371288895473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070196328","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021341937,0.00003959904,0.9897321,0.0006352201,0.00003079909,0.00046076294,0.006518514,0.000024382034,0.0004244206],"genre_scores_gemma":[0.051689487,0.000020922997,0.9464951,0.000019338584,0.00008336576,0.00008045852,0.001446621,0.00001638174,0.00014831398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975959,0.00022413653,0.0012610115,0.0005073546,0.00022621713,0.0001853674],"domain_scores_gemma":[0.98535275,0.012163571,0.00046564356,0.001802502,0.00015979318,0.000055747292],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023240813,0.00012338597,0.00061276334,0.00025295626,0.000035487185,0.000012574093,0.0007123935,0.00009658136,0.00010843508],"category_scores_gemma":[0.021217616,0.000116323215,0.00016645688,0.0010888723,0.00004703669,0.000082865496,0.00013838283,0.000088975554,0.000007280116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055711536,0.0072914707,0.062198922,0.00065144605,0.0026135126,0.0000012842686,0.00011992083,0.047555204,0.002147231,0.7116291,0.11348781,0.05174699],"study_design_scores_gemma":[0.00033908364,0.00002007348,0.018229594,0.000019265999,0.0012709567,9.591377e-8,0.00000452852,0.28223673,0.0000734867,0.6975551,0.00014015633,0.00011088235],"about_ca_topic_score_codex":0.00005826993,"about_ca_topic_score_gemma":0.00024398744,"teacher_disagreement_score":0.23468152,"about_ca_system_score_codex":0.000041023417,"about_ca_system_score_gemma":0.000037433045,"threshold_uncertainty_score":0.9870271},"labels":[],"label_agreement":null},{"id":"W2070320306","doi":"10.1016/j.yrtph.2008.01.011","title":"Development of good modelling practice for physiologically based pharmacokinetic models for use in risk assessment: The first steps","year":2008,"lang":"en","type":"review","venue":"Regulatory Toxicology and Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":126,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Physiologically based pharmacokinetic modelling; Documentation; Risk assessment; Risk analysis (engineering); Computer science; Management science; Data science; Medicine; Engineering; Pharmacokinetics; Pharmacology","score_opus":0.6373778513633809,"score_gpt":0.580341614261531,"score_spread":0.05703623710184991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070320306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047960694,0.36703318,0.6207436,0.00014083672,0.0011291273,0.009747147,0.0005931198,0.0000605758,0.00007283048],"genre_scores_gemma":[0.00007712372,0.4696967,0.52733094,0.00031259013,0.0001598328,0.0023379158,0.00001296285,0.00005582578,0.000016130443],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922219,0.0034675961,0.0025544327,0.00090053235,0.00021674192,0.0006387882],"domain_scores_gemma":[0.82593,0.17152108,0.0018602962,0.00033008415,0.00024284175,0.00011569002],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005163474,0.00062613963,0.0032597051,0.00020009218,0.00036634027,0.00001580864,0.00056400493,0.0010940387,0.00006214053],"category_scores_gemma":[0.00549626,0.00043828195,0.00052041403,0.00023431545,0.00061427103,0.00012016801,0.00018278447,0.0010140892,0.000001004361],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028510718,0.004878073,0.0000071414993,0.04086257,0.0040251547,0.000036555153,0.0003822448,0.016754497,0.0000757596,0.06528864,0.0047355667,0.8601027],"study_design_scores_gemma":[0.005033503,0.000651638,0.000006587784,0.0010639515,0.0044678953,0.000026347214,0.000017468701,0.13519554,0.00007553041,0.082155176,0.77064824,0.0006581537],"about_ca_topic_score_codex":0.0000011567204,"about_ca_topic_score_gemma":0.000004440754,"teacher_disagreement_score":0.85944456,"about_ca_system_score_codex":0.00018263335,"about_ca_system_score_gemma":0.0008747853,"threshold_uncertainty_score":0.9998069},"labels":[],"label_agreement":null},{"id":"W2070555156","doi":"10.1186/1745-6215-14-s1-o12","title":"Using adaptive designs for decision making within the optima trial: optimal personalized treatment of early breast cancer using multi-parameter tests","year":2013,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institute for Health and Care Research","keywords":"Medicine; Concordance; Breast cancer; Test (biology); Medical physics; Clinical trial; Physical therapy; Cancer; Internal medicine","score_opus":0.8954064640619268,"score_gpt":0.6546175954865979,"score_spread":0.24078886857532888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070555156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33519775,0.00010190871,0.6561607,0.000046295045,0.0007584398,0.007315015,0.0003772676,0.00003620536,0.000006424127],"genre_scores_gemma":[0.107151955,0.000011464167,0.8912778,0.00003655351,0.0006114645,0.0007821505,5.2544516e-7,0.00008481558,0.000043262622],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923368,0.0032969797,0.0028109467,0.00056477735,0.00052083476,0.00046962724],"domain_scores_gemma":[0.7869043,0.20991266,0.0020363356,0.00055426673,0.00046641644,0.00012603597],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0091399,0.00043075302,0.002355887,0.00011445562,0.00021352762,0.00014317584,0.00033467932,0.00027966438,0.0005325995],"category_scores_gemma":[0.10504133,0.00025009297,0.0007681211,0.00024937897,0.00032604017,0.00016022145,0.00007256776,0.00014158765,0.0000062666463],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.539407,0.0074719745,0.00093661586,0.000504336,0.007909977,0.000032739965,0.011106543,0.013111944,0.069281876,0.042420343,0.0006520126,0.3071646],"study_design_scores_gemma":[0.14195178,0.004289375,0.00059448765,0.0020063901,0.005034954,0.000035553272,0.00077599345,0.31075308,0.0074009364,0.52607274,0.000011805473,0.0010728703],"about_ca_topic_score_codex":0.000420106,"about_ca_topic_score_gemma":0.0000084035055,"teacher_disagreement_score":0.4836524,"about_ca_system_score_codex":0.00031219292,"about_ca_system_score_gemma":0.00028028572,"threshold_uncertainty_score":0.9999951},"labels":[],"label_agreement":null},{"id":"W2070568765","doi":"10.2147/clep.s30816","title":"Matched case-control studies: a review of reported statistical methodology","year":2012,"lang":"en","type":"review","venue":"Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Confounding; Medicine; Case-control study; Statistics; Statistical analysis; Statistical significance; Meta-analysis; Sample size determination; Disease; Internal medicine; Mathematics","score_opus":0.9765472903717273,"score_gpt":0.7807672798787588,"score_spread":0.19578001049296845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070568765","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.096266e-7,0.7418706,0.24940798,0.00040030802,0.004085169,0.002901687,0.0009643173,0.00012602995,0.00024383934],"genre_scores_gemma":[9.194628e-8,0.5190393,0.4771798,0.0020070581,0.0011753492,0.00039492658,0.000022642238,0.00011487629,0.00006599121],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7235433,0.230509,0.04097937,0.0025626188,0.00048452834,0.001921193],"domain_scores_gemma":[0.11666592,0.86123765,0.017077334,0.0032510208,0.0008209656,0.0009471245],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.30210567,0.0014249585,0.053946927,0.00022300023,0.00009251901,0.000003954613,0.0011335397,0.004014986,0.0029223217],"category_scores_gemma":[0.9785821,0.0009532587,0.0050138594,0.00063443754,0.0037646135,0.000048479644,0.00070481957,0.004215289,0.00028932324],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005511284,0.00031683335,0.000024155841,0.22857969,0.0048459424,0.00085153687,0.0000066279376,1.3767717e-8,3.9656936e-9,0.09425359,0.0140220225,0.6570445],"study_design_scores_gemma":[0.0006988685,0.0004374469,0.000006215487,0.047420833,0.032967214,0.0032458962,0.000010739483,0.0000043424034,1.5967842e-8,0.5401315,0.37449762,0.00057931023],"about_ca_topic_score_codex":0.000016666287,"about_ca_topic_score_gemma":0.000004440566,"teacher_disagreement_score":0.6764764,"about_ca_system_score_codex":0.00018384302,"about_ca_system_score_gemma":0.00074564357,"threshold_uncertainty_score":0.99985003},"labels":[],"label_agreement":null},{"id":"W2071158082","doi":"10.1177/0962280207081606","title":"Stratified and randomized play-the-winner rule","year":2008,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Randomized controlled trial; Confounding; Computer science; Selection (genetic algorithm); Selection bias; Medicine; Statistics; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.7300653694511776,"score_gpt":0.7097057590069843,"score_spread":0.02035961044419332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071158082","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030141878,0.00026029587,0.9729402,0.0048171887,0.00047923514,0.0016360796,0.00006074785,0.000072147894,0.01671991],"genre_scores_gemma":[0.00982452,0.0006520205,0.98739195,0.00045637647,0.00038315446,0.0004665792,0.0000025992947,0.000058008358,0.0007647695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9275453,0.06223586,0.0028137218,0.0011526902,0.0046396377,0.0016128024],"domain_scores_gemma":[0.29652825,0.7011834,0.00014993371,0.0007806313,0.00035224165,0.0010055517],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1393079,0.00033800566,0.0019778681,0.0002810246,0.00045885053,0.000076432705,0.000925139,0.00058818166,0.007055494],"category_scores_gemma":[0.8714675,0.00020449646,0.00015452472,0.0007828408,0.010040703,0.00006411024,0.00063058635,0.0037828228,0.00006939682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005650241,0.00025923608,0.00008516525,0.00012172448,0.00006565465,0.00055294944,0.0004213907,1.457807e-7,0.000051259743,0.76037246,0.0057917093,0.22662807],"study_design_scores_gemma":[0.026454093,0.00013871354,0.00095868384,0.00012967046,0.000036552196,0.00007916672,0.00012742387,0.0040077474,0.00016918627,0.9667336,0.0009348115,0.00023039206],"about_ca_topic_score_codex":0.00012952981,"about_ca_topic_score_gemma":0.00002091834,"teacher_disagreement_score":0.73215955,"about_ca_system_score_codex":0.00009324988,"about_ca_system_score_gemma":0.00050542434,"threshold_uncertainty_score":0.9985155},"labels":[],"label_agreement":null},{"id":"W2071412894","doi":"10.1177/0962280211416038","title":"Measuring continuous baseline covariate imbalances in clinical trial data","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Brain Institute","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Covariate; Statistics; Baseline (sea); Analysis of covariance; Test statistic; Statistic; Type I and type II errors; Econometrics; Mathematics; Medicine; Statistical hypothesis testing","score_opus":0.9591079010063465,"score_gpt":0.7651604513098256,"score_spread":0.1939474496965209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071412894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024195572,0.00015809297,0.9770606,0.00075421913,0.0024218038,0.0021002067,0.00033148617,0.00010679445,0.014647195],"genre_scores_gemma":[0.0093945945,0.00042477084,0.9882727,0.00026112335,0.0011461711,0.00025370656,0.000018986953,0.00009325169,0.00013469401],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8460084,0.13009137,0.009853249,0.003544012,0.007201209,0.0033017641],"domain_scores_gemma":[0.17811501,0.81459594,0.00056161184,0.0038441082,0.0007308595,0.0021524925],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4092959,0.0004675223,0.0027588734,0.0006180527,0.00013553373,0.0000877326,0.0039345697,0.0011314946,0.011180243],"category_scores_gemma":[0.9459789,0.00038007653,0.00016788153,0.0017964777,0.0030876067,0.00018076594,0.0026407347,0.006641019,0.00015532176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018828643,0.0026807596,0.0024006956,0.00021260513,0.00007291404,0.0015490688,0.00014568504,6.433889e-8,0.000010987402,0.2713148,0.0029421425,0.6998416],"study_design_scores_gemma":[0.029964518,0.0011266021,0.00554166,0.0005145044,0.000047070364,0.0000122731135,0.00017659913,0.011682262,0.000049029222,0.9488743,0.0015954248,0.00041577828],"about_ca_topic_score_codex":0.0005986322,"about_ca_topic_score_gemma":0.00036986376,"teacher_disagreement_score":0.6994259,"about_ca_system_score_codex":0.00018521091,"about_ca_system_score_gemma":0.0012816591,"threshold_uncertainty_score":0.9998651},"labels":[],"label_agreement":null},{"id":"W2071526903","doi":"10.1007/s13571-012-0049-9","title":"Many to one comparisons in a longitudinal binary data setup","year":2012,"lang":"en","type":"article","venue":"Sankhya B","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Estimator; Binary number; Binary data; Computer science; Group (periodic table); Type I and type II errors; Statistics; Algorithm; Mathematics; Arithmetic","score_opus":0.8887343292358844,"score_gpt":0.641131526691856,"score_spread":0.24760280254402833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071526903","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25212798,0.000483417,0.71612537,0.003970131,0.003080609,0.0021760347,0.0013559046,0.00035930413,0.020321272],"genre_scores_gemma":[0.29499224,0.000005842216,0.7041914,0.00022609667,0.00041811296,0.000025086441,0.000009535604,0.000025713989,0.000106005595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974485,0.00052659155,0.000738534,0.00039258704,0.00034546087,0.00054831366],"domain_scores_gemma":[0.98136675,0.016855223,0.00008359756,0.0013596838,0.000033107,0.000301615],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041291905,0.00016721536,0.00061973615,0.000102078804,0.00004581712,0.000024830037,0.0006868831,0.00012488902,0.0011584167],"category_scores_gemma":[0.040463194,0.00015569439,0.000048125574,0.00035934983,0.0000805841,0.00014658141,0.0008145655,0.0003423614,0.000707783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047226148,0.004244906,0.19136728,0.0003899797,0.00020752398,0.00006665383,0.0006799889,0.0000045247166,0.0008241533,0.39287472,0.39155203,0.017315986],"study_design_scores_gemma":[0.0019340896,0.00029140213,0.3560095,0.00040807528,0.00024305728,0.000014420962,0.00018098633,0.00089993275,0.00041744567,0.6189134,0.019955544,0.0007321134],"about_ca_topic_score_codex":0.000039711533,"about_ca_topic_score_gemma":0.00003408232,"teacher_disagreement_score":0.3715965,"about_ca_system_score_codex":0.000054760534,"about_ca_system_score_gemma":0.00003121279,"threshold_uncertainty_score":0.99975467},"labels":[],"label_agreement":null},{"id":"W2071607258","doi":"10.1007/s002800000228","title":"A review of dose-limiting events in phase I trials: antimetabolites show unpredictable relationships between dose and toxicity","year":2000,"lang":"en","type":"review","venue":"Cancer Chemotherapy and Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute","keywords":"Toxicity; Maximum tolerated dose; Limiting; Pharmacology; Medicine; Oncology; Internal medicine","score_opus":0.7038922919024159,"score_gpt":0.6398705854915662,"score_spread":0.0640217064108497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071607258","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005950843,0.9947292,0.0002024797,0.00019727829,0.00032911764,0.0027141005,0.0010288047,0.000031586656,0.00017230932],"genre_scores_gemma":[0.00001916551,0.98013383,0.017982196,0.0005412351,0.00079970155,0.0003827101,0.000022739718,0.00006808641,0.000050360795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9879943,0.007511492,0.0032641494,0.0006430054,0.00019228783,0.0003947487],"domain_scores_gemma":[0.9297882,0.0680238,0.0016623408,0.00026154058,0.00006875929,0.00019536984],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012667941,0.00051251566,0.0068195187,0.00019282497,0.00007981591,0.000009595438,0.00027111528,0.0006041017,0.0021744638],"category_scores_gemma":[0.012558181,0.00040593155,0.0003946587,0.00052332616,0.00026463077,0.00007516701,0.000065920816,0.0010240996,0.0000018397429],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013798577,0.00019910223,0.00010893447,0.08898635,0.0005609463,0.000002587031,0.000059224956,3.223397e-8,0.000017379287,0.0001883701,0.0012642876,0.9084748],"study_design_scores_gemma":[0.010655638,0.00023230024,0.000038619768,0.11284838,0.0079527525,0.000012047466,0.000007095257,0.000017345536,0.00025979118,0.082186654,0.7850688,0.000720584],"about_ca_topic_score_codex":0.000009067291,"about_ca_topic_score_gemma":9.411305e-7,"teacher_disagreement_score":0.9077542,"about_ca_system_score_codex":0.00007559129,"about_ca_system_score_gemma":0.0002859503,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W2071765390","doi":"10.1016/j.jclinepi.2009.04.010","title":"Correlation between serial tests made disease probability estimates erroneous","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Children’s Health Research Institute; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Statistics; Correlation; Medicine; Mathematics","score_opus":0.7797870899597635,"score_gpt":0.665207925896476,"score_spread":0.1145791640632875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071765390","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38915542,0.00014540865,0.5876548,0.017838841,0.0040594665,0.00062420894,0.00005303915,0.000086314554,0.00038246613],"genre_scores_gemma":[0.27359432,0.000057563317,0.72118783,0.001221472,0.003870636,0.0000028625625,0.000002247778,0.000019335037,0.00004375336],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9736201,0.013738571,0.011198758,0.00048936513,0.00040666075,0.00054653187],"domain_scores_gemma":[0.2750745,0.7151675,0.007273391,0.00071336434,0.0005515361,0.0012196649],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0753423,0.00030355217,0.0046634157,0.00008424333,0.00007820352,0.0000149425505,0.0004628705,0.000705832,0.00024059386],"category_scores_gemma":[0.9380143,0.00021559426,0.001118175,0.00016058914,0.0005753135,0.00013314988,0.00008115934,0.0017296574,0.00004178761],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036728715,0.0014640895,0.7479676,0.00014123887,0.0002831498,0.00017713882,0.000027863989,0.00062200095,0.000015207547,0.11943402,0.010060905,0.11613391],"study_design_scores_gemma":[0.001023009,0.0010841604,0.41272235,0.00009421719,0.0002883722,0.000022186681,0.0000015100782,0.00086361077,0.0000026744167,0.5836182,0.00016280427,0.00011685211],"about_ca_topic_score_codex":0.0000024213057,"about_ca_topic_score_gemma":9.0571996e-7,"teacher_disagreement_score":0.86267203,"about_ca_system_score_codex":0.000069246824,"about_ca_system_score_gemma":0.00032272228,"threshold_uncertainty_score":0.95212966},"labels":[],"label_agreement":null},{"id":"W2071845884","doi":"10.1080/10428190601078126","title":"Development of adapted RECIST criteria to assess response in lymphoma and their comparison to the International Workshop Criteria","year":2007,"lang":"en","type":"article","venue":"Leukemia & lymphoma/Leukemia and lymphoma","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Juravinski Cancer Centre; McGill University Health Centre; Princess Margaret Cancer Centre; BC Cancer Agency; Jewish General Hospital; Queen's University; McGill University","funders":"","keywords":"Response Evaluation Criteria in Solid Tumors; Medicine; Concordance; Lymphoma; Hodgkin lymphoma; Concordance correlation coefficient; Nuclear medicine; Clinical trial; Internal medicine; Oncology; Statistics; Mathematics; Phases of clinical research","score_opus":0.2976124603191652,"score_gpt":0.4829481651784053,"score_spread":0.18533570485924006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071845884","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91638047,0.00013639765,0.079051435,0.00077563606,0.0012179691,0.0010013914,0.00010375581,0.000109747736,0.0012231995],"genre_scores_gemma":[0.6540934,0.00002095352,0.3440485,0.0011298567,0.00025561778,0.000110575806,0.000008629424,0.000080036196,0.0002524352],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99292666,0.001062287,0.002970817,0.001174606,0.00087845925,0.0009871701],"domain_scores_gemma":[0.9668262,0.030614251,0.0005677422,0.0009969576,0.00033565506,0.0006591774],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011428119,0.00073279865,0.001555954,0.00057209836,0.00029443638,0.0002680258,0.0011685725,0.00051769277,0.000125453],"category_scores_gemma":[0.026317513,0.00056456565,0.00015892353,0.0010008404,0.00032644355,0.00017674093,0.0009852496,0.00016937622,0.00002819865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02055925,0.00061848096,0.0016428118,0.00022181754,0.00030775013,0.0001334313,0.015522346,0.000022619848,0.028576627,0.0076429816,0.008549485,0.9162024],"study_design_scores_gemma":[0.0319342,0.0011349326,0.5502741,0.0033769608,0.00026413068,0.0004977667,0.017139465,0.012510549,0.13957874,0.06011999,0.17959453,0.003574644],"about_ca_topic_score_codex":0.0001779498,"about_ca_topic_score_gemma":0.0005473459,"teacher_disagreement_score":0.91262776,"about_ca_system_score_codex":0.003965255,"about_ca_system_score_gemma":0.0015084381,"threshold_uncertainty_score":0.9998583},"labels":[],"label_agreement":null},{"id":"W2072728595","doi":"10.1118/1.2760716","title":"SU‐FF‐T‐65: An Analytic Investigation of the Effect of Inter‐Patient Heterogeneity On Alpha/beta Ratio Estimates for Tumors","year":2007,"lang":"en","type":"article","venue":"Medical Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Population; Poisson distribution; Mathematics; Statistics; Population model; Econometrics; Medicine","score_opus":0.27426090465611386,"score_gpt":0.5167774851420961,"score_spread":0.24251658048598224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072728595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6278893,0.0000050151134,0.37085682,0.0001635716,0.00031326423,0.00065181724,0.000039786486,0.000023020935,0.00005741016],"genre_scores_gemma":[0.9529601,5.4248517e-7,0.046574563,0.00018879469,0.00021047598,0.000027722166,0.000006632869,0.000027741597,0.000003482199],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997022,0.000606054,0.0010322618,0.00028332256,0.0008087426,0.0002476553],"domain_scores_gemma":[0.9523145,0.046232946,0.0005648613,0.000539781,0.00013305512,0.00021487639],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047833184,0.00020024135,0.00076509046,0.00003332429,0.000055330715,0.000009525983,0.000380817,0.00015020181,0.000026340356],"category_scores_gemma":[0.069220036,0.00012296558,0.00026792858,0.00024285812,0.0005952496,0.00004674205,0.00009921119,0.0002634864,0.0000022770955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004190642,0.0033503072,0.13524814,0.008105375,0.0015018134,0.000025596379,0.0025496942,0.0002626676,0.017648539,0.29017553,0.005175996,0.5317657],"study_design_scores_gemma":[0.0008424268,0.0019203207,0.0020818675,0.00037376906,0.00018677015,7.290406e-7,0.000009365121,0.0037646927,0.6132799,0.37742737,0.0000048846514,0.00010790869],"about_ca_topic_score_codex":0.000009006826,"about_ca_topic_score_gemma":0.000008219224,"teacher_disagreement_score":0.59563136,"about_ca_system_score_codex":0.000046240402,"about_ca_system_score_gemma":0.0000682646,"threshold_uncertainty_score":0.9386203},"labels":[],"label_agreement":null},{"id":"W2072862476","doi":"10.1081/sac-200047105","title":"Using James–Stein Estimators in Homogeneity Tests of the Risk Difference","year":2005,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistics; Mathematics; Estimator; Homogeneity (statistics); Contingency table; Absolute risk reduction; Type I and type II errors; Mean squared error; Econometrics; Confidence interval","score_opus":0.6569001376245625,"score_gpt":0.6170157563794907,"score_spread":0.039884381245071765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072862476","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34894308,0.00007232734,0.65025926,0.00009351936,0.000055090026,0.00036088852,0.00011561431,0.000015694814,0.0000845034],"genre_scores_gemma":[0.5161293,0.000024652923,0.4837958,0.000018358282,0.000008273332,0.000007259964,0.000004219009,0.000008259666,0.000003854798],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969001,0.001443229,0.0010841261,0.00019939308,0.00023193416,0.00014123748],"domain_scores_gemma":[0.96486557,0.033671267,0.0005546471,0.0006894522,0.00017701926,0.00004207569],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014316442,0.0001362111,0.0003360491,0.00014089166,0.00014562153,0.000028719687,0.00036634586,0.00009981995,0.000009901226],"category_scores_gemma":[0.023028973,0.000119579374,0.00003491419,0.00049812987,0.0003231895,0.00006802292,0.00025593943,0.0003242455,0.0000013317116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003473429,0.00049059925,0.13132164,0.000084225234,0.00001868234,4.2914786e-7,0.00110482,0.55332816,0.000064637454,0.13302802,0.000019607058,0.18050446],"study_design_scores_gemma":[0.00039197726,0.000010764322,0.14113002,0.00006831463,0.000022083314,3.475573e-7,0.000034520905,0.53270876,0.000013320192,0.32554612,0.000008042676,0.000065732806],"about_ca_topic_score_codex":0.00010543773,"about_ca_topic_score_gemma":0.00042231576,"teacher_disagreement_score":0.1925181,"about_ca_system_score_codex":0.00010538425,"about_ca_system_score_gemma":0.000064788896,"threshold_uncertainty_score":0.98520046},"labels":[],"label_agreement":null},{"id":"W2073143097","doi":"10.1111/j.1541-0420.2006.00533.x","title":"A Multivariate Two‐Sample Mean Test for Small Sample Size and Missing Data","year":2006,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Multivariate statistics; Statistics; Sample size determination; Missing data; Sample (material); Multivariate analysis; Mathematics; Test (biology); Biology; Chemistry; Chromatography","score_opus":0.7422006601323592,"score_gpt":0.5704161396961355,"score_spread":0.17178452043622372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073143097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002352821,0.00012051842,0.9886321,0.00028206228,0.00040209581,0.00068837265,0.007151003,0.00012343796,0.00024762203],"genre_scores_gemma":[0.009273853,0.0000141824885,0.9897879,0.000111615,0.0005751931,0.000020275402,0.000051829986,0.000056846446,0.00010833942],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975212,0.0002206229,0.0008899665,0.0006401982,0.0002970068,0.00043098908],"domain_scores_gemma":[0.4006431,0.5975673,0.00036626728,0.0010459167,0.00019344297,0.00018398186],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047339313,0.0002252777,0.0005929332,0.00034462675,0.0001579654,0.00016418575,0.0005300662,0.00016520137,0.0000769232],"category_scores_gemma":[0.75924367,0.00019735812,0.000074456344,0.0017426519,0.00014430747,0.000073272204,0.00041960197,0.00013759447,0.00000468986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032874517,0.0030511157,0.01216844,0.0016547494,0.00028003435,0.000022808872,0.00018122175,0.00000286416,0.013254037,0.2542286,0.015175734,0.69965166],"study_design_scores_gemma":[0.0021920588,0.00014008016,0.002061733,0.000039762777,0.00017047518,0.0000025577624,0.000014931018,0.0057799034,0.00059814216,0.9814374,0.0072731096,0.00028987837],"about_ca_topic_score_codex":0.00087290694,"about_ca_topic_score_gemma":0.0000564355,"teacher_disagreement_score":0.7545097,"about_ca_system_score_codex":0.000047120273,"about_ca_system_score_gemma":0.000052051848,"threshold_uncertainty_score":0.8048031},"labels":[],"label_agreement":null},{"id":"W2073184828","doi":"10.1198/sbr.2010.09050","title":"Estimating Simultaneous Confidence Intervals for Multiple Contrasts of Proportions by the Method of Variance Estimates Recovery","year":2010,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ontario Ministry of Research and Innovation","keywords":"Confidence interval; Statistics; Confidence distribution; Variance (accounting); Mathematics; Robust confidence intervals; Multivariate statistics; CDF-based nonparametric confidence interval; Binomial (polynomial); Credible interval; Sample size determination; Coverage probability; Econometrics","score_opus":0.5664644995065378,"score_gpt":0.6641135688704715,"score_spread":0.0976490693639337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073184828","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020603375,0.000039435035,0.9845256,0.00034022375,0.00052826013,0.002076452,0.010211464,0.000024502731,0.00019372886],"genre_scores_gemma":[0.13808519,0.000019157635,0.86132985,0.000034113767,0.00008785498,0.0002912817,0.000018810653,0.000040982522,0.00009277407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940453,0.001612694,0.0020132,0.0005351364,0.0010397198,0.00075390347],"domain_scores_gemma":[0.4659784,0.5314168,0.00045408786,0.00055225054,0.0013987274,0.00019973467],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019635772,0.00023329088,0.0008799218,0.0001470866,0.00015901198,0.000051505125,0.00081972254,0.00024857782,0.0007979075],"category_scores_gemma":[0.74127716,0.00017281114,0.00011310962,0.0005514314,0.001958916,0.00005695298,0.00025945186,0.0015433037,0.000006828994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015130837,0.0011808979,0.00033974103,0.0021515957,0.00018225031,0.00003251697,0.00026556494,0.00022371481,0.15681885,0.6739522,0.008536827,0.15480275],"study_design_scores_gemma":[0.00085650943,0.0002557912,0.000039397968,0.00018100231,0.000049559178,0.000006556198,0.000041985713,0.30828127,0.03961306,0.65037614,0.00017772923,0.00012101397],"about_ca_topic_score_codex":0.00008736319,"about_ca_topic_score_gemma":0.000049778315,"teacher_disagreement_score":0.72164136,"about_ca_system_score_codex":0.00005327829,"about_ca_system_score_gemma":0.0002877389,"threshold_uncertainty_score":0.8736527},"labels":[],"label_agreement":null},{"id":"W2074774273","doi":"10.2202/1557-4679.1224","title":"A First Passage Time Model for Long-Term Survivors with Competing Risks","year":2011,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Expectation–maximization algorithm; Inverse Gaussian distribution; Term (time); Gompertz function; Econometrics; Computer science; Maximization; Accelerated failure time model; Statistics; Maximum likelihood; Distribution (mathematics); Mathematics; Covariate; Mathematical optimization","score_opus":0.556491896583013,"score_gpt":0.5140196862311603,"score_spread":0.04247221035185267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074774273","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020822993,0.000014925801,0.9766361,0.00061631156,0.0006129757,0.00027713185,0.0004815625,0.000018080624,0.00051992637],"genre_scores_gemma":[0.19791889,0.00002883633,0.8013006,0.00017940543,0.00034312005,0.0000070410256,0.000002785824,0.000037364123,0.00018194178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761444,0.00020612818,0.0010878982,0.00014944679,0.0007251673,0.00021691533],"domain_scores_gemma":[0.9687907,0.028615925,0.0012077439,0.00021999022,0.0010559714,0.00010967476],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032172494,0.00018189798,0.0004418859,0.000086496744,0.000098582284,0.00006652562,0.0009315323,0.00007489442,0.00020314443],"category_scores_gemma":[0.022071183,0.0001099602,0.00014563052,0.000069407426,0.000232967,0.00007370796,0.00010342538,0.00030274235,0.000012389577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012303281,0.0026544181,0.02399039,0.00053091213,0.005678669,0.0010097368,0.008952928,0.0016381145,0.0004826435,0.88659745,0.015192767,0.040968668],"study_design_scores_gemma":[0.0017856704,0.0004683873,0.0030977966,0.00035763456,0.00037100646,0.00016570599,0.00007751989,0.056156117,0.00048697286,0.9367658,0.000044926634,0.00022248398],"about_ca_topic_score_codex":0.0000139096155,"about_ca_topic_score_gemma":0.000053655684,"teacher_disagreement_score":0.1770959,"about_ca_system_score_codex":0.00007317375,"about_ca_system_score_gemma":0.000106629675,"threshold_uncertainty_score":0.9861663},"labels":[],"label_agreement":null},{"id":"W2075535893","doi":"10.1371/journal.pone.0115065","title":"Network Meta-Analysis Using R: A Review of Currently Available Automated Packages","year":2014,"lang":"en","type":"review","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":389,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Meta-analysis; Computational biology; Medicine; Bioinformatics; Data science; Biology; Internal medicine","score_opus":0.921579771556096,"score_gpt":0.6141508616884526,"score_spread":0.3074289098676435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075535893","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3424148e-8,0.98715234,0.009049989,0.000022080003,0.00010574558,0.0021313352,0.00052741106,0.00027678814,0.00073427666],"genre_scores_gemma":[7.4327207e-9,0.5390147,0.46020412,0.0000754189,0.00019843823,0.00013379783,0.000025176989,0.00007291194,0.00027544494],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9845842,0.0075525683,0.005207378,0.00086728734,0.0012336225,0.0005549341],"domain_scores_gemma":[0.91950786,0.07300408,0.004638235,0.0021297128,0.00051286625,0.0002072343],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013112943,0.00077344815,0.028786289,0.00024385743,0.00006647299,0.000038434086,0.0008081803,0.00052379956,0.009044421],"category_scores_gemma":[0.11981743,0.00053311203,0.0062982608,0.0024508885,0.00015930239,0.000040148047,0.00030033744,0.00070009904,0.00036258437],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027372698,0.00078016234,3.0022773e-7,0.6064601,0.36833584,0.000003631094,0.00000183419,4.912505e-7,1.2056115e-7,0.0017627211,0.011546557,0.011105514],"study_design_scores_gemma":[0.00007078873,0.000040972373,1.3574623e-8,0.11421838,0.81446785,9.704271e-7,1.6245885e-7,0.00034563395,0.000001645288,0.024114048,0.046334017,0.0004054956],"about_ca_topic_score_codex":0.000005975476,"about_ca_topic_score_gemma":8.945834e-7,"teacher_disagreement_score":0.4922417,"about_ca_system_score_codex":0.00007941081,"about_ca_system_score_gemma":0.00019995456,"threshold_uncertainty_score":0.99971205},"labels":[],"label_agreement":null},{"id":"W2075806409","doi":"10.1111/bmsp.12045","title":"Equivalence tests for comparing correlation and regression coefficients","year":2014,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Equivalence (formal languages); Mathematics; Statistics; Correlation; Regression analysis; Regression; Linear regression; Applied mathematics; Null hypothesis; Econometrics; Pure mathematics","score_opus":0.4380628287343638,"score_gpt":0.5641740061112318,"score_spread":0.126111177376868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075806409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03612513,0.00014738881,0.961938,0.0002878743,0.00032886086,0.00025575602,0.000041407307,0.000017148328,0.00085838145],"genre_scores_gemma":[0.30291727,0.000080684964,0.6966165,0.000170867,0.00014859984,0.000006846712,0.0000010255666,0.000019804107,0.000038421753],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99715585,0.00060447154,0.0013217388,0.00029527716,0.00031874247,0.00030391166],"domain_scores_gemma":[0.95175207,0.04712495,0.00045748707,0.00013726178,0.00022270958,0.00030555303],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041760425,0.00016505986,0.00093024457,0.000062662846,0.00012951942,0.00007518494,0.00016251966,0.00018177305,0.00011447417],"category_scores_gemma":[0.10647586,0.00013927718,0.00007168234,0.00007176376,0.000552094,0.000066630564,0.00007038334,0.00038797784,0.000004894787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003541697,0.0004892002,0.00042245176,0.0005537031,0.00004706828,0.00005001892,0.00006515581,0.0000013511764,0.00011378713,0.73540676,0.005629856,0.25686648],"study_design_scores_gemma":[0.0022899879,0.0007339989,0.004699898,0.00071045116,0.00012514195,0.0015420859,0.0000176427,0.009230399,0.000009121891,0.98018056,0.0003062186,0.00015447686],"about_ca_topic_score_codex":7.635494e-7,"about_ca_topic_score_gemma":9.468086e-7,"teacher_disagreement_score":0.26679215,"about_ca_system_score_codex":0.000011918234,"about_ca_system_score_gemma":0.000013352174,"threshold_uncertainty_score":0.9010507},"labels":[],"label_agreement":null},{"id":"W2075888392","doi":"10.1016/j.jclinepi.2010.02.021","title":"Survival distributions impact the power of randomized placebo-phase design and parallel groups randomized clinical trials","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Public Health Ontario; University of Toronto; Hospital for Sick Children","funders":"","keywords":"Weibull distribution; Sample size determination; Randomized controlled trial; Placebo; Statistics; Log-normal distribution; Completely randomized design; Mathematics; Medicine; Time point; Surgery; Physics","score_opus":0.7783455377838716,"score_gpt":0.7020928746141641,"score_spread":0.07625266316970747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075888392","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09145996,0.00031491023,0.89115995,0.007345782,0.0067277183,0.0027316946,0.00010466433,0.00002264798,0.00013268943],"genre_scores_gemma":[0.2464448,0.002079305,0.74840283,0.00057786214,0.0023565593,0.000063785265,0.0000025908605,0.000042036147,0.000030228495],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.22749177,0.69920343,0.070080705,0.0009948431,0.0010665101,0.001162749],"domain_scores_gemma":[0.007885518,0.962506,0.026544811,0.0010033597,0.0010825316,0.0009777987],"candidate_categories":["metaresearch","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.8541882,0.00053027156,0.032587986,0.00014222621,0.00014121637,0.000032123287,0.000992836,0.001547754,0.00089384307],"category_scores_gemma":[0.9950083,0.00024026394,0.010214617,0.00022404558,0.007882792,0.000117240605,0.00023051942,0.0048353546,0.000010248338],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.71879375,0.0011743247,0.0012342407,0.000025133497,0.0029804232,0.0000181041,0.000036039753,0.00001811619,0.000014381086,0.2629434,0.0049954224,0.0077666733],"study_design_scores_gemma":[0.44088918,0.00085573044,0.00072882476,0.000055407392,0.0018643613,0.000054787266,0.000017027523,0.0024462363,0.0000043080454,0.55284154,0.0001061232,0.00013643758],"about_ca_topic_score_codex":0.000013221598,"about_ca_topic_score_gemma":0.0000028213162,"teacher_disagreement_score":0.28989816,"about_ca_system_score_codex":0.000020442918,"about_ca_system_score_gemma":0.00062152796,"threshold_uncertainty_score":0.99974847},"labels":[],"label_agreement":null},{"id":"W2076608994","doi":"10.1007/s10998-010-3183-z","title":"Sequential confidence intervals for time series","year":2010,"lang":"en","type":"article","venue":"Periodica Mathematica Hungarica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematics; Confidence interval; Series (stratigraphy); Statistics; Robust confidence intervals; Sequence (biology); Sample (material); Sequential estimation; Algorithm","score_opus":0.29679231555786517,"score_gpt":0.5037833356764022,"score_spread":0.20699102011853704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076608994","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018019157,0.000031015268,0.924239,0.0061312728,0.002596551,0.0042575076,0.00057377206,0.0012254643,0.042926256],"genre_scores_gemma":[0.023324545,0.0000050810427,0.970502,0.00026772165,0.000651643,0.00051520445,0.0000063219827,0.00010905617,0.0046184054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960619,0.00035847,0.0015813753,0.0006948619,0.0006059672,0.00069740665],"domain_scores_gemma":[0.9666625,0.030953126,0.0005362731,0.0011730231,0.00032191988,0.00035315458],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004155856,0.0004357962,0.0012805129,0.00010859994,0.00035250396,0.00029591212,0.00089630333,0.0003807028,0.008357644],"category_scores_gemma":[0.12963016,0.00036453176,0.00045771542,0.00021338134,0.00092600624,0.00020244751,0.0002708122,0.0006676404,0.0007407749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019567931,0.0004265858,0.000012871381,0.0006964221,0.0001685034,0.000012281952,0.0008884635,9.2599606e-8,0.03208821,0.940618,0.021380398,0.0035125015],"study_design_scores_gemma":[0.00073399197,0.00027239686,0.000024586976,0.00011782424,0.00023647599,0.00006578229,0.00005650639,0.0007403641,0.009271686,0.97613204,0.011894282,0.00045409147],"about_ca_topic_score_codex":0.0000031534635,"about_ca_topic_score_gemma":0.0000056104614,"teacher_disagreement_score":0.1254743,"about_ca_system_score_codex":0.000033616987,"about_ca_system_score_gemma":0.0001562467,"threshold_uncertainty_score":0.9998807},"labels":[],"label_agreement":null},{"id":"W2078660705","doi":"10.1016/j.pharmthera.2005.06.012","title":"Involving the pharmaceutical and biotech communities in medication development for substance abuse","year":2005,"lang":"en","type":"review","venue":"Pharmacology & Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nalcor Energy (Canada)","funders":"","keywords":"Legislation; General partnership; Substance abuse; Drug development; Business; Pharmaceutical industry; Medicine; Clinical trial; Marketing; Public relations; Risk analysis (engineering); Drug; Pharmacology; Psychiatry; Finance; Political science","score_opus":0.7951575327030591,"score_gpt":0.6443657248602361,"score_spread":0.15079180784282298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078660705","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000092585564,0.9814957,0.013699455,0.000768112,0.0009001555,0.0028586946,0.000068258894,0.00008149709,0.000035537352],"genre_scores_gemma":[0.000009982662,0.83712196,0.15906116,0.0022483738,0.00039421782,0.0010310505,0.000016084472,0.00008367959,0.000033507273],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99421996,0.002812427,0.0017680173,0.00039345573,0.00023981906,0.0005663295],"domain_scores_gemma":[0.9066846,0.09216198,0.0005987743,0.00034914058,0.00009651841,0.00010902423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006596103,0.0005072005,0.0017933827,0.00017093503,0.00025032446,0.00004025221,0.0007840065,0.0006278292,0.00019060884],"category_scores_gemma":[0.000503129,0.0003480162,0.00018561563,0.00027350255,0.0007736392,0.000048927286,0.00009612426,0.0015084895,0.000010434575],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049243234,0.00021068132,0.0000039046377,0.0037318985,0.0006400898,0.0000015804194,0.0019845597,1.5543881e-7,0.0000051983734,0.0026774972,0.00029872078,0.9903965],"study_design_scores_gemma":[0.0010512688,0.000034658144,0.0000014891673,0.0012767119,0.002971007,0.000012551579,0.00012721268,0.000348175,0.000048445527,0.02092114,0.9728521,0.00035525617],"about_ca_topic_score_codex":0.0000017804683,"about_ca_topic_score_gemma":0.000041399024,"teacher_disagreement_score":0.9900412,"about_ca_system_score_codex":0.00026502207,"about_ca_system_score_gemma":0.00025299645,"threshold_uncertainty_score":0.9998972},"labels":[],"label_agreement":null},{"id":"W2079556917","doi":"10.1038/nrneurol.2015.34","title":"The promise of futility trials in neurological diseases","year":2015,"lang":"en","type":"review","venue":"Nature Reviews Neurology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; Foothills Medical Centre; University of Calgary","funders":"","keywords":"Medicine; Clinical trial; Randomized controlled trial; Neurology; Intensive care medicine; Disease; Gold standard (test); Multiple sclerosis; Stroke (engine); Alternative medicine; Physical therapy; Internal medicine; Psychiatry; Pathology","score_opus":0.8346530298655925,"score_gpt":0.6866078971367704,"score_spread":0.14804513272882214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079556917","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000025597094,0.98919,0.00006670322,0.00046866207,0.0021903152,0.0074380287,0.00030906004,0.00004928522,0.00028542549],"genre_scores_gemma":[5.962514e-7,0.9865516,0.01129112,0.00044972924,0.0006872358,0.0009028049,0.000009461107,0.00007158431,0.000035887977],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9071934,0.08214231,0.00835424,0.0011184004,0.0005626653,0.00062897825],"domain_scores_gemma":[0.570264,0.42099634,0.0058918605,0.0023112076,0.00022681229,0.00030982817],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06119025,0.0008243386,0.017873585,0.00016622567,0.00006259533,0.000027932052,0.0017294672,0.002853446,0.00010770461],"category_scores_gemma":[0.7997976,0.0003836069,0.0026706893,0.00080236705,0.00068624853,0.000029643985,0.0005147511,0.005423628,0.000043994674],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024577076,0.00023734682,0.000015049676,0.014722503,0.00006153767,0.000052235162,0.0000024909175,1.386777e-8,1.6077758e-8,0.015016392,0.010788076,0.95885855],"study_design_scores_gemma":[0.00033584333,0.00029759912,0.000018172266,0.0013107373,0.0013643749,0.000026713818,1.3802452e-7,0.0000017170853,2.853817e-8,0.29075226,0.7057137,0.00017871502],"about_ca_topic_score_codex":9.1439017e-7,"about_ca_topic_score_gemma":0.000005875635,"teacher_disagreement_score":0.95867985,"about_ca_system_score_codex":0.000025880898,"about_ca_system_score_gemma":0.000437343,"threshold_uncertainty_score":0.9998616},"labels":[],"label_agreement":null},{"id":"W2079560246","doi":"10.1002/pds.1614","title":"Exclusion of immortal person‐time","year":2008,"lang":"en","type":"letter","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Biostatistics; Epidemiology; Medicine; Public health; Pharmacoepidemiology; Observational study; Family medicine; Library science; Gerontology; Medical prescription; Pathology; Computer science","score_opus":0.4580469138931446,"score_gpt":0.5335704982226009,"score_spread":0.07552358432945633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079560246","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017778272,0.0029662622,0.029489748,0.94539326,0.0038063687,0.0017048165,0.0016304523,0.0003117362,0.012919528],"genre_scores_gemma":[0.00046994587,0.0042758384,0.48081106,0.5022301,0.007330668,0.000056247816,0.00013125618,0.00015043763,0.004544458],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875383,0.008611441,0.002039323,0.0008482331,0.0003206478,0.0006420897],"domain_scores_gemma":[0.8046606,0.19362983,0.0010313012,0.00043837118,0.00010804439,0.0001318459],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009529319,0.00054762745,0.002858988,0.00013182186,0.00018382582,0.000003324186,0.0004322444,0.001335416,0.0019528402],"category_scores_gemma":[0.08230403,0.00044015312,0.00047780777,0.00012479778,0.0010829392,0.00004774873,0.00027149954,0.0029998743,0.000069880094],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024092736,0.000055605247,0.00019739894,0.00049379346,0.00027511342,0.00019968982,0.00012279631,0.0000011059366,0.0000897331,0.0011127616,0.9925559,0.004655154],"study_design_scores_gemma":[0.002946373,0.00016025272,0.0005110995,0.00035634273,0.0012529105,0.0002709302,0.000021541127,0.0019081662,0.0002776592,0.4581985,0.5329723,0.001123943],"about_ca_topic_score_codex":0.000036539557,"about_ca_topic_score_gemma":4.965363e-7,"teacher_disagreement_score":0.45958364,"about_ca_system_score_codex":0.000044855486,"about_ca_system_score_gemma":0.000077465425,"threshold_uncertainty_score":0.9999611},"labels":[],"label_agreement":null},{"id":"W2080093778","doi":"10.1016/j.ijrobp.2014.05.2485","title":"Commissioning of a Prostate Model Created Using Knowledge-Based Planning as a Tool to Guide the Planning Process","year":2014,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba","funders":"","keywords":"Medicine; Rectum; Prostate; Radiation treatment planning; Nuclear medicine; Prostate cancer; Medical physics; Radiology; Radiation therapy; Surgery; Cancer; Internal medicine","score_opus":0.28146128432852563,"score_gpt":0.5588886812334513,"score_spread":0.2774273969049256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080093778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33452925,0.000045264722,0.66244173,0.0008006217,0.0008114719,0.00029973194,0.000030371686,0.000031453656,0.0010100965],"genre_scores_gemma":[0.63005745,0.0000042404913,0.36827326,0.00070642686,0.00086768233,0.000015046449,0.000004953616,0.00003612486,0.000034824814],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961736,0.0010932618,0.0017956904,0.0002562239,0.00040455937,0.00027664553],"domain_scores_gemma":[0.9782277,0.017684288,0.0021987574,0.0002298209,0.0015198579,0.00013961918],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004663941,0.00023692333,0.0007755564,0.00017570902,0.00014360576,0.000044126442,0.00079790194,0.00023701276,0.000030677595],"category_scores_gemma":[0.044482,0.00017214613,0.00021197805,0.0002633583,0.00021067368,0.00014435498,0.00011250954,0.00057899934,0.0000064292194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026324247,0.001163903,0.048134927,0.00012848015,0.0010155555,0.00003060901,0.0071440567,0.6746849,0.010043461,0.13019036,0.002916695,0.12191462],"study_design_scores_gemma":[0.0029777978,0.0007303376,0.00026975386,0.00053095794,0.00015596328,0.000030952066,0.00012333311,0.45031685,0.0060648746,0.53683716,0.0017566005,0.00020539433],"about_ca_topic_score_codex":0.000006536937,"about_ca_topic_score_gemma":3.630025e-7,"teacher_disagreement_score":0.40664682,"about_ca_system_score_codex":0.00035686867,"about_ca_system_score_gemma":0.00089379534,"threshold_uncertainty_score":0.9635667},"labels":[],"label_agreement":null},{"id":"W2080113627","doi":"10.1245/s10434-013-3054-y","title":"Clinical Research in Surgical Oncology: An Analysis of ClinicalTrials.gov","year":2013,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Surgical oncology; Clinical trial; Randomized controlled trial; Internal medicine; Observational study; Oncology; Surgery","score_opus":0.9109205879097394,"score_gpt":0.7531355984178664,"score_spread":0.15778498949187303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080113627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88997185,0.00028284674,0.0005491389,0.02019641,0.0013862363,0.0023122362,0.00019688565,0.000105268846,0.08499914],"genre_scores_gemma":[0.77801776,0.012950902,0.2062709,0.00058902195,0.0014494568,0.00027477197,0.000026966174,0.00009115836,0.0003290602],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9524337,0.034440186,0.0091147935,0.0013045283,0.0014107202,0.0012960685],"domain_scores_gemma":[0.5663591,0.42741704,0.0018497925,0.0014744556,0.0019489252,0.0009506625],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.09285156,0.0003859325,0.0066881343,0.0012475129,0.00007596287,0.00002390982,0.0013133442,0.0022420376,0.0051144375],"category_scores_gemma":[0.052715626,0.00030809554,0.0016081871,0.0034964355,0.0034834403,0.0001976481,0.0006195376,0.002325141,0.00014190652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005684337,0.017708063,0.02365561,0.0001617514,0.0021795114,0.0011243381,0.0001947417,0.000036204827,0.00005094735,0.20515157,0.008810311,0.7352426],"study_design_scores_gemma":[0.006107197,0.010160061,0.011658771,0.00010838205,0.0007203471,0.00002071006,0.0003052282,0.0013279397,0.00018604548,0.71706766,0.2519043,0.00043335746],"about_ca_topic_score_codex":0.0004925936,"about_ca_topic_score_gemma":0.0001766581,"teacher_disagreement_score":0.7348093,"about_ca_system_score_codex":0.000120730496,"about_ca_system_score_gemma":0.0007787781,"threshold_uncertainty_score":0.9999765},"labels":[],"label_agreement":null},{"id":"W2080153379","doi":"10.1016/j.cct.2005.02.006","title":"Pre-trial evaluation of the potential for unblinding in drug trials: A prototype example","year":2005,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Blinding; Medicine; Placebo; Clinical trial; Set (abstract data type); Research design; Statistical significance; Clinical study design; Medical physics; Alternative medicine; Physical therapy; Statistics; Computer science; Internal medicine; Pathology","score_opus":0.9244809313587626,"score_gpt":0.6978058308229155,"score_spread":0.22667510053584716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080153379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69190764,0.0014471663,0.11769201,0.0075852647,0.022356287,0.153711,0.001121907,0.00030660944,0.0038720889],"genre_scores_gemma":[0.7989172,0.000038532893,0.19079718,0.00024062564,0.006472599,0.0031743504,0.000010643935,0.00008084788,0.00026805032],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82270294,0.14296402,0.028714992,0.0017612877,0.0029873524,0.0008694182],"domain_scores_gemma":[0.30121794,0.68521434,0.00997461,0.002010106,0.0012501033,0.0003329154],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50174457,0.00041123037,0.0051070424,0.00018703203,0.00012461795,0.00007736125,0.00095548737,0.00067273027,0.0003889222],"category_scores_gemma":[0.8947023,0.00026193468,0.0024032844,0.0005342261,0.00039082882,0.00023163373,0.000242449,0.00074636284,0.000011502784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3858905,0.0073891957,0.0019859292,0.0006873716,0.0015837108,0.0000045081947,0.00060839206,0.00019797563,0.00079005584,0.07050474,0.040393475,0.48996413],"study_design_scores_gemma":[0.16882497,0.0009946055,0.0005853148,0.00044612415,0.0010215158,7.413011e-7,0.00007077162,0.004068888,0.001258506,0.81847006,0.0039122635,0.00034622432],"about_ca_topic_score_codex":0.00006786366,"about_ca_topic_score_gemma":0.00005003536,"teacher_disagreement_score":0.74796534,"about_ca_system_score_codex":0.0001242632,"about_ca_system_score_gemma":0.001462542,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W2080813654","doi":"10.1002/sim.1173","title":"Number needed to treat (NNT): estimation of a measure of clinical benefit","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"","keywords":"Number needed to treat; Estimator; Context (archaeology); Event (particle physics); Medicine; Randomized controlled trial; Statistics; Absolute risk reduction; Clinical trial; Confidence interval; Econometrics; Computer science; Relative risk; Mathematics; Surgery; Internal medicine","score_opus":0.5337564789862494,"score_gpt":0.6268482031556304,"score_spread":0.09309172416938094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080813654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06820636,0.000021188838,0.9210532,0.00080205913,0.0006724323,0.00065457314,0.00030631034,0.000028865916,0.008255048],"genre_scores_gemma":[0.12834954,0.00006515127,0.8707464,0.00023955504,0.00024316323,0.000020547426,0.000009351901,0.000032849523,0.00029349502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944819,0.0006243607,0.0033712965,0.00035987096,0.00087302265,0.00028950477],"domain_scores_gemma":[0.93778205,0.060258504,0.0007058089,0.0005626336,0.00046456093,0.00022644973],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0074099563,0.00021892549,0.0017384215,0.00015265544,0.00002111141,0.000003589773,0.0002843479,0.0002194473,0.0013720412],"category_scores_gemma":[0.32151693,0.00017308877,0.00008068218,0.0006172201,0.00043984657,0.000029779203,0.00007016233,0.00034605057,0.000025170832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013664386,0.00082867086,0.011011326,0.0007196868,0.00009719249,0.00008179738,0.0009967112,0.0001443285,0.00020684033,0.671365,0.02851841,0.28466356],"study_design_scores_gemma":[0.0034352574,0.00073754723,0.006223049,0.00079359947,0.00022560105,0.000008316575,0.00024339609,0.0025485596,0.00027404493,0.9852033,0.00014241395,0.00016486985],"about_ca_topic_score_codex":0.0002703744,"about_ca_topic_score_gemma":0.00007236811,"teacher_disagreement_score":0.31410697,"about_ca_system_score_codex":0.000043140764,"about_ca_system_score_gemma":0.000074960626,"threshold_uncertainty_score":0.99954087},"labels":[],"label_agreement":null},{"id":"W2081266165","doi":"10.1007/bf03190054","title":"Differences in reference products: dissolution and in vivo evidence","year":2000,"lang":"en","type":"article","venue":"European Journal of Drug Metabolism and Pharmacokinetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Pharmacists Association","funders":"","keywords":"Human physiology; In vivo; Dissolution; Clinical chemistry; Chemistry; Medicine; Pharmacology; Internal medicine; Biology; Biotechnology","score_opus":0.33785891534596624,"score_gpt":0.46446672292087726,"score_spread":0.12660780757491102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081266165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918068,0.0052938755,0.00049230247,0.0006742135,0.0003021578,0.00016698614,0.000015566455,0.000008195078,0.001239877],"genre_scores_gemma":[0.8895016,0.020501954,0.089314125,0.000100318946,0.00037061985,0.0000010726694,7.83181e-8,0.0000189813,0.00019125783],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99532473,0.0027621605,0.0011668298,0.00023193065,0.0002940727,0.00022028598],"domain_scores_gemma":[0.9941751,0.0051018503,0.00033564502,0.0001423499,0.00009974176,0.00014531128],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005819577,0.00017180236,0.00056528556,0.00013436087,0.000030237223,0.00004988605,0.00020405272,0.000025989038,0.00025217043],"category_scores_gemma":[0.009981369,0.00012929349,0.000031442483,0.00025997,0.00017183615,0.00018106149,0.000062262705,0.00052657886,0.0000030706346],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005129116,0.0018547341,0.030916313,0.0017303333,0.00023723161,0.0017981416,0.010810055,0.00006048572,0.04429106,0.013923169,0.0077525973,0.8814968],"study_design_scores_gemma":[0.013663983,0.0005677474,0.68295634,0.004505835,0.0009367358,0.0004030037,0.0004722383,0.0010906939,0.013928711,0.2501215,0.029960005,0.0013931922],"about_ca_topic_score_codex":0.000003882552,"about_ca_topic_score_gemma":0.0000017549144,"teacher_disagreement_score":0.8801036,"about_ca_system_score_codex":0.000008952377,"about_ca_system_score_gemma":0.000023494511,"threshold_uncertainty_score":0.99835795},"labels":[],"label_agreement":null},{"id":"W2081579622","doi":"10.1002/cncr.24628","title":"Bayesian statistics in oncology","year":2009,"lang":"en","type":"review","venue":"Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Bayesian probability; Bayesian statistics; Bayesian econometrics; Computer science; Scope (computer science); Bayesian inference; Statistics; Data science; Medicine; Medical physics; Artificial intelligence; Mathematics","score_opus":0.7836948925511034,"score_gpt":0.7098888224687316,"score_spread":0.07380607008237172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081579622","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.873421e-9,0.91351646,0.078982495,0.000046969988,0.0011220236,0.00084638165,0.0007679496,0.000042433167,0.004675283],"genre_scores_gemma":[7.952835e-9,0.5750051,0.42376584,0.00010944977,0.00044066107,0.00018211486,0.0000050304325,0.000044014094,0.000447729],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99545836,0.0016064682,0.0017704082,0.00050529395,0.00024053185,0.00041891672],"domain_scores_gemma":[0.9431025,0.055536777,0.00065798825,0.00049377786,0.0000610356,0.00014795722],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001899637,0.000389007,0.0039021678,0.00014427413,0.00002292246,0.00001916115,0.00041099207,0.0007867035,0.0017866511],"category_scores_gemma":[0.04270881,0.0003087384,0.00025688438,0.0003435315,0.00012134273,0.000017041622,0.00007109325,0.0009610806,0.00009083529],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005338442,0.000076743425,4.0733752e-7,0.0066775056,0.000047460224,0.00008576974,0.000012105068,1.0105764e-7,5.297786e-9,0.05125192,0.018944558,0.9228981],"study_design_scores_gemma":[0.00016270451,0.00005057989,4.491439e-7,0.005172813,0.00037366274,0.0000033031697,0.0000011283752,0.000005145628,4.446754e-8,0.42741206,0.5666334,0.00018468668],"about_ca_topic_score_codex":0.000014120915,"about_ca_topic_score_gemma":0.000073589516,"teacher_disagreement_score":0.9227134,"about_ca_system_score_codex":0.00075038057,"about_ca_system_score_gemma":0.0009569357,"threshold_uncertainty_score":0.99993646},"labels":[],"label_agreement":null},{"id":"W2081877752","doi":"10.1111/j.0006-341x.2004.00199.x","title":"Small‐Sample Inference for the Comparison of Means of Log‐Normal Distributions","year":2004,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; Okanagan College","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Statistics; Sample (material); Mathematics; Computer science; Artificial intelligence; Chromatography; Chemistry","score_opus":0.7734442251240047,"score_gpt":0.5978762975389873,"score_spread":0.17556792758501738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081877752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007298552,0.000115372415,0.9893421,0.0001800939,0.0003330702,0.000458232,0.0021460643,0.000021642338,0.00010486039],"genre_scores_gemma":[0.4086277,0.000018325023,0.5912649,0.000007923394,0.000042299245,0.000018599283,0.000006599993,0.0000072455437,0.000006393628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982468,0.00011315053,0.0009798234,0.0001527186,0.0002980827,0.00020944297],"domain_scores_gemma":[0.8198406,0.1788306,0.00048020532,0.00040433952,0.00038046914,0.000063780666],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021223114,0.00010754915,0.0005158485,0.00023063234,0.00007540958,0.000012240619,0.00040625516,0.00012789952,0.000043589032],"category_scores_gemma":[0.38180822,0.00007377218,0.00017225479,0.00227324,0.00031450024,0.000021416317,0.00010255958,0.00012271275,0.0000022740023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005669799,0.00072062353,0.002911141,0.0002510847,0.00009447596,1.734002e-7,0.00012239645,0.00007323167,0.00047849255,0.96677524,0.00025841454,0.028258018],"study_design_scores_gemma":[0.0009675761,0.00040350546,0.002815583,0.00004068429,0.00019762837,2.465541e-7,0.00011009532,0.0006971993,0.022661552,0.9711733,0.0008228725,0.00010979685],"about_ca_topic_score_codex":0.00007854143,"about_ca_topic_score_gemma":0.000018540166,"teacher_disagreement_score":0.40132913,"about_ca_system_score_codex":0.000044306093,"about_ca_system_score_gemma":0.000088437846,"threshold_uncertainty_score":0.6233991},"labels":[],"label_agreement":null},{"id":"W2081968012","doi":"10.1118/1.2031029","title":"Sci‐YIS Fri ‐ 07: Fitting the linear‐quadratic model to detailed data set for different dose ranges","year":2005,"lang":"en","type":"article","venue":"Medical Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Regional Cancer Foundation","funders":"","keywords":"Mathematics; Goodness of fit; Statistics; Data set; Monte Carlo method; Range (aeronautics); Nuclear medicine; Physics; Medicine; Materials science","score_opus":0.7184066795323826,"score_gpt":0.5909839713637757,"score_spread":0.1274227081686069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081968012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014409934,0.00004377302,0.9690277,0.014133905,0.0003871847,0.0011945921,0.00047856275,0.000115488896,0.0002088755],"genre_scores_gemma":[0.117780976,0.000032821892,0.871274,0.005472848,0.0047447938,0.0002601632,0.00004630663,0.00009821309,0.0002898927],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99611783,0.00047594274,0.001064023,0.00062031444,0.0011750913,0.0005467791],"domain_scores_gemma":[0.9402631,0.057398915,0.00022483496,0.0015455589,0.0001236176,0.00044397172],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0048123244,0.00030185553,0.0008353773,0.000021535669,0.00021680954,0.00005617988,0.0015690019,0.00020730516,0.00023352905],"category_scores_gemma":[0.14691062,0.0001804315,0.0001539138,0.00017718523,0.00024577198,0.000092059236,0.0007866873,0.00056780735,0.00012040073],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045595752,0.001809313,0.000087489534,0.00086221256,0.00045354766,0.000011055584,0.0018729403,0.0007731857,0.0002465495,0.06994078,0.13998242,0.78350455],"study_design_scores_gemma":[0.0012202837,0.00008866107,0.000014004321,0.00015252545,0.00019392882,5.8593895e-7,0.000029429752,0.42448592,0.0008721758,0.57127136,0.0014564953,0.00021461437],"about_ca_topic_score_codex":0.0000025273127,"about_ca_topic_score_gemma":0.000024188743,"teacher_disagreement_score":0.78328997,"about_ca_system_score_codex":0.000051985025,"about_ca_system_score_gemma":0.00013698946,"threshold_uncertainty_score":0.8602753},"labels":[],"label_agreement":null},{"id":"W2082074737","doi":"10.1007/s40273-014-0134-1","title":"Methods for Identifying the Cost-effective Case Definition Cut-Off for Sequential Monitoring Tests: An Extension of Phelps and Mushlin","year":2014,"lang":"en","type":"article","venue":"PharmacoEconomics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Capital District Health Authority","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Health administration; Health economics; Test (biology); Quality of Life Research; Cost effectiveness; Medicine; Health care; Population health; Actuarial science; Population; Risk analysis (engineering); Public health; Business; Economics; Environmental health; Nursing","score_opus":0.7227974291532423,"score_gpt":0.6577397002386661,"score_spread":0.06505772891457617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082074737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21444374,0.00007803806,0.7807957,0.00006898225,0.0014460514,0.002925973,0.00016647777,0.000037376238,0.000037697897],"genre_scores_gemma":[0.124272995,0.0000766287,0.8736138,0.000109967055,0.00085423863,0.0010123189,0.000004208467,0.000051393898,0.000004469224],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973418,0.0011219257,0.0008139708,0.00040747056,0.000057606874,0.00025724107],"domain_scores_gemma":[0.9078244,0.09112558,0.00046412696,0.00028703938,0.0001850761,0.000113769216],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009489249,0.00019321578,0.0005551658,0.00005781102,0.00021622809,0.00006723711,0.00016009735,0.000109178814,0.000015369402],"category_scores_gemma":[0.028025934,0.00016262755,0.00016020813,0.000047251568,0.00014112073,0.00017257794,0.000087331486,0.00017711226,0.0000013623514],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006246579,0.00016538141,0.00008236458,0.0005780031,0.00018469592,0.0000030471404,0.0004519829,0.00003650644,0.03557752,0.0641409,0.00014247526,0.89801246],"study_design_scores_gemma":[0.0026601655,0.00022490384,0.000050059214,0.000058073576,0.00056772726,0.000052491567,0.00022453103,0.05759742,0.11365018,0.823725,0.0009786988,0.00021075935],"about_ca_topic_score_codex":0.000012265023,"about_ca_topic_score_gemma":0.000004591561,"teacher_disagreement_score":0.8978017,"about_ca_system_score_codex":0.0000688379,"about_ca_system_score_gemma":0.000022255374,"threshold_uncertainty_score":0.9801614},"labels":[],"label_agreement":null},{"id":"W2082939789","doi":"10.1016/s0378-3758(00)00227-5","title":"Sample size determination in step-down and step-up multiple tests for comparing treatments with a control","year":2001,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Mathematics; Sample size determination; Statistics; Sample (material); Multiple comparisons problem; Econometrics; Chromatography","score_opus":0.40173761604778924,"score_gpt":0.53015615459137,"score_spread":0.12841853854358076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082939789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21307454,0.000033715714,0.78639156,0.000048647744,0.000063924446,0.00023578595,0.00010826915,0.0000071667846,0.00003641503],"genre_scores_gemma":[0.51677394,0.000013405168,0.48313385,0.000025139694,0.000032070824,0.0000075816392,6.024672e-7,0.0000070610135,0.000006342185],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983451,0.00021080516,0.00079595344,0.00018173813,0.00023216748,0.0002342726],"domain_scores_gemma":[0.84819984,0.15104766,0.00036212496,0.00007482494,0.00015689898,0.00015862637],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001178091,0.00015843046,0.00069039816,0.000073631934,0.00006962761,0.000071837174,0.000077142184,0.0000775098,0.000018013614],"category_scores_gemma":[0.1136952,0.00011204793,0.000025608966,0.000075378135,0.00014136767,0.00011978676,0.000020893243,0.00023978521,2.7399093e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040465407,0.00039027014,0.78136545,0.0002810939,0.00013943588,0.00019855691,0.0004773924,0.000027693175,0.0001451014,0.019645168,0.00021559488,0.19306771],"study_design_scores_gemma":[0.015810277,0.0030051756,0.404585,0.0011100611,0.0003155941,0.00016089079,0.0002741593,0.15681085,0.000023302355,0.41751528,0.00008633566,0.00030307073],"about_ca_topic_score_codex":0.000025806441,"about_ca_topic_score_gemma":0.00002174481,"teacher_disagreement_score":0.39787012,"about_ca_system_score_codex":0.000038735343,"about_ca_system_score_gemma":0.000045829627,"threshold_uncertainty_score":0.8937705},"labels":[],"label_agreement":null},{"id":"W2082983435","doi":"10.1111/bmsp.12001","title":"Consequences of choosing samples in hypothesis testing to ensure homogeneity of variance","year":2013,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Statistics; Mathematics; Homogeneity (statistics); F-test of equality of variances; Type I and type II errors; Sample size determination; Variance (accounting); Levene's test; Standard deviation; Population; Econometrics; Statistical hypothesis testing; Test statistic; Demography","score_opus":0.5089277066177947,"score_gpt":0.5105138001551611,"score_spread":0.0015860935373663843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082983435","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40657485,0.00015854754,0.5909809,0.0005309901,0.00012043522,0.00036486168,0.00018891315,0.000008484204,0.0010720532],"genre_scores_gemma":[0.36850658,0.000038425875,0.6312853,0.000103718114,0.000040786366,0.000006868792,1.02504444e-7,0.000012959987,0.000005241133],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955393,0.0009225098,0.002532024,0.00027195388,0.0003988297,0.00033538358],"domain_scores_gemma":[0.9180248,0.08037716,0.00069992634,0.00018156496,0.00044962738,0.00026694656],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035612867,0.00017384576,0.0014706383,0.00013280107,0.000035961573,0.000032178352,0.0002954497,0.0001817033,0.0007082716],"category_scores_gemma":[0.2442217,0.00015582114,0.00009216076,0.0002956148,0.0009299186,0.00007190069,0.000070625254,0.00040072296,0.0000076004135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036358772,0.0022327444,0.004863988,0.0019198327,0.00023428345,0.0004801627,0.00034072582,0.000005615622,0.028355367,0.42348665,0.0025277056,0.53518933],"study_design_scores_gemma":[0.0007963313,0.0005000694,0.05117899,0.0010439545,0.00006916356,0.0009971987,0.000065572545,0.00004961409,0.0007708415,0.94438183,0.0000060321836,0.00014037998],"about_ca_topic_score_codex":0.00007224587,"about_ca_topic_score_gemma":0.000008560138,"teacher_disagreement_score":0.53504896,"about_ca_system_score_codex":0.000015661213,"about_ca_system_score_gemma":0.000057367026,"threshold_uncertainty_score":0.7755077},"labels":[],"label_agreement":null},{"id":"W2083645524","doi":"10.1198/016214506000000951","title":"A Multiresolution Hazard Model for Multicenter Survival Studies","year":2007,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"National Cancer Institute","keywords":"Hazard ratio; Hazard; Statistics; Econometrics; Proportional hazards model; Survival analysis; Computer science; Mathematics; Confidence interval; Biology","score_opus":0.4978380573074715,"score_gpt":0.5919939326207032,"score_spread":0.09415587531323172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083645524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039857753,0.000020377194,0.95676607,0.0015187116,0.0012223588,0.00035660865,0.00018458805,0.000017393848,0.00005612755],"genre_scores_gemma":[0.24791813,0.000022902563,0.75098294,0.00032489156,0.00047446744,0.0000063356074,4.6602835e-7,0.000023577733,0.00024629533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961888,0.00077579264,0.0015486734,0.00017147548,0.0009074823,0.00040774996],"domain_scores_gemma":[0.8876317,0.10753283,0.0033022906,0.00020196171,0.0011893535,0.00014186713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0115856165,0.00016671914,0.0008980509,0.00006798379,0.0001445033,0.000029874536,0.00028501212,0.000075710705,0.00000737586],"category_scores_gemma":[0.32812747,0.00010730278,0.0003187008,0.00022072866,0.00023998298,0.00007646204,0.00008007635,0.00037787075,0.0000031890843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0128513,0.003409185,0.06653983,0.0006751554,0.0061793765,0.000048260994,0.00402989,0.001386808,0.0051583075,0.5045889,0.1606153,0.2345177],"study_design_scores_gemma":[0.0022511727,0.00041782676,0.026913272,0.00009537982,0.0006948285,0.0000037437237,0.0005136082,0.0508806,0.00029067212,0.9174685,0.0002590283,0.00021136737],"about_ca_topic_score_codex":0.000005338986,"about_ca_topic_score_gemma":0.000034252247,"teacher_disagreement_score":0.4128796,"about_ca_system_score_codex":0.00081385823,"about_ca_system_score_gemma":0.00008339913,"threshold_uncertainty_score":0.677532},"labels":[],"label_agreement":null},{"id":"W2084451141","doi":"10.4212/cjhp.v63i1.875","title":"Introduction to Statistics in Pharmaceutical Clinical Trials","year":2010,"lang":"en","type":"article","venue":"The Canadian Journal of Hospital Pharmacy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Statistics; Medicine; Family medicine; Data science; Computer science; Mathematics","score_opus":0.5821694469645882,"score_gpt":0.6361079475077291,"score_spread":0.05393850054314098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084451141","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68639505,0.00016158582,0.060433436,0.18333666,0.06509823,0.0027712805,0.00059147936,0.000041511583,0.0011707556],"genre_scores_gemma":[0.5739415,0.00004047712,0.40922278,0.0015786341,0.015007004,0.000012979935,0.0000010777654,0.000056056997,0.00013947272],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99191093,0.0034459794,0.003367149,0.0002643023,0.00047874064,0.00053289306],"domain_scores_gemma":[0.94192266,0.053943414,0.0010983942,0.00049413776,0.0006354959,0.0019059094],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049058188,0.00021568975,0.0011044435,0.00025532104,0.0001419406,0.00013795,0.0007823573,0.00012781398,0.0024861752],"category_scores_gemma":[0.40289834,0.0001453944,0.000290358,0.0003815413,0.000458089,0.00013124912,0.000044984816,0.0025272965,0.000108107524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076443347,0.0005346675,0.009862032,0.000050926632,0.00034793626,0.0005817353,0.0007516841,0.000018933095,0.0007120515,0.18938532,0.5591404,0.2378499],"study_design_scores_gemma":[0.0039443886,0.0006733594,0.0036893971,0.000044890174,0.00039562953,0.00009561397,0.00007983702,0.00024378877,0.0011777678,0.82155395,0.16774166,0.00035972867],"about_ca_topic_score_codex":0.00065819843,"about_ca_topic_score_gemma":0.0072971894,"teacher_disagreement_score":0.6321686,"about_ca_system_score_codex":0.00012523671,"about_ca_system_score_gemma":0.0012889843,"threshold_uncertainty_score":0.9997739},"labels":[],"label_agreement":null},{"id":"W2085436062","doi":"10.1007/s11229-014-0602-3","title":"Early stopping of RCTs: two potential issues for error statistics","year":2014,"lang":"en","type":"article","venue":"Synthese","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Philosophy of science; Philosophy of language; Interim; Early stopping; Randomized controlled trial; Statistics; Metaphysics; Epistemology; Econometrics; Computer science; Mathematics; Philosophy; Medicine; Artificial intelligence; Law; Political science; Surgery","score_opus":0.46037923445413526,"score_gpt":0.5776411474025115,"score_spread":0.11726191294837623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085436062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023517696,0.000019325196,0.9736923,0.0002543817,0.00064942695,0.0005168618,0.0004974696,0.00006714267,0.00078539195],"genre_scores_gemma":[0.18853323,0.000004117158,0.81051177,0.00004532453,0.00041713828,0.0000388255,0.0000015662634,0.000042684795,0.00040532963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975458,0.00064869213,0.00087091903,0.0002889333,0.00033459888,0.00031109786],"domain_scores_gemma":[0.9436917,0.055133954,0.00035502657,0.0004772963,0.00023303296,0.00010904299],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035354735,0.00017393816,0.0007052577,0.000060704508,0.000058350794,0.000027066186,0.00028896212,0.00011037397,0.00027763436],"category_scores_gemma":[0.19670953,0.00014708836,0.00014128763,0.00008279165,0.00020131975,0.000045883127,0.000076391676,0.0001355242,0.00003091692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027179124,0.0002555503,0.00012323375,0.0006441834,0.00014288552,0.0000042325373,0.00029730203,0.000013320698,0.003774677,0.9227622,0.0035605573,0.068150036],"study_design_scores_gemma":[0.0008228224,0.0002563846,0.00021367367,0.00014704466,0.00015796993,0.0000011950468,0.000062248764,0.0033023153,0.0052531017,0.9883267,0.0012765526,0.00017997783],"about_ca_topic_score_codex":0.00004263972,"about_ca_topic_score_gemma":0.0000055796945,"teacher_disagreement_score":0.19317406,"about_ca_system_score_codex":0.00001858055,"about_ca_system_score_gemma":0.00002782624,"threshold_uncertainty_score":0.8100569},"labels":[],"label_agreement":null},{"id":"W2085857606","doi":"10.4065/75.4.423","title":"Use of Likelihood Ratio Computation to Standardize the Predictive Power of Noninvasive Cardiovascular Tests","year":2000,"lang":"en","type":"letter","venue":"Mayo Clinic Proceedings","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Nutrition, Metabolism and Diabetes","funders":"","keywords":"Medicine; Test (biology); Pre- and post-test probability; Disease; Diagnostic test; Population; Categorical variable; Statistics; Internal medicine; Pediatrics; Mathematics","score_opus":0.28863184765906624,"score_gpt":0.456617902223793,"score_spread":0.16798605456472676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085857606","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037383124,0.0013243995,0.5448512,0.31319803,0.010060539,0.03759291,0.02089134,0.0012986237,0.03339983],"genre_scores_gemma":[0.0119638555,0.0003625944,0.8691987,0.11097737,0.004944321,0.00062236836,0.000056693112,0.0005224942,0.0013516132],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926186,0.00056198204,0.0031425771,0.0010136265,0.0020616024,0.00060158694],"domain_scores_gemma":[0.9376768,0.057672624,0.0017461258,0.00076964137,0.0019900852,0.00014475461],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0062394054,0.00062290323,0.0029343718,0.00023607098,0.00009988474,0.00010116855,0.00082180114,0.0012485608,0.00034831022],"category_scores_gemma":[0.117973514,0.00046033136,0.0013502393,0.00066094205,0.000580118,0.0001591059,0.00028902604,0.0020677983,0.000048090307],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004967488,0.0001762789,0.00008979921,0.0012140376,0.0026112571,0.00003768506,0.0016020181,0.00001529782,0.000034870085,0.000369568,0.9844195,0.00893294],"study_design_scores_gemma":[0.003662681,0.0044046827,0.0011411645,0.0045162765,0.0070251115,0.00005323999,0.00062240707,0.00017542926,0.0032220269,0.7174588,0.25601363,0.0017045693],"about_ca_topic_score_codex":0.000022538685,"about_ca_topic_score_gemma":7.416228e-7,"teacher_disagreement_score":0.7284059,"about_ca_system_score_codex":0.00013815059,"about_ca_system_score_gemma":0.00036239251,"threshold_uncertainty_score":0.9997848},"labels":[],"label_agreement":null},{"id":"W2086570160","doi":"10.1142/s0218957704001351","title":"CRITICAL REVIEW OF THE ARMITAGE AND BROSS SEQUENTIAL PROCEDURES IN CLINICAL REHABILITATION TRIALS","year":2004,"lang":"en","type":"article","venue":"Journal of Musculoskeletal Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; University of Alberta","funders":"","keywords":"Rehabilitation; Clinical trial; Medical physics; Sequential analysis; Computer science; Sample size determination; Research design; Clinical study; Medicine; Physical therapy; Mathematics; Surgery; Statistics","score_opus":0.7101460095033213,"score_gpt":0.70459610986341,"score_spread":0.00554989963991126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086570160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9520735,0.008784023,0.005074539,0.029303454,0.0013488246,0.0025279121,0.000043550055,0.0000117342925,0.00083244214],"genre_scores_gemma":[0.58276266,0.009778289,0.40600452,0.00025046826,0.0010583061,0.000053727847,2.0519339e-7,0.00004450861,0.000047298206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9758413,0.015969168,0.005295465,0.0003007353,0.0021745884,0.00041878692],"domain_scores_gemma":[0.5598633,0.43395218,0.0018172015,0.00081750535,0.0031044076,0.0004453656],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13999622,0.00015041261,0.0016039386,0.00020223927,0.0000773942,0.00003825573,0.0005248663,0.00022330396,0.00013318192],"category_scores_gemma":[0.9222099,0.000084567546,0.0008259108,0.0006346706,0.0015858415,0.00016628776,0.00024578095,0.0016979888,0.0000033506174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00344238,0.0065326914,0.013651035,0.12201516,0.0005611777,0.00020726059,0.00074144814,0.000008907607,0.0038793932,0.7136639,0.015566318,0.11973032],"study_design_scores_gemma":[0.0024513183,0.0016749976,0.01915324,0.016627781,0.00013113227,0.00003924085,0.00012678454,0.000003530981,0.0002702884,0.9591745,0.0002459228,0.000101240104],"about_ca_topic_score_codex":0.000009785317,"about_ca_topic_score_gemma":0.000017548107,"teacher_disagreement_score":0.78221375,"about_ca_system_score_codex":0.00012244366,"about_ca_system_score_gemma":0.0008668034,"threshold_uncertainty_score":0.88555485},"labels":[],"label_agreement":null},{"id":"W2086701312","doi":"10.1177/0962280211399562","title":"Bayesian sample size calculation for estimation of the difference between two binomial proportions","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; University of Tehran","keywords":"Dirichlet distribution; Sample size determination; Statistics; Mathematics; Bayesian probability; Binomial (polynomial); Beta-binomial distribution; Binomial distribution; Negative binomial distribution; Econometrics; Prior probability; Computer science; Poisson distribution","score_opus":0.7821547142411684,"score_gpt":0.7131122956078051,"score_spread":0.06904241863336336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086701312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015516534,0.0000043953582,0.99355537,0.00050676736,0.00031421537,0.0017881624,0.001346207,0.00003314305,0.0009000646],"genre_scores_gemma":[0.07066869,0.0000043005584,0.9284818,0.000037183367,0.00020839821,0.00047591366,0.000011350693,0.000039108305,0.000073258736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98257476,0.011573321,0.0021330223,0.0006389759,0.00225688,0.00082302303],"domain_scores_gemma":[0.27656975,0.7210425,0.00036748618,0.00086504733,0.00058928004,0.00056591415],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037365764,0.00022015175,0.00091631693,0.00018374628,0.00021699024,0.000024952098,0.00089595624,0.00039157714,0.0062600053],"category_scores_gemma":[0.91480875,0.00014790634,0.00016205013,0.0010141303,0.002085638,0.00004655328,0.00038846495,0.0013839926,0.0000053873787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018499784,0.00030229273,0.0024155139,0.00028272308,0.00003328347,0.0000040992886,0.00019897436,0.0000010343425,0.00009586909,0.3775213,0.0005761691,0.6183837],"study_design_scores_gemma":[0.0010240162,0.00026370925,0.04774433,0.00024491682,0.00005679792,0.0000013010559,0.00003613592,0.022684978,0.0018191651,0.92591536,0.00006321132,0.00014605369],"about_ca_topic_score_codex":0.00038258234,"about_ca_topic_score_gemma":0.000079474776,"teacher_disagreement_score":0.87744296,"about_ca_system_score_codex":0.00015134765,"about_ca_system_score_gemma":0.0006474956,"threshold_uncertainty_score":0.9946484},"labels":[],"label_agreement":null},{"id":"W2088311091","doi":"10.1198/jasa.2009.0004","title":"Robust Estimation of Mean Functions and Treatment Effects for Recurrent Events Under Event-Dependent Censoring and Termination: Application to Skeletal Complications in Cancer Metastatic to Bone","year":2009,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Censoring (clinical trials); Inverse probability; Statistics; Event (particle physics); Breast cancer; Marginal structural model; Event data; Marginal distribution; Clinical trial; Mathematics; Econometrics; Medicine; Cancer; Confidence interval; Covariate; Internal medicine; Random variable","score_opus":0.20039376046594784,"score_gpt":0.5090273976216245,"score_spread":0.3086336371556767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088311091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23168957,0.000019751536,0.7627064,0.00419447,0.00013233814,0.0010412821,0.00020294983,0.0000061062246,0.000007139991],"genre_scores_gemma":[0.6583256,0.000021415535,0.34133172,0.0001318981,0.00005171992,0.00009938244,0.000002413314,0.000009447962,0.000026377165],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977371,0.00048794856,0.00096941064,0.0002054488,0.0004157451,0.00018434011],"domain_scores_gemma":[0.9861829,0.01198871,0.0012555973,0.00014887525,0.00027680089,0.00014709504],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001427146,0.00014321081,0.0006033218,0.00014343228,0.000087441105,0.000022421871,0.00009360017,0.000033618348,0.000002761444],"category_scores_gemma":[0.013856045,0.000108134285,0.000076672186,0.0003338821,0.000041151638,0.00006785733,0.000028600876,0.00012459142,8.273431e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004954331,0.0012244978,0.003878563,0.00013142878,0.00024473848,0.0000011715586,0.0005931503,0.008076759,0.0024850578,0.030321505,0.00042929812,0.9521184],"study_design_scores_gemma":[0.0019993922,0.0028969126,0.63688344,0.0002833135,0.00072259316,0.000009342619,0.00021660744,0.014533304,0.00044162344,0.34176156,0.000039933926,0.00021201598],"about_ca_topic_score_codex":0.00003701082,"about_ca_topic_score_gemma":0.00008415188,"teacher_disagreement_score":0.9519064,"about_ca_system_score_codex":0.00077338755,"about_ca_system_score_gemma":0.00005742775,"threshold_uncertainty_score":0.9944507},"labels":[],"label_agreement":null},{"id":"W2088394756","doi":"10.1016/j.ahj.2007.09.011","title":"Monitoring the ACTIVE-W trial: Some issues in monitoring a noninferiority trial","year":2007,"lang":"en","type":"review","venue":"American Heart Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Libin Cardiovascular Institute of Alberta; University of British Columbia","funders":"","keywords":"Medicine; Intensive care medicine; Medical physics","score_opus":0.7710759885028773,"score_gpt":0.6814990308159752,"score_spread":0.0895769576869021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088394756","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015141994,0.9777179,0.000686187,0.0002672439,0.015483987,0.004026491,0.00003251552,0.00011041752,0.00016106859],"genre_scores_gemma":[0.000014856958,0.81836283,0.15556417,0.000024661731,0.025618693,0.0001839685,2.7799211e-7,0.00014397025,0.00008658131],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98588073,0.0069168364,0.004074235,0.0006751606,0.0013355853,0.0011174647],"domain_scores_gemma":[0.8983244,0.097877726,0.0023163352,0.000894924,0.00016622848,0.0004204133],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.016777186,0.0008087036,0.006517294,0.00045574908,0.00036448974,0.00032964302,0.0010513521,0.00046931388,0.0000870627],"category_scores_gemma":[0.08663646,0.00052400504,0.0017232682,0.0011135478,0.0006183806,0.00021186603,0.00027132288,0.005171249,0.000063300045],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012938881,0.00029283963,0.00003587017,0.00065253524,0.0002722394,0.00010727082,0.00011065025,1.1869384e-7,3.992584e-7,0.0002817717,0.00021760476,0.98508984],"study_design_scores_gemma":[0.055175934,0.0025568842,0.000070442125,0.019819913,0.001549386,0.00031680462,0.0004644505,0.0000011290126,0.000018883899,0.07266024,0.846221,0.0011448903],"about_ca_topic_score_codex":0.0001301585,"about_ca_topic_score_gemma":0.0000019369606,"teacher_disagreement_score":0.98394495,"about_ca_system_score_codex":0.00069870276,"about_ca_system_score_gemma":0.0007558071,"threshold_uncertainty_score":0.99972117},"labels":[],"label_agreement":null},{"id":"W2088499232","doi":"10.1016/j.biologicals.2011.06.006","title":"Statistical considerations for confirmatory clinical trials for similar biotherapeutic products","year":2011,"lang":"en","type":"review","venue":"Biologicals","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"Health Canada","keywords":"Equivalence (formal languages); Clinical trial; Medicine; Product (mathematics); Computer science; Risk analysis (engineering); Mathematics; Pathology","score_opus":0.9821581373665009,"score_gpt":0.749156292279861,"score_spread":0.2330018450866399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088499232","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9053672e-7,0.7007928,0.2668809,0.00020582436,0.0026738003,0.016376346,0.0126089305,0.00025532153,0.00020590809],"genre_scores_gemma":[3.6995837e-7,0.49784568,0.4968252,0.00039456412,0.0015536596,0.0030666383,0.000090094625,0.00009313239,0.00013066905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.96934974,0.018105922,0.009626751,0.0017879974,0.00023900988,0.0008905925],"domain_scores_gemma":[0.3666791,0.6279801,0.0032331394,0.001119536,0.0006132869,0.00037482215],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059459735,0.0010351496,0.012814905,0.0001505988,0.00026053318,0.00011315733,0.0006456966,0.0026159512,0.001570485],"category_scores_gemma":[0.8325521,0.0006231966,0.0027370758,0.00018587934,0.0011112859,0.00003756221,0.00014917829,0.0008060447,0.00011835555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012671888,0.00044447122,6.0009603e-7,0.009767089,0.0008568918,0.0000035779274,0.000005482214,4.641664e-9,9.0035553e-7,0.4774035,0.041819885,0.46957088],"study_design_scores_gemma":[0.0007541576,0.00064204674,7.0775013e-7,0.0010105916,0.002750321,0.000007899724,0.0000025105592,0.0000031325376,0.0000030283586,0.48101112,0.5133791,0.00043540017],"about_ca_topic_score_codex":8.0638944e-7,"about_ca_topic_score_gemma":6.715396e-7,"teacher_disagreement_score":0.7730923,"about_ca_system_score_codex":0.00007571301,"about_ca_system_score_gemma":0.000900178,"threshold_uncertainty_score":0.9996219},"labels":[],"label_agreement":null},{"id":"W2088680000","doi":"10.1186/1471-2407-13-193","title":"Fool’s gold, lost treasures, and the randomized clinical trial","year":2013,"lang":"en","type":"article","venue":"BMC Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Toronto","keywords":"Randomized controlled trial; Medicine; Clinical trial; Population; Intensive care medicine; Clinical endpoint; Gold standard (test); Oncology; Internal medicine","score_opus":0.6467025600910756,"score_gpt":0.6022433548714857,"score_spread":0.0444592052195899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088680000","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2843466,0.0098488955,0.5030038,0.02283043,0.032972157,0.056276213,0.00044880924,0.0007187204,0.08955439],"genre_scores_gemma":[0.062594585,0.002636099,0.901175,0.0029364042,0.0100745605,0.004760086,0.000001701963,0.00014678849,0.015674733],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901034,0.007072323,0.0017369256,0.00040327333,0.00038894266,0.00029510478],"domain_scores_gemma":[0.7194446,0.27926674,0.00045728352,0.00052764657,0.00013573556,0.00016804118],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018526359,0.0002124268,0.00173923,0.00002531001,0.00006160475,0.00010402764,0.0002790617,0.00023190299,0.0025873333],"category_scores_gemma":[0.3041438,0.00010911523,0.0005247355,0.00011121666,0.0012835687,0.000051658164,0.00012005584,0.00038289494,0.00016342066],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6625333,0.00019822491,0.00018038286,0.00007373525,0.00033690606,0.000001352767,0.00009162644,5.314865e-7,0.0000027030699,0.20508307,0.05589796,0.07560024],"study_design_scores_gemma":[0.4585322,0.000050574075,0.00012995914,0.000033954555,0.0002885823,8.7315084e-7,0.00001303624,0.00039898133,0.0000050521508,0.5392468,0.0011994353,0.000100567806],"about_ca_topic_score_codex":0.0003998322,"about_ca_topic_score_gemma":0.0001631193,"teacher_disagreement_score":0.39817128,"about_ca_system_score_codex":0.000033552165,"about_ca_system_score_gemma":0.00015665052,"threshold_uncertainty_score":0.99832445},"labels":[],"label_agreement":null},{"id":"W2089415104","doi":"10.1002/sim.1687","title":"Inflation of the type I error rate when a continuous confounding variable is categorized in logistic regression analyses","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":248,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Confounding; Statistics; Categorical variable; Type I and type II errors; Logistic regression; Mathematics; Inflation (cosmology); Sample size determination; Econometrics; Variable (mathematics); Regression analysis","score_opus":0.5624346742081207,"score_gpt":0.6001798666323802,"score_spread":0.037745192424259555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089415104","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029097944,0.00013634084,0.96289057,0.0012509488,0.0020454063,0.0011871739,0.00019653847,0.000039158545,0.0031559404],"genre_scores_gemma":[0.32353976,0.000047576654,0.67574507,0.0002629384,0.00012399018,0.000015802114,0.00000951733,0.000026209096,0.00022912295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99638414,0.0009272852,0.0015951133,0.00030818328,0.0004924686,0.0002928249],"domain_scores_gemma":[0.97070897,0.027735071,0.00070214516,0.000486944,0.00029503801,0.000071861425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047478164,0.00020883449,0.0010236447,0.00018084003,0.000049782313,0.000010818799,0.00029685095,0.00016430931,0.0005797995],"category_scores_gemma":[0.22493549,0.00012903995,0.000034233548,0.0007293968,0.0005066833,0.000038071492,0.00008817995,0.0004530701,0.0000058590203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060708635,0.00026026522,0.004528323,0.00062082143,0.00009215776,0.000075152064,0.0036297007,0.00042334676,0.008536065,0.975642,0.0033447503,0.0022403342],"study_design_scores_gemma":[0.0037563362,0.00020834288,0.003439062,0.0012531028,0.00015880747,0.0000025250936,0.00036992726,0.0017775685,0.00053911353,0.9882916,0.00007056141,0.00013301738],"about_ca_topic_score_codex":0.0006772228,"about_ca_topic_score_gemma":0.00013842386,"teacher_disagreement_score":0.29444182,"about_ca_system_score_codex":0.00017446566,"about_ca_system_score_gemma":0.00019862801,"threshold_uncertainty_score":0.7815932},"labels":[],"label_agreement":null},{"id":"W2090257361","doi":"10.1200/jco.2009.26.3343","title":"Randomized Phase II Trials: Inevitable or Inadvisable?","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Citation; Medicine; Clinical Oncology; Randomized controlled trial; Clinical trial; Library science; Oncology; Internal medicine; Cancer; Computer science","score_opus":0.8457395369729281,"score_gpt":0.7345951961345429,"score_spread":0.1111443408383852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090257361","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56031954,0.0003533071,0.26691845,0.040501326,0.081910215,0.0047065914,0.000118673976,0.00019157513,0.044980325],"genre_scores_gemma":[0.041433524,0.00042687356,0.94563335,0.001961472,0.008635338,0.0000290849,5.165236e-7,0.000051653846,0.0018282109],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95317334,0.023933973,0.020933324,0.00043216383,0.0009417368,0.0005854763],"domain_scores_gemma":[0.12201391,0.86005884,0.014798642,0.00072046113,0.0013678618,0.0010402867],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2703559,0.00031849378,0.0122762425,0.00018711107,0.00012993276,0.000039622177,0.00084268,0.0013369983,0.006280933],"category_scores_gemma":[0.9639343,0.00017061643,0.002490527,0.0003105254,0.0011851566,0.0002143743,0.0002474537,0.003996822,0.000048763217],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5091994,0.008544073,0.000034320416,0.00006174507,0.0011268675,0.00038209712,0.00006697545,7.677347e-7,0.00027178897,0.0830688,0.053801876,0.3434413],"study_design_scores_gemma":[0.35701296,0.008091565,0.000009579047,0.000056455432,0.0011127287,0.00011065884,0.000025246301,0.00012648935,0.0001188348,0.5504248,0.082767636,0.00014300503],"about_ca_topic_score_codex":0.00000719749,"about_ca_topic_score_gemma":0.00002763737,"teacher_disagreement_score":0.83612484,"about_ca_system_score_codex":0.000054626125,"about_ca_system_score_gemma":0.0023766432,"threshold_uncertainty_score":0.99995947},"labels":[],"label_agreement":null},{"id":"W2090386787","doi":"10.4236/jbise.2011.411090","title":"Implementation of an open-source customizable minimization program for allocation of patients to parallel groups in clinical trials","year":2011,"lang":"en","type":"article","venue":"Journal of Biomedical Science and Engineering","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":247,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Minification; Computer science; Python (programming language); Open source; Data center; Clinical trial; Computer network; Programming language; Software; Medicine","score_opus":0.4627300461880791,"score_gpt":0.5825008320195479,"score_spread":0.11977078583146883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090386787","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5754164,0.0000038332814,0.42348218,0.00005787315,0.00027497142,0.0007433064,0.000008224459,0.000004631663,0.000008579808],"genre_scores_gemma":[0.3474984,0.000009800978,0.652397,0.000014889663,0.000057272217,0.000015746089,7.1502495e-7,0.0000054724615,7.4443335e-7],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99664897,0.00023873168,0.002311588,0.00014759741,0.0004863222,0.00016677627],"domain_scores_gemma":[0.9936362,0.0047266283,0.00086037413,0.00010460747,0.00042440149,0.00024779644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027620783,0.00007196935,0.0006179454,0.0002334303,0.000021177806,0.00002156509,0.00035793544,0.00007709048,0.000019655783],"category_scores_gemma":[0.07499105,0.000053156855,0.000053609056,0.0005164586,0.00015283114,0.00028062973,0.00008184087,0.00009058055,9.616272e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008152379,0.002019177,0.0044734133,0.00027839717,0.000049201997,0.0000011361345,0.0011679851,0.00010751339,0.0031374577,0.0061825006,0.00024245329,0.98152554],"study_design_scores_gemma":[0.04110496,0.042014707,0.5676564,0.0019306304,0.00072439533,0.000014083528,0.0032865468,0.12122531,0.021911176,0.1964723,0.0025614782,0.0010979945],"about_ca_topic_score_codex":0.000017038534,"about_ca_topic_score_gemma":0.0000029875735,"teacher_disagreement_score":0.9804275,"about_ca_system_score_codex":0.00003420625,"about_ca_system_score_gemma":0.00012848759,"threshold_uncertainty_score":0.9572867},"labels":[],"label_agreement":null},{"id":"W2090437681","doi":"10.1007/s12561-010-9030-1","title":"Sequential Testing with Recurrent Events over Multiple Treatment Periods","year":2010,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; GlaxoSmithKline","keywords":"Statistics; Medicine; Clinical trial; Null hypothesis; Biostatistics; Baseline (sea); Event (particle physics); Early stopping; Accrual; Statistical hypothesis testing; Econometrics; Computer science; Mathematics; Internal medicine; Epidemiology; Machine learning","score_opus":0.5242442790962877,"score_gpt":0.5618258742737673,"score_spread":0.03758159517747961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090437681","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81366986,0.000012373762,0.17743987,0.00013796063,0.004397558,0.0010526766,0.0013326285,0.00012349652,0.0018335958],"genre_scores_gemma":[0.34421828,0.0000060098328,0.6555188,0.000019488503,0.0001184452,0.000036870042,0.0000021670405,0.000013801101,0.00006616115],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974546,0.0002838445,0.0006724377,0.0005425907,0.00058687263,0.0004596827],"domain_scores_gemma":[0.9743374,0.024753148,0.00027063585,0.00035114752,0.00012058902,0.00016707764],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016799453,0.00024098717,0.00043061146,0.00010795521,0.00017364103,0.00007839202,0.0003386062,0.000103799415,0.00027264902],"category_scores_gemma":[0.062236737,0.00016249648,0.000037434682,0.0004844048,0.00064928597,0.00007861482,0.00007966298,0.00031277657,0.000012881557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038083087,0.00229612,0.40599525,0.00016607104,0.00007853565,0.00019166748,0.001348557,0.000018652825,0.012488067,0.35887423,0.0007499295,0.21741208],"study_design_scores_gemma":[0.0019862896,0.0014538189,0.062233746,0.00012598051,0.00006561703,0.000014992606,0.00014581761,0.008080654,0.0012760612,0.92365193,0.0004924823,0.00047258445],"about_ca_topic_score_codex":0.00016559706,"about_ca_topic_score_gemma":0.0017452718,"teacher_disagreement_score":0.56477773,"about_ca_system_score_codex":0.00008295154,"about_ca_system_score_gemma":0.00021690872,"threshold_uncertainty_score":0.94566244},"labels":[],"label_agreement":null},{"id":"W2090888216","doi":"10.1007/s10549-007-9595-7","title":"Decision making in adjuvant trials in breast cancer: the NCIC CTG MA.17 trial as an example","year":2007,"lang":"en","type":"article","venue":"Breast Cancer Research and Treatment","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Interim; Interim analysis; Medicine; Hazard ratio; Breast cancer; Confidence interval; Internal medicine; Placebo; Sample size determination; Letrozole; Oncology; Clinical endpoint; Relative risk; Absolute risk reduction; Clinical trial; Adjuvant; Cancer; Statistics; Mathematics; Tamoxifen; Alternative medicine; Pathology","score_opus":0.742129627608868,"score_gpt":0.6636178839131149,"score_spread":0.07851174369575309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090888216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988875,0.0009604122,0.0012742655,0.0023633076,0.0006051452,0.004508384,0.0007950051,0.000044164888,0.0005743245],"genre_scores_gemma":[0.971668,0.0020926017,0.022940412,0.000111081885,0.0013397143,0.0015565129,0.0000043787445,0.00006550415,0.00022179332],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99134624,0.003726256,0.0017669426,0.00086503325,0.0011798553,0.0011156593],"domain_scores_gemma":[0.92414355,0.074349076,0.000276285,0.00068778975,0.00019600095,0.0003472949],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031307768,0.00033280096,0.0013620021,0.0003756709,0.0002317165,0.00016468865,0.00038035633,0.00021589517,0.0011930519],"category_scores_gemma":[0.008870003,0.00019486535,0.00016111693,0.00076383445,0.0003381107,0.0001235336,0.00017788698,0.00053494633,0.0000145250715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.110777095,0.0015906155,0.0076706936,0.000036364345,0.00011928988,0.00023863013,0.00055818126,0.0000055352775,0.000042328556,0.0074758297,0.00040220245,0.87108326],"study_design_scores_gemma":[0.07143636,0.0018750211,0.16649215,0.0011746826,0.00012111867,0.00011487304,0.00077826576,0.00012884753,0.00025392833,0.75641465,0.00080482033,0.0004052762],"about_ca_topic_score_codex":0.026462015,"about_ca_topic_score_gemma":0.029843295,"teacher_disagreement_score":0.87067795,"about_ca_system_score_codex":0.0012666704,"about_ca_system_score_gemma":0.00057124376,"threshold_uncertainty_score":0.99972},"labels":[],"label_agreement":null},{"id":"W2090985974","doi":"10.1016/j.cct.2014.02.007","title":"Continuous covariate imbalance and conditional power for clinical trial interim analyses","year":2014,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Covariate; Interim; Medicine; Econometrics; Outcome (game theory); Statistics; Baseline (sea); Mathematics","score_opus":0.9483473968389263,"score_gpt":0.7402696079276763,"score_spread":0.20807778891125006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090985974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051924203,0.0006727746,0.9057247,0.003951978,0.018940117,0.009766334,0.0017347606,0.00051685004,0.006768289],"genre_scores_gemma":[0.59764344,0.00027063355,0.3891264,0.0037356124,0.00766035,0.0004970577,0.00006675804,0.00013054063,0.0008692347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9538262,0.029537935,0.013682054,0.0016637811,0.0006542553,0.0006357565],"domain_scores_gemma":[0.28168935,0.71012104,0.005112826,0.001403951,0.000715935,0.0009569274],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15787806,0.00061304064,0.0069838315,0.00013192941,0.00019521512,0.00021798923,0.00070140907,0.0010867197,0.0004933653],"category_scores_gemma":[0.83297926,0.00047101142,0.0023077198,0.00020830761,0.0013791622,0.00021450056,0.00030550972,0.0009772608,0.000065795844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.20230797,0.004075106,0.0066626417,0.00027994165,0.003234851,0.000037148133,0.000050072347,3.8615534e-7,0.00015311086,0.3788403,0.3565357,0.04782277],"study_design_scores_gemma":[0.12645884,0.0058046854,0.0018780137,0.00015488906,0.0005587755,0.0000043586238,0.000029271037,0.0002913589,0.000059884645,0.81050056,0.05369965,0.0005597039],"about_ca_topic_score_codex":0.000005711523,"about_ca_topic_score_gemma":0.0000012179078,"teacher_disagreement_score":0.68058306,"about_ca_system_score_codex":0.000025768122,"about_ca_system_score_gemma":0.0003565721,"threshold_uncertainty_score":0.99977416},"labels":[],"label_agreement":null},{"id":"W2092203331","doi":"10.1093/aje/kwi340","title":"Two-Stage Case-Control Studies: Precision of Parameter Estimates and Considerations in Selecting Sample Size","year":2005,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Sample size determination; Covariate; Confounding; Estimator; Variance (accounting); Binary number; Econometrics; Mathematics; Sample (material); Variance inflation factor; Regression analysis; Chemistry","score_opus":0.5139129799182378,"score_gpt":0.5990592145549641,"score_spread":0.08514623463672633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092203331","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7177853,0.0007560437,0.27871424,0.0022676957,0.0001548859,0.00023558346,0.00004649427,0.000009806509,0.00002996172],"genre_scores_gemma":[0.47160402,0.000067382985,0.5277549,0.00047883324,0.00008185971,0.0000034519187,2.8540322e-8,0.000007982516,0.0000015321104],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99196416,0.004634001,0.0027814265,0.00021507582,0.00010300683,0.00030231618],"domain_scores_gemma":[0.29130593,0.7063597,0.0018446683,0.00015595373,0.00023223036,0.00010155945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017374087,0.00015702602,0.002118723,0.00012016415,0.00005231909,0.000004983077,0.000086512235,0.000065844106,0.00011237885],"category_scores_gemma":[0.91807526,0.000114972405,0.00013134697,0.00016436177,0.0007897535,0.00007169211,0.000044282235,0.00042934247,6.1879535e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017516108,0.00095009047,0.49589878,0.00031103284,0.0024526978,0.0009843969,0.004478805,0.00926372,0.0014894488,0.13654484,0.0020143627,0.3438602],"study_design_scores_gemma":[0.0016779907,0.0011222509,0.0024625422,0.000120639954,0.00020078153,0.001161569,0.0009190393,0.0040259757,0.00013392251,0.98803365,0.000022662885,0.00011899554],"about_ca_topic_score_codex":0.000110666464,"about_ca_topic_score_gemma":0.00010197483,"teacher_disagreement_score":0.90070117,"about_ca_system_score_codex":0.00005982455,"about_ca_system_score_gemma":0.000061608014,"threshold_uncertainty_score":0.6021546},"labels":[],"label_agreement":null},{"id":"W2094057648","doi":"10.1016/j.clinbiochem.2006.12.014","title":"Error propagation in calculated ratios","year":2007,"lang":"en","type":"article","venue":"Clinical Biochemistry","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital; University of British Columbia Hospital","funders":"","keywords":"Standard deviation; Statistics; Random error; Mathematics; Gaussian; Standard error; Contrast (vision); Coefficient of variation; Approximation error; Propagation of uncertainty; Random variable; Computer science; Physics","score_opus":0.5713247441010512,"score_gpt":0.6229706491643003,"score_spread":0.051645905063249176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094057648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92058116,0.000031781306,0.069217004,0.00062063587,0.0008227548,0.0006216225,0.00002674521,0.00019240777,0.007885867],"genre_scores_gemma":[0.68153554,0.0000073002334,0.31687424,0.0003904847,0.0006247139,0.000015433294,0.000010164205,0.000030293435,0.0005118418],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596596,0.00038571339,0.0023517287,0.00057374436,0.00032809345,0.00039477914],"domain_scores_gemma":[0.9595192,0.03914279,0.00037238168,0.00058676477,0.0001248671,0.00025397516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01161211,0.00019084057,0.00060118525,0.0000396993,0.000037994545,0.000020026555,0.00027281002,0.0006910955,0.0003294827],"category_scores_gemma":[0.21678391,0.00016796324,0.00017241728,0.00032438853,0.00030499668,0.000034482026,0.0000884395,0.00077025767,0.00008098015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056327498,0.013825177,0.18976052,0.0027032446,0.00065520644,0.0014971142,0.00040690752,0.000011645025,0.21460122,0.115233846,0.060420338,0.39525205],"study_design_scores_gemma":[0.0048973765,0.00026740463,0.016575601,0.00033088482,0.00011632678,0.000014776469,0.00013606407,0.0007748994,0.2385598,0.73631036,0.0012160401,0.0008004722],"about_ca_topic_score_codex":0.0000037973634,"about_ca_topic_score_gemma":0.000006075169,"teacher_disagreement_score":0.6210765,"about_ca_system_score_codex":0.00007533197,"about_ca_system_score_gemma":0.00009898407,"threshold_uncertainty_score":0.78981346},"labels":[],"label_agreement":null},{"id":"W2094585052","doi":"10.1007/s10928-011-9196-2","title":"A Bayesian approach for the estimation of patient compliance based on the last sampling information","year":2011,"lang":"en","type":"article","venue":"Journal of Pharmacokinetics and Pharmacodynamics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Sampling (signal processing); Bayesian probability; Computer science; Medical prescription; Population; Range (aeronautics); Statistics; Econometrics; Compliance (psychology); Data mining; Medicine; Mathematics; Pharmacology; Engineering; Psychology","score_opus":0.42951854781924165,"score_gpt":0.4953635317776973,"score_spread":0.06584498395845567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094585052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008525271,0.000039053073,0.9895408,0.00026974594,0.00044693012,0.00065452664,0.00010721751,0.0000070049255,0.00040941982],"genre_scores_gemma":[0.48579013,0.000073222924,0.51360065,0.0004297618,0.0000772469,0.000015013005,0.0000013384388,0.000011596583,0.0000010370735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980233,0.0002402798,0.0011176389,0.000086122236,0.00037330712,0.0001593903],"domain_scores_gemma":[0.98359436,0.014537726,0.0012450084,0.0001618209,0.00037597487,0.00008510321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025890388,0.00015569846,0.00032592096,0.00007900124,0.00012072047,0.000033810462,0.0002977352,0.000052075015,0.00004722119],"category_scores_gemma":[0.0041649374,0.00008587647,0.00015154431,0.00015374238,0.00014675784,0.00009948938,0.000038546987,0.00034639717,3.284066e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054712608,0.0021750391,0.00036835409,0.0026092872,0.0010362449,0.000004377582,0.004580143,0.22340468,0.002641574,0.14058232,0.0042464705,0.61288023],"study_design_scores_gemma":[0.0013261001,0.00031135534,0.00010160995,0.00009185518,0.00034110047,0.000007247616,0.000119591095,0.9269556,0.0020103683,0.06832026,0.00032020675,0.00009472594],"about_ca_topic_score_codex":0.0000012843452,"about_ca_topic_score_gemma":9.999958e-8,"teacher_disagreement_score":0.7035509,"about_ca_system_score_codex":0.000024711253,"about_ca_system_score_gemma":0.00004240794,"threshold_uncertainty_score":0.498612},"labels":[],"label_agreement":null},{"id":"W2094994198","doi":"10.1016/j.ejca.2010.05.027","title":"The unclear zone in phase II clinical trials","year":2010,"lang":"en","type":"review","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Cancer Centre; McMaster University","funders":"","keywords":"Clinical trial; Medicine; Phase (matter); Internal medicine; Chemistry","score_opus":0.8800723677077351,"score_gpt":0.7352433186910667,"score_spread":0.14482904901666838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094994198","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008313733,0.98365486,0.0044304496,0.0003965565,0.008293505,0.000779323,0.000077665514,0.000014216257,0.0023451396],"genre_scores_gemma":[8.6080325e-7,0.90221566,0.088690795,0.0000952694,0.007803793,0.000009697277,3.5595187e-7,0.00014575254,0.0010378137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9192934,0.06318206,0.015576182,0.0004433286,0.0009899524,0.00051506876],"domain_scores_gemma":[0.7888547,0.20029852,0.009395563,0.00074447965,0.00036292657,0.00034381475],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19625689,0.00045394595,0.006742186,0.00015637252,0.00014783768,0.000109412606,0.0015054562,0.0002967932,0.00063247955],"category_scores_gemma":[0.48362598,0.00022720003,0.0024217942,0.00032760215,0.00041897423,0.00005496531,0.00028902906,0.0048496183,0.00007068437],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020570167,0.00031544923,4.38577e-7,0.0006936038,0.0003542257,0.0002722256,0.000022888244,8.083086e-8,2.8083977e-7,0.0022367786,0.013769021,0.98212934],"study_design_scores_gemma":[0.0035264157,0.0008441221,0.0000015102514,0.010481415,0.0018953194,0.000043464854,0.0000064980263,0.0000013626977,4.3478505e-7,0.023260135,0.9597045,0.00023481036],"about_ca_topic_score_codex":0.0000010712474,"about_ca_topic_score_gemma":0.000007539261,"teacher_disagreement_score":0.9818945,"about_ca_system_score_codex":0.00009700536,"about_ca_system_score_gemma":0.0007453556,"threshold_uncertainty_score":0.99744624},"labels":[],"label_agreement":null},{"id":"W2095437242","doi":"10.1186/1471-2288-13-92","title":"A tutorial on sensitivity analyses in clinical trials: the what, why, when and how","year":2013,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":901,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Waterloo; Toronto General Hospital; Hamilton Health Sciences; University of Ottawa; GlaxoSmithKline (Canada); St. Joseph’s Healthcare Hamilton; McMaster University; Population Health Research Institute","funders":"","keywords":"Sensitivity (control systems); Clinical trial; Missing data; Computer science; Protocol (science); Outlier; Data science; Robustness (evolution); Research design; Data mining; Medical physics; Medicine; Management science; Alternative medicine; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.9873875398748938,"score_gpt":0.8105356203029017,"score_spread":0.1768519195719921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095437242","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086347654,0.00080521044,0.8229362,0.07917384,0.005781418,0.004025973,0.000021535743,0.00011355627,0.0007946452],"genre_scores_gemma":[0.011275894,0.001418719,0.9789947,0.0022804206,0.005199804,0.00042939145,0.0000015454556,0.00005411499,0.00034538953],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.44284627,0.54866326,0.0028104386,0.0012005117,0.0032224753,0.0012570418],"domain_scores_gemma":[0.013512972,0.9832157,0.0004922445,0.001176087,0.0005657029,0.0010372826],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6132049,0.00031718786,0.0030573236,0.00034981317,0.0001902024,0.00033570844,0.0007733087,0.001216768,0.0022593432],"category_scores_gemma":[0.9914974,0.00017435347,0.000452038,0.00058694795,0.0036194006,0.00019956878,0.00081979966,0.0041222298,0.00010033535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020070488,0.00067586557,0.001062465,0.00023783806,0.00025956082,0.00020080878,0.00041911835,6.944042e-7,0.000443726,0.15334792,0.09015042,0.75119454],"study_design_scores_gemma":[0.0027952052,0.00073950127,0.0033425752,0.0003010958,0.00007178306,0.000023319853,0.0011466736,0.002818521,0.00017486556,0.9853399,0.0030515247,0.0001950714],"about_ca_topic_score_codex":0.0005576465,"about_ca_topic_score_gemma":0.0009740432,"teacher_disagreement_score":0.8319919,"about_ca_system_score_codex":0.00008199604,"about_ca_system_score_gemma":0.0008632043,"threshold_uncertainty_score":0.99909216},"labels":[],"label_agreement":null},{"id":"W2095567388","doi":"10.4103/2153-3539.91130","title":"An open-source software program for performing Bonferroni and related corrections for multiple comparisons","year":2011,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Calgary Laboratory Services","funders":"","keywords":"Bonferroni correction; Spurious relationship; False discovery rate; Multiple comparisons problem; Computer science; Python (programming language); Software; Open source; Open source software; Type I and type II errors; Data mining; Statistics; Machine learning; Mathematics; Programming language; Biology","score_opus":0.48574364412457904,"score_gpt":0.5342493131655418,"score_spread":0.04850566904096276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095567388","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0962129,0.000015971356,0.90075594,0.000042294007,0.00092010316,0.0016164134,0.00008073186,0.00006724863,0.0002884078],"genre_scores_gemma":[0.040798947,0.000013208306,0.95878977,0.0000905049,0.000090951384,0.000118239484,0.000004296914,0.00003410965,0.000059960315],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970512,0.00022816959,0.0021463728,0.00010447537,0.00014622216,0.00032360238],"domain_scores_gemma":[0.98315215,0.014097306,0.0016927639,0.00027769126,0.000572847,0.00020724026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0049567977,0.00018381455,0.0008367117,0.00013781621,0.00027315549,0.00007542725,0.00046761375,0.00029861502,0.000035557692],"category_scores_gemma":[0.046557263,0.00014664626,0.00014793598,0.00010217367,0.00022664903,0.00047041956,0.00011637432,0.0004518976,0.0000019435215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046376935,0.007613099,0.037589103,0.002737478,0.0013040877,0.000082945706,0.05891829,0.00020317569,0.00028127938,0.080824494,0.020506326,0.78530204],"study_design_scores_gemma":[0.013619367,0.017235192,0.0035285335,0.00042478886,0.001412175,0.0023330757,0.012092609,0.09119828,0.0006750449,0.8478729,0.008865059,0.00074296707],"about_ca_topic_score_codex":0.0000015809139,"about_ca_topic_score_gemma":0.0000060597276,"teacher_disagreement_score":0.7845591,"about_ca_system_score_codex":0.00003891817,"about_ca_system_score_gemma":0.00010852128,"threshold_uncertainty_score":0.961474},"labels":[],"label_agreement":null},{"id":"W2095603014","doi":"10.1186/1745-6215-15-33","title":"Methodological survey of designed uneven randomization trials (DU-RANDOM): a protocol","year":2014,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"State Administration of Traditional Chinese Medicine of the People's Republic of China; McMaster University","keywords":"Randomization; Medicine; Protocol (science); Clinical trial; Randomized controlled trial; Research design; Family medicine; Alternative medicine; Statistics; Surgery; Pathology","score_opus":0.9510803312324886,"score_gpt":0.7053885090892636,"score_spread":0.24569182214322494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095603014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065237394,0.0000057231186,0.86897177,0.00015007395,0.00055371824,0.1284941,0.0001252467,0.00012488986,0.00092210824],"genre_scores_gemma":[0.0070712166,0.000007896198,0.9321779,0.00010620892,0.0008358246,0.059617486,0.000009220125,0.000060000886,0.000114236],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.60870564,0.37661532,0.012111697,0.0008705495,0.0011084924,0.0005883076],"domain_scores_gemma":[0.096957095,0.89635074,0.0050047985,0.0007733319,0.00069854385,0.00021550909],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5563999,0.00039206212,0.008603862,0.00015833636,0.000089561676,0.00006060776,0.00052727776,0.0005311322,0.0019297451],"category_scores_gemma":[0.98406285,0.00024542847,0.0009138352,0.0005207991,0.00025694206,0.00007388364,0.00011279646,0.0002524509,0.000036167075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.37458584,0.0028542299,0.0013262583,0.0015039436,0.0028411255,0.00001024164,0.0003681304,0.00014125028,0.031598896,0.33733314,0.028288404,0.21914856],"study_design_scores_gemma":[0.08206262,0.00066754513,0.0007716905,0.00013033637,0.0007301507,0.0000019773042,0.00000544547,0.00044543625,0.022982964,0.89139897,0.0004903428,0.0003125005],"about_ca_topic_score_codex":0.0000699991,"about_ca_topic_score_gemma":0.000009116426,"teacher_disagreement_score":0.5540659,"about_ca_system_score_codex":0.000035993824,"about_ca_system_score_gemma":0.0001443999,"threshold_uncertainty_score":0.9999998},"labels":[],"label_agreement":null},{"id":"W2095702029","doi":"10.1093/biostatistics/kxn034","title":"Exact and efficient inference procedure for meta-analysis and its application to the analysis of independent 2 x 2 tables with all available data but without artificial continuity correction","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; Université du Québec à Montréal","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute","keywords":"Computer science; Inference; Simple (philosophy); Meta-analysis; Data mining; Continuity correction; Statistics; Econometrics; Mathematics; Artificial intelligence; Medicine; Internal medicine","score_opus":0.5257705219849328,"score_gpt":0.5038448131116642,"score_spread":0.021925708873268612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095702029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03421656,0.00009659882,0.9565046,0.00012657748,0.00005149193,0.001402277,0.007552418,0.000022466855,0.00002704406],"genre_scores_gemma":[0.63398325,0.00003515729,0.3654271,0.00006202205,0.000031156123,0.0001692241,0.0001005484,0.000015250949,0.00017627953],"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760616,0.0002873314,0.000802589,0.00063645694,0.00045544739,0.000212013],"domain_scores_gemma":[0.9816052,0.016434973,0.000588758,0.00075722573,0.00048798075,0.00012590668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024987995,0.00020804943,0.0012616115,0.00020233492,0.00015857846,0.00004811703,0.00027176325,0.00010055547,0.00008741433],"category_scores_gemma":[0.029424801,0.00012978053,0.000114778275,0.0010190312,0.00016773555,0.000040846317,0.00016775898,0.0001236644,0.0000026347432],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00585093,0.0042159557,0.052898865,0.0023155764,0.61929,0.000025883308,0.0059236228,0.015864117,0.006984565,0.2310822,0.017743075,0.03780521],"study_design_scores_gemma":[0.0005957601,0.0003711851,0.016829316,0.00001331504,0.43670517,0.000006964473,0.00021683605,0.52822345,0.0032737844,0.0127842575,0.0005151564,0.00046480718],"about_ca_topic_score_codex":0.00015694294,"about_ca_topic_score_gemma":0.0014572414,"teacher_disagreement_score":0.5997667,"about_ca_system_score_codex":0.000021848626,"about_ca_system_score_gemma":0.00007791476,"threshold_uncertainty_score":0.97875077},"labels":[],"label_agreement":null},{"id":"W2096206421","doi":"10.1177/0962280208092346","title":"The case-crossover study design in pharmacoepidemiology","year":2008,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Pharmacoepidemiology; Crossover study; Crossover; Medicine; Computer science; Pharmacology; Alternative medicine; Artificial intelligence","score_opus":0.9107676203454614,"score_gpt":0.7895228873335225,"score_spread":0.12124473301193894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096206421","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007578008,0.00020519763,0.98474,0.0020526035,0.0007756311,0.002492466,0.0000313148,0.000057980804,0.0020667901],"genre_scores_gemma":[0.041361913,0.00041124914,0.9565368,0.0002760998,0.0003178461,0.0007832706,5.983648e-7,0.00006583877,0.00024635054],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7452556,0.23940074,0.0052893804,0.0019790104,0.004492835,0.0035824473],"domain_scores_gemma":[0.19702874,0.8006013,0.00016435393,0.0009501172,0.00034921625,0.00090627105],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27730417,0.0003685841,0.0015722369,0.00039033042,0.0006623239,0.000055774915,0.0014168667,0.00057463825,0.0033292116],"category_scores_gemma":[0.9292687,0.00023832863,0.00010929834,0.0018960898,0.004822175,0.00006528135,0.0008757352,0.005873616,0.0000988882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017035316,0.00227804,0.0036248816,0.00008416734,0.000087372486,0.065169364,0.0007901061,0.0000055735836,0.000027723234,0.3232525,0.016690446,0.5862863],"study_design_scores_gemma":[0.0035016902,0.0007441092,0.0038808451,0.00006740793,0.000019345423,0.0007532061,0.0007650864,0.012934333,0.000049077746,0.9759517,0.0010758194,0.00025740408],"about_ca_topic_score_codex":0.00056093157,"about_ca_topic_score_gemma":0.00032863987,"teacher_disagreement_score":0.6526992,"about_ca_system_score_codex":0.00034400297,"about_ca_system_score_gemma":0.0008148605,"threshold_uncertainty_score":0.9978861},"labels":[],"label_agreement":null},{"id":"W2096864872","doi":"10.1200/jco.2006.10.3523","title":"Proposal for Standardized Definitions for Efficacy End Points in Adjuvant Breast Cancer Trials: The STEEP System","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":885,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Sunnybrook Health Science Centre","funders":"","keywords":"Breast cancer; Medicine; Clinical trial; Clinical endpoint; Cancer; Medical physics; End point; Oncology; Internal medicine; Computer science","score_opus":0.793096103122032,"score_gpt":0.685672168665247,"score_spread":0.107423934456785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096864872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03328101,0.00035638394,0.91414577,0.027116496,0.01611434,0.005947098,0.0019428162,0.000049963663,0.0010461406],"genre_scores_gemma":[0.09209808,0.00016100066,0.9014199,0.0007232642,0.0053373324,0.00015885576,0.0000014935271,0.00005647431,0.000043601973],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97900265,0.0070642256,0.012286796,0.00036113124,0.0006702846,0.0006149138],"domain_scores_gemma":[0.45708913,0.5358066,0.005389487,0.00028916393,0.0011133138,0.00031234516],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18637656,0.00024499217,0.0046601705,0.0001509721,0.00012937497,0.000032664753,0.00054902973,0.00069474435,0.00013141744],"category_scores_gemma":[0.5577547,0.00013526333,0.0016477932,0.00022056446,0.0004618925,0.000080342994,0.00006938103,0.0011549369,0.000003706827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.060212694,0.003299183,0.0009177499,0.00043117552,0.001136401,0.000121807716,0.0001961527,0.0000126927425,0.000059270384,0.3919279,0.014579742,0.5271052],"study_design_scores_gemma":[0.047256675,0.005812701,0.0077931806,0.0007232937,0.0017882155,0.00018065202,0.0006692672,0.00018254168,0.00014136302,0.9221726,0.013019864,0.00025966033],"about_ca_topic_score_codex":0.000007576065,"about_ca_topic_score_gemma":0.00017054573,"teacher_disagreement_score":0.5302447,"about_ca_system_score_codex":0.00043907145,"about_ca_system_score_gemma":0.0030421598,"threshold_uncertainty_score":0.83779657},"labels":[],"label_agreement":null},{"id":"W2097428061","doi":"10.1207/s15374424jccp3303_19","title":"Pairwise Multiple Comparison Test Procedures: An Update for Clinical Child and Adolescent Psychologists","year":2004,"lang":"en","type":"review","venue":"Journal of Clinical Child & Adolescent Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Jaccard index; Pairwise comparison; Context (archaeology); Variance (accounting); Inference; Psychology; Statistics; Multiple comparisons problem; Econometrics; Computer science; Mathematics; Artificial intelligence","score_opus":0.7172075097882616,"score_gpt":0.6844885769326317,"score_spread":0.03271893285562999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097428061","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000075666685,0.919595,0.057048317,0.0036024572,0.012579517,0.0059460695,0.0006580626,0.00018597713,0.0003089272],"genre_scores_gemma":[0.00036219793,0.7884892,0.19698958,0.00490262,0.008844134,0.00006667357,0.000031226344,0.00029749353,0.000016874448],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9636524,0.008119142,0.023162194,0.0025662025,0.0010954362,0.0014046455],"domain_scores_gemma":[0.9091053,0.069974326,0.015656056,0.0022780043,0.0009070204,0.002079283],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.030335018,0.0017258114,0.01552076,0.0005149299,0.00031274155,0.00016828254,0.0026923053,0.004044359,0.000092220514],"category_scores_gemma":[0.26895043,0.0012628484,0.0052828626,0.0005076147,0.0020286515,0.00022081983,0.00040490876,0.010343783,0.00006423471],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029329546,0.033782285,0.0068947165,0.028962776,0.0011970818,0.00016365747,0.000024113384,9.0226007e-7,5.135482e-8,0.0010843636,0.053141486,0.8718156],"study_design_scores_gemma":[0.016857225,0.008695394,0.006775231,0.07594425,0.0051663234,0.0015242462,0.000022172153,0.000018499837,2.9115017e-7,0.057393935,0.8261014,0.0015009842],"about_ca_topic_score_codex":5.0879765e-7,"about_ca_topic_score_gemma":0.0000090833255,"teacher_disagreement_score":0.87031466,"about_ca_system_score_codex":0.00015657573,"about_ca_system_score_gemma":0.0008677849,"threshold_uncertainty_score":0.9995488},"labels":[],"label_agreement":null},{"id":"W2097775534","doi":"10.1208/s12248-011-9294-5","title":"Harmonization of Regulatory Approaches for Evaluating Therapeutic Equivalence and Interchangeability of Multisource Drug Products: Workshop Summary Report","year":2011,"lang":"en","type":"article","venue":"The AAPS Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada); Health Canada","funders":"","keywords":"Interchangeability; Harmonization; Bioequivalence; Regulatory science; Risk analysis (engineering); Regulatory authority; Business; Equivalence (formal languages); Biosimilar; Pharmaceutical industry; Pharmacology; Management science; Computer science; Medicine; Biotechnology; Engineering; Political science; Biology; Mathematics; Pharmacokinetics","score_opus":0.8440144888399592,"score_gpt":0.5456233684349235,"score_spread":0.2983911204050357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097775534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4978264,0.00069979054,0.49965307,0.00038512656,0.00032683986,0.00093710003,0.0000127475005,0.000017408853,0.00014151617],"genre_scores_gemma":[0.5099964,0.000031397238,0.48973712,0.000012620104,0.00010288575,0.000014075398,2.8055007e-7,0.000016221657,0.00008894654],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967359,0.001310007,0.00121394,0.00021986768,0.00034870548,0.00017162056],"domain_scores_gemma":[0.981092,0.016406227,0.0013898188,0.00055491435,0.00049853465,0.000058531357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02030801,0.0001230365,0.00044265809,0.000043727574,0.00009737642,0.000013175159,0.00029598924,0.00006699075,0.00003380279],"category_scores_gemma":[0.08333234,0.00007782904,0.000097121054,0.00013417412,0.000481496,0.00008110269,0.0001236334,0.00027577035,1.579095e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037800537,0.0016848905,0.012309718,0.0044174185,0.001076927,0.000015125046,0.05345623,0.000047436482,0.020839896,0.046356563,0.0009636186,0.8550521],"study_design_scores_gemma":[0.00069383276,0.00020717457,0.0044913227,0.0004346646,0.0003378559,0.000114555856,0.001591481,0.0032711949,0.021362577,0.9673662,0.000007725647,0.0001214213],"about_ca_topic_score_codex":0.0000032884736,"about_ca_topic_score_gemma":5.7174293e-7,"teacher_disagreement_score":0.92100966,"about_ca_system_score_codex":0.000027719421,"about_ca_system_score_gemma":0.00006538998,"threshold_uncertainty_score":0.9243891},"labels":[],"label_agreement":null},{"id":"W2098257709","doi":"10.1016/j.clinthera.2011.07.014","title":"The Need for Additional Metrics to Assess Therapeutic Equivalence of Some Multiphasic Modified-Release Products","year":2011,"lang":"en","type":"article","venue":"Clinical Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; University of Toronto; McMaster University","funders":"","keywords":"Medicine; Bioequivalence; Food and drug administration; Equivalence (formal languages); Statement (logic); Metric (unit); Position statement; Advisory committee; Drug; Pharmacology; Actuarial science; Medical physics; Family medicine; Pharmacokinetics; Law; Operations management; Public administration; Mathematics","score_opus":0.8843704126214491,"score_gpt":0.6060957014774468,"score_spread":0.27827471114400226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098257709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01548285,0.00079966855,0.9633731,0.0028286015,0.0065961187,0.005923423,0.003357428,0.00031425426,0.0013245399],"genre_scores_gemma":[0.12618297,0.0003706635,0.8681524,0.0030804942,0.0010841376,0.0004692656,0.000013112841,0.00012555951,0.000521408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934817,0.0015407623,0.0027767164,0.0007401764,0.0007644231,0.0006962546],"domain_scores_gemma":[0.7907345,0.20563622,0.00090807007,0.0013343698,0.0010739911,0.000312848],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009537883,0.0003875794,0.0011155441,0.000116678886,0.00025505314,0.000051172578,0.0012994289,0.0004004613,0.00026711772],"category_scores_gemma":[0.14978386,0.00026240628,0.0005599764,0.0007363116,0.0009077368,0.00011013078,0.00022358244,0.0006174122,0.00003643612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018591004,0.00242682,0.0003014748,0.00023286484,0.0008776514,0.0000041388676,0.00017989142,0.0000071783297,0.00043504895,0.73265195,0.0052039237,0.25581998],"study_design_scores_gemma":[0.0018112441,0.0013152689,0.0010777318,0.0000892102,0.00048399344,0.0000017424566,0.00008274217,0.0019937898,0.0031689326,0.9804162,0.009175896,0.0003832547],"about_ca_topic_score_codex":0.0000021475328,"about_ca_topic_score_gemma":0.0000011007272,"teacher_disagreement_score":0.25543672,"about_ca_system_score_codex":0.000054026215,"about_ca_system_score_gemma":0.00028442772,"threshold_uncertainty_score":0.99998283},"labels":[],"label_agreement":null},{"id":"W2098430370","doi":"10.1002/cjs.5550350306","title":"Testing noninferiority in three‐armed clinical trials based on likelihood ratio statistics","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Bonferroni correction; Likelihood-ratio test; Mathematics; Statistics; Score test; Statistical hypothesis testing; Exact test; Medicine; Econometrics","score_opus":0.6909048346521448,"score_gpt":0.5804296374203769,"score_spread":0.11047519723176791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098430370","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005521949,0.00003346554,0.9865917,0.00022653567,0.0029067644,0.00061448786,0.0030343665,0.000017776452,0.0010529394],"genre_scores_gemma":[0.111460306,0.0000076214087,0.8867506,0.0006069904,0.0010729977,0.0000040013592,0.000008017549,0.000071604736,0.000017852306],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.987096,0.0032795588,0.0072612856,0.00041187482,0.00089322036,0.0010580712],"domain_scores_gemma":[0.6867595,0.30664638,0.0027644231,0.00050839584,0.0013495408,0.0019718234],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07107069,0.00041302782,0.0023491369,0.00068352424,0.00017500481,0.00015195388,0.00057851995,0.00044224897,0.00054154935],"category_scores_gemma":[0.7212175,0.00037045876,0.00024464063,0.00066288066,0.00048811117,0.000088277346,0.000025576583,0.0018094736,0.000029935192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012626856,0.0007923547,0.17395365,0.0003779128,0.00028724904,0.007948444,0.00023385893,0.00024012389,0.00006862208,0.34024855,0.03272885,0.4418577],"study_design_scores_gemma":[0.0044100005,0.0015734723,0.1003878,0.0005210637,0.00031656487,0.000037989434,0.000087885914,0.008099494,0.00006081941,0.883448,0.0005858035,0.00047112023],"about_ca_topic_score_codex":0.0009060554,"about_ca_topic_score_gemma":0.033988144,"teacher_disagreement_score":0.6501468,"about_ca_system_score_codex":0.00051958044,"about_ca_system_score_gemma":0.0052498817,"threshold_uncertainty_score":0.9998747},"labels":[],"label_agreement":null},{"id":"W2098841909","doi":"10.1177/1740774511401764","title":"Quantitative evaluation of single-arm versus randomized phase II cancer clinical trials","year":2011,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Randomized controlled trial; Medicine; Clinical trial; Phase (matter); Statistics; Surgery; Internal medicine; Mathematics","score_opus":0.9827110079089646,"score_gpt":0.7883904939711813,"score_spread":0.19432051393778327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098841909","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5403751,0.0034971964,0.29154998,0.0020132826,0.08939983,0.038231246,0.0026541676,0.00074269786,0.031536467],"genre_scores_gemma":[0.18497911,0.0017686576,0.80626523,0.00035985876,0.0049263136,0.0012857011,0.0000187806,0.00016827844,0.00022806879],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.474006,0.46426353,0.05442948,0.002502261,0.0036339643,0.0011647554],"domain_scores_gemma":[0.024671994,0.95291644,0.016913839,0.0017865802,0.0029006554,0.0008105013],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.75138956,0.00069255865,0.017838903,0.00023381576,0.00017715344,0.000049466904,0.00094088493,0.0014281409,0.011987438],"category_scores_gemma":[0.98871326,0.00048257245,0.0063499575,0.0005871749,0.002648315,0.00019432617,0.0003622682,0.0012042205,0.00010523047],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5439648,0.01582867,0.000043051736,0.000100471654,0.0046593985,0.0000067604524,0.00034027963,0.000001819591,0.0002296159,0.12042367,0.0053770826,0.3090244],"study_design_scores_gemma":[0.40884462,0.0077732126,0.000023439241,0.0002661846,0.010789063,3.9948813e-7,0.000108691114,0.0012324475,0.0014058722,0.568922,0.00026189312,0.0003722024],"about_ca_topic_score_codex":0.00005393538,"about_ca_topic_score_gemma":0.000018384704,"teacher_disagreement_score":0.51471525,"about_ca_system_score_codex":0.0001238939,"about_ca_system_score_gemma":0.0010351291,"threshold_uncertainty_score":0.9998682},"labels":[],"label_agreement":null},{"id":"W2099146388","doi":"10.1158/1078-0432.ccr-05-0130","title":"Objective Responses in Patients with Malignant Melanoma or Renal Cell Cancer in Early Clinical Studies Do Not Predict Regulatory Approval","year":2005,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Melanoma; Renal cell carcinoma; Cancer; Oncology; Internal medicine; Clinical trial; Phases of clinical research; Kidney cancer; Carcinoma; Colorectal cancer; Cancer research","score_opus":0.8410193157045681,"score_gpt":0.7118782048524943,"score_spread":0.1291411108520738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099146388","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031521913,0.95259994,0.00005019148,0.00020810412,0.0023184284,0.01047565,0.0023259728,0.0001169326,0.00038285943],"genre_scores_gemma":[0.0005897598,0.965005,0.025188034,0.00008925484,0.0028861158,0.0038135403,0.000008528984,0.00032375767,0.0020960213],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94359124,0.03713157,0.010111462,0.0034252158,0.0036284898,0.0021120037],"domain_scores_gemma":[0.7221945,0.27195185,0.0018374231,0.0019429628,0.0013755243,0.0006977531],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06671719,0.0011970489,0.009881116,0.0009994814,0.00019488209,0.00013830236,0.002041299,0.0023670194,0.00062408845],"category_scores_gemma":[0.21912839,0.00074214017,0.0011885689,0.0024259586,0.003739964,0.00018622878,0.0014921944,0.009357884,0.00008790637],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019055579,0.0028616278,0.029884499,0.009103399,0.0010373474,0.00034165505,0.00019067539,0.0000020850907,4.2135728e-8,0.00045109904,0.0032391716,0.9338328],"study_design_scores_gemma":[0.042586062,0.02370514,0.23234825,0.21396646,0.0041639637,0.000010784312,0.0004350815,0.00003067258,0.0000096474,0.03838918,0.43885913,0.005495618],"about_ca_topic_score_codex":0.00021919682,"about_ca_topic_score_gemma":0.001260428,"teacher_disagreement_score":0.9283372,"about_ca_system_score_codex":0.0020573386,"about_ca_system_score_gemma":0.007178491,"threshold_uncertainty_score":0.99950296},"labels":[],"label_agreement":null},{"id":"W2099322009","doi":"10.1093/aje/kwr057","title":"Reducing the Variance of the Prescribing Preference-based Instrumental Variable Estimates of the Treatment Effect","year":2011,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Confounding; Estimator; Variance inflation factor; Variance (accounting); Instrumental variable; Statistics; Medicine; Preference; Homogeneous; Econometrics; Standard deviation; Inflation (cosmology); Estimation; Variable (mathematics); Mathematics; Regression analysis; Economics","score_opus":0.5414984694703878,"score_gpt":0.49268934855375246,"score_spread":0.04880912091663536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099322009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8323365,0.00021192676,0.16253088,0.0011369428,0.0015994621,0.0008710709,0.0000523257,0.000011949462,0.0012489721],"genre_scores_gemma":[0.54051304,0.000028476363,0.45921272,0.00014977371,0.00006666807,0.000010312251,7.237776e-8,0.000011273425,0.000007682732],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895563,0.007934212,0.0018362126,0.00018527603,0.0001916497,0.0002963312],"domain_scores_gemma":[0.8556021,0.13979371,0.003717234,0.00068700383,0.000130917,0.00006907619],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010352935,0.00019628678,0.0014250362,0.000034796794,0.000097695556,0.0000030189906,0.0008410373,0.000074659445,0.00010943663],"category_scores_gemma":[0.15230952,0.00007293839,0.0004128281,0.00028174618,0.0017105564,0.000033047807,0.00010164473,0.00038447618,6.13176e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004070744,0.0022596193,0.4396208,0.0004156063,0.0030649973,0.000008090121,0.003460739,0.002037745,0.011292825,0.26795304,0.0012291481,0.26458666],"study_design_scores_gemma":[0.001522585,0.0061084107,0.038555022,0.0010326932,0.001012202,0.000058449663,0.00019898299,0.0016475123,0.032412965,0.9171931,0.000101215206,0.00015681858],"about_ca_topic_score_codex":0.0004135384,"about_ca_topic_score_gemma":0.0000034136503,"teacher_disagreement_score":0.64924014,"about_ca_system_score_codex":0.000084133026,"about_ca_system_score_gemma":0.0001956875,"threshold_uncertainty_score":0.8548309},"labels":[],"label_agreement":null},{"id":"W2099457688","doi":"10.1111/bmsp.12015","title":"Evaluating clinical significance: Incorporating robust statistics with normative comparison tests","year":2013,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Statistics; Normative; Econometrics; Statistical hypothesis testing; Mathematics; Epistemology; Philosophy","score_opus":0.6101012297971987,"score_gpt":0.6102618176534461,"score_spread":0.00016058785624739613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099457688","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04905751,0.00011732883,0.94752705,0.00047217112,0.00034620348,0.0007619636,0.00020916293,0.000043452594,0.0014651454],"genre_scores_gemma":[0.09328864,0.000061955674,0.9056772,0.0004542693,0.00035064138,0.000041280455,0.000004271246,0.0000618045,0.00005994684],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98998904,0.0029904626,0.0047423635,0.0005806143,0.0010513448,0.0006461556],"domain_scores_gemma":[0.91402656,0.0816954,0.0019955202,0.0003289632,0.0012014138,0.00075212994],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008745326,0.00040923792,0.002289513,0.000112797905,0.0002225252,0.00026690474,0.00045714062,0.00035746512,0.0018107562],"category_scores_gemma":[0.115373015,0.00032865463,0.00013942963,0.0002688788,0.0018824532,0.00025559837,0.00013311302,0.0017672266,0.00009774339],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068877556,0.0030911984,0.0035085317,0.00086145336,0.0005616484,0.0009975286,0.000276813,0.00002304709,0.000111884096,0.4520267,0.041858096,0.49599433],"study_design_scores_gemma":[0.0031002893,0.0033834828,0.013035988,0.0006428364,0.00032264309,0.002351528,0.0002469734,0.007094473,0.00000884751,0.9693679,0.000035725283,0.00040931386],"about_ca_topic_score_codex":0.000014048558,"about_ca_topic_score_gemma":0.00001054344,"teacher_disagreement_score":0.5173412,"about_ca_system_score_codex":0.000042622585,"about_ca_system_score_gemma":0.00015904529,"threshold_uncertainty_score":0.99991655},"labels":[],"label_agreement":null},{"id":"W2099844674","doi":"10.1002/sim.1115","title":"Current and future challenges in the design and analysis of cluster randomization trials","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":172,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Cancer Care Ontario","funders":"","keywords":"Randomization; Cluster (spacecraft); Cluster randomised controlled trial; Restricted randomization; Psychological intervention; Randomized controlled trial; Research design; Computer science; Medicine; Statistics; Mathematics; Psychiatry","score_opus":0.6291099124678506,"score_gpt":0.5903951121051839,"score_spread":0.038714800362666724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099844674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001715755,0.0048192185,0.98924136,0.0027831167,0.00028096745,0.00091041316,0.000069839945,0.0000061125875,0.00017320535],"genre_scores_gemma":[0.01685627,0.075076796,0.9073563,0.00014925827,0.00046258228,0.00006380152,0.000012682366,0.000016031265,0.0000062487443],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924769,0.0052543897,0.0014894587,0.00024871886,0.0003760933,0.00015448678],"domain_scores_gemma":[0.84550714,0.1538071,0.00035681235,0.00021193716,0.00007410357,0.000042870775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02845252,0.00014075421,0.0014874549,0.0003282651,0.000022015072,0.000007754959,0.00011448592,0.000090219415,0.00010397249],"category_scores_gemma":[0.13853988,0.00007918111,0.00003325487,0.0005794817,0.0002655987,0.000020496891,0.000028493756,0.00023035564,1.9453749e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017293831,0.000215166,0.002131017,0.00038500706,0.0003363965,0.000025227242,0.0054616905,0.000047135538,0.00000878353,0.48034698,0.0015453998,0.50776786],"study_design_scores_gemma":[0.008749942,0.00018901021,0.012706195,0.00017069658,0.0015746111,0.000003125225,0.0008593666,0.012628359,0.000002147579,0.9624972,0.000521298,0.00009805933],"about_ca_topic_score_codex":0.00000854579,"about_ca_topic_score_gemma":0.000056519228,"teacher_disagreement_score":0.50766975,"about_ca_system_score_codex":0.000014787286,"about_ca_system_score_gemma":0.000015508514,"threshold_uncertainty_score":0.9861132},"labels":[],"label_agreement":null},{"id":"W2100713463","doi":"10.1016/j.arthro.2003.09.022","title":"Considerations on sample size and power calculations in randomized clinical trials","year":2003,"lang":"en","type":"article","venue":"Arthroscopy The Journal of Arthroscopic and Related Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fowler Kennedy Sport Medicine Clinic","funders":"","keywords":"Sample size determination; Statistical power; Sample (material); Randomized controlled trial; Medical physics; Computer science; Research design; Statistics; Clinical trial; Type I and type II errors; Clinical study design; Power (physics); Data science; Psychology; Management science; Data mining; Medicine; Mathematics; Engineering; Physics; Surgery; Internal medicine","score_opus":0.42942247517185,"score_gpt":0.5527858119445691,"score_spread":0.1233633367727191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100713463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9609091,0.0024548564,0.023375396,0.005581476,0.0045697554,0.0014897133,0.000029079623,0.000033640834,0.0015569523],"genre_scores_gemma":[0.867369,0.005859969,0.12573141,0.00083056226,0.00009104453,0.000009472545,2.5116822e-7,0.000029689903,0.00007858186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97320724,0.021437347,0.004549779,0.00021714822,0.00032138874,0.00026708894],"domain_scores_gemma":[0.26355213,0.7343102,0.0015216754,0.000275071,0.00014740559,0.00019350313],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.079188526,0.0002232146,0.0025819202,0.00014426622,0.00023697614,0.00005791743,0.000060585546,0.00029037977,0.0008128811],"category_scores_gemma":[0.76920825,0.00012655323,0.00044241038,0.00020045709,0.0010037281,0.00011003851,0.000026846436,0.00083467393,0.000004909466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019709567,0.0016848717,0.03187941,0.00011769358,0.0027113487,0.00017884426,0.002882975,0.00011277655,0.00037175562,0.9226188,0.013531432,0.004200535],"study_design_scores_gemma":[0.025241725,0.00019374477,0.0018654584,0.00039911963,0.00038828322,0.00010856017,0.00019688258,0.00006449928,0.00012933886,0.9710015,0.00025802536,0.0001528488],"about_ca_topic_score_codex":0.000006127034,"about_ca_topic_score_gemma":0.0000068795166,"teacher_disagreement_score":0.71287286,"about_ca_system_score_codex":0.000018353783,"about_ca_system_score_gemma":0.000214638,"threshold_uncertainty_score":0.9481692},"labels":[],"label_agreement":null},{"id":"W2100742577","doi":"10.1111/anzs.12103","title":"A Stepwise Confidence Interval Procedure Under Unknown Variances Based on an Asymmetric Loss Function for Toxicological Evaluation","year":2015,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Equivalence (formal languages); Mathematics; Confidence interval; Statistics; Function (biology); Reliability (semiconductor); Econometrics; Discrete mathematics","score_opus":0.5782939274920902,"score_gpt":0.5434422712956477,"score_spread":0.03485165619644248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100742577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006364554,0.000012996391,0.98852485,0.0021441956,0.0016470326,0.0008503846,0.0002714322,0.000026738879,0.00015778543],"genre_scores_gemma":[0.29132256,0.0000073731503,0.70636,0.0004376079,0.0009602234,0.000018010518,0.00001471277,0.00003271662,0.00084680563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956308,0.0010382893,0.001456131,0.00032361154,0.0011870394,0.00036411232],"domain_scores_gemma":[0.9798282,0.016542964,0.0012095292,0.00026281294,0.0014918115,0.00066470914],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007256937,0.00026658652,0.0007447205,0.00020799512,0.000071892915,0.00013592698,0.000324869,0.0002650605,0.0002291374],"category_scores_gemma":[0.06737775,0.00020175613,0.00013133734,0.00033576175,0.00014383026,0.00019465154,0.000019798243,0.00048275065,0.000009654336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010400406,0.0026464672,0.0015579419,0.00032585653,0.00039726048,0.00011788851,0.000361564,0.004895022,0.00008814787,0.5518395,0.3424276,0.08494239],"study_design_scores_gemma":[0.0064014248,0.011004347,0.0035469476,0.00022891944,0.00075464917,0.000047805876,0.00016717406,0.007632113,0.0001147995,0.9673451,0.0025001045,0.00025662477],"about_ca_topic_score_codex":0.000009962929,"about_ca_topic_score_gemma":0.00002652079,"teacher_disagreement_score":0.41550565,"about_ca_system_score_codex":0.000188839,"about_ca_system_score_gemma":0.0011098387,"threshold_uncertainty_score":0.94047815},"labels":[],"label_agreement":null},{"id":"W2101855600","doi":"10.1111/j.1537-2995.2010.02930.x","title":"Composite outcomes in clinical trials: what are they and when should they be used?","year":2010,"lang":"en","type":"article","venue":"Transfusion","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Library science; Family medicine; Citation; Medicine; Psychology; Computer science","score_opus":0.7130242284610977,"score_gpt":0.6074404734372855,"score_spread":0.10558375502381223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101855600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9774012,0.00005133435,0.009572279,0.008602263,0.0024885708,0.0013101537,0.000078312325,0.00012849132,0.00036739415],"genre_scores_gemma":[0.54291254,0.0016262323,0.45325068,0.0013389733,0.0005518497,0.00006595538,0.0000037509433,0.000094170944,0.00015586177],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99163824,0.0043490552,0.0025482138,0.0006010757,0.0005175653,0.00034586166],"domain_scores_gemma":[0.85624313,0.14249656,0.00035971848,0.0006096151,0.00006395312,0.00022700349],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027567212,0.00030416765,0.001964171,0.00009953391,0.00009121319,0.00015319783,0.0003314658,0.0006184072,0.00042466176],"category_scores_gemma":[0.083582714,0.0002066983,0.00038645472,0.00006795653,0.00019880084,0.00022028697,0.00008541477,0.0013526427,0.00001554883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027080388,0.0037698825,0.4102625,0.0005478252,0.00040460922,0.00012659788,0.007934692,0.0000022268582,0.020231918,0.11597223,0.00096409506,0.43707538],"study_design_scores_gemma":[0.004963192,0.00019417761,0.04793145,0.00026924175,0.00022108953,0.0000049849627,0.0003489632,0.0001733096,0.0006603493,0.94433755,0.00056425744,0.00033146358],"about_ca_topic_score_codex":0.00012307263,"about_ca_topic_score_gemma":0.0027987638,"teacher_disagreement_score":0.82836527,"about_ca_system_score_codex":0.000014539537,"about_ca_system_score_gemma":0.000030383273,"threshold_uncertainty_score":0.95543003},"labels":[],"label_agreement":null},{"id":"W2102100691","doi":"10.1093/humrep/deg238","title":"Pitfalls in the design and analysis of efficacy trials in subfertility: Associate editor's commentary: on the article 'Common statistical errors in the design and analysis of subfertility trials' by A.Vail and E.Gardner.","year":2003,"lang":"en","type":"letter","venue":"Human Reproduction","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistical analysis; Medicine; Clinical trial; Research design; Gynecology; Pathology; Statistics","score_opus":0.5236123102319973,"score_gpt":0.5174168655065309,"score_spread":0.006195444725466404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102100691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8185251,0.000505921,0.04003882,0.1310517,0.0008037559,0.008178405,0.0008379405,0.000031770935,0.000026622529],"genre_scores_gemma":[0.8478055,0.00076503854,0.09111011,0.05427312,0.0039693746,0.0012313604,0.0005708662,0.00020374967,0.00007086637],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89549696,0.09664783,0.0049033086,0.0013375311,0.0011521268,0.00046224328],"domain_scores_gemma":[0.7229269,0.27313042,0.0021235882,0.0016439337,0.00012393783,0.0000511731],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17483965,0.0004794582,0.0046951203,0.00070686935,0.00015087404,0.00012190342,0.00043871114,0.00058454246,0.00009043431],"category_scores_gemma":[0.20992874,0.0002677899,0.0004344019,0.002078607,0.00081083784,0.00006213767,0.000079863275,0.0016355916,3.4650802e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006921509,0.0052779354,0.031429734,0.0007235033,0.014481962,0.000062113024,0.009454905,0.0006784611,0.0009574942,0.0026984697,0.91684407,0.01046986],"study_design_scores_gemma":[0.0075795804,0.0016498718,0.38183352,0.00034633043,0.05674074,0.0000029901214,0.0015441038,0.006482477,0.0019481762,0.53879,0.0019097502,0.0011724519],"about_ca_topic_score_codex":0.0005227366,"about_ca_topic_score_gemma":0.00020901416,"teacher_disagreement_score":0.9149343,"about_ca_system_score_codex":0.00014518159,"about_ca_system_score_gemma":0.00003674576,"threshold_uncertainty_score":0.9999774},"labels":[],"label_agreement":null},{"id":"W2102817893","doi":"10.1111/j.2044-8317.2012.02056.x","title":"Robust tests of equivalence for <i>k</i> independent groups","year":2012,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Mathematics; Statistics; Equivalence (formal languages); Population; Null hypothesis; Analysis of variance; Psychology; Social psychology; Econometrics; Pure mathematics; Demography","score_opus":0.5007231631368919,"score_gpt":0.5401128261342657,"score_spread":0.03938966299737379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102817893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029712843,0.0005393483,0.9671225,0.00026130202,0.00056509237,0.00036004191,0.00027793695,0.000014007125,0.0011469251],"genre_scores_gemma":[0.21874747,0.00015433194,0.7804552,0.00020681025,0.00035233074,0.000014249341,9.132922e-7,0.000030374924,0.0000383192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99590105,0.00060224143,0.002186376,0.00024499683,0.0005120902,0.00055322103],"domain_scores_gemma":[0.94962585,0.04858591,0.00074715173,0.00020596877,0.00034097114,0.00049413723],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063365754,0.00020538298,0.0012853214,0.00007892391,0.00006728344,0.000032095646,0.00031509346,0.00025881725,0.0006648179],"category_scores_gemma":[0.08847126,0.00018162122,0.0001922005,0.000115152914,0.0007060056,0.00013058678,0.000090686284,0.0005003466,0.000008325077],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039744398,0.0018599685,0.00044710218,0.0009773535,0.00015157978,0.000079620375,0.00011206953,3.8017797e-7,0.00032490242,0.9262589,0.009860469,0.059530217],"study_design_scores_gemma":[0.001981612,0.00079488335,0.005816716,0.0003879865,0.0002452037,0.0028703988,0.000052508807,0.000060915037,0.00007161372,0.9873152,0.00021262138,0.0001903794],"about_ca_topic_score_codex":0.0000011853175,"about_ca_topic_score_gemma":0.0000010575999,"teacher_disagreement_score":0.18903463,"about_ca_system_score_codex":0.000018823515,"about_ca_system_score_gemma":0.00003280396,"threshold_uncertainty_score":0.9192069},"labels":[],"label_agreement":null},{"id":"W2104126672","doi":"10.2147/clep.s56554","title":"Empirical comparison of four baseline covariate adjustment methods in analysis of continuous outcomes in randomized controlled trials","year":2014,"lang":"en","type":"article","venue":"Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; St. Joseph’s Healthcare Hamilton; Population Health Research Institute; McMaster University","funders":"","keywords":"Analysis of covariance; Medicine; Randomized controlled trial; Covariate; Confidence interval; Analysis of variance; Sample size determination; Statistics; Physical therapy; Internal medicine; Mathematics","score_opus":0.8521315348875381,"score_gpt":0.7325592599955091,"score_spread":0.11957227489202904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104126672","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051714,0.00036354145,0.94062334,0.0024970304,0.0013807184,0.0029942116,0.00006951861,0.000035112243,0.0003225038],"genre_scores_gemma":[0.15166596,0.00020978981,0.8463288,0.001256951,0.00017262858,0.0002839295,0.00000819516,0.000027502521,0.000046258854],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.37318924,0.5636389,0.060239725,0.0014255533,0.0005350127,0.0009715356],"domain_scores_gemma":[0.039805926,0.945891,0.0125244185,0.0011324611,0.00036805932,0.00027813908],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6617769,0.0005069491,0.07913311,0.0009267643,0.000018157107,0.0000039010765,0.0006165086,0.0011995938,0.00055967126],"category_scores_gemma":[0.99192756,0.00030628804,0.0072673024,0.0010608713,0.0013392593,0.00002704654,0.00022699052,0.0011190381,0.000005516232],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15473197,0.0038292047,0.6608513,0.00015064172,0.010983696,0.000004082378,0.000118628224,0.0010857653,0.000029025681,0.13143781,0.0005073868,0.036270477],"study_design_scores_gemma":[0.22518471,0.00044126672,0.06500127,0.0000856574,0.00752302,2.2293636e-7,0.000028849401,0.15169066,0.000015922225,0.54980344,0.00003170001,0.00019330502],"about_ca_topic_score_codex":0.00017040818,"about_ca_topic_score_gemma":0.0001236959,"teacher_disagreement_score":0.59585005,"about_ca_system_score_codex":0.000056240253,"about_ca_system_score_gemma":0.00012686527,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W2104999300","doi":"10.1080/02664763.2013.800035","title":"Estimating the proportion of true null hypotheses using the pattern of observed<i>p</i>-values","year":2013,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Hong Kong Baptist University; St. Jude Children's Research Hospital; National Institutes of Health; National Science Foundation","keywords":"Statistics; Mathematics; Null (SQL); Null hypothesis; Econometrics; Computer science; Data mining","score_opus":0.5316892023117963,"score_gpt":0.5023413434252647,"score_spread":0.029347858886531575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104999300","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19539781,0.000025954037,0.8033739,0.000085027925,0.0003777645,0.0004949743,0.00010175205,0.0000065954773,0.00013623701],"genre_scores_gemma":[0.38297814,0.000006772501,0.6167631,0.000044016506,0.00017123326,0.0000050561184,3.9735664e-7,0.000023715596,0.0000075108505],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596465,0.0004233707,0.0024516436,0.0001301375,0.0008095727,0.00022062953],"domain_scores_gemma":[0.9602627,0.034665912,0.0037514518,0.00042367505,0.0008322871,0.00006397035],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004182937,0.00018742315,0.00080139044,0.000053794676,0.00010516022,0.00004545948,0.00050741417,0.00009482396,0.00017633091],"category_scores_gemma":[0.027997766,0.00009633484,0.00014313625,0.00017617398,0.00045557716,0.00006397265,0.000089709065,0.00042933243,0.000003497953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067672366,0.0018668844,0.0031248294,0.0036494643,0.0017930595,0.000029482144,0.009295838,0.00830686,0.05872825,0.31995097,0.013078056,0.5794996],"study_design_scores_gemma":[0.00055357546,0.00020011277,0.0014842772,0.000230576,0.0004047385,0.00001805529,0.00081027887,0.016819196,0.009889883,0.9694615,0.000012320362,0.00011547602],"about_ca_topic_score_codex":0.00003058258,"about_ca_topic_score_gemma":0.0000017616279,"teacher_disagreement_score":0.64951056,"about_ca_system_score_codex":0.00004221626,"about_ca_system_score_gemma":0.00012394208,"threshold_uncertainty_score":0.9801898},"labels":[],"label_agreement":null},{"id":"W2105385152","doi":"10.1002/sim.5676","title":"Comparing diagnostic tests: trials in people with discordant test results","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"National Institutes of Health; Universiteit van Amsterdam; National Institute for Health and Care Research","keywords":"Statistics; Test (biology); Gold standard (test); Statistical hypothesis testing; Computer science; Medicine; Econometrics; Mathematics","score_opus":0.5460293344991152,"score_gpt":0.5771006422312617,"score_spread":0.031071307732146503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105385152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05335245,0.00047517204,0.9246786,0.0024349159,0.0027283723,0.0034719699,0.0024230136,0.00016990713,0.0102655515],"genre_scores_gemma":[0.41672453,0.00011775302,0.5822122,0.00011183883,0.0005787688,0.00010093059,0.000029400904,0.000044483782,0.00008006794],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922604,0.0021849554,0.0034885614,0.00046131163,0.0007960029,0.00080879213],"domain_scores_gemma":[0.4581117,0.54017943,0.0007510307,0.000562416,0.000107404885,0.00028800964],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027723521,0.00036161082,0.00262076,0.00027598976,0.000052698048,0.000020740355,0.00032048547,0.00008895268,0.00022653842],"category_scores_gemma":[0.8694941,0.00024038667,0.000042491738,0.0007573203,0.0004475876,0.00008929633,0.00011117981,0.0007275244,0.000027799917],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090958626,0.0016010888,0.6677448,0.00058655447,0.00006898374,0.0003968465,0.002384065,0.00002426902,0.000079941645,0.30176768,0.018645423,0.005790741],"study_design_scores_gemma":[0.009878109,0.00082708214,0.33791915,0.00217841,0.00025236479,0.000032084696,0.0007287342,0.0006097908,0.000053093267,0.6468367,0.00026331606,0.00042117716],"about_ca_topic_score_codex":0.00031214007,"about_ca_topic_score_gemma":0.0019345573,"teacher_disagreement_score":0.8417706,"about_ca_system_score_codex":0.00019589758,"about_ca_system_score_gemma":0.00008509805,"threshold_uncertainty_score":0.9802684},"labels":[],"label_agreement":null},{"id":"W2105400786","doi":"10.1158/1078-0432.ccr-09-1357","title":"The Cross-Validated Adaptive Signature Design","year":2010,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":190,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Classifier (UML); Adaptive design; Computer science; Signature (topology); Clinical trial; Cross-validation; Data mining; Medicine; Artificial intelligence; Machine learning; Mathematics; Pathology","score_opus":0.9293997658481492,"score_gpt":0.77552257358576,"score_spread":0.15387719226238916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105400786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38028067,0.0026718264,0.4625733,0.04129512,0.051223923,0.019362375,0.0011145843,0.0018153464,0.039662864],"genre_scores_gemma":[0.25392428,0.00079102925,0.72931737,0.0005998096,0.0064004716,0.0009641284,0.0000016570799,0.00017518441,0.007826094],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882316,0.0063880635,0.0017566622,0.0008620814,0.0016593521,0.0011022595],"domain_scores_gemma":[0.5650147,0.43114576,0.0002741835,0.0013920406,0.0016513902,0.0005219341],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.070676595,0.00023528421,0.00068888447,0.000065324166,0.0008528597,0.0003443585,0.0016745002,0.00082053465,0.0018446846],"category_scores_gemma":[0.4899555,0.00014022052,0.00030286174,0.00073622324,0.0038324539,0.000084271865,0.0005422208,0.0070127617,0.0003190964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058995816,0.00081657385,0.0026361644,0.0000736559,0.00041200398,0.000092086426,0.000111913374,0.000010144469,0.0034893956,0.5459272,0.22861005,0.21192119],"study_design_scores_gemma":[0.0011893504,0.00047575377,0.0022402797,0.000046040168,0.00003173449,0.0000017106903,0.000031681484,0.0005393244,0.003449813,0.97423905,0.01755017,0.00020509673],"about_ca_topic_score_codex":0.000046331974,"about_ca_topic_score_gemma":0.000097323624,"teacher_disagreement_score":0.4283118,"about_ca_system_score_codex":0.00007064987,"about_ca_system_score_gemma":0.0007371856,"threshold_uncertainty_score":0.9990678},"labels":[],"label_agreement":null},{"id":"W2106094950","doi":"10.1177/1740774512467404","title":"Determining optimal sample sizes for multistage adaptive randomized clinical trials from an industry perspective using value of information methods","year":2012,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Frequentist inference; Sample size determination; Profit (economics); Value of information; Randomized controlled trial; Bayesian probability; Expected utility hypothesis; Computer science; Actuarial science; Econometrics; Statistics; Medicine; Economics; Mathematics; Bayesian inference; Microeconomics; Artificial intelligence","score_opus":0.901972840808825,"score_gpt":0.7468425831810588,"score_spread":0.15513025762776622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106094950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056873005,0.0001427921,0.9266692,0.00012791205,0.0062061045,0.006720566,0.002950766,0.0001463645,0.00016329481],"genre_scores_gemma":[0.03730988,0.00007519836,0.95507026,0.0004098043,0.006639409,0.00034690436,0.000037706144,0.000098448625,0.000012371563],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.67933166,0.2820302,0.034870975,0.0013409903,0.0011239758,0.0013022096],"domain_scores_gemma":[0.027537296,0.95465356,0.014099802,0.0013365329,0.0012695357,0.0011032582],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.58986664,0.0007324118,0.015256528,0.00024346125,0.00021730653,0.00015003799,0.0008117151,0.002940342,0.0007062705],"category_scores_gemma":[0.9847271,0.00055077206,0.0048506265,0.0003555815,0.0015310377,0.0010939428,0.0003543186,0.002038001,0.000012411004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.25450814,0.0034912182,0.001885875,0.00021923288,0.006339953,0.000003164644,0.0026545906,0.00019918071,0.00035995196,0.2833339,0.00059049367,0.4464143],"study_design_scores_gemma":[0.1816476,0.0012155251,0.0005119224,0.00034864395,0.0062718894,0.0000021199141,0.0028512701,0.06905222,0.0016885501,0.7353167,0.0002965359,0.0007970152],"about_ca_topic_score_codex":0.00018534053,"about_ca_topic_score_gemma":0.0000021656872,"teacher_disagreement_score":0.6726234,"about_ca_system_score_codex":0.00016466634,"about_ca_system_score_gemma":0.000567421,"threshold_uncertainty_score":0.9996944},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2106247158","doi":"10.1002/cjs.5550330407","title":"Cure rate models: A unified approach","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":170,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Markov chain; Covariate; Class (philosophy); Population; Bayesian probability; Mathematics; Artificial intelligence; Machine learning","score_opus":0.591728175816646,"score_gpt":0.4805929130659556,"score_spread":0.11113526275069047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106247158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043907348,0.00013939057,0.98393375,0.00067234994,0.00053093163,0.00016948186,0.00078975613,0.000011530073,0.013313747],"genre_scores_gemma":[0.025533106,0.000048003763,0.97243637,0.00042293768,0.00070255296,0.0000026595253,0.0000028992997,0.000045780504,0.0008056762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972369,0.0005473512,0.0012800163,0.000174968,0.00030808305,0.00045266692],"domain_scores_gemma":[0.9871792,0.010183906,0.00061433966,0.00029783408,0.0005957847,0.0011289258],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031199357,0.0002002393,0.00064984086,0.00022128777,0.00011665296,0.00008761769,0.0004354468,0.00016506769,0.00044486314],"category_scores_gemma":[0.03146145,0.00017469072,0.000110896246,0.00021705456,0.00023287092,0.00014178563,0.000015980284,0.000610286,0.000022501206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038044996,0.000055623063,0.000037022353,0.00007225697,0.000101698795,0.00017055779,0.00032779603,0.00075884094,0.0000082404895,0.8656822,0.099883124,0.0328646],"study_design_scores_gemma":[0.00080989295,0.00012134356,0.000067391215,0.00006342542,0.0001581048,0.00009463121,0.00012870577,0.01281398,0.000028002389,0.97149456,0.014012935,0.00020705625],"about_ca_topic_score_codex":0.00014460045,"about_ca_topic_score_gemma":0.001503648,"teacher_disagreement_score":0.10581233,"about_ca_system_score_codex":0.0002085073,"about_ca_system_score_gemma":0.001334182,"threshold_uncertainty_score":0.97669697},"labels":[],"label_agreement":null},{"id":"W2106303555","doi":"10.18433/j3z88f","title":"Sample Sizes for Designing Bioequivalence Studies for Highly Variable Drugs","year":2011,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sample size determination; Sample (material); Bioequivalence; Statistics; Constraint (computer-aided design); Econometrics; Variable (mathematics); Mathematics; Point (geometry); Variation (astronomy); Medicine; Chemistry; Pharmacology; Physics; Chromatography","score_opus":0.8718751607281915,"score_gpt":0.6628438347039814,"score_spread":0.20903132602421004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106303555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009232308,0.0017197522,0.9826112,0.0013273526,0.0031459345,0.0011238274,0.00013380863,0.000061496256,0.00064434373],"genre_scores_gemma":[0.07441337,0.0006193291,0.9231811,0.00074482244,0.00090759015,0.00006714734,1.5302565e-7,0.000026408492,0.000040056297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99566686,0.00058578025,0.0017753622,0.000421002,0.00078506215,0.000765924],"domain_scores_gemma":[0.8767915,0.12074325,0.0009623321,0.00015284122,0.0009160981,0.00043399679],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014853748,0.00028777285,0.0009610339,0.0001652264,0.00045391254,0.00008777326,0.0010372897,0.00006737327,0.0004622144],"category_scores_gemma":[0.106794395,0.0001984737,0.00038981732,0.00051481824,0.0011474657,0.00050325115,0.00014568072,0.00033954543,0.0000039847255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004972018,0.0017450117,0.0011874489,0.0020353983,0.0013488902,0.000024815261,0.003317021,0.00003515958,0.07435637,0.6499326,0.019341085,0.24170415],"study_design_scores_gemma":[0.0032773942,0.0007932454,0.000007891195,0.00016075946,0.0007682527,0.000017661316,0.00054146006,0.0032011848,0.13406864,0.8366232,0.020265715,0.000274621],"about_ca_topic_score_codex":0.000006689657,"about_ca_topic_score_gemma":2.5423972e-7,"teacher_disagreement_score":0.24142954,"about_ca_system_score_codex":0.00008503288,"about_ca_system_score_gemma":0.0003006737,"threshold_uncertainty_score":0.9007295},"labels":[],"label_agreement":null},{"id":"W2106584438","doi":"10.1177/0272989x0002000113","title":"An Assessment of Methods to Combine Published Survival Curves","year":2000,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Regional Cancer Foundation; University of Ottawa","funders":"","keywords":"Censoring (clinical trials); Covariate; Statistics; Survival analysis; Medicine; Mathematics; Oncology","score_opus":0.5056615645167237,"score_gpt":0.6965193766699368,"score_spread":0.19085781215321307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106584438","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0136656435,0.000043336997,0.97525597,0.0011739513,0.0010231535,0.00042971756,0.000022748782,0.000103617946,0.008281847],"genre_scores_gemma":[0.028940538,0.00006751102,0.96905327,0.0015468469,0.00023521097,0.000028255163,0.0000019314728,0.00003979452,0.00008662943],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9906761,0.0038206938,0.0021394705,0.0006228829,0.0023199802,0.00042088295],"domain_scores_gemma":[0.8560016,0.14155526,0.00028999313,0.0011709777,0.0002742587,0.000707889],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03169734,0.00022873537,0.0012385757,0.00013893528,0.000071925584,0.000063998086,0.0010520088,0.00027661648,0.046198063],"category_scores_gemma":[0.3404889,0.00017238407,0.00018625516,0.00068348553,0.00017135637,0.00012759017,0.0002168478,0.00055082253,0.00003427034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000108035376,0.0004997255,0.00032439426,0.00011080165,0.0000317755,0.000019313777,0.000022074308,0.000007630205,0.00007554073,0.04486774,0.0070525063,0.94688046],"study_design_scores_gemma":[0.0010412233,0.00048780435,0.0066789254,0.001900926,0.00006803302,0.000006524569,0.000018553541,0.007823421,0.00010765885,0.9787047,0.0029150913,0.00024711888],"about_ca_topic_score_codex":0.000006409715,"about_ca_topic_score_gemma":0.0000052507776,"teacher_disagreement_score":0.94663334,"about_ca_system_score_codex":0.00004752913,"about_ca_system_score_gemma":0.0001525538,"threshold_uncertainty_score":0.9970714},"labels":[],"label_agreement":null},{"id":"W2106597354","doi":"10.2214/ajr.184.4.01841047","title":"Statistical Inference for Continuous Variables","year":2005,"lang":"en","type":"article","venue":"American Journal of Roentgenology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; McGill University; Montreal General Hospital","funders":"","keywords":"Medicine; Sophistication; Inference; Complement (music); Medical physics; Statistical inference; Software; Web site; Association (psychology); Series (stratigraphy); Data science; The Internet; Artificial intelligence; World Wide Web; Statistics; Computer science; Programming language","score_opus":0.28003946704751503,"score_gpt":0.5401356834381219,"score_spread":0.26009621639060687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106597354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038445707,0.000044117947,0.9586438,0.0017499248,0.00045429447,0.0001889369,0.00007628772,0.000020076253,0.0003768328],"genre_scores_gemma":[0.2506328,0.000041488296,0.7483255,0.00043178734,0.0004872128,0.000008072183,4.5554984e-7,0.000020495318,0.000052150426],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99719334,0.00063654996,0.0013460569,0.00018803924,0.00023609561,0.0003999143],"domain_scores_gemma":[0.94380456,0.05421198,0.0011489757,0.00022224277,0.00041816643,0.00019407112],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021924924,0.0001574374,0.0011082651,0.00011142297,0.00004770394,0.000018072824,0.00037217274,0.000076286895,0.00038986397],"category_scores_gemma":[0.08732458,0.00012531398,0.00014909008,0.00013771554,0.00065270305,0.00005731945,0.000053298594,0.0003151287,0.000014716964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076457235,0.00038883596,0.0013309269,0.00003133063,0.0003159772,0.000032399166,0.00015019317,0.000030335805,0.00046322538,0.5012706,0.0075477087,0.48767388],"study_design_scores_gemma":[0.001676117,0.0038633342,0.0006193021,0.000037731414,0.00025753284,0.00017517849,0.00023767179,0.00019256443,0.0004242242,0.976628,0.015711922,0.00017643363],"about_ca_topic_score_codex":0.000005782576,"about_ca_topic_score_gemma":0.0000042533306,"teacher_disagreement_score":0.48749745,"about_ca_system_score_codex":0.0000636937,"about_ca_system_score_gemma":0.00014601288,"threshold_uncertainty_score":0.92036325},"labels":[],"label_agreement":null},{"id":"W2107476951","doi":"10.1002/sim.1764","title":"Test of treatment effect in pre‐drug and post‐drug count data with zero‐inflation","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"National Cancer Institute","keywords":"Likelihood-ratio test; Score test; Statistics; Statistic; Mathematics; Test statistic; Null hypothesis; Medicine; Statistical hypothesis testing","score_opus":0.21690093327361057,"score_gpt":0.5248629691353153,"score_spread":0.3079620358617047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107476951","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4138276,0.0004003686,0.5757674,0.0016222588,0.00046750557,0.0031158584,0.0039255396,0.00006142483,0.00081206777],"genre_scores_gemma":[0.31588,0.00017516587,0.6836015,0.00006322498,0.00007947956,0.000029725556,0.00008222092,0.000029161487,0.000059506197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99748105,0.00039469253,0.0010284242,0.00042566223,0.00043203405,0.00023814937],"domain_scores_gemma":[0.93555546,0.063270144,0.000309123,0.000661437,0.00010638445,0.00009746221],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036756399,0.000242421,0.0009596188,0.00014218217,0.000024669587,0.000008041184,0.00022188328,0.000069743255,0.00006033714],"category_scores_gemma":[0.07483487,0.00015326287,0.000011118272,0.0002516783,0.00045858775,0.000057310986,0.00008580708,0.00023213992,0.000002122412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041930894,0.0032216785,0.26063713,0.0054499945,0.00044596748,0.0009757462,0.0145900715,0.00050879404,0.0022407887,0.5616491,0.0066793486,0.13940834],"study_design_scores_gemma":[0.011533423,0.0033749787,0.05567244,0.0015427782,0.00028372786,0.000009884228,0.00012226435,0.0014066505,0.0003703838,0.92541295,0.000050951774,0.00021955933],"about_ca_topic_score_codex":0.0014387171,"about_ca_topic_score_gemma":0.0019025955,"teacher_disagreement_score":0.3637639,"about_ca_system_score_codex":0.00020951648,"about_ca_system_score_gemma":0.00011719677,"threshold_uncertainty_score":0.9329582},"labels":[],"label_agreement":null},{"id":"W2107964785","doi":"10.1002/bimj.201400244","title":"Optimal individualized dosing strategies: A pharmacologic approach to developing dynamic treatment regimens for continuous‐valued treatments","year":2015,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Dosing; Pharmacodynamics; Medicine; Warfarin; Intensive care medicine; Clinical study design; Clinical trial; Pharmacokinetics; Computer science; Pharmacology; Internal medicine","score_opus":0.7096372808610444,"score_gpt":0.6014963020028388,"score_spread":0.10814097885820562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107964785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0691988,0.00018057584,0.9261169,0.00039715756,0.00090815854,0.0017530398,0.00015412155,0.00012085036,0.001170441],"genre_scores_gemma":[0.02959494,0.000040756066,0.9691709,0.00019518062,0.00041997922,0.00021987865,0.000009244255,0.00006121531,0.00028785577],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952677,0.0010600897,0.001455475,0.00057489175,0.0008052394,0.0008366409],"domain_scores_gemma":[0.9842626,0.013416727,0.0006165104,0.00027460468,0.00044352765,0.0009860173],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004340836,0.00044705335,0.0013022036,0.0010339565,0.0002548462,0.00040922896,0.0004680101,0.00027856254,0.00003698358],"category_scores_gemma":[0.033868004,0.00031094317,0.00037194244,0.0021278528,0.000116620206,0.00015327992,0.00012018691,0.0002762932,0.000024718034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0212825,0.026194096,0.0009824663,0.0006443873,0.0147387395,0.00081548013,0.008365514,0.0008702623,0.007851464,0.14869495,0.056750722,0.71280944],"study_design_scores_gemma":[0.07223506,0.02041257,0.0007040131,0.00034656932,0.0038900373,0.0008958744,0.0051923473,0.012058341,0.0035627745,0.8622406,0.01598546,0.0024763376],"about_ca_topic_score_codex":0.0000058166647,"about_ca_topic_score_gemma":2.705216e-7,"teacher_disagreement_score":0.7135457,"about_ca_system_score_codex":0.0016092646,"about_ca_system_score_gemma":0.00060636055,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W2109054675","doi":"10.1177/1740774507087551","title":"Sensible approaches for reducing clinical trial costs","year":2008,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":181,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute","funders":"","keywords":"Clinical trial; Medicine; Randomized controlled trial; Payment; Duration (music); Cost–benefit analysis; Operations management; Operations research; Business; Surgery; Engineering; Finance; Internal medicine","score_opus":0.9772817153848696,"score_gpt":0.7307094998449754,"score_spread":0.24657221553989428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109054675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28941554,0.0003494565,0.61309063,0.004505509,0.049864918,0.025355373,0.00076712033,0.001349132,0.015302344],"genre_scores_gemma":[0.03545307,0.0005034011,0.93843573,0.0008664038,0.022205893,0.0005596886,0.00001559493,0.00017677457,0.0017834557],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94453454,0.03285517,0.01839224,0.00213342,0.0009653827,0.00111924],"domain_scores_gemma":[0.24319251,0.7495364,0.003834724,0.0019724965,0.00046772455,0.0009961684],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22057709,0.0006035994,0.006994665,0.00013350786,0.0003987238,0.00008899564,0.0008476813,0.0016205194,0.00037915003],"category_scores_gemma":[0.9264608,0.00046917042,0.004040637,0.0004116771,0.0014534186,0.00013492822,0.00029756653,0.0014648404,0.00020904421],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13812257,0.006530461,0.0010624898,0.00024439834,0.0015844557,0.00009074555,0.000081791964,0.000005859795,0.000024150146,0.16822574,0.24547169,0.43855566],"study_design_scores_gemma":[0.15710147,0.004514127,0.0004044351,0.00019387418,0.0010266688,0.000026080957,0.000053678465,0.0010406089,0.00024841126,0.8169404,0.017624347,0.00082587014],"about_ca_topic_score_codex":0.000007391456,"about_ca_topic_score_gemma":0.0000023005027,"teacher_disagreement_score":0.7166812,"about_ca_system_score_codex":0.00009086327,"about_ca_system_score_gemma":0.0006424894,"threshold_uncertainty_score":0.999776},"labels":[],"label_agreement":null},{"id":"W2109920122","doi":"10.1002/sim.1261","title":"Exact unconditional tests for testing non‐inferiority in matched‐pairs design","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Nuisance parameter; Exact statistics; Mathematics; Confidence interval; Sample size determination; Statistics; Monotonic function; Statistical hypothesis testing; Nominal level; Exact test; Score test; Applied mathematics; Estimator; Mathematical analysis","score_opus":0.6511081763640518,"score_gpt":0.5669361148639607,"score_spread":0.08417206150009116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109920122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00142505,0.00003587284,0.9933546,0.0005647678,0.00065429596,0.0012156707,0.00062797137,0.00006034517,0.0020613924],"genre_scores_gemma":[0.038291145,0.00002145011,0.9604501,0.0002799008,0.00049217744,0.00020474446,0.000021490632,0.000052173087,0.000186805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962431,0.0005451982,0.00161147,0.00048476004,0.00057099084,0.00054448616],"domain_scores_gemma":[0.82954144,0.16943027,0.0003108117,0.00033175093,0.00022839097,0.00015732613],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0064164153,0.00029005684,0.0010468299,0.0002273588,0.00006979025,0.00001648989,0.00027065456,0.00019545652,0.0013028666],"category_scores_gemma":[0.38962734,0.00025521012,0.000038587008,0.00055607484,0.0003877556,0.000054325148,0.000053595675,0.0005347592,0.0000284546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004352017,0.0020735364,0.03580517,0.0026440239,0.00014876368,0.00091517426,0.0024333186,0.00039061913,0.001125337,0.5949416,0.24572814,0.1133591],"study_design_scores_gemma":[0.003559438,0.0005802412,0.014334956,0.0005976014,0.000061620245,0.000009306306,0.00010621621,0.031259082,0.00004305964,0.9490823,0.00010932995,0.00025685458],"about_ca_topic_score_codex":0.00006255198,"about_ca_topic_score_gemma":0.00006927885,"teacher_disagreement_score":0.38321093,"about_ca_system_score_codex":0.00019755,"about_ca_system_score_gemma":0.00007454694,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W2111128280","doi":"10.1200/jco.2009.25.2205","title":"Optimizing the Delivery of Targeted Research: An Opportunity for Comparative Effectiveness Research","year":2010,"lang":"en","type":"editorial","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Comparative effectiveness research; Intensive care medicine; Alternative medicine; Pathology","score_opus":0.9570904995417888,"score_gpt":0.7893693240462735,"score_spread":0.16772117549551535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111128280","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01614786,0.00030832496,0.012581496,0.0010333997,0.9637981,0.0033631723,0.000674795,0.000022998513,0.002069867],"genre_scores_gemma":[0.0030999703,0.00052288314,0.4567589,0.000042984753,0.5392692,0.000098999444,0.000011951039,0.00008613665,0.00010899962],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85620195,0.12434375,0.011964243,0.000942414,0.005304801,0.0012428365],"domain_scores_gemma":[0.043641698,0.9217019,0.007993064,0.0012677768,0.024307419,0.0010881625],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4497329,0.0004239009,0.007403866,0.000552063,0.0004348901,0.00007236395,0.0030780435,0.005642987,0.00019613399],"category_scores_gemma":[0.9129448,0.00025891844,0.0015521429,0.00061804,0.0051471707,0.00019087619,0.0007205862,0.02573238,0.000007636831],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02200484,0.0041216873,0.000014886395,0.00064166967,0.0012121608,0.000117210155,0.00041647567,0.000008047392,0.00020385502,0.007446836,0.9361819,0.027630422],"study_design_scores_gemma":[0.005033406,0.024451785,0.000109754685,0.00057099684,0.0004242024,0.0000065509603,0.0005378445,0.000117236494,0.000277471,0.59013534,0.3781203,0.00021510985],"about_ca_topic_score_codex":0.00005826093,"about_ca_topic_score_gemma":0.00012895293,"teacher_disagreement_score":0.81256026,"about_ca_system_score_codex":0.0003724943,"about_ca_system_score_gemma":0.017093645,"threshold_uncertainty_score":0.9999863},"labels":[],"label_agreement":null},{"id":"W2111616613","doi":"10.1002/sim.5827","title":"Inverse probability weighted estimating equations for randomized trials in transfusion medicine","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Confounding; Randomized controlled trial; Inverse probability; Clinical trial; Platelet transfusion; Intensive care medicine; Platelet; Emergency medicine; Internal medicine; Statistics; Mathematics","score_opus":0.5703369182139181,"score_gpt":0.5825705942847677,"score_spread":0.012233676070849575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111616613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019687875,0.000047150563,0.9802781,0.0055706403,0.0014337075,0.009570028,0.00018211405,0.00006974602,0.0008797272],"genre_scores_gemma":[0.0035732365,0.000104265746,0.99291474,0.00036748956,0.0006857097,0.0021447372,0.000052667456,0.00004896643,0.000108167544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98408204,0.0076779868,0.0062975558,0.00063726347,0.00076225394,0.00054287346],"domain_scores_gemma":[0.38310555,0.61440885,0.0011338614,0.00056753185,0.0005453125,0.00023891818],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0719812,0.0003763464,0.0047757127,0.00040977108,0.00008790536,0.000016210139,0.00030319963,0.00025929563,0.003334058],"category_scores_gemma":[0.8818281,0.00024849336,0.00015599991,0.0006322368,0.0012723905,0.00008858288,0.000044119308,0.00055274647,0.000014534006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0074456064,0.00039059727,0.00017330499,0.0012707703,0.00011001218,0.00001335658,0.0027995796,0.00004741611,0.00036758106,0.91596526,0.020482318,0.05093422],"study_design_scores_gemma":[0.10784712,0.00025398599,0.00008022649,0.00088454835,0.00027779778,8.673316e-7,0.00019498804,0.1528567,0.000017757548,0.7373855,0.000026081467,0.00017443152],"about_ca_topic_score_codex":0.0010404366,"about_ca_topic_score_gemma":0.00056690443,"teacher_disagreement_score":0.80984694,"about_ca_system_score_codex":0.00017709935,"about_ca_system_score_gemma":0.00011625573,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W2111941108","doi":"10.1200/jco.2007.14.0673","title":"Nomograms to Predict Serious Adverse Events in Phase II Clinical Trials of Molecularly Targeted Agents","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Cancer Institute","keywords":"Medicine; Nomogram; Adverse effect; Internal medicine; Clinical trial; Body surface area; Oncology; Surgery; Emergency medicine","score_opus":0.7789254010076008,"score_gpt":0.6974319729904782,"score_spread":0.08149342801712256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111941108","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.941763,0.000066451816,0.04872434,0.0014646058,0.005979171,0.0013762481,0.00008186075,0.00002423218,0.0005200783],"genre_scores_gemma":[0.4804759,0.00039043222,0.5161308,0.0013367789,0.0014795869,0.000018129715,0.0000017552229,0.000048099286,0.0001184773],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9394383,0.02714639,0.030726112,0.0006446765,0.0013768781,0.0006676404],"domain_scores_gemma":[0.7493227,0.23274179,0.014408328,0.000828459,0.001160574,0.0015381605],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.12769815,0.00037524686,0.009008789,0.00037074648,0.000073812225,0.000003118799,0.0010253971,0.0013924215,0.0005415703],"category_scores_gemma":[0.7790145,0.00028402678,0.0027951421,0.00063191616,0.0006098085,0.0001528489,0.00037593208,0.0024141574,0.00003160085],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0681473,0.09374308,0.13140178,0.000253035,0.004216101,0.0072134123,0.00090094947,0.00014049864,0.00077136705,0.002663318,0.031083582,0.65946555],"study_design_scores_gemma":[0.18193102,0.17989874,0.20512667,0.0011886306,0.0027633465,0.0005090395,0.00022504345,0.0010803273,0.0006090884,0.39205033,0.033447582,0.0011701902],"about_ca_topic_score_codex":0.000016088343,"about_ca_topic_score_gemma":0.000015947104,"teacher_disagreement_score":0.6582954,"about_ca_system_score_codex":0.00015035743,"about_ca_system_score_gemma":0.001871422,"threshold_uncertainty_score":0.9999612},"labels":[],"label_agreement":null},{"id":"W2112488309","doi":"10.18433/j3fg63","title":"How Critical is the Duration of the Sampling Scheme for the Determination of Half-Life, Characterization of Exposure and Assessment of Bioequivalence?","year":2011,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Bioequivalence; Statistics; Confidence interval; Sampling (signal processing); Mathematics; Duration (music); Sampling scheme; Bioavailability; Geometric mean; Half-life; Econometrics; Pharmacokinetics; Medicine; Computer science; Pharmacology","score_opus":0.7576287729824264,"score_gpt":0.6302472505021868,"score_spread":0.1273815224802396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112488309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6271344,0.0002866539,0.3627305,0.008176701,0.00078246335,0.0007301531,0.000080694044,0.0000038915623,0.00007456207],"genre_scores_gemma":[0.7692755,0.0002575459,0.23022717,0.00011657414,0.00010716836,0.0000069080065,8.940882e-8,0.0000056305735,0.000003408554],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99673814,0.00062420464,0.001435332,0.00015005306,0.00087357144,0.00017871748],"domain_scores_gemma":[0.97623634,0.021071905,0.0016648053,0.0001649828,0.00077126,0.00009067947],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007661225,0.00012309225,0.00044014907,0.00006698239,0.00015480131,0.000032899854,0.00062660594,0.000050464765,0.00008857632],"category_scores_gemma":[0.024059236,0.00005735411,0.00021309909,0.00035517063,0.0018105052,0.000304921,0.00011023044,0.00026321056,4.1738613e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039299316,0.0005765292,0.013427397,0.0009862969,0.00012750049,6.105478e-7,0.001230417,0.0000017765246,0.79769075,0.10958211,0.000027298933,0.07595631],"study_design_scores_gemma":[0.001516883,0.0005424484,0.014386351,0.00031841418,0.00083144195,0.000016419443,0.00057929556,0.028488211,0.85291415,0.09984148,0.00044368676,0.000121194316],"about_ca_topic_score_codex":0.0000040134514,"about_ca_topic_score_gemma":3.9884713e-7,"teacher_disagreement_score":0.14214112,"about_ca_system_score_codex":0.000015267511,"about_ca_system_score_gemma":0.00019287951,"threshold_uncertainty_score":0.98416156},"labels":[],"label_agreement":null},{"id":"W2113330311","doi":"10.1348/000711002159680","title":"Controlling the rate of Type I error over a large set of statistical tests","year":2002,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"False discovery rate; Type I and type II errors; Multiple comparisons problem; Statistical power; Null hypothesis; Statistics; Statistical hypothesis testing; p-value; Mathematics; Word error rate; Null (SQL); Set (abstract data type); Statistical process control; Statistical significance; Sample size determination; False positive rate; Computer science; Data mining; Artificial intelligence; Process (computing); Biology","score_opus":0.39724289716766226,"score_gpt":0.5422999661469321,"score_spread":0.14505706897926984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113330311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056374665,0.00078247,0.9377987,0.00091351755,0.00047300698,0.0004550552,0.0012088083,0.00001722352,0.0019765496],"genre_scores_gemma":[0.5133141,0.00035285126,0.48556527,0.0004300406,0.0002101849,0.0000042559,0.0000018499271,0.00004221961,0.000079176774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994015,0.0018124849,0.002845096,0.00030462525,0.0005406337,0.00048219576],"domain_scores_gemma":[0.9232587,0.07469788,0.0009660983,0.0003047733,0.00047750122,0.0002950419],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0060563837,0.0002465922,0.0017390171,0.00008486458,0.0000882426,0.000039454048,0.00040396667,0.00024968386,0.0047605787],"category_scores_gemma":[0.12097358,0.00017804181,0.00017575722,0.00023340681,0.0012926867,0.000064961256,0.000100085505,0.0007770594,0.000019123705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061784167,0.0012639081,0.00016532883,0.0005327695,0.00032448405,0.00047431616,0.00019340048,0.0000010373791,0.00027091688,0.9506126,0.021158379,0.024385016],"study_design_scores_gemma":[0.003386142,0.0011345138,0.0026859692,0.00043718732,0.00037281658,0.0012381126,0.00008443206,0.0031670704,0.000024772713,0.98685956,0.00042340154,0.00018604063],"about_ca_topic_score_codex":0.0000061990568,"about_ca_topic_score_gemma":0.0000040265195,"teacher_disagreement_score":0.4569395,"about_ca_system_score_codex":0.000018358878,"about_ca_system_score_gemma":0.000032929158,"threshold_uncertainty_score":0.9961492},"labels":[],"label_agreement":null},{"id":"W2113647194","doi":"10.1002/jmri.24567","title":"How much net gain does a diagnostic imaging test provide?","year":2014,"lang":"en","type":"letter","venue":"Journal of Magnetic Resonance Imaging","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Pre- and post-test probability; Diagnostic test; Test (biology); Population; Disease; Predictive value; Statistics; Medicine; Heston model; Econometrics; Computer science; Internal medicine; Mathematics; Pediatrics; Environmental health","score_opus":0.14192076845402676,"score_gpt":0.4300170091707381,"score_spread":0.28809624071671136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113647194","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009778913,0.013629944,0.06736257,0.9127573,0.0036940095,0.0010727757,0.00014328599,0.0001064928,0.0011358659],"genre_scores_gemma":[0.00088448124,0.00084839825,0.71985143,0.2514855,0.022538334,0.000072478215,0.000004493277,0.00037603074,0.0039388575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99053985,0.0021361052,0.003195361,0.00085719867,0.00201906,0.0012523993],"domain_scores_gemma":[0.79536116,0.19894844,0.0033954803,0.001096896,0.0009228042,0.00027521048],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006942723,0.00092784985,0.0026308438,0.0004662234,0.0001632061,0.0009267066,0.0016640616,0.00046552476,0.00035263025],"category_scores_gemma":[0.43734223,0.000650861,0.000784021,0.00034694676,0.0006765713,0.00035689358,0.0002962209,0.0051400587,0.000027559614],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003099619,0.00009261155,0.0024500182,0.0006897586,0.000023021003,0.0040057753,0.000057366095,2.7971362e-7,0.00006688066,0.0002178407,0.8040546,0.18831082],"study_design_scores_gemma":[0.0013623716,0.00021620365,0.00032277755,0.002970701,0.00047967845,0.0008913156,0.000053824428,0.00063225726,0.000090057525,0.40511099,0.5872264,0.000643458],"about_ca_topic_score_codex":0.000012092581,"about_ca_topic_score_gemma":0.0000018313176,"teacher_disagreement_score":0.66127175,"about_ca_system_score_codex":0.00024053609,"about_ca_system_score_gemma":0.00034479913,"threshold_uncertainty_score":0.9995943},"labels":[],"label_agreement":null},{"id":"W2114041580","doi":"10.1177/009286150003400220","title":"Adjustment of Treatment Effect for Covariates in Clinical Trials: Statistical and Regulatory Issues","year":2000,"lang":"en","type":"article","venue":"Drug Information Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Covariate; Credibility; Clinical trial; Outcome (game theory); Medicine; Statistical analysis; Treatment effect; Econometrics; Intensive care medicine; Statistics; Internal medicine; Mathematics; Political science","score_opus":0.4218002662689594,"score_gpt":0.6041925948611838,"score_spread":0.18239232859222443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114041580","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5583381,0.0008571618,0.42496789,0.0018651161,0.0031465762,0.006725459,0.0013857147,0.00011745633,0.0025965038],"genre_scores_gemma":[0.034746807,0.0012390072,0.9628829,0.00016601564,0.0006516257,0.00010347716,0.000015769838,0.000020146468,0.00017428388],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99209106,0.0032281836,0.004061658,0.0001234102,0.0002705471,0.00022511228],"domain_scores_gemma":[0.9124267,0.086195074,0.00089204876,0.00017989338,0.00012295533,0.00018329859],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029257521,0.00018138754,0.0012903004,0.00012445901,0.00006264392,0.000057738733,0.00010709781,0.00013938469,0.0007947443],"category_scores_gemma":[0.08650434,0.000118800155,0.00022636139,0.000082559935,0.00014285085,0.0002982864,0.000015516927,0.00022750167,0.000015006178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018031172,0.00020902306,0.00076794514,0.00020755037,0.00017436742,0.000001907572,0.0008296743,0.00003844124,0.000003994183,0.062212896,0.005949045,0.927802],"study_design_scores_gemma":[0.019199414,0.0035222638,0.012994699,0.0003618488,0.00051448407,0.000050013594,0.0003383199,0.0077615865,0.00050779857,0.9397117,0.014709546,0.00032831277],"about_ca_topic_score_codex":0.000008025039,"about_ca_topic_score_gemma":0.0000017553717,"teacher_disagreement_score":0.9274737,"about_ca_system_score_codex":0.0001044359,"about_ca_system_score_gemma":0.0001119721,"threshold_uncertainty_score":0.99958366},"labels":[],"label_agreement":null},{"id":"W2115420947","doi":"10.1191/0962280205sm411oa","title":"The role of proxy information in missing data analysis","year":2005,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Statistics Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Proxy (statistics); Missing data; Computer science; Data mining; Econometrics; Mathematics; Machine learning","score_opus":0.7108746652615446,"score_gpt":0.7422157901858673,"score_spread":0.031341124924322616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115420947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003526494,0.00022189955,0.98796016,0.003366327,0.00010370748,0.00065540476,0.00017414057,0.000021677808,0.007144039],"genre_scores_gemma":[0.011635098,0.00018478706,0.98782235,0.000079651094,0.00013976004,0.0000755943,0.000016365208,0.000017656128,0.000028718914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9661383,0.02368517,0.0037186008,0.00070581975,0.0044959113,0.0012562191],"domain_scores_gemma":[0.4581985,0.5387499,0.0002837178,0.0018008103,0.0004329561,0.0005341628],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1485063,0.00018524105,0.0010019292,0.00068994536,0.00014418674,0.00009644919,0.0020789453,0.0003707121,0.0015777873],"category_scores_gemma":[0.8501134,0.00012444211,0.0000830714,0.0032395944,0.0016580514,0.00024697674,0.0011558358,0.0022349409,0.000027828599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013582727,0.00016668659,0.000781725,0.00006405112,0.000062376355,0.000008157393,0.00013583682,0.0000036842268,0.000019162148,0.3002184,0.00030683205,0.6980973],"study_design_scores_gemma":[0.0005074963,0.000063121595,0.0022276319,0.00010088891,0.00005571467,0.0000012608901,0.00030891394,0.2208648,0.00019807153,0.7664724,0.0090973405,0.00010233745],"about_ca_topic_score_codex":0.00019735564,"about_ca_topic_score_gemma":0.00025860014,"teacher_disagreement_score":0.7016071,"about_ca_system_score_codex":0.00017616329,"about_ca_system_score_gemma":0.0005825273,"threshold_uncertainty_score":0.99933493},"labels":[],"label_agreement":null},{"id":"W2115499099","doi":"10.1093/jnci/djp079","title":"Dose Escalation Methods in Phase I Cancer Clinical Trials","year":2009,"lang":"en","type":"review","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":861,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; Fondation de France","keywords":"Clinical trial; Medicine; Clinical endpoint; Maximum tolerated dose; Phases of clinical research; Drug; Surrogate endpoint; Pharmacology; Oncology; Drug development; Internal medicine","score_opus":0.9534115106481834,"score_gpt":0.8140813552163118,"score_spread":0.13933015543187166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115499099","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000060257985,0.94026643,0.03505295,0.0011583006,0.020481832,0.0017914533,0.000636208,0.000018921906,0.0005878469],"genre_scores_gemma":[0.0000013137852,0.6759012,0.31613553,0.00038715955,0.007267259,0.0000889193,0.0000023578314,0.000039240025,0.00017704112],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9671364,0.018502053,0.011596515,0.00048916263,0.0019079223,0.00036795033],"domain_scores_gemma":[0.8820696,0.10393598,0.012033784,0.00040298823,0.0012948198,0.0002628515],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08421661,0.00055888476,0.006891569,0.0004987524,0.00011595502,0.00008884594,0.0013890472,0.00093241624,0.00039842728],"category_scores_gemma":[0.42456755,0.00031958334,0.0031796894,0.0011271551,0.0003243099,0.00030350508,0.00015275781,0.0028749036,0.0000067077594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022304266,0.0004868117,0.000004446238,0.0013376501,0.0006199031,0.000011829868,0.000016043576,0.000052915177,0.0000014142495,0.014071044,0.010919903,0.972255],"study_design_scores_gemma":[0.0027586927,0.000097992284,0.000022325825,0.011959451,0.0021695227,0.000035407014,0.0000011372206,0.00005298216,0.0000046283812,0.3511168,0.63152623,0.00025484772],"about_ca_topic_score_codex":0.000018865865,"about_ca_topic_score_gemma":0.00004293351,"teacher_disagreement_score":0.9720001,"about_ca_system_score_codex":0.0015818123,"about_ca_system_score_gemma":0.005247324,"threshold_uncertainty_score":0.9999256},"labels":[],"label_agreement":null},{"id":"W2115837083","doi":"10.1093/jnci/djq463","title":"When Are \"Positive\" Clinical Trials in Oncology Truly Positive?","year":2010,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Clinical trial; Clinical endpoint; Medicine; Food and drug administration; Internal medicine; Randomized controlled trial; Surrogate endpoint; Protocol (science); Oncology; Clinical Oncology; Clinical research; Cancer; Alternative medicine; Pharmacology; Pathology","score_opus":0.7888293470765901,"score_gpt":0.6885523414472793,"score_spread":0.10027700562931086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115837083","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70280236,0.00039517324,0.037291467,0.12468347,0.10845273,0.003043772,0.0020734959,0.00006247644,0.02119507],"genre_scores_gemma":[0.37394723,0.00020218724,0.6035405,0.0064113517,0.015229065,0.00005051596,0.000001495373,0.000050670293,0.00056701],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9893961,0.004931113,0.004001974,0.0002487612,0.0011733483,0.00024871624],"domain_scores_gemma":[0.8843195,0.10867781,0.004766757,0.00024738163,0.0017491683,0.00023937039],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045238994,0.00019481055,0.0015757085,0.00018161873,0.00010988344,0.000045827735,0.00078860734,0.0004130023,0.00041516565],"category_scores_gemma":[0.46229032,0.00012150015,0.00074491807,0.00026832175,0.00051636534,0.00025154097,0.00013664569,0.0021416887,0.000011595439],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0062716147,0.003270708,0.029394643,0.00013874796,0.0017609932,0.00029051467,0.00075341377,0.0002841031,0.006302189,0.6045469,0.17527635,0.17170979],"study_design_scores_gemma":[0.003989375,0.000176904,0.05006837,0.00033269078,0.00022643738,0.000112701324,0.000018549692,0.00007931949,0.0011130705,0.9168984,0.026809137,0.00017501767],"about_ca_topic_score_codex":0.000026556943,"about_ca_topic_score_gemma":0.00044333292,"teacher_disagreement_score":0.566249,"about_ca_system_score_codex":0.000439695,"about_ca_system_score_gemma":0.0015878003,"threshold_uncertainty_score":0.98312736},"labels":[],"label_agreement":null},{"id":"W2115961074","doi":"10.1158/1078-0432.ccr-14-1760","title":"The Neoadjuvant Model Is Still the Future for Drug Development in Breast Cancer","year":2015,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Center for Advancing Translational Sciences; National Cancer Institute","keywords":"Lapatinib; Medicine; Trastuzumab; Breast cancer; Oncology; Clinical trial; Internal medicine; Neoadjuvant therapy; Cancer; Clinical endpoint; Surrogate endpoint; Regimen; Hazard ratio; Confidence interval","score_opus":0.8736747486636635,"score_gpt":0.7238382028301892,"score_spread":0.14983654583347428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115961074","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20397723,0.012667488,0.044807963,0.7022912,0.014439908,0.015784657,0.0026775403,0.0002870779,0.0030669428],"genre_scores_gemma":[0.15101229,0.015918858,0.7584073,0.012064873,0.020376977,0.018484524,0.000007911376,0.0005045213,0.023222752],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992092,0.002693349,0.0018874351,0.0007172502,0.0015670308,0.0010429425],"domain_scores_gemma":[0.8953916,0.101587705,0.00024666556,0.00095106405,0.0013600675,0.00046289593],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04894222,0.00023670313,0.0007173843,0.000060176946,0.00037848201,0.00014022841,0.0014519107,0.00028294392,0.00015881346],"category_scores_gemma":[0.05026502,0.00011897321,0.00021439782,0.00052226015,0.00096684566,0.00006206922,0.0005708784,0.0018625373,0.00003861993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002723078,0.00040165972,0.0033664936,0.00013264423,0.0001500734,0.000006602229,0.0017636692,0.00010923847,0.000004241781,0.043612726,0.5091984,0.43853116],"study_design_scores_gemma":[0.0026094383,0.000075501164,0.0019548656,0.00018178565,0.00003259766,0.0000011594663,0.00069211685,0.011988101,0.0000780386,0.83899206,0.14316079,0.00023356211],"about_ca_topic_score_codex":0.00019385798,"about_ca_topic_score_gemma":0.0016014596,"teacher_disagreement_score":0.79537934,"about_ca_system_score_codex":0.00047933133,"about_ca_system_score_gemma":0.0027360562,"threshold_uncertainty_score":0.97931415},"labels":[],"label_agreement":null},{"id":"W2116181250","doi":"10.6000/1929-6029.2015.04.01.13","title":"Use of Geometric Mean in Bioequivalence Trials","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Confusion; Logarithm; Normality; Geometric mean; Mathematics; Transformation (genetics); Statistics; Logarithmic scale; Econometrics; Scale (ratio); Medicine; Psychology; Pharmacology; Geography","score_opus":0.9369601174424793,"score_gpt":0.7400837680119565,"score_spread":0.1968763494305228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116181250","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10876433,0.00033817958,0.8810325,0.0036295042,0.0040136874,0.000629915,0.00061347644,0.000009778612,0.0009686318],"genre_scores_gemma":[0.25871712,0.0010701644,0.73950005,0.000079107806,0.0005270085,0.0000075135167,0.0000019619579,0.000022109833,0.00007497669],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97708416,0.0073636873,0.004903444,0.00026457466,0.009910038,0.0004741072],"domain_scores_gemma":[0.59431386,0.39796913,0.0012977471,0.00030643027,0.0054112226,0.0007016254],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11776343,0.00013598167,0.0011805492,0.0022667686,0.000013075809,0.00006467608,0.0014410325,0.0002444636,0.0008912309],"category_scores_gemma":[0.92383623,0.000104872655,0.00012140513,0.001293155,0.0007148214,0.00016804328,0.00036026232,0.0017327894,0.000012805112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032677003,0.0024551656,0.01661663,0.00019626002,0.00032391635,0.005271501,0.0008409943,0.00007375493,0.00016448201,0.5173168,0.03578653,0.41768625],"study_design_scores_gemma":[0.003125764,0.0005265329,0.002352362,0.0008478039,0.000018344263,0.000056565455,0.00022461066,0.0014896482,0.0003945154,0.98983943,0.0010222825,0.00010212511],"about_ca_topic_score_codex":0.00020570104,"about_ca_topic_score_gemma":0.000093741844,"teacher_disagreement_score":0.80607283,"about_ca_system_score_codex":0.00043833273,"about_ca_system_score_gemma":0.00137651,"threshold_uncertainty_score":0.9758353},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2116750865","doi":"10.1093/aje/kwn104","title":"On the Estimation of Additive Interaction by Use of the Four-by-two Table and Beyond","year":2008,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":278,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation","keywords":"Confidence interval; Table (database); Row; Set (abstract data type); Computer science; Statistics; Perspective (graphical); Interval (graph theory); Mathematics; Data mining; Artificial intelligence; Combinatorics; Database","score_opus":0.4928062528372004,"score_gpt":0.5403994502683522,"score_spread":0.04759319743115181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116750865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66797614,0.00005987461,0.32667398,0.0043129474,0.0003640708,0.00020585592,0.00017402356,0.0000039671163,0.00022915418],"genre_scores_gemma":[0.65164065,0.00021444669,0.34670284,0.0013365253,0.000054699456,0.0000036454694,7.1745666e-7,0.000011296815,0.00003515945],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936152,0.0046022087,0.0013624906,0.00011797746,0.00015203338,0.0001500514],"domain_scores_gemma":[0.7469386,0.2499311,0.0027255376,0.00019261116,0.00016006482,0.00005210698],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051883687,0.00010547892,0.00091082876,0.000040012386,0.000057237557,0.000002131514,0.00018093623,0.00004982181,0.00009403559],"category_scores_gemma":[0.3511679,0.00005376829,0.00012977341,0.00015989553,0.0013793868,0.000070582464,0.000044768854,0.0004013587,8.5809137e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021220928,0.0007389027,0.010243548,0.000054738484,0.00094773376,0.000009671157,0.000879301,0.0013871237,0.003997108,0.24576995,0.5402874,0.19356246],"study_design_scores_gemma":[0.000666199,0.0020998782,0.0026562822,0.0001716031,0.00017150256,0.00017541189,0.0002466612,0.002994117,0.0031661906,0.98648673,0.0010572841,0.000108156426],"about_ca_topic_score_codex":0.00007468774,"about_ca_topic_score_gemma":0.0000013364378,"teacher_disagreement_score":0.74071676,"about_ca_system_score_codex":0.00003091116,"about_ca_system_score_gemma":0.000040677718,"threshold_uncertainty_score":0.6542975},"labels":[],"label_agreement":null},{"id":"W2116831767","doi":"10.1158/1078-0432.ccr-09-1961","title":"Approaches to Phase 1 Clinical Trial Design Focused on Safety, Efficiency, and Selected Patient Populations: A Report from the Clinical Trial Design Task Force of the National Cancer Institute Investigational Drug Steering Committee","year":2010,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":199,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Institutes of Health","keywords":"Clinical trial; Medicine; Clinical study design; Population; Drug development; Investigational Drugs; Phases of clinical research; Patient safety; Intensive care medicine; Medical physics; Drug; Oncology; Pharmacology; Internal medicine; Health care","score_opus":0.9461285919310349,"score_gpt":0.6823623987532028,"score_spread":0.2637661931778321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116831767","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8349006,0.0000889661,0.1237226,0.014969151,0.01099216,0.014225092,0.00077038957,0.00010060667,0.00023044617],"genre_scores_gemma":[0.46026346,0.00012115963,0.526312,0.0013875957,0.008810285,0.0027317237,0.000028406326,0.00012100321,0.00022438452],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9669268,0.019928068,0.007330248,0.0016004979,0.003449702,0.0007646853],"domain_scores_gemma":[0.63078904,0.3625194,0.0020937712,0.0017514935,0.0019644431,0.0008818351],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08384932,0.00042648168,0.0016278806,0.00014298798,0.0007671227,0.00016684132,0.0015559503,0.0007401212,0.00022389548],"category_scores_gemma":[0.56797373,0.0002660551,0.0005950127,0.0013745348,0.0036540248,0.00014471619,0.0008276859,0.0044926843,0.000013253789],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6702516,0.010222118,0.009353511,0.0000905517,0.0010107826,0.000028009257,0.0005926752,0.0015431251,0.0001660646,0.044744164,0.08223962,0.17975776],"study_design_scores_gemma":[0.2471476,0.010076497,0.01582357,0.00065408123,0.0005130778,0.0000053485637,0.00006326619,0.015563207,0.0004889071,0.7013312,0.00746499,0.0008682408],"about_ca_topic_score_codex":0.00033489257,"about_ca_topic_score_gemma":0.00053771574,"teacher_disagreement_score":0.65658706,"about_ca_system_score_codex":0.00020593913,"about_ca_system_score_gemma":0.0042982525,"threshold_uncertainty_score":0.99997914},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2117734248","doi":"10.1200/jco.2014.55.9344","title":"Twenty-Twenty Hindsight: An Adjuvant Breast Cancer Trial Through the Retrospectoscope","year":2014,"lang":"en","type":"letter","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Clinical Oncology Group; Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; University of Toronto; McMaster University; Juravinski Hospital; Juravinski Cancer Centre","funders":"","keywords":"Medicine; Breast cancer; Hazard ratio; Oncology; Internal medicine; Cyclophosphamide; Cancer; Sample size determination; Adjuvant; Clinical trial; Chemotherapy; Adjuvant chemotherapy; Surgery; Confidence interval; Statistics","score_opus":0.6772385168178936,"score_gpt":0.6476783877179321,"score_spread":0.02956012909996153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117734248","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018323531,0.00031885895,0.0125575755,0.9256951,0.05267995,0.0016829935,0.0004131003,0.00006978326,0.004750288],"genre_scores_gemma":[0.0007033681,0.0012627057,0.21320792,0.6142003,0.16891247,0.00006833225,0.0000091227075,0.00023255922,0.0014032371],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.957928,0.02270368,0.014709904,0.001054271,0.0024916083,0.0011125315],"domain_scores_gemma":[0.75087464,0.2287201,0.016901994,0.0016129857,0.0013666103,0.0005236457],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.04013226,0.00087882293,0.009568088,0.00014239548,0.00022728975,0.0001389245,0.0031510503,0.0057431874,0.0041767578],"category_scores_gemma":[0.21194603,0.00047683672,0.0030349179,0.00032128402,0.0016733997,0.00028252642,0.0004059304,0.018509079,0.0001009677],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.024025414,0.0014074683,0.00016802219,0.00012480297,0.001222883,0.0009992616,0.00007269995,0.000002237788,0.0000014260878,0.0029925387,0.93735456,0.03162867],"study_design_scores_gemma":[0.030608378,0.008594978,0.00046254805,0.00029749508,0.002017244,0.00023494058,0.000017618391,0.000021327127,0.00000255834,0.38007534,0.5772805,0.00038703755],"about_ca_topic_score_codex":0.0000754062,"about_ca_topic_score_gemma":0.000050672694,"teacher_disagreement_score":0.3770828,"about_ca_system_score_codex":0.00052565336,"about_ca_system_score_gemma":0.0031754936,"threshold_uncertainty_score":0.9997683},"labels":[],"label_agreement":null},{"id":"W2118250868","doi":"10.1093/jnci/djn267","title":"Speeding up the Evaluation of New Agents in Cancer","year":2008,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Cancer Research UK","keywords":"Computer science; Medicine; Clinical trial; Medical physics; Risk analysis (engineering); Pathology","score_opus":0.9361033159653933,"score_gpt":0.6900978641711965,"score_spread":0.24600545179419686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118250868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9605716,0.0010519838,0.0043332083,0.01123821,0.018552212,0.00087170454,0.00010880995,0.000008295543,0.003263965],"genre_scores_gemma":[0.95022804,0.0005988916,0.044025064,0.0008257009,0.0035673075,0.000023159813,2.5259845e-7,0.000018487783,0.0007131051],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99590987,0.00043340778,0.001070446,0.000102622216,0.0023562268,0.00012744384],"domain_scores_gemma":[0.99381167,0.0035146347,0.001130118,0.00012037968,0.0013653426,0.000057842728],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063370042,0.00010092001,0.0003303183,0.00009593961,0.000099339224,0.000010610969,0.0005067458,0.00007236354,0.00039944047],"category_scores_gemma":[0.05311899,0.000055751305,0.00017812868,0.00041078293,0.0001832279,0.00017938054,0.00006453013,0.00038419568,0.0000016724794],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015514824,0.0008424124,0.04907109,0.00028218102,0.0015717639,0.000021916623,0.0065895254,0.09897174,0.0032154543,0.15743303,0.5251324,0.15531696],"study_design_scores_gemma":[0.0032223463,0.000040548817,0.07822957,0.0005323916,0.00029190423,0.000046725334,0.000032346066,0.0022250495,0.0029965483,0.9055849,0.006674804,0.00012288008],"about_ca_topic_score_codex":0.00016806328,"about_ca_topic_score_gemma":0.00017785399,"teacher_disagreement_score":0.74815184,"about_ca_system_score_codex":0.00066830363,"about_ca_system_score_gemma":0.0019903085,"threshold_uncertainty_score":0.954857},"labels":[],"label_agreement":null},{"id":"W2118262583","doi":"10.1002/jclp.10217","title":"Recommendations for applying tests of equivalence","year":2003,"lang":"en","type":"article","venue":"Journal of Clinical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; York University","funders":"","keywords":"Equivalence (formal languages); Psychology; Statistics; Test (biology); Null hypothesis; Population; Mathematics; Social psychology; Econometrics; Discrete mathematics; Medicine","score_opus":0.9165425026823134,"score_gpt":0.7543093287273303,"score_spread":0.16223317395498316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118262583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015432492,0.00009647425,0.9652277,0.0044589248,0.0069462336,0.0005787513,0.000037360394,0.000014553129,0.007207504],"genre_scores_gemma":[0.05610057,0.000173554,0.9420699,0.000998261,0.0005259732,0.00001496379,1.8661878e-7,0.00002143755,0.00009519529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926145,0.0018891263,0.0047893664,0.00022580808,0.00024169478,0.0002395181],"domain_scores_gemma":[0.8373913,0.1587583,0.0027529222,0.00036353583,0.00055560045,0.0001783165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020912556,0.00012238158,0.0012759758,0.000097363736,0.0000365773,0.0000064344536,0.00038227,0.00029855667,0.00048614852],"category_scores_gemma":[0.45064604,0.000095919364,0.00057648227,0.00017267482,0.00029758504,0.000058153386,0.000025326404,0.0005980247,0.000007750751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015590505,0.003540638,0.008485169,0.00025933393,0.00053868693,0.000020108939,0.00007324642,0.0000030985298,0.0009601051,0.55118734,0.1394708,0.29390243],"study_design_scores_gemma":[0.003025972,0.0013787744,0.0012574282,0.00011584087,0.00014070648,0.00004570878,0.000024499517,0.0000087850785,0.00016937606,0.9650521,0.02868928,0.00009150348],"about_ca_topic_score_codex":1.7110618e-7,"about_ca_topic_score_gemma":4.954547e-7,"teacher_disagreement_score":0.42973348,"about_ca_system_score_codex":0.00001084234,"about_ca_system_score_gemma":0.000109325454,"threshold_uncertainty_score":0.72479165},"labels":[],"label_agreement":null},{"id":"W2118852500","doi":"10.1093/beheco/arn020","title":"Time for some a priori thinking about post hoc testing","year":2008,"lang":"en","type":"article","venue":"Behavioral Ecology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":602,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"University of Glasgow","keywords":"Biology; A priori and a posteriori; Post hoc; Post-hoc analysis; Statistics; Mathematics; Epistemology; Internal medicine","score_opus":0.6153986132544237,"score_gpt":0.5598863649413716,"score_spread":0.055512248313052126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118852500","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941709,0.000025972358,0.0025833675,0.0003169026,0.00096011156,0.0011474459,0.00012898855,0.0002872304,0.0003790706],"genre_scores_gemma":[0.042334676,0.000004778757,0.9555046,0.0005242292,0.0005458869,0.0001994784,0.000006286499,0.00006710226,0.0008129928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975452,0.0003503625,0.0008835791,0.00043911746,0.00021321303,0.00056854554],"domain_scores_gemma":[0.964027,0.034881264,0.0003372057,0.00036391927,0.000247054,0.00014359874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016836798,0.00022250188,0.0007738843,0.0000773022,0.00031117865,0.000019759877,0.00035209476,0.0003032446,0.00041214764],"category_scores_gemma":[0.049081117,0.00020561523,0.00017660749,0.00013807355,0.00033750254,0.00009094081,0.00016017903,0.00030188044,0.00018841533],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026974052,0.010289436,0.0504006,0.0009474647,0.00041006503,0.002487904,0.0048015933,0.000019801962,0.040312335,0.5858542,0.040145382,0.26163384],"study_design_scores_gemma":[0.0023508498,0.0026495382,0.019320732,0.000053839933,0.00027989663,0.00015781773,0.000039732513,0.00026152382,0.0006277815,0.97316635,0.00062153145,0.00047039497],"about_ca_topic_score_codex":0.000011183969,"about_ca_topic_score_gemma":0.000010219318,"teacher_disagreement_score":0.9529212,"about_ca_system_score_codex":0.00009679824,"about_ca_system_score_gemma":0.00016966442,"threshold_uncertainty_score":0.9589289},"labels":[],"label_agreement":null},{"id":"W2119209233","doi":"10.1186/1471-2288-11-164","title":"Stopping rules employing response rates, time to progression, and early progressive disease for phase II oncology trials","year":2011,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Clinical Oncology Group; McMaster University; Juravinski Hospital; Juravinski Cancer Centre","funders":"","keywords":"Medicine; Early stopping; Clinical endpoint; Stage (stratigraphy); Clinical trial; Oncology; Relative risk; Disease; Progressive disease; Internal medicine; Surrogate endpoint; Confidence interval; Computer science; Artificial intelligence","score_opus":0.9617852519897551,"score_gpt":0.7777558971622159,"score_spread":0.18402935482753913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119209233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20882034,0.001000991,0.77599,0.0051625934,0.00060550147,0.007685617,0.00019837548,0.00021644298,0.00032012543],"genre_scores_gemma":[0.0017095135,0.00005247897,0.99305874,0.00035079324,0.0007938111,0.0032390007,0.000004542887,0.00009622811,0.0006949108],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82191116,0.16957924,0.0030891346,0.0014939915,0.0021087572,0.0018177174],"domain_scores_gemma":[0.1710286,0.8230581,0.00066681707,0.0009059695,0.0011479134,0.0031925824],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.35315308,0.00039883723,0.0028375476,0.00063409016,0.00063824025,0.0000579572,0.0010082647,0.0008413583,0.003960066],"category_scores_gemma":[0.9793455,0.00028775734,0.0003287849,0.0005375921,0.002071943,0.00009898215,0.0013860433,0.0012511847,0.000119224394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.1314074,0.0028143954,0.00020787475,0.00081937894,0.0002843793,0.0005988704,0.0025679173,7.4671156e-8,0.003144733,0.065288976,0.010350567,0.7825154],"study_design_scores_gemma":[0.009512245,0.014828242,0.0010141163,0.00092606235,0.00022934262,0.000034459295,0.00020404195,0.0003340865,0.0021650917,0.95783496,0.012480207,0.00043714698],"about_ca_topic_score_codex":0.0000149157095,"about_ca_topic_score_gemma":0.000006071581,"teacher_disagreement_score":0.892546,"about_ca_system_score_codex":0.00015889342,"about_ca_system_score_gemma":0.0029342033,"threshold_uncertainty_score":0.99995744},"labels":[],"label_agreement":null},{"id":"W2119513306","doi":"10.1111/j.0006-341x.2000.00879.x","title":"Sample Size Determination for Testing Whether an Identified Treatment Is Best","year":2000,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Normality; Sample size determination; Statistics; Wilcoxon signed-rank test; Biometrics; Mathematics; Mann–Whitney U test; Sample (material); Normality test; Statistical hypothesis testing; Computer science; Artificial intelligence","score_opus":0.7958203069179602,"score_gpt":0.6066968572577125,"score_spread":0.18912344966024774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119513306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2820104,0.00008007046,0.7095717,0.00027290086,0.001011344,0.0023084225,0.0016509593,0.00031247645,0.0027817334],"genre_scores_gemma":[0.010410112,0.000026510575,0.98623276,0.00012124521,0.0003331095,0.00010372397,0.00000445438,0.000046775625,0.0027213304],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981226,0.00021653576,0.0006662095,0.0003922777,0.00030762568,0.00029476554],"domain_scores_gemma":[0.8275353,0.17141941,0.00020492075,0.00046318115,0.00022351311,0.00015368905],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016730101,0.00018166404,0.00040245627,0.00027816996,0.00012403405,0.000102737664,0.00019614892,0.00017613808,0.001291917],"category_scores_gemma":[0.23940408,0.00015333098,0.00012332748,0.001752432,0.000061943836,0.00008860831,0.000018825729,0.00005671545,0.000073662784],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045426077,0.0006239164,0.00038614613,0.00005613467,0.000028127019,0.0000019989986,0.00013032317,3.0817944e-7,0.00073098077,0.0013087807,0.00036698766,0.99632084],"study_design_scores_gemma":[0.0019106714,0.0016352446,0.0009860698,0.00003881153,0.00025415936,0.0000031629634,0.000049782317,0.004239274,0.0059403726,0.9767527,0.007850332,0.0003394382],"about_ca_topic_score_codex":0.0000771583,"about_ca_topic_score_gemma":0.0000048103943,"teacher_disagreement_score":0.99598145,"about_ca_system_score_codex":0.00013007232,"about_ca_system_score_gemma":0.000034687713,"threshold_uncertainty_score":0.99962103},"labels":[],"label_agreement":null},{"id":"W2120330210","doi":"10.18433/j3vc8j","title":"The revised EMA guideline for the investigation of bioequivalence for immediate release oral formulations with systemic action","year":2012,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Cmax; Guideline; Medicine; Pharmacology; Bioavailability; Mathematics","score_opus":0.7590541181696229,"score_gpt":0.6469479455553726,"score_spread":0.11210617261425027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120330210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1348174,0.0029001017,0.84289706,0.014466674,0.0023194673,0.0024332644,0.00010406424,0.000025321926,0.000036631078],"genre_scores_gemma":[0.6446144,0.00059712626,0.3533935,0.00035734483,0.000940429,0.00006587999,5.952297e-7,0.000012661882,0.000018093733],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963084,0.00058298296,0.0017627921,0.00015315623,0.00076040556,0.00043224968],"domain_scores_gemma":[0.93809867,0.059128396,0.001522822,0.00015979065,0.0008040809,0.0002862658],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020429958,0.00015873733,0.00040565938,0.00006809757,0.0005431229,0.000069610214,0.0005828178,0.000041687952,0.000036233403],"category_scores_gemma":[0.033203162,0.00007086936,0.00023086662,0.00044476893,0.00091378804,0.00047369322,0.000044091892,0.0002610613,0.0000014007809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00848111,0.00067153637,0.011739983,0.002056551,0.00084500335,0.000003105078,0.0011130866,0.0007675158,0.10298816,0.24738106,0.029420422,0.5945325],"study_design_scores_gemma":[0.015351794,0.0018650178,0.00057529606,0.00087020616,0.00510783,0.00026736414,0.0014905467,0.18021235,0.22445793,0.4459455,0.123142175,0.0007139787],"about_ca_topic_score_codex":0.0000030034817,"about_ca_topic_score_gemma":9.794419e-7,"teacher_disagreement_score":0.5938185,"about_ca_system_score_codex":0.00006224823,"about_ca_system_score_gemma":0.00023807335,"threshold_uncertainty_score":0.9749406},"labels":[],"label_agreement":null},{"id":"W2121029321","doi":"10.1200/jco.2001.19.3.785","title":"Application of a New Multinomial Phase II Stopping Rule Using Response and Early Progression","year":2001,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Multinomial distribution; Medicine; Early stopping; Clinical trial; Statistics; Internal medicine; Artificial intelligence; Computer science; Mathematics","score_opus":0.7528928351643551,"score_gpt":0.711611258546088,"score_spread":0.041281576618267146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121029321","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8059501,0.00007621749,0.19193432,0.001101289,0.00057988643,0.00027274626,0.0000030418903,0.000009413089,0.00007296171],"genre_scores_gemma":[0.3653945,0.000054704822,0.63342375,0.00009656443,0.0009730441,0.0000017956559,6.1145656e-8,0.00001473594,0.000040850835],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915284,0.002883554,0.004735449,0.000235576,0.0003944083,0.00022262028],"domain_scores_gemma":[0.91066,0.08334935,0.0049032415,0.00025079833,0.0004045319,0.00043202142],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021908727,0.00014130138,0.0017998165,0.00012261276,0.00007399777,0.000010745647,0.00023862126,0.0005104237,0.000046989055],"category_scores_gemma":[0.2403882,0.00010578828,0.00032090893,0.00017095776,0.0003312894,0.00011360124,0.000151327,0.0007853756,0.0000016765567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.033842053,0.0029304777,0.00818358,0.000034607765,0.00013177651,0.0001003619,0.00023312004,0.000005502174,0.007553675,0.0013155667,0.00032010663,0.94534916],"study_design_scores_gemma":[0.0627458,0.059163973,0.07009294,0.00082153926,0.0013220401,0.0006001463,0.00020527138,0.0072171288,0.0017652876,0.7692914,0.026253182,0.00052125665],"about_ca_topic_score_codex":0.000013569006,"about_ca_topic_score_gemma":0.0000016305522,"teacher_disagreement_score":0.9448279,"about_ca_system_score_codex":0.00007095722,"about_ca_system_score_gemma":0.00078716164,"threshold_uncertainty_score":0.76601034},"labels":[],"label_agreement":null},{"id":"W2121734380","doi":"10.6000/1929-6029.2015.04.01.8","title":"On the Translation of a Treatment's Effect on Disease Progression Into an Effect on Overall Survival","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Tumor progression; Medicine; Hazard ratio; Oncology; Progression-free survival; Bevacizumab; Disease; Internal medicine; Proportional hazards model; Cancer; Overall survival; Chemotherapy; Confidence interval","score_opus":0.58865762749821,"score_gpt":0.6797552771109773,"score_spread":0.09109764961276723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121734380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92201406,0.00006717602,0.06450967,0.006146717,0.002823603,0.0015509718,0.00034134957,0.000019484025,0.0025269887],"genre_scores_gemma":[0.9527369,0.00008012745,0.046206925,0.00012264385,0.0007251333,0.000047678885,0.000011060444,0.000036931848,0.000032561602],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9834112,0.008250272,0.0012002644,0.00026859227,0.00657437,0.0002952883],"domain_scores_gemma":[0.78590906,0.21206912,0.0003497124,0.00027505317,0.0008290014,0.00056803686],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029385496,0.00020942382,0.00061939866,0.00041651487,0.00005406529,0.00006250914,0.0008785596,0.00016128676,0.00033805324],"category_scores_gemma":[0.394638,0.000109422035,0.00013673639,0.00020410107,0.00046864114,0.00006726558,0.00006603444,0.0012305944,0.000020147318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028173633,0.0023058604,0.0013006566,0.00010815055,0.00022321992,0.0011056635,0.00047629134,0.00008236617,0.000084907224,0.43564314,0.0018759029,0.52862024],"study_design_scores_gemma":[0.0059664478,0.027280843,0.0014202882,0.0015977697,0.00004067662,0.000006449745,0.000031741678,0.004810846,0.0007564149,0.95774084,0.00023916304,0.00010849434],"about_ca_topic_score_codex":0.000039756655,"about_ca_topic_score_gemma":0.000021111426,"teacher_disagreement_score":0.5285117,"about_ca_system_score_codex":0.00063254376,"about_ca_system_score_gemma":0.0006248863,"threshold_uncertainty_score":0.9994519},"labels":[],"label_agreement":null},{"id":"W2122343697","doi":"10.1093/aje/kwn003","title":"Detecting Trends in Noisy Data Series: Application to Biomarker Series","year":2008,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Series (stratigraphy); Bayesian probability; Bayes' theorem; Time series; Statistics; Data mining; Machine learning; Econometrics; Artificial intelligence; Mathematics","score_opus":0.6548799209541651,"score_gpt":0.5978180136286868,"score_spread":0.057061907325478334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122343697","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14590068,0.000089428904,0.843207,0.009443654,0.0005286288,0.00018833618,0.00005918604,0.000035229445,0.00054787064],"genre_scores_gemma":[0.15260679,0.00011467435,0.8459888,0.0008859045,0.0003108462,0.000009869036,0.0000024187625,0.00002526907,0.00005539721],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9928868,0.0036216984,0.0024941934,0.00039840472,0.00016671613,0.00043218536],"domain_scores_gemma":[0.92374897,0.07293693,0.0019393767,0.00093351444,0.00016423696,0.00027694262],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015372407,0.0001867346,0.0016305947,0.00034433499,0.00006546775,0.0000038325775,0.0007796476,0.000102278784,0.00009532437],"category_scores_gemma":[0.2945778,0.00014862027,0.00012323371,0.0008868566,0.0006854283,0.00018691176,0.00023893209,0.00044797256,0.000012957312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017101776,0.00020844703,0.04679464,0.000028790027,0.0001996712,0.00012972696,0.00048814897,0.000074900345,0.0010785804,0.014373213,0.010574895,0.9243388],"study_design_scores_gemma":[0.0014150128,0.0037779007,0.097915694,0.000166346,0.00015783342,0.003041205,0.0009803242,0.0009558851,0.0002589422,0.8669837,0.023712218,0.0006349298],"about_ca_topic_score_codex":0.00010362883,"about_ca_topic_score_gemma":0.00006621017,"teacher_disagreement_score":0.92370385,"about_ca_system_score_codex":0.000078207726,"about_ca_system_score_gemma":0.000067602785,"threshold_uncertainty_score":0.71136427},"labels":[],"label_agreement":null},{"id":"W2122813583","doi":"10.1200/jco.2007.14.1044","title":"Phase II Stopping Rules That Employ Response Rates and Early Progression","year":2008,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Juravinski Cancer Centre; Queen's University","funders":"Amgen","keywords":"Medicine; Clinical endpoint; Phases of clinical research; Type I and type II errors; Stage (stratigraphy); Statistics; End point; Clinical trial; Mathematics; Internal medicine","score_opus":0.8084065580692215,"score_gpt":0.704092019154906,"score_spread":0.10431453891431541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122813583","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98604035,0.00031430158,0.0075554713,0.0039079715,0.0015657664,0.0002630747,0.000008897248,0.000028528093,0.00031565357],"genre_scores_gemma":[0.4178419,0.00052129105,0.5800037,0.0004365255,0.0009801214,0.0000050102553,1.08202514e-7,0.000026835454,0.00018452843],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98755246,0.0068354825,0.004370837,0.00030754894,0.0005940904,0.00033955224],"domain_scores_gemma":[0.79223293,0.20337401,0.003227482,0.00026377407,0.00039237677,0.0005094273],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031167619,0.00021011116,0.0024225714,0.0001386439,0.00022287856,0.000019635412,0.00033972142,0.00064113666,0.00012366765],"category_scores_gemma":[0.4045291,0.00014033372,0.00046461532,0.00011764972,0.00092834403,0.0001808218,0.0002294343,0.0014088379,0.000011036371],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07251133,0.0149836205,0.038479194,0.00010539209,0.0006902796,0.0038905144,0.0011201955,6.2944827e-7,0.0011369896,0.008429011,0.015607906,0.84304494],"study_design_scores_gemma":[0.034579508,0.09376125,0.11111592,0.0005958753,0.00052379473,0.0011442658,0.0001447499,0.000070854905,0.0008872018,0.72182167,0.034911785,0.00044310678],"about_ca_topic_score_codex":0.0000018321986,"about_ca_topic_score_gemma":8.657828e-7,"teacher_disagreement_score":0.84260184,"about_ca_system_score_codex":0.000057741847,"about_ca_system_score_gemma":0.0007333238,"threshold_uncertainty_score":0.9976168},"labels":[],"label_agreement":null},{"id":"W2123532766","doi":"10.1200/jco.2007.13.5913","title":"Review of Phase II Trial Designs Used in Studies of Molecular Targeted Agents: Outcomes and Predictors of Success in Phase III","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Regional Health Centre; Queen's University","funders":"National Cancer Institute; American Association for Cancer Research","keywords":"Medicine; Phase (matter); Oncology; Internal medicine","score_opus":0.8553149010815388,"score_gpt":0.7327753985139422,"score_spread":0.1225395025675966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123532766","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015237933,0.9787604,0.0009232025,0.00014815615,0.001997105,0.002733004,0.0001522316,0.0000049525015,0.00004299076],"genre_scores_gemma":[0.00023045679,0.9239231,0.07532203,0.00015248226,0.0002721131,0.00004165358,0.0000029684059,0.000046681027,0.000008515395],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9528969,0.0155442385,0.029799405,0.00047375457,0.00091881515,0.0003669042],"domain_scores_gemma":[0.7612075,0.21372554,0.023415497,0.0005270762,0.0008391063,0.00028524097],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035919085,0.00055501173,0.029057339,0.0005973131,0.000020898668,0.0000026863293,0.00082083413,0.0012780561,0.00010098101],"category_scores_gemma":[0.56651634,0.00036448592,0.0026763268,0.00074056577,0.0013051484,0.00009093404,0.0003351262,0.0020139003,3.919216e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019312112,0.030244147,0.00028075153,0.10249549,0.00524201,0.0008842291,0.00017491794,6.597249e-7,0.0000038780245,0.00064482435,0.0023534952,0.83836347],"study_design_scores_gemma":[0.46347043,0.08953789,0.00007045653,0.2943499,0.016053166,0.000112491376,0.00008967265,0.000009110455,0.000032012424,0.047932208,0.087489225,0.0008534061],"about_ca_topic_score_codex":0.0000074507284,"about_ca_topic_score_gemma":0.0000071372265,"teacher_disagreement_score":0.83751005,"about_ca_system_score_codex":0.00016457199,"about_ca_system_score_gemma":0.00236996,"threshold_uncertainty_score":0.99988073},"labels":[],"label_agreement":null},{"id":"W2123852523","doi":"10.1079/ahr200474","title":"The design of randomized controlled trials of veterinary vaccines","year":2004,"lang":"en","type":"review","venue":"Animal Health Research Reviews","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Randomized controlled trial; Clinical trial; Medicine; Outcome (game theory); Clinical study design; Vaccine trial; Vaccine efficacy; Intensive care medicine; Sample size determination; Veterinary medicine; Vaccination; Immunology; Pathology; Statistics; Mathematics","score_opus":0.97179774970907,"score_gpt":0.7806499980384358,"score_spread":0.19114775167063414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123852523","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.887838e-8,0.9351693,0.009386707,0.00035424056,0.00034662767,0.05442284,0.000114302515,0.000020240142,0.00018567256],"genre_scores_gemma":[2.0125829e-7,0.75624204,0.23750497,0.000017609093,0.00034872064,0.0056347004,0.0000028993265,0.00007845052,0.00017040105],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.3703885,0.575632,0.047722142,0.0011972403,0.003181371,0.0018787448],"domain_scores_gemma":[0.06455814,0.914015,0.017913045,0.0018614561,0.0012043756,0.00044797864],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.68970877,0.0007510389,0.07140298,0.00046355976,0.00031107632,0.000058809535,0.0016713981,0.0005423087,0.0002586845],"category_scores_gemma":[0.9266659,0.0003075579,0.008626802,0.0011511648,0.0010517625,0.0000422578,0.00040311768,0.0018004867,0.00006186601],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04938812,0.00018038151,6.6707515e-9,0.17993766,0.00078643975,0.000004349866,0.000021491018,2.4424379e-8,6.289819e-7,0.060568932,0.0034486859,0.70566326],"study_design_scores_gemma":[0.06487021,0.0021691066,2.9602893e-8,0.11680018,0.0017936995,0.0000093684985,0.000007268334,0.000005471904,8.2954654e-7,0.233257,0.5808943,0.00019253942],"about_ca_topic_score_codex":0.000048760256,"about_ca_topic_score_gemma":0.00000162479,"teacher_disagreement_score":0.70547074,"about_ca_system_score_codex":0.00028528494,"about_ca_system_score_gemma":0.004114834,"threshold_uncertainty_score":0.99993765},"labels":[],"label_agreement":null},{"id":"W2124612672","doi":"10.1177/0962280212436447","title":"Minimal sufficient balance—a new strategy to balance baseline covariates and preserve randomness of treatment allocation","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Covariate; Categorical variable; Randomization; Baseline (sea); Restricted randomization; Randomness; Statistics; Randomized controlled trial; Medicine; Mathematics; Surgery","score_opus":0.6337766155694683,"score_gpt":0.6851863314577871,"score_spread":0.051409715888318774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124612672","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012133463,0.00040320115,0.9828664,0.001471446,0.00037153868,0.0014382722,0.0001924127,0.00003296987,0.0010902729],"genre_scores_gemma":[0.089288056,0.00023612488,0.90944713,0.00008432268,0.0004552401,0.00021955746,0.00000869457,0.000041562762,0.00021932108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97533524,0.01776009,0.0021838506,0.0008307165,0.0024075569,0.0014825271],"domain_scores_gemma":[0.61731297,0.37913826,0.0001935879,0.00071799115,0.0004782811,0.0021588972],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06395736,0.00032571144,0.0014494564,0.0003053347,0.000098220255,0.00004615737,0.00054344407,0.00040307353,0.003274916],"category_scores_gemma":[0.61901015,0.00024408927,0.00008284411,0.001013301,0.00091533875,0.00008585429,0.00038835366,0.0009167476,0.00002608506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019427809,0.001416553,0.0031271167,0.00041815185,0.00007947448,0.000031481868,0.0005654806,0.000008107209,0.0010059123,0.52222127,0.0023375442,0.46684614],"study_design_scores_gemma":[0.007352473,0.003174561,0.012598608,0.00054831064,0.0000990958,0.000014475529,0.00037915824,0.026818996,0.0036902304,0.9432756,0.001602287,0.0004462277],"about_ca_topic_score_codex":0.00051975413,"about_ca_topic_score_gemma":0.00004041615,"teacher_disagreement_score":0.5550528,"about_ca_system_score_codex":0.00026645281,"about_ca_system_score_gemma":0.0007917726,"threshold_uncertainty_score":0.9976362},"labels":[],"label_agreement":null},{"id":"W2125296802","doi":"10.1002/sim.5327","title":"An efficient alternative to the stratified Cox model analysis","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Gilead Sciences (Canada)","funders":"","keywords":"Stratum; Proportional hazards model; Statistics; Inference; Categorical variable; Sample size determination; Hazard ratio; Econometrics; Mathematics; Computer science; Confidence interval; Geology; Artificial intelligence","score_opus":0.5116409653596984,"score_gpt":0.6119579326220749,"score_spread":0.10031696726237649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125296802","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014464063,0.000027398615,0.9812558,0.00081522367,0.0006363465,0.00057972845,0.00056009437,0.000033554516,0.0016277373],"genre_scores_gemma":[0.40506166,0.000006937334,0.59391147,0.00046075287,0.0003986397,0.000042219555,0.000010697981,0.000018689336,0.00008897018],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962434,0.0009919598,0.0010745234,0.00034832433,0.0008335674,0.00050823076],"domain_scores_gemma":[0.967865,0.030551208,0.00023708149,0.0007927823,0.00017784322,0.00037611826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008041374,0.0002257037,0.00081478886,0.00023902814,0.00008783435,0.000018592194,0.0004809946,0.000086603206,0.0005108204],"category_scores_gemma":[0.06838692,0.0001380192,0.00005312698,0.0009350548,0.0002921291,0.000031279556,0.00007115249,0.00039331947,0.000030870364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009905157,0.00038798046,0.0008566967,0.00003330328,0.0002476612,0.000010704386,0.004894448,0.024392592,0.00008498602,0.95848006,0.0064710747,0.004041468],"study_design_scores_gemma":[0.00053497776,0.00017364846,0.0019484942,0.000032098837,0.0006061092,7.618384e-7,0.0004565354,0.40380478,0.000058212692,0.5921779,0.000056137298,0.00015030659],"about_ca_topic_score_codex":0.0000965689,"about_ca_topic_score_gemma":0.00014612914,"teacher_disagreement_score":0.39059758,"about_ca_system_score_codex":0.00009291739,"about_ca_system_score_gemma":0.00004077506,"threshold_uncertainty_score":0.93946046},"labels":[],"label_agreement":null},{"id":"W2126022166","doi":"10.1002/cjs.5550340410","title":"Classification with reject option","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":194,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Class (philosophy); Binary number; Mathematical economics; Mathematics; Computer science; Econometrics; Actuarial science; Artificial intelligence; Economics; Arithmetic","score_opus":0.43610163096619564,"score_gpt":0.4725475954723197,"score_spread":0.036445964506124084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126022166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00776162,0.000038685102,0.9879899,0.00036665128,0.00044236198,0.00013476153,0.0003424951,0.000008947018,0.002914561],"genre_scores_gemma":[0.20179911,0.0000057532075,0.79753476,0.000049414895,0.00036174397,0.0000017392925,0.000003580226,0.00002311484,0.0002208076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982729,0.00023889965,0.0008352472,0.00011545455,0.000290014,0.0002474649],"domain_scores_gemma":[0.99161226,0.006637946,0.0006269071,0.00018625092,0.0005824769,0.00035418288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013075586,0.00011891276,0.00035509394,0.0001703111,0.00009220971,0.00006560223,0.00017360497,0.00009014785,0.00020816889],"category_scores_gemma":[0.01506369,0.00009438465,0.000044080385,0.00018438714,0.00019692146,0.00006853988,0.0000036219337,0.00027602626,0.000012524939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044664994,0.00003029036,0.003562667,0.00004132598,0.00003293604,0.00022209389,0.000035894813,0.000024345576,0.000066688335,0.95555156,0.03273604,0.007651477],"study_design_scores_gemma":[0.00055682566,0.0002869723,0.01977132,0.000090892965,0.0001253142,0.0001123981,0.00005686169,0.00022028114,0.000078767785,0.9750461,0.003520486,0.00013378033],"about_ca_topic_score_codex":0.0006685427,"about_ca_topic_score_gemma":0.0065124105,"teacher_disagreement_score":0.19403748,"about_ca_system_score_codex":0.00018081372,"about_ca_system_score_gemma":0.0008515169,"threshold_uncertainty_score":0.99323285},"labels":[],"label_agreement":null},{"id":"W2126207657","doi":"10.1002/pds.1438","title":"‘Why me?’ versus ‘why now?’—differences between operational hypotheses in case‐control versus case‐crossover studies","year":2007,"lang":"en","type":"letter","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Library science; Citation; Medicine; Control (management); Management; Computer science","score_opus":0.6425357156549517,"score_gpt":0.5859987699991862,"score_spread":0.0565369456557655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126207657","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013483619,0.008473131,0.060961332,0.88435465,0.016896363,0.0037444362,0.008775288,0.00039853674,0.0029126548],"genre_scores_gemma":[0.023391148,0.003765197,0.1638811,0.7871851,0.02045445,0.00040118638,0.00012588939,0.00023789512,0.00055806705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98121667,0.012263933,0.0032763903,0.0014845137,0.00046313004,0.0012953607],"domain_scores_gemma":[0.53770834,0.46078596,0.0007069395,0.00040763506,0.00020395483,0.0001871599],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.018541973,0.0010403831,0.004034853,0.00032883557,0.0005131632,0.000043378357,0.00047714272,0.0016527419,0.0007624934],"category_scores_gemma":[0.13098714,0.0008316028,0.000426023,0.00027554572,0.0016950015,0.00016607472,0.00033730062,0.004293046,0.000044420238],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040370375,0.00008952885,0.0046333265,0.00052295206,0.0029438464,0.02108982,0.00024881642,0.000011660156,0.0000019943034,0.0041159266,0.9591426,0.0031624488],"study_design_scores_gemma":[0.05171343,0.0008184043,0.0011900406,0.00060848927,0.0077388724,0.0033521075,0.00072912587,0.0009679876,0.000071404,0.43713498,0.49204373,0.0036314025],"about_ca_topic_score_codex":0.00033978545,"about_ca_topic_score_gemma":0.0004624407,"teacher_disagreement_score":0.4670989,"about_ca_system_score_codex":0.00025803852,"about_ca_system_score_gemma":0.0001269987,"threshold_uncertainty_score":0.9996433},"labels":[],"label_agreement":null},{"id":"W2126930228","doi":"10.1093/biostatistics/4.3.365","title":"A closer look at the distribution of number needed to treat (NNT): a Bayesian approach","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Number needed to treat; Point estimation; Posterior probability; Bayesian probability; Mathematics; Statistics; Prior probability; Econometrics; Computer science; Confidence interval; Relative risk","score_opus":0.28032836460518146,"score_gpt":0.4902424701533613,"score_spread":0.20991410554817985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126930228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012922354,0.00001626567,0.97039866,0.0003365202,0.00030726148,0.00092354073,0.0024173416,0.000051830368,0.012626251],"genre_scores_gemma":[0.09978774,0.000010512475,0.89761835,0.00033316153,0.000099903125,0.00006852095,0.000045676337,0.000048879487,0.0019872684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967859,0.0010019038,0.00095730484,0.00038191877,0.0004794747,0.00039354223],"domain_scores_gemma":[0.9769889,0.021569451,0.00029306047,0.000727247,0.00020886281,0.00021249444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018797398,0.00025854114,0.00060140196,0.00002606835,0.000137092,0.000033283617,0.0002563727,0.00018066411,0.0007246483],"category_scores_gemma":[0.078827664,0.00017592641,0.00013157849,0.00038933792,0.00029539564,0.000023817498,0.00010649168,0.00018830634,0.00014129355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017741151,0.0003863674,0.0005621281,0.00021542849,0.00006278856,0.000009160707,0.00026547024,0.000005836242,0.00026831782,0.86992437,0.12464483,0.0034778866],"study_design_scores_gemma":[0.0014021824,0.00021625275,0.0005381785,0.00006227921,0.00037441452,0.000031301548,0.00042998398,0.00038973018,0.00967009,0.9772959,0.009173545,0.00041617025],"about_ca_topic_score_codex":0.00003928067,"about_ca_topic_score_gemma":0.000008023766,"teacher_disagreement_score":0.11547128,"about_ca_system_score_codex":0.00014113433,"about_ca_system_score_gemma":0.00007268114,"threshold_uncertainty_score":0.9289318},"labels":[],"label_agreement":null},{"id":"W2127195807","doi":"10.1093/biostatistics/4.3.479","title":"Conditional analysis of mixed Poisson processes with baseline counts: implications for trial design and analysis","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Baseline (sea); Sample size determination; Count data; Negative binomial distribution; Multiple baseline design; Poisson distribution; Randomization; Mathematics; Computer science; Econometrics; Clinical trial; Medicine; Internal medicine","score_opus":0.4690235198847609,"score_gpt":0.5372107865117601,"score_spread":0.06818726662699925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127195807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005008145,0.00002975597,0.9923706,0.00007336487,0.00004436851,0.0005629467,0.006285072,0.00001757499,0.00011549907],"genre_scores_gemma":[0.03500222,0.00002936666,0.9645604,0.000035701625,0.00002860806,0.00008893089,0.00017230796,0.0000134942975,0.00006896687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99858886,0.0003274641,0.0005655847,0.00022843048,0.00016534804,0.00012430768],"domain_scores_gemma":[0.9353122,0.0635751,0.0003138401,0.00020700869,0.00052227813,0.000069540445],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015280409,0.00011276119,0.0005863684,0.00020857342,0.000055875244,0.000019080358,0.00006927474,0.0000716982,0.00021980323],"category_scores_gemma":[0.087930724,0.000089609464,0.00008131832,0.0012382467,0.0001487896,0.000017987564,0.0000070449587,0.000044347038,0.0000011744531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022413216,0.0003842437,0.0011152249,0.00023870742,0.0055674454,9.724079e-7,0.000025350642,0.00013026754,0.000034556804,0.98313016,0.0058415756,0.0012901529],"study_design_scores_gemma":[0.0062875156,0.0005412538,0.002406667,0.000016319773,0.023819964,9.696606e-7,0.000022502543,0.0040330947,0.00035526042,0.96161246,0.0006856323,0.00021835527],"about_ca_topic_score_codex":0.0000017113479,"about_ca_topic_score_gemma":0.000010806445,"teacher_disagreement_score":0.086402684,"about_ca_system_score_codex":0.000016348997,"about_ca_system_score_gemma":0.00015620141,"threshold_uncertainty_score":0.919752},"labels":[],"label_agreement":null},{"id":"W2128373232","doi":"10.1093/jnci/djh182","title":"Phase I Trial Design for Solid Tumor Studies of Targeted, Non-Cytotoxic Agents: Theory and Practice","year":2004,"lang":"en","type":"review","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cytotoxic T cell; Solid tumor; Medicine; Biology; Cancer; Internal medicine; Genetics; In vitro","score_opus":0.8358492860840319,"score_gpt":0.7003415538770064,"score_spread":0.1355077322070255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128373232","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012117511,0.8733596,0.112704046,0.00029678197,0.008821598,0.0037664631,0.0009540592,0.000007948833,0.000077384975],"genre_scores_gemma":[0.000011152772,0.65776366,0.33907184,0.00022231712,0.0025937115,0.00022405965,0.0000011258053,0.00004037408,0.000071765164],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99257314,0.0025652202,0.0031115182,0.0002742555,0.0012480232,0.0002278202],"domain_scores_gemma":[0.87579596,0.114819884,0.0067145196,0.0002164189,0.0023362206,0.000116991505],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021178657,0.00039081974,0.002876415,0.0002115803,0.0001733904,0.00003826933,0.0006878784,0.00022683499,0.00003224947],"category_scores_gemma":[0.4649375,0.00022623013,0.00095644797,0.00032295412,0.00055073533,0.0002950684,0.00014299786,0.00070322916,0.0000011614956],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.120101735,0.005201881,9.4471744e-8,0.075768776,0.02226567,0.000099835575,0.0007472528,0.00060933037,0.000049652997,0.26282945,0.04089608,0.47143027],"study_design_scores_gemma":[0.029260907,0.0012777244,6.242511e-8,0.0193812,0.006233605,0.00021848392,0.000036512847,0.0000075980006,0.00009821009,0.7267547,0.21646254,0.00026841476],"about_ca_topic_score_codex":0.0000013594828,"about_ca_topic_score_gemma":9.050179e-7,"teacher_disagreement_score":0.47116184,"about_ca_system_score_codex":0.00079667155,"about_ca_system_score_gemma":0.0038250473,"threshold_uncertainty_score":0.9225397},"labels":[],"label_agreement":null},{"id":"W2129017495","doi":"10.1002/sim.5723","title":"Correction: ‘Generating survival times to simulate Cox proportional hazards models with time‐varying covariates’","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Covariate; Weibull distribution; Proportional hazards model; Statistics; Mathematics; Cumulative distribution function; Event (particle physics); Hazard; Expression (computer science); Gompertz function; Function (biology); Econometrics; Probability density function; Computer science; Physics","score_opus":0.23952068522826894,"score_gpt":0.49038527983643865,"score_spread":0.2508645946081697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129017495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020147916,0.000013985214,0.9863764,0.0009025473,0.0015953509,0.0011590513,0.00014800078,0.000113712216,0.007676165],"genre_scores_gemma":[0.027963629,0.0000072374223,0.96733755,0.0005288406,0.00073584303,0.00013965936,0.000036477086,0.0000736916,0.003177088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958164,0.0006293631,0.0014479613,0.0005620365,0.0010404229,0.00050378736],"domain_scores_gemma":[0.96624756,0.032018,0.0003541305,0.0004259531,0.0006463877,0.00030797612],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035078388,0.0003386236,0.0010269715,0.00017285193,0.00014508549,0.000050996958,0.00024330203,0.00014554326,0.004692396],"category_scores_gemma":[0.06031557,0.00024957568,0.000032285156,0.0004879416,0.00030646374,0.000110403205,0.00009847206,0.0005155163,0.00017548336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006726728,0.0005430035,0.00086378277,0.00040712458,0.00033768394,0.00025946068,0.001879132,0.049537133,0.0012425823,0.68688524,0.21099404,0.04637815],"study_design_scores_gemma":[0.0012552623,0.00043724725,0.00018338657,0.00033332137,0.00006894137,0.000010271654,0.00007424859,0.40813148,0.000050355906,0.58915997,0.000061005783,0.0002345442],"about_ca_topic_score_codex":0.0002379635,"about_ca_topic_score_gemma":0.000032872795,"teacher_disagreement_score":0.35859433,"about_ca_system_score_codex":0.00013246591,"about_ca_system_score_gemma":0.00018826591,"threshold_uncertainty_score":0.99999565},"labels":[],"label_agreement":null},{"id":"W2129048052","doi":"10.1002/0470011815.b2a04025","title":"Diagnostic Tests, Likelihood Ratio","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Hospital","funders":"","keywords":"Bayes' theorem; Diagnostic test; Test (biology); Pre- and post-test probability; Diagnostic odds ratio; Likelihood ratios in diagnostic testing; Statistics; Sensitivity (control systems); Likelihood-ratio test; Computer science; Mathematics; Medicine; Bayesian probability; Receiver operating characteristic; Engineering","score_opus":0.13667496144872449,"score_gpt":0.4597763115975819,"score_spread":0.32310135014885744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129048052","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026876369,0.0008571613,0.2083598,0.00013130576,0.002334376,0.0011655862,0.0071416833,0.00034348996,0.7796639],"genre_scores_gemma":[0.000014750639,0.0047088587,0.73815525,0.00009184589,0.002398319,0.00005696907,0.00005409033,0.0007484836,0.25377145],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954919,0.00057027634,0.0018270293,0.0006861771,0.00082002365,0.00060456444],"domain_scores_gemma":[0.9059468,0.09114454,0.0014095189,0.0010440857,0.00015627034,0.0002988205],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010920202,0.0006630708,0.0017136841,0.00029660508,0.00004211749,0.00002720664,0.0006271043,0.00082855154,0.014880815],"category_scores_gemma":[0.24047087,0.00061536854,0.00021583894,0.0003193593,0.00044122463,0.000027406435,0.00019176757,0.0006140452,0.0005250475],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009842109,0.00031861608,0.00010901805,0.0006529987,0.00015384161,0.00005121137,0.000044537595,1.9829244e-7,0.0000031149955,0.08650637,0.84053975,0.07161048],"study_design_scores_gemma":[0.0007674268,0.00021887425,0.00025069554,0.0008057064,0.00061058137,0.000005431378,0.000020942269,0.00002278217,0.000029266108,0.3998066,0.59677076,0.00069095346],"about_ca_topic_score_codex":0.0000612677,"about_ca_topic_score_gemma":0.00014184616,"teacher_disagreement_score":0.5297954,"about_ca_system_score_codex":0.000062181905,"about_ca_system_score_gemma":0.00028233664,"threshold_uncertainty_score":0.9996298},"labels":[],"label_agreement":null},{"id":"W2129073959","doi":"10.1093/annonc/mdt122","title":"Performance of multinomial designs in comparison with response-based designs in non-randomized phase II trials of targeted cancer agents","year":2013,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Kingston General Hospital; Université de Montréal; Hôpital Notre-Dame","funders":"Canadian Institutes of Health Research","keywords":"Multinomial distribution; Medicine; Clinical trial; Research design; Accrual; Randomized controlled trial; Clinical study design; Oncology; Internal medicine; Statistics; Mathematics","score_opus":0.7589916766225049,"score_gpt":0.632251201882201,"score_spread":0.12674047474030392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129073959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98163366,0.000047542206,0.014441488,0.0005339775,0.00017175448,0.0029273853,0.00010003885,0.000009855684,0.0001343131],"genre_scores_gemma":[0.7112001,0.0000382344,0.2882367,0.00010395344,0.000028918206,0.00035499898,0.0000019439228,0.000019440056,0.000015716287],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9838314,0.010644963,0.0044476977,0.0003236189,0.00034654423,0.0004057612],"domain_scores_gemma":[0.8705461,0.12588994,0.0026505548,0.00034320154,0.0004688195,0.0001013645],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027985463,0.00024382098,0.004663286,0.00038974534,0.000025192752,0.000003472149,0.00033103095,0.00034366327,0.0007276487],"category_scores_gemma":[0.12403309,0.00018052782,0.00026037882,0.00042696003,0.00076025,0.00007020223,0.000059762933,0.00029522213,0.0000028047104],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.88132936,0.008482938,0.0065356707,0.0006207868,0.00043905032,0.000015126238,0.002191486,0.0017358171,0.06172339,0.00027254707,0.0022372704,0.034416556],"study_design_scores_gemma":[0.52844894,0.022557573,0.00990038,0.001099801,0.0003668033,9.3761275e-7,0.00022779236,0.062479552,0.3596668,0.014756181,0.000057492838,0.00043774687],"about_ca_topic_score_codex":0.00048828864,"about_ca_topic_score_gemma":0.00008136105,"teacher_disagreement_score":0.35288045,"about_ca_system_score_codex":0.00006276333,"about_ca_system_score_gemma":0.0006101532,"threshold_uncertainty_score":0.9699259},"labels":[],"label_agreement":null},{"id":"W2129597433","doi":"10.1080/03610918.2012.752833","title":"Confidence Intervals of Effect Size for Randomized Comparative Parallel-Group Studies with Unequal Variances","year":2013,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"American Lebanese Syrian Associated Charities","keywords":"Confidence interval; Statistics; Sample size determination; Mathematics; Nominal level; Measure (data warehouse); Yield (engineering); Coverage probability; Econometrics; Computer science; Data mining; Physics","score_opus":0.659799464658017,"score_gpt":0.6383188112552726,"score_spread":0.02148065340274441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129597433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010972652,0.00028313158,0.98505265,0.00017864809,0.00008494515,0.0031559863,0.000091223505,0.000035991583,0.00014478326],"genre_scores_gemma":[0.49505082,0.00006681666,0.50439906,0.000026181971,0.000008862589,0.00041298446,0.000016345557,0.000008868425,0.0000100742145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99544436,0.00255076,0.0013690311,0.00025770493,0.00022355927,0.00015461445],"domain_scores_gemma":[0.7017509,0.29652008,0.00065528305,0.00036511704,0.0006649348,0.000043737196],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030940014,0.0002033946,0.001199167,0.00009578658,0.00013662841,0.00005713707,0.00025978588,0.00007861784,0.000021936443],"category_scores_gemma":[0.039527103,0.00015815199,0.000059017177,0.00023059372,0.0009211005,0.0001523457,0.000117367774,0.00016491722,0.000002637243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049846256,0.00023364535,0.00022442143,0.00045371527,0.0002867938,3.1764392e-7,0.0030255748,0.032179505,0.000019806968,0.94499254,0.00015168016,0.01344739],"study_design_scores_gemma":[0.016654365,0.00023854879,0.00044728443,0.00016962088,0.00010180495,2.7913634e-7,0.0003319984,0.43944266,0.000010123508,0.54249513,0.0000057615016,0.000102400714],"about_ca_topic_score_codex":0.00003632275,"about_ca_topic_score_gemma":0.000042989162,"teacher_disagreement_score":0.48407817,"about_ca_system_score_codex":0.00004174348,"about_ca_system_score_gemma":0.000030364527,"threshold_uncertainty_score":0.9685634},"labels":[],"label_agreement":null},{"id":"W2129733505","doi":"10.1186/1745-6215-13-120","title":"Allocation techniques for balance at baseline in cluster randomized trials: a methodological review","year":2012,"lang":"en","type":"review","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":259,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; Health Sciences Centre; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre; University Health Network; University of Toronto; Women's College Hospital","funders":"Canadian Institutes of Health Research; Department of Family and Community Medicine, University of Toronto; University of Toronto","keywords":"Randomized controlled trial; Covariate; Medicine; Randomization; External validity; Statistical power; Matching (statistics); Baseline (sea); Observational study; Credibility; Research design; Cluster randomised controlled trial; Statistics; Surgery; Mathematics; Internal medicine","score_opus":0.9616323734160546,"score_gpt":0.7454275232970856,"score_spread":0.21620485011896895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129733505","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.104856e-9,0.5848168,0.37816554,0.00036983544,0.0009048695,0.035006065,0.00043705414,0.00013771698,0.00016212823],"genre_scores_gemma":[5.1409166e-9,0.5024278,0.47983173,0.00039947897,0.0017218237,0.015190455,0.00007633487,0.00008542603,0.00026692665],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.5420108,0.42415622,0.030164288,0.0016361353,0.00094744714,0.0010851374],"domain_scores_gemma":[0.05659938,0.9297346,0.011663466,0.0014110908,0.0003301627,0.0002613253],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7328447,0.0011103947,0.055329077,0.0003145689,0.00006958227,0.000048918766,0.00085036445,0.0017536667,0.0018687281],"category_scores_gemma":[0.97918355,0.0006266278,0.0072533833,0.0005623136,0.00026582027,0.00008141533,0.00030596185,0.0008394555,0.00010387874],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013535738,0.00018330278,2.3894318e-8,0.09865976,0.00049072976,0.000001989592,0.0000058299324,1.1216509e-8,7.64204e-7,0.012505536,0.018170195,0.85644615],"study_design_scores_gemma":[0.03293963,0.0000582897,6.2403283e-9,0.058582615,0.015707837,0.000008914509,5.1032816e-7,0.000009266213,0.000011665964,0.28720856,0.6049905,0.00048220632],"about_ca_topic_score_codex":0.0000046151417,"about_ca_topic_score_gemma":0.0000025943423,"teacher_disagreement_score":0.8559639,"about_ca_system_score_codex":0.00038640018,"about_ca_system_score_gemma":0.00026382436,"threshold_uncertainty_score":0.99961853},"labels":[],"label_agreement":null},{"id":"W2131336573","doi":"10.1002/sim.3398","title":"A geometric confidence ellipse approach to the estimation of the ratio of two variables","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ellipse; Tangent; Confidence interval; Coverage probability; Mathematics; Confidence distribution; Confidence region; Point estimation; Statistics; Applied mathematics; Geometry","score_opus":0.41984205646303874,"score_gpt":0.5298368237881074,"score_spread":0.10999476732506863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131336573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002709794,0.00005733646,0.9932517,0.00041434466,0.00040811775,0.0008130453,0.00018234855,0.00000965108,0.0021536541],"genre_scores_gemma":[0.25881734,0.000044558456,0.7407067,0.00014610318,0.000097193406,0.00003270098,0.0000026817274,0.000013200601,0.00013952471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99648494,0.00082948315,0.0013997214,0.00023198164,0.0008522244,0.00020163182],"domain_scores_gemma":[0.94202924,0.05643355,0.00052860624,0.00066219666,0.000280451,0.000065967426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051992936,0.00014774501,0.0006963223,0.00016504223,0.00007366422,0.000003580149,0.0005379015,0.00006657472,0.00012110158],"category_scores_gemma":[0.2649202,0.00007842133,0.00003716365,0.0014477371,0.00082173466,0.000021598731,0.00010683602,0.0002954617,0.000003851157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005210369,0.0001933874,0.00046163832,0.00027153257,0.000033346663,0.000003357502,0.001517827,0.002717023,0.00013962599,0.9774645,0.012366004,0.0047796555],"study_design_scores_gemma":[0.0010787018,0.00017929309,0.0029066808,0.00024960676,0.00011035761,0.000010439442,0.00016821225,0.025893496,0.0007428184,0.9685143,0.00005381473,0.00009226039],"about_ca_topic_score_codex":0.00019399478,"about_ca_topic_score_gemma":0.000018591414,"teacher_disagreement_score":0.2597209,"about_ca_system_score_codex":0.0000376137,"about_ca_system_score_gemma":0.000116951865,"threshold_uncertainty_score":0.7412717},"labels":[],"label_agreement":null},{"id":"W2131715846","doi":"10.1002/sim.3645","title":"Two‐stage design of clinical trials involving recurrent events","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Interim; Interim analysis; Sample size determination; Clinical trial; Event (particle physics); Poisson regression; Poisson distribution; Population; Statistics; Stage (stratigraphy); Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.8501905449859165,"score_gpt":0.7057092213771811,"score_spread":0.14448132360873545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131715846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096807687,0.00026644056,0.99329466,0.0005057636,0.002285058,0.0012293487,0.00029974707,0.00004626546,0.0011046214],"genre_scores_gemma":[0.020857967,0.00069999124,0.97694623,0.00037586794,0.0008608582,0.000019889321,0.000010200869,0.000032041182,0.00019694089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9767825,0.012692276,0.008246478,0.0006217211,0.0011447375,0.000512279],"domain_scores_gemma":[0.74081695,0.2563162,0.0017632147,0.0005896572,0.00026758478,0.00024636902],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08820321,0.00031514623,0.0033751496,0.00022386342,0.000040993375,0.00000710958,0.0004655099,0.00023601735,0.0009806791],"category_scores_gemma":[0.7832535,0.00023617143,0.00014959517,0.0004273379,0.000412934,0.000042401945,0.00006922685,0.0008408881,0.000012881058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010687545,0.0008236416,0.0016364496,0.00026104643,0.00010446766,0.00009585411,0.0003240647,0.000030535084,0.00021947305,0.7621546,0.018293101,0.21498805],"study_design_scores_gemma":[0.0061173015,0.0017446791,0.00276707,0.000923973,0.00022241703,0.0000018102384,0.00012162929,0.003769808,0.000091057766,0.98387045,0.00015527241,0.0002145155],"about_ca_topic_score_codex":0.000023226188,"about_ca_topic_score_gemma":0.000010210107,"teacher_disagreement_score":0.6950503,"about_ca_system_score_codex":0.00006558933,"about_ca_system_score_gemma":0.00017391563,"threshold_uncertainty_score":0.9999326},"labels":[],"label_agreement":null},{"id":"W2132487780","doi":"10.1177/1087057103258284","title":"Statistical and Graphical Methods for Quality Control Determination of High-Throughput Screening Data","year":2003,"lang":"en","type":"article","venue":"SLAS DISCOVERY","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":67,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Merck Canada Inc. (Canada)","funders":"","keywords":"Computer science; Automation; Throughput; Software; Process (computing); Quality (philosophy); Statistical process control; Data mining; Embedded system; Reliability engineering; Operating system; Engineering","score_opus":0.6141009287284397,"score_gpt":0.6389300450615336,"score_spread":0.024829116333093926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132487780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030170581,0.000062103565,0.993328,0.000114384966,0.00037586372,0.0006606353,0.0022785375,0.000029084415,0.00013436633],"genre_scores_gemma":[0.10949815,0.00001564448,0.8901933,0.00009242624,0.000077780394,0.000038371498,0.000025029763,0.00002868381,0.000030599567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941623,0.0034261937,0.0012260337,0.00060125836,0.00028353074,0.0003006355],"domain_scores_gemma":[0.83274806,0.16585772,0.00038458256,0.00078509375,0.0001173655,0.00010717797],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012515464,0.00019650997,0.000933585,0.000056864843,0.00007790281,0.00006269564,0.00028352233,0.00018624931,0.000048015518],"category_scores_gemma":[0.2917617,0.00016627784,0.00009134778,0.00012999904,0.0004475338,0.00029199012,0.00013280308,0.00020187137,6.391486e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024561115,0.00014197677,0.0005239557,0.0002588278,0.00007515692,0.0000013094905,0.00001904104,3.4345047e-7,0.0002770571,0.94214034,0.00020370776,0.05611269],"study_design_scores_gemma":[0.0024443776,0.00018982877,0.002394649,0.000054877404,0.0002856928,0.0000032675591,0.000044840228,0.0021629292,0.0010943316,0.99089235,0.0002343661,0.00019848076],"about_ca_topic_score_codex":0.000025967383,"about_ca_topic_score_gemma":0.000009390827,"teacher_disagreement_score":0.2792462,"about_ca_system_score_codex":0.000015222941,"about_ca_system_score_gemma":0.00006223641,"threshold_uncertainty_score":0.71420413},"labels":[],"label_agreement":null},{"id":"W2132981975","doi":"10.14740/wjon842e","title":"Application of Bayesian Approach in Cancer Clinical Trial","year":2014,"lang":"en","type":"review","venue":"World Journal of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Medicine; Bayesian inference; Bayesian experimental design; Statement (logic); Clinical trial; Bayesian statistics; Inference; Machine learning; Medical physics; Artificial intelligence; Computer science; Internal medicine","score_opus":0.7526338008122788,"score_gpt":0.6983310240118346,"score_spread":0.054302776800444263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132981975","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023947755,0.74127644,0.24817558,0.0001465912,0.0036917333,0.002064428,0.000030455703,0.000009970695,0.004602388],"genre_scores_gemma":[0.0000074233485,0.5989381,0.39831066,0.00004104966,0.002496312,0.00009105912,0.000001036426,0.000039244103,0.000075092634],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98084575,0.008713805,0.009308519,0.00038166263,0.0004469104,0.00030335784],"domain_scores_gemma":[0.8865678,0.10320021,0.009304579,0.00049065816,0.00024458702,0.00019220432],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025997162,0.00033723962,0.008988425,0.00058191386,0.000018258348,0.0000088438255,0.0008770812,0.00091955543,0.00015400647],"category_scores_gemma":[0.050015282,0.00023954795,0.0014406254,0.0006470135,0.0003365223,0.000030123734,0.00011785429,0.0022254558,0.0000067859073],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002062416,0.0012256784,0.000017080663,0.0050521824,0.00026105708,0.000011863206,0.000010298773,9.691075e-7,3.29942e-8,0.018862657,0.0020785388,0.9704172],"study_design_scores_gemma":[0.013558017,0.0013291844,0.000004938862,0.0032138503,0.0016855961,0.000035594592,0.0000034509847,0.00003664816,8.9286054e-8,0.14847492,0.831477,0.00018073167],"about_ca_topic_score_codex":0.00000762998,"about_ca_topic_score_gemma":0.000038758964,"teacher_disagreement_score":0.9702365,"about_ca_system_score_codex":0.00037285354,"about_ca_system_score_gemma":0.001321596,"threshold_uncertainty_score":0.9768482},"labels":[],"label_agreement":null},{"id":"W2133300801","doi":"10.1002/sim.6085","title":"Value of information methods for assessing a new diagnostic test","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Value of information; Test (biology); Value (mathematics); Sample (material); Sample size determination; Statistics; Econometrics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.3956805353606469,"score_gpt":0.635194064645554,"score_spread":0.23951352928490705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133300801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000092886636,0.000030229032,0.99576056,0.0005185592,0.00081253145,0.00065057795,0.00013540866,0.000032610784,0.0019666296],"genre_scores_gemma":[0.0028046807,0.000032917156,0.9962839,0.00034163744,0.00039658786,0.000043089432,0.000019120376,0.000025114914,0.000052942938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965553,0.0008180749,0.0017891467,0.00019656385,0.00035339565,0.00028749398],"domain_scores_gemma":[0.52094716,0.47782296,0.00055445917,0.00031510813,0.00022769015,0.00013261924],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01096513,0.00018429787,0.0009361801,0.0001848767,0.000039703147,0.0000181862,0.00024190206,0.00013769857,0.0001476288],"category_scores_gemma":[0.89572906,0.00014904446,0.00004320128,0.00030143198,0.00026707348,0.0001117658,0.000052905696,0.00024849092,0.000004662432],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020203426,0.000050832183,0.00039450554,0.00048980815,0.0000132982905,6.15441e-7,0.00027448358,0.000009255777,0.00010035493,0.65074044,0.007889866,0.3400163],"study_design_scores_gemma":[0.0023327887,0.00045290464,0.0021711774,0.0005848526,0.00015955322,0.0000018639694,0.00009795269,0.019832289,0.00026560528,0.9708758,0.0030826936,0.00014253876],"about_ca_topic_score_codex":0.000062410014,"about_ca_topic_score_gemma":0.000006581092,"teacher_disagreement_score":0.88476396,"about_ca_system_score_codex":0.000052931682,"about_ca_system_score_gemma":0.00011547902,"threshold_uncertainty_score":0.60778564},"labels":[],"label_agreement":null},{"id":"W2134095592","doi":"10.1158/1078-0432.ccr-06-0909","title":"Setting the Bar in Phase II Trials: The Use of Historical Data for Determining “Go/No Go” Decision for Definitive Phase III Testing","year":2007,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Immunovaccine (Canada)","funders":"National Cancer Institute; National Institutes of Health","keywords":"Null hypothesis; Clinical trial; Medicine; Null (SQL); Sample size determination; Protocol (science); Phase (matter); Statistics; Oncology; Research design; Internal medicine; Data mining; Computer science; Pathology; Alternative medicine; Mathematics","score_opus":0.991818251432903,"score_gpt":0.8241548003108323,"score_spread":0.1676634511220707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134095592","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061183724,0.7244115,0.23751862,0.000478864,0.0040227207,0.02284996,0.010421112,0.0000722178,0.00016382102],"genre_scores_gemma":[0.0000032500247,0.46357277,0.5296381,0.00012248894,0.0035801055,0.0026030533,0.00006859809,0.0001787731,0.00023285697],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9559845,0.022673076,0.014994461,0.002367519,0.0021975792,0.0017828658],"domain_scores_gemma":[0.06398237,0.92582625,0.0039911764,0.0035613687,0.0022288028,0.0004100262],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28484434,0.000720015,0.008078989,0.00037367578,0.0008344031,0.00018628019,0.004170471,0.001280057,0.0001459333],"category_scores_gemma":[0.9634472,0.00038908233,0.0017148226,0.0014873343,0.0012994425,0.00018160827,0.0026925323,0.0044023637,0.000014387443],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033539557,0.0012603337,0.000002781685,0.004776169,0.0002780509,0.000017175564,0.00004720825,5.397701e-7,5.3331667e-7,0.0012650036,0.04917443,0.9398238],"study_design_scores_gemma":[0.011556861,0.0030079966,4.574093e-7,0.0183481,0.001620355,0.000004850597,0.00003256501,0.0029017632,0.0000016761542,0.06354497,0.8985676,0.00041278746],"about_ca_topic_score_codex":0.000092265145,"about_ca_topic_score_gemma":0.00006235845,"teacher_disagreement_score":0.93941104,"about_ca_system_score_codex":0.000996003,"about_ca_system_score_gemma":0.003029011,"threshold_uncertainty_score":0.9998561},"labels":[],"label_agreement":null},{"id":"W2134235269","doi":"10.1200/jco.2013.52.7804","title":"Shifting Patterns in the Interpretation of Phase III Clinical Trial Outcomes in Advanced Non–Small-Cell Lung Cancer: The Bar Is Dropping","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Lung cancer; Oncology; Interpretation (philosophy); Internal medicine; Clinical trial; Cancer; Pathology","score_opus":0.5294642514651834,"score_gpt":0.6664420095163952,"score_spread":0.13697775805121182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134235269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90173423,0.000054197895,0.08741729,0.0052638818,0.003934674,0.0010064298,0.0000122650445,0.0000061327137,0.0005708747],"genre_scores_gemma":[0.9110779,0.00038000906,0.08355193,0.003444786,0.0014559344,0.000039493254,3.261454e-7,0.00002742848,0.000022166078],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.972396,0.013221253,0.012901004,0.00039466366,0.000666941,0.00042012462],"domain_scores_gemma":[0.62972534,0.36188212,0.0073499554,0.0005435845,0.000326614,0.00017241194],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07849623,0.00025585448,0.0036691604,0.00014028998,0.000053802538,0.000026619733,0.001170233,0.00063218153,0.00013989193],"category_scores_gemma":[0.29376674,0.00013743376,0.0010779549,0.00025981717,0.00035191653,0.00011915148,0.00017792995,0.0029170972,0.0000029656414],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.059389398,0.009527541,0.22727107,0.00025356928,0.0004795381,0.00010276911,0.00330637,0.00014689198,0.000032355678,0.0028054358,0.00074549817,0.6959396],"study_design_scores_gemma":[0.5246569,0.03254096,0.1109986,0.0020787378,0.0020903717,0.000022445782,0.0032455549,0.06640035,0.00010957579,0.25567856,0.0014544699,0.00072351185],"about_ca_topic_score_codex":0.000053326603,"about_ca_topic_score_gemma":0.00020710017,"teacher_disagreement_score":0.69521606,"about_ca_system_score_codex":0.0001105633,"about_ca_system_score_gemma":0.00066340185,"threshold_uncertainty_score":0.9993832},"labels":[],"label_agreement":null},{"id":"W2134384386","doi":"10.1093/bioinformatics/btl109","title":"Construction of null statistics in permutation-based multiple testing for multi-factorial microarray experiments","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Null distribution; Statistics; Permutation (music); Test statistic; Mathematics; Null (SQL); Statistical hypothesis testing; Statistic; False discovery rate; Null hypothesis; Asymptotic distribution; Ancillary statistic; p-value; Data mining; Computer science; Biology; Genetics","score_opus":0.4215325324378103,"score_gpt":0.49919503487273753,"score_spread":0.07766250243492723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134384386","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02986747,0.0000057556963,0.96674436,0.0000104961955,0.00092597865,0.0010218861,0.0011657914,0.000056123736,0.00020215454],"genre_scores_gemma":[0.033535928,4.7979336e-7,0.9661198,0.000026407924,0.00015138747,0.0000691583,0.000050823455,0.000029223665,0.000016774764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997182,0.00013125876,0.0019135965,0.00016448446,0.00030764635,0.00030098832],"domain_scores_gemma":[0.9697432,0.02877404,0.0008119204,0.0002487982,0.00036101768,0.00006100233],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010926531,0.00020886282,0.00054689666,0.00014209992,0.000067524794,0.000033530847,0.00015965186,0.00018504779,0.000029599756],"category_scores_gemma":[0.05953895,0.00019833897,0.00008582432,0.00022435594,0.0001897007,0.000100000696,0.000026820895,0.00013316424,0.0000058126443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003242555,0.0075300555,0.28312105,0.013316523,0.00039162685,0.000020217742,0.006372569,0.0037543133,0.06072812,0.47939205,0.014226501,0.12790442],"study_design_scores_gemma":[0.012380282,0.0003957723,0.0033327485,0.00031785955,0.00010724924,0.0000032630378,0.00065145025,0.6248128,0.048242707,0.3089438,0.00023088639,0.00058116566],"about_ca_topic_score_codex":0.00007040043,"about_ca_topic_score_gemma":0.000025926382,"teacher_disagreement_score":0.62105846,"about_ca_system_score_codex":0.000106159496,"about_ca_system_score_gemma":0.0001533628,"threshold_uncertainty_score":0.948383},"labels":[],"label_agreement":null},{"id":"W2134647083","doi":"10.1093/biostatistics/kxn037","title":"Statistical monitoring of clinical trials with multivariate response and/or multiple arms: a flexible approach","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Interim; Multivariate statistics; Clinical trial; Robustness (evolution); Computer science; Randomized controlled trial; Interim analysis; Multivariate analysis; Statistics; Medicine; Mathematics; Machine learning; Internal medicine","score_opus":0.8559835100558566,"score_gpt":0.644237374207395,"score_spread":0.21174613584846158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134647083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09901484,0.000045617922,0.89688945,0.00006602363,0.0005710262,0.0010907385,0.002035609,0.00014212959,0.0001445635],"genre_scores_gemma":[0.2086388,0.00013651226,0.79048365,0.000030024587,0.00035756483,0.000056868386,0.000007907564,0.00007422724,0.00021441287],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9847631,0.008692994,0.0042870934,0.00082944473,0.0008563355,0.0005710188],"domain_scores_gemma":[0.6825101,0.31504798,0.0011466305,0.0005794104,0.00031198753,0.00040394304],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.023402935,0.00044518826,0.0028309838,0.00014729323,0.00017006454,0.00003651802,0.00031377058,0.00039160278,0.00010524506],"category_scores_gemma":[0.62918097,0.00029506543,0.0001692872,0.00035465558,0.0013517899,0.00007553144,0.00016724234,0.00062019797,0.000011307708],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24616756,0.009590223,0.3115653,0.0037034082,0.00308989,0.002122219,0.004679816,0.000051390885,0.003339944,0.27343056,0.011486635,0.13077305],"study_design_scores_gemma":[0.04035088,0.0102179665,0.5279213,0.0012160289,0.0022657204,0.0005399532,0.002369328,0.01729994,0.0067141615,0.3870822,0.0014181524,0.0026043737],"about_ca_topic_score_codex":0.000042449803,"about_ca_topic_score_gemma":0.000001736209,"teacher_disagreement_score":0.605778,"about_ca_system_score_codex":0.00004106017,"about_ca_system_score_gemma":0.00044516084,"threshold_uncertainty_score":0.9999502},"labels":[],"label_agreement":null},{"id":"W2134869849","doi":"10.1186/2193-1801-3-323","title":"Interim analysis for binary outcome trials with a long fixed follow-up time and repeated outcome assessments at pre-specified times","year":2014,"lang":"en","type":"article","venue":"SpringerPlus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; Ontario Clinical Oncology Group","funders":"","keywords":"Interim; Interim analysis; Outcome (game theory); Duration (music); Accrual; Event (particle physics); Early stopping; Statistics; Medicine; Randomized controlled trial; Computer science; Mathematics; Surgery; Accounting","score_opus":0.5317796162819506,"score_gpt":0.5636421808676351,"score_spread":0.03186256458568448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134869849","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5140763,0.000032864464,0.48108822,0.0002567276,0.00066942896,0.0020416512,0.0001554742,0.00029468216,0.0013846715],"genre_scores_gemma":[0.40885738,0.0000061252613,0.5795674,0.0001296024,0.00022766972,0.00019119156,0.000021807307,0.00009782738,0.010901035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99389434,0.0016220813,0.00250823,0.0009092037,0.0005231909,0.00054296746],"domain_scores_gemma":[0.94990325,0.047483433,0.0011169524,0.0010313357,0.00019083575,0.0002741896],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011235954,0.00046710775,0.0030670222,0.0003008441,0.00017449782,0.00013435858,0.0003875927,0.00027755453,0.0008718355],"category_scores_gemma":[0.07490191,0.00033884592,0.00064149895,0.00048404344,0.00017393328,0.000101306956,0.00037912777,0.0002615909,0.000050282833],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06553992,0.0024457097,0.7661331,0.0034933202,0.036578145,0.00023240868,0.0013540272,0.00032035142,0.009626121,0.047139645,0.0067302817,0.060406923],"study_design_scores_gemma":[0.054348942,0.0075307745,0.55027413,0.0009134603,0.034146786,0.00003615406,0.00011171,0.06907131,0.008189517,0.26741913,0.0033658396,0.004592226],"about_ca_topic_score_codex":0.000019352874,"about_ca_topic_score_gemma":0.000034794597,"teacher_disagreement_score":0.2202795,"about_ca_system_score_codex":0.0001663357,"about_ca_system_score_gemma":0.000031652005,"threshold_uncertainty_score":0.99990636},"labels":[],"label_agreement":null},{"id":"W2135772515","doi":"10.1016/j.jval.2013.03.694","title":"Economic Evaluations Of Companion Diagnostics In Cancer Therapy","year":2013,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Medicine; Cancer; Breast cancer; Companion diagnostic; Colorectal cancer; Lung cancer; Oncology; Medical physics; Intensive care medicine; Internal medicine","score_opus":0.7216186709408293,"score_gpt":0.6334271941979627,"score_spread":0.08819147674286665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135772515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985981,0.0008696181,0.005916151,0.0036774818,0.0009265976,0.00208456,0.000091206275,0.00002696007,0.00042641972],"genre_scores_gemma":[0.52032185,0.0056089363,0.47303092,0.00045567311,0.00017946548,0.0003431013,0.0000016872901,0.000032291267,0.00002606713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967526,0.0014158656,0.001252177,0.00018979615,0.0001555022,0.00023405072],"domain_scores_gemma":[0.9538641,0.04540823,0.00033318307,0.0002666299,0.00004886561,0.000079010395],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037575897,0.00009385138,0.0005261,0.0001079651,0.000019387146,0.00000797243,0.00014310237,0.000078489255,0.000713272],"category_scores_gemma":[0.017589621,0.00008447075,0.00004148894,0.00014550905,0.000063362386,0.00004061259,0.000025681993,0.00018840187,0.000036813683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007304498,0.0016508411,0.2063781,0.00093327806,0.000051509807,0.0000018414723,0.0024523793,0.018448874,0.000105367886,0.55556303,0.012035079,0.20230664],"study_design_scores_gemma":[0.0010192019,0.0001255599,0.087194465,0.000301227,0.0000029618438,2.0985347e-7,0.000045365385,0.020703744,0.00010132468,0.8903368,0.00008987057,0.00007925241],"about_ca_topic_score_codex":0.013407509,"about_ca_topic_score_gemma":0.0004144627,"teacher_disagreement_score":0.46711478,"about_ca_system_score_codex":0.00029282022,"about_ca_system_score_gemma":0.00033771433,"threshold_uncertainty_score":0.9931623},"labels":[],"label_agreement":null},{"id":"W2138878140","doi":"10.1002/sim.2069","title":"The value of information and optimal clinical trial design","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Population Health Research Institute; SickKids Foundation; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Sick Kids Foundation","keywords":"Type I and type II errors; Sample size determination; Null hypothesis; Value (mathematics); Sample (material); Set (abstract data type); Value of information; Computer science; Perspective (graphical); Statistics; Clinical trial; Medicine; Mathematics; Artificial intelligence; Internal medicine","score_opus":0.5587308049738138,"score_gpt":0.6187845387614808,"score_spread":0.060053733787666985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138878140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029421945,0.00007956684,0.9934734,0.0011440597,0.000808301,0.000795131,0.00006130837,0.000016507225,0.0006795272],"genre_scores_gemma":[0.0077439924,0.0005403189,0.99081933,0.00021127284,0.00059889944,0.000025214345,0.000002594898,0.000011181103,0.00004721653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99506074,0.001457587,0.002590185,0.00015859936,0.0005026592,0.00023020935],"domain_scores_gemma":[0.8475086,0.1514656,0.00051153946,0.00028184304,0.00013668714,0.00009570134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018654851,0.00013181522,0.00064774737,0.00006821886,0.000063417596,0.000014540296,0.00022135378,0.00013402995,0.000084873434],"category_scores_gemma":[0.3376411,0.000080769554,0.000030892825,0.00015192125,0.0009333927,0.0000684545,0.0000707949,0.0003898998,0.0000073825613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065332497,0.000082585866,0.00006960158,0.000050994557,0.000031500374,0.00000245476,0.00024789886,0.000029109138,0.000002312445,0.7330124,0.013361771,0.24657613],"study_design_scores_gemma":[0.02598109,0.001740946,0.0006570011,0.00010192818,0.00009625724,0.000002700716,0.0001621973,0.014393834,0.00002182247,0.95330745,0.0034345584,0.000100239],"about_ca_topic_score_codex":0.000011612451,"about_ca_topic_score_gemma":0.0000070461006,"teacher_disagreement_score":0.31898624,"about_ca_system_score_codex":0.000028173667,"about_ca_system_score_gemma":0.00008635099,"threshold_uncertainty_score":0.66793823},"labels":[],"label_agreement":null},{"id":"W2140495900","doi":"10.1093/aje/kwn183","title":"A Cautionary Note on the Evaluation of Biomarkers of Subtypes of a Single Disease","year":2008,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fondation pour la Recherche Médicale","keywords":"Disease; Homogeneous; Biomarker; Biomarker discovery; Computational biology; Medicine; Bioinformatics; Biology; Internal medicine; Mathematics; Genetics; Gene","score_opus":0.6819866434161447,"score_gpt":0.5863832651973597,"score_spread":0.09560337821878495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140495900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9342504,0.0002755727,0.06139435,0.0031772663,0.00025937698,0.00023463237,0.000058858117,0.0000035364806,0.00034600013],"genre_scores_gemma":[0.7470317,0.00008038525,0.25260374,0.00020572414,0.000064581094,0.0000028502398,3.7351163e-7,0.000008031202,0.0000026552843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98788404,0.009260111,0.0021433297,0.0001294979,0.000422792,0.00016022667],"domain_scores_gemma":[0.8021927,0.19275877,0.0039332723,0.00031851046,0.0006903343,0.000106439875],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022241766,0.00010534971,0.0011959417,0.00012063823,0.00002685849,3.6057753e-7,0.00024708564,0.000052076008,0.00015170663],"category_scores_gemma":[0.5064848,0.0000633571,0.0003197431,0.00025705263,0.0020641128,0.000022067878,0.000033176726,0.00017912088,0.0000011272992],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020090716,0.005901024,0.18582506,0.0005195342,0.0038916357,0.00008093953,0.0018226691,0.0029258071,0.022234164,0.43386495,0.019036116,0.30380738],"study_design_scores_gemma":[0.0007102261,0.0023144537,0.07467194,0.0002035841,0.0005204033,0.00003390274,0.00013207243,0.0011499655,0.001162551,0.9189748,0.000046962017,0.00007915377],"about_ca_topic_score_codex":0.00003390863,"about_ca_topic_score_gemma":9.851385e-7,"teacher_disagreement_score":0.48510984,"about_ca_system_score_codex":0.000052659463,"about_ca_system_score_gemma":0.0002846604,"threshold_uncertainty_score":0.77085966},"labels":[],"label_agreement":null},{"id":"W2142281918","doi":"10.1186/s40364-014-0027-7","title":"RiGoR: reporting guidelines to address common sources of bias in risk model development","year":2015,"lang":"en","type":"article","venue":"Biomarker Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"CLARITY; Transparency (behavior); Computer science; Data science; Risk analysis (engineering); Publication bias; Rigour; Model selection; Selection bias; Conflation; Medicine; Meta-analysis; Artificial intelligence; Computer security; Pathology","score_opus":0.970106049984621,"score_gpt":0.7255547746195153,"score_spread":0.24455127536510568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142281918","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9550984,0.00011297695,0.037676394,0.0005719,0.00015861468,0.001058221,0.00004381128,0.00005550984,0.005224168],"genre_scores_gemma":[0.21300493,0.00000968589,0.78626364,0.000027625301,0.00006537928,0.00009768302,0.0000011930091,0.000033459542,0.00049638085],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990083,0.0029495142,0.004007456,0.0005003921,0.0018445671,0.00061510835],"domain_scores_gemma":[0.95890504,0.036784343,0.0011785402,0.0009112938,0.0017416242,0.00047918473],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09140667,0.00016886994,0.0007818723,0.0004456369,0.00009144775,0.00004480911,0.00055482757,0.00017870402,0.00005273895],"category_scores_gemma":[0.645482,0.00013322635,0.0000844778,0.0008869593,0.00019953618,0.00004506282,0.00073241716,0.0004062861,0.000036196187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034783874,0.0020166684,0.31845552,0.0011994581,0.00041240922,0.00035517022,0.007946449,0.0010037681,0.002584406,0.015646644,0.17276178,0.47413933],"study_design_scores_gemma":[0.0018839933,0.00021616944,0.015554714,0.0009009333,0.000027850952,0.000008746885,0.0010217956,0.036974363,0.015801147,0.92348593,0.0036616756,0.00046268568],"about_ca_topic_score_codex":0.00049656216,"about_ca_topic_score_gemma":0.0002788407,"teacher_disagreement_score":0.9078393,"about_ca_system_score_codex":0.00015592312,"about_ca_system_score_gemma":0.0004817573,"threshold_uncertainty_score":0.93558806},"labels":[],"label_agreement":null},{"id":"W2143013795","doi":"10.1634/theoncologist.2015-0008","title":"Choice of Starting Dose for Biopharmaceuticals in First-in-Human Phase I Cancer Clinical Trials","year":2015,"lang":"en","type":"article","venue":"The Oncologist","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Clinical trial; Oncology; Cancer; Pharmacology; Intensive care medicine; Internal medicine; Medical physics","score_opus":0.9526026533308177,"score_gpt":0.7811456566783852,"score_spread":0.17145699665243253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143013795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93317574,0.0008564728,0.033187974,0.01361251,0.003935706,0.00929845,0.0007377764,0.00015808358,0.0050372775],"genre_scores_gemma":[0.7115814,0.00015644604,0.28441986,0.0009855578,0.0016346086,0.00090339885,0.000002974493,0.00006115763,0.0002545872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9887731,0.0059573716,0.0041181566,0.00038706147,0.0003155613,0.00044876485],"domain_scores_gemma":[0.67537636,0.32232815,0.0013659338,0.0005255276,0.00019100323,0.00021302246],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0858764,0.00019877678,0.0019021658,0.00007550434,0.000058767597,0.000021625234,0.00054270035,0.0002817732,0.00013694017],"category_scores_gemma":[0.5888545,0.00012532661,0.00028566862,0.00031065533,0.00068978185,0.000045665147,0.00015085415,0.0005099968,0.000006157949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017224401,0.016579904,0.03536968,0.0013946285,0.00056745665,0.00008776113,0.0017611466,0.00031925098,0.0031198158,0.621682,0.029677946,0.27221602],"study_design_scores_gemma":[0.02567507,0.0012819354,0.0008961904,0.00021197116,0.0002608516,4.0873414e-7,0.0002097055,0.0021876586,0.0014968703,0.9604361,0.0071193064,0.00022392513],"about_ca_topic_score_codex":0.0003262133,"about_ca_topic_score_gemma":0.00097064726,"teacher_disagreement_score":0.5029781,"about_ca_system_score_codex":0.00020527384,"about_ca_system_score_gemma":0.00024048254,"threshold_uncertainty_score":0.94128263},"labels":[],"label_agreement":null},{"id":"W2144216228","doi":"10.1200/jco.2009.25.9606","title":"Choice of Starting Dose for Molecularly Targeted Agents Evaluated in First-in-Human Phase I Cancer Clinical Trials","year":2010,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Maximum tolerated dose; Medicine; Clinical trial; Therapeutic index; Cancer; Toxicity; Effective dose (radiation); Pharmacology; Limiting; Oncology; Internal medicine; Nuclear medicine; Drug","score_opus":0.9418097147584127,"score_gpt":0.8078207380371335,"score_spread":0.13398897672127918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144216228","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065476224,0.9377735,0.017346103,0.001263565,0.02343373,0.011995731,0.0011724478,0.000041532192,0.00042577204],"genre_scores_gemma":[0.000099415585,0.74033946,0.25459158,0.00032918647,0.004186805,0.00023687915,0.00001246305,0.00014825547,0.000055954948],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8869807,0.050398972,0.059434272,0.0010391803,0.0012304325,0.00091640843],"domain_scores_gemma":[0.279314,0.6701155,0.047177587,0.00094228785,0.0015776163,0.00087301346],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.28726527,0.0007824951,0.031130519,0.00068699755,0.000061149345,0.000033467728,0.0015868972,0.0051844907,0.00064439874],"category_scores_gemma":[0.90636283,0.00055483193,0.006962605,0.0007349363,0.00071261957,0.00013422176,0.00025814434,0.008258378,0.000006247647],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002601364,0.0082651,0.00028719107,0.0055851904,0.0013487713,0.0002501738,0.000028758095,0.0000040638743,0.0000053061362,0.001575973,0.0020856739,0.97796243],"study_design_scores_gemma":[0.049909662,0.012542689,0.00025284736,0.017352125,0.009235348,0.000012781342,0.0000133280255,0.00035610178,0.0000055019523,0.19221698,0.71743304,0.0006695904],"about_ca_topic_score_codex":0.000060843253,"about_ca_topic_score_gemma":0.00047269254,"teacher_disagreement_score":0.97729284,"about_ca_system_score_codex":0.0004157843,"about_ca_system_score_gemma":0.0058192615,"threshold_uncertainty_score":0.99981683},"labels":[],"label_agreement":null},{"id":"W2145061705","doi":"10.1136/bmjopen-2014-006531","title":"Treatment crossovers in time-to-event non-inferiority randomised trials of radiotherapy in patients with breast cancer","year":2014,"lang":"en","type":"article","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Cancer Centre; St. Joseph's Hospital; McMaster University; Ontario Clinical Oncology Group","funders":"","keywords":"Medicine; Crossover; Crossover study; Breast cancer; Type I and type II errors; Radiation therapy; Random effects model; Randomized controlled trial; Clinical trial; Statistics; Meta-analysis; Cancer; Internal medicine; Mathematics; Alternative medicine; Artificial intelligence; Computer science","score_opus":0.33306585163090197,"score_gpt":0.5853440398446919,"score_spread":0.2522781882137899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145061705","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92882204,0.000005867168,0.01632658,0.00094336946,0.00035932264,0.05054227,0.00084444357,0.00002361041,0.0021325243],"genre_scores_gemma":[0.26650637,0.000019728126,0.7234617,0.0005090672,0.0003525287,0.007923432,0.000009985686,0.00012761683,0.0010896097],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99493045,0.0023026138,0.0017495834,0.00034966585,0.0004046197,0.0002630884],"domain_scores_gemma":[0.977292,0.02126394,0.00068461057,0.0005373687,0.00009185951,0.0001301936],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011585386,0.0002155372,0.0021928123,0.00008777943,0.000021334987,0.000056739,0.0004292288,0.000107840366,0.0014002924],"category_scores_gemma":[0.022549333,0.00014020827,0.00013323434,0.0002376661,0.00006455723,0.00007027141,0.00010683378,0.000089389236,0.000018506764],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.32045785,0.006035854,0.47633624,0.00034840804,0.0007494893,0.000013169061,0.0013603522,0.00042576672,0.0003134158,0.0014713681,0.0018087487,0.19067936],"study_design_scores_gemma":[0.39383182,0.0023185718,0.5673346,0.0013356758,0.00017503183,9.230068e-7,0.000017402772,0.0007471651,0.0008233325,0.03234608,0.00045413736,0.0006152929],"about_ca_topic_score_codex":0.0007105906,"about_ca_topic_score_gemma":0.00013512577,"teacher_disagreement_score":0.7071351,"about_ca_system_score_codex":0.00029682613,"about_ca_system_score_gemma":0.00018631492,"threshold_uncertainty_score":0.99951255},"labels":[],"label_agreement":null},{"id":"W2146514939","doi":"10.1177/1740774507087972","title":"Do we need to adjudicate major clinical events?","year":2008,"lang":"en","type":"review","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":120,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute","funders":"","keywords":"Adjudication; Medicine; Clinical trial; Political science; Law; Internal medicine","score_opus":0.949609721965297,"score_gpt":0.7577542437055319,"score_spread":0.19185547825976512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146514939","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002401706,0.9473287,0.016425842,0.0016392518,0.019762592,0.011244412,0.0013924348,0.00059567264,0.0016086922],"genre_scores_gemma":[1.892655e-7,0.65785044,0.32565483,0.00066502165,0.012987261,0.0007372887,0.000019791309,0.00039231798,0.0016928631],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81900734,0.121303745,0.05058715,0.004732025,0.0023285889,0.0020411487],"domain_scores_gemma":[0.3175006,0.66400695,0.010612164,0.004570367,0.00049597473,0.0028139867],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.19687335,0.0022310896,0.042075723,0.0005976148,0.0002883776,0.00017327536,0.00399044,0.006232312,0.003579156],"category_scores_gemma":[0.9282384,0.0015807181,0.017974148,0.0018103137,0.0011228805,0.00011062401,0.0018526928,0.00605414,0.011431359],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034200202,0.0012711931,0.000014071946,0.003639254,0.00200418,0.00012186368,0.000008252141,3.104777e-8,1.849599e-8,0.008381782,0.18781517,0.79640216],"study_design_scores_gemma":[0.0029028093,0.00074255455,0.000006352809,0.015107384,0.0051292405,0.000036168498,0.0000053403623,9.759846e-7,1.8377938e-7,0.32676458,0.6481919,0.0011124933],"about_ca_topic_score_codex":0.0000045816273,"about_ca_topic_score_gemma":0.0000015221016,"teacher_disagreement_score":0.7952897,"about_ca_system_score_codex":0.00022489608,"about_ca_system_score_gemma":0.0018406931,"threshold_uncertainty_score":0.99904287},"labels":[],"label_agreement":null},{"id":"W2146785136","doi":"10.1001/2012.jama.11235","title":"How to Use a Noninferiority Trial","year":2012,"lang":"en","type":"article","venue":"JAMA","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Randomized controlled trial; Clinical trial; Intensive care medicine; External validity; Medical physics; Surgery; Statistics; Pathology","score_opus":0.6750620277625126,"score_gpt":0.5735045463373779,"score_spread":0.10155748142513465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146785136","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5045732,0.000013706087,0.4750767,0.0072085517,0.0060854834,0.00202541,0.00013196547,0.0002874069,0.0045975256],"genre_scores_gemma":[0.12765768,0.0000016596963,0.86706674,0.0006303919,0.0028956102,0.000060479968,3.811567e-7,0.000025388756,0.0016616784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813193,0.0005801125,0.00039503488,0.00018974637,0.00031273474,0.00039042885],"domain_scores_gemma":[0.9556395,0.043278895,0.000118743104,0.0004958085,0.00009655069,0.00037049284],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030683551,0.00013072201,0.0004517613,0.000038049497,0.000045461038,0.00019476043,0.00017825325,0.00018070106,0.00025652943],"category_scores_gemma":[0.39710045,0.00010477194,0.00012387459,0.00015655442,0.00004347578,0.0002598398,0.00012649524,0.00023706057,0.00019433002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014263614,0.0010773857,0.0032829253,0.00009668645,0.00011217482,0.000013943846,0.0006004848,8.239723e-8,0.0005386376,0.75326234,0.08097602,0.1457757],"study_design_scores_gemma":[0.03604857,0.0005910473,0.008914415,0.00005721032,0.0001421566,0.000005333239,0.00005377738,0.000016538173,0.0019417708,0.82621586,0.12556744,0.00044585968],"about_ca_topic_score_codex":0.0000098994215,"about_ca_topic_score_gemma":0.0000022252489,"teacher_disagreement_score":0.39403212,"about_ca_system_score_codex":0.000040785686,"about_ca_system_score_gemma":0.000022875023,"threshold_uncertainty_score":0.60797805},"labels":[],"label_agreement":null},{"id":"W2147251974","doi":"10.1080/00949650410001729445","title":"Calculating the power or sample size for the logistic and proportional hazards models","year":2005,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Windsor","keywords":"Covariate; Univariate; Mathematics; Statistics; Wald test; Multivariate statistics; Sample size determination; Covariance matrix; Test plan; Algorithm; Econometrics; Statistical hypothesis testing","score_opus":0.5406773557319422,"score_gpt":0.5730639785823223,"score_spread":0.032386622850380076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147251974","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060137324,0.000044528108,0.9915373,0.0016797574,0.00014761518,0.0004453704,0.00009153794,0.000010765006,0.000029449538],"genre_scores_gemma":[0.49579346,0.0000063317834,0.5037935,0.00021879186,0.00016288363,0.0000039379684,7.9125374e-7,0.000008041128,0.000012279602],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794203,0.00031830522,0.0010368561,0.00013946451,0.00041875383,0.00014460341],"domain_scores_gemma":[0.774896,0.22405401,0.0004755709,0.00006851068,0.0004237013,0.000082185026],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002299777,0.000120758414,0.00031790131,0.0000306499,0.00027077275,0.00011059163,0.00007840007,0.00006962376,0.00008671171],"category_scores_gemma":[0.11331833,0.00005903497,0.00005897511,0.000081197824,0.00023694178,0.00012745807,0.00003175361,0.00021451214,4.6429437e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083514745,0.00010841414,0.000114274146,0.00008383407,0.00010645625,0.0000030818942,0.00037467814,0.42726502,0.000010248816,0.4076031,0.00074064074,0.1627551],"study_design_scores_gemma":[0.00057454023,0.00014674956,0.0017221505,0.000016934611,0.00008423432,0.000011883188,0.00006181879,0.50949985,9.933598e-7,0.48772871,0.00010706241,0.000045059278],"about_ca_topic_score_codex":0.0000028350412,"about_ca_topic_score_gemma":0.000004022805,"teacher_disagreement_score":0.48977974,"about_ca_system_score_codex":0.00003449804,"about_ca_system_score_gemma":0.000075616495,"threshold_uncertainty_score":0.89415056},"labels":[],"label_agreement":null},{"id":"W2148021011","doi":"10.1158/1078-0432.ccr-12-1384","title":"Publication and Reporting Conduct for Pharmacodynamic Analyses of Tumor Tissue in Early-Phase Oncology Trials","year":2012,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Clinical trial; Cancer; Pharmacodynamics; Internal medicine; Oncology; Family medicine; Pharmacokinetics","score_opus":0.9837610538107621,"score_gpt":0.8569733973284804,"score_spread":0.12678765648228163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148021011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822393,0.000823072,0.01077172,0.0018340483,0.0008357739,0.002720111,0.00020427855,0.000031532407,0.00054018456],"genre_scores_gemma":[0.7705208,0.0002691336,0.22699083,0.000109905326,0.001098339,0.0007999885,0.000005184191,0.000037517624,0.00016831704],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97977585,0.010173644,0.008087139,0.00057605584,0.0006354237,0.00075189635],"domain_scores_gemma":[0.5600186,0.4323725,0.0049083056,0.0007123674,0.0013943699,0.0005938793],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17893593,0.00015375827,0.0021914146,0.00028077594,0.00007685694,0.000035114503,0.0003085958,0.00026891968,0.0004897311],"category_scores_gemma":[0.8058114,0.00011993469,0.00022844013,0.000605679,0.0007456084,0.00016310197,0.00020730773,0.00087490655,0.0000062992212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066123996,0.0055201147,0.047606807,0.0016280883,0.0006123107,0.000028711067,0.0005614895,0.0000021711173,0.051795244,0.032871995,0.014286787,0.83847386],"study_design_scores_gemma":[0.02738461,0.0047848094,0.019720696,0.00052606326,0.0008316242,0.000014539354,0.00041773324,0.002477992,0.07490445,0.8511744,0.017081572,0.00068149756],"about_ca_topic_score_codex":0.00023952995,"about_ca_topic_score_gemma":0.000026490687,"teacher_disagreement_score":0.8377924,"about_ca_system_score_codex":0.00015579135,"about_ca_system_score_gemma":0.00042573508,"threshold_uncertainty_score":0.84545827},"labels":[],"label_agreement":null},{"id":"W2148357625","doi":"10.1002/sim.4434","title":"Weighted multiple testing correction for correlated tests","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"","keywords":"Bonferroni correction; Type I and type II errors; Multiple comparisons problem; Sequence (biology); Mathematics; Correlation; Statistics; False discovery rate; Statistical hypothesis testing; Null hypothesis; Statistical power; Algorithm; Computer science","score_opus":0.6250874573824682,"score_gpt":0.5510253799376074,"score_spread":0.07406207744486082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148357625","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022961511,0.00002370112,0.986422,0.000054145996,0.004147218,0.0010176401,0.00021172118,0.00015183003,0.005675578],"genre_scores_gemma":[0.03874521,0.00001086246,0.9600566,0.00013251534,0.00035423916,0.00011496625,0.000019982337,0.00005740513,0.0005082242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971684,0.00036548226,0.0013147783,0.00040919692,0.00033227474,0.00040982311],"domain_scores_gemma":[0.86600465,0.1327642,0.00037238037,0.0003207228,0.00039569483,0.00014234723],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003341958,0.00023648908,0.0007473304,0.00016762108,0.00008757331,0.0000066297243,0.00021003315,0.00019365692,0.0005195954],"category_scores_gemma":[0.48747438,0.00019422964,0.00003363566,0.0004962209,0.00033112845,0.000035245972,0.000045425222,0.00042648235,0.000019736315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015354318,0.0012704835,0.06430301,0.0008560711,0.0002021319,0.00023414899,0.0039299857,0.0000059366457,0.0011058949,0.44765088,0.14055964,0.3383464],"study_design_scores_gemma":[0.0031939368,0.000720533,0.010464695,0.00043578056,0.00013940889,0.000010916392,0.00014484326,0.042487003,0.00021323083,0.9417349,0.00023436984,0.00022037303],"about_ca_topic_score_codex":0.00017938482,"about_ca_topic_score_gemma":0.00011691187,"teacher_disagreement_score":0.49408403,"about_ca_system_score_codex":0.00008803698,"about_ca_system_score_gemma":0.000057569603,"threshold_uncertainty_score":0.7920455},"labels":[],"label_agreement":null},{"id":"W2148973996","doi":"","title":"A New Nonparametric Levene Test for Equal Variances","year":2010,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":214,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Nonparametric statistics; Levene's test; Statistics; F-test of equality of variances; Mathematics; Type I and type II errors; Population; Sampling (signal processing); Goldfeld–Quandt test; Econometrics; Test (biology); Statistical hypothesis testing; Computer science; Z-test; Test statistic; Demography","score_opus":0.8284200588886782,"score_gpt":0.7350414308632734,"score_spread":0.09337862802540475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148973996","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060813133,0.0027114504,0.91088474,0.0007896897,0.0076009114,0.0034511655,0.0007196829,0.00018024923,0.012849003],"genre_scores_gemma":[0.10234708,0.0008606961,0.8932035,0.00029862885,0.0017189299,0.00013222285,0.000003182309,0.0001262603,0.001309477],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948481,0.0005636293,0.00227713,0.0006929154,0.0009770689,0.00064116926],"domain_scores_gemma":[0.88118887,0.11506165,0.001732345,0.000875991,0.0005461695,0.00059499015],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00936028,0.00044051567,0.0018076875,0.0007069516,0.0002447876,0.0012627632,0.004038271,0.00035342577,0.020115606],"category_scores_gemma":[0.26359707,0.00037042206,0.0004365259,0.0016769598,0.00022466238,0.001044758,0.00088854,0.0009876463,0.000038560105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010807121,0.002185487,0.07342542,0.0007280229,0.0008193679,0.00005730275,0.00014385532,0.000017512806,0.1333836,0.088516906,0.3279957,0.3716461],"study_design_scores_gemma":[0.0014705819,0.000053393775,0.029686382,0.00024107868,0.0002633377,0.000011724951,0.000011748203,0.00013861462,0.018747734,0.9406485,0.008251711,0.0004751908],"about_ca_topic_score_codex":0.00023675626,"about_ca_topic_score_gemma":0.000046156714,"teacher_disagreement_score":0.8521316,"about_ca_system_score_codex":0.00005554664,"about_ca_system_score_gemma":0.00041370688,"threshold_uncertainty_score":0.9998748},"labels":[],"label_agreement":null},{"id":"W2148999650","doi":"10.3758/s13428-015-0667-z","title":"Effect size measures in a two-independent-samples case with nonnormal and nonhomogeneous data","year":2015,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Statistics; Computer science; Mathematics","score_opus":0.9138052411701298,"score_gpt":0.754588885036263,"score_spread":0.15921635613386687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148999650","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80796933,0.00033410738,0.18629968,0.00011146805,0.00031738429,0.003517406,0.00038348595,0.00013390977,0.00093322434],"genre_scores_gemma":[0.12591474,0.000015586162,0.8732692,0.000013373797,0.0001810149,0.00039196856,0.00000480559,0.000079038444,0.00013025869],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.963642,0.03142296,0.00094439863,0.0011389913,0.0018158832,0.001035775],"domain_scores_gemma":[0.78370845,0.21261178,0.0001616978,0.002150407,0.0005286045,0.0008390655],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1264354,0.00034646178,0.0010464878,0.00028269083,0.00017308493,0.00020635131,0.0009911794,0.00021073862,0.000096069976],"category_scores_gemma":[0.33380154,0.00025169257,0.000058353267,0.0007451635,0.0007577518,0.00020587424,0.0015107729,0.0014132543,0.00001281175],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002492505,0.0009369171,0.02821771,0.0003417199,0.00009777203,0.02567615,0.0006471905,0.0000030587187,0.0028971918,0.0031216976,0.00032236433,0.93524575],"study_design_scores_gemma":[0.067055,0.021375934,0.019569408,0.0018764902,0.0026957844,0.048842784,0.006403408,0.0054405723,0.0713721,0.7460118,0.0042204564,0.0051362463],"about_ca_topic_score_codex":0.0015045638,"about_ca_topic_score_gemma":0.0012985477,"teacher_disagreement_score":0.9301095,"about_ca_system_score_codex":0.00015234793,"about_ca_system_score_gemma":0.00036556122,"threshold_uncertainty_score":0.9999935},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2149134506","doi":"10.1158/1078-0432.ccr-03-0783","title":"Biomarkers, Surrogate End Points, and the Acceleration of Drug Development for Cancer Prevention and Treatment","year":2004,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Drug development; Clinical trial; Surrogate endpoint; Cancer; Cancer drugs; Clinical endpoint; Intensive care medicine; Drug; Clinical Oncology; Oncology; Internal medicine; Pharmacology","score_opus":0.8866212378948998,"score_gpt":0.7355782408196071,"score_spread":0.15104299707529267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149134506","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021963746,0.98986566,0.0012100706,0.0007402093,0.00051708944,0.007005142,0.00035692696,0.000019057692,0.00006620567],"genre_scores_gemma":[0.00001307928,0.89458233,0.10038104,0.000013239058,0.0004045845,0.0039233956,0.000014827477,0.000058459045,0.0006090217],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98939013,0.005722747,0.0028949897,0.00084750407,0.0006749629,0.00046965407],"domain_scores_gemma":[0.8666936,0.131423,0.00081206975,0.0004661012,0.00040919305,0.00019600776],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028686741,0.00036763298,0.0029076508,0.00013805885,0.00024309558,0.00008663478,0.00035162366,0.00044035586,0.00020427884],"category_scores_gemma":[0.04159534,0.00020674184,0.00050521933,0.0003150896,0.0015489794,0.00004815436,0.00029227507,0.0006414708,0.0000032634296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055420195,0.0002119491,0.000016997083,0.012907014,0.00087126927,0.0000012097073,0.00010693028,4.2229562e-8,8.3371035e-8,0.01255917,0.0003934104,0.9723777],"study_design_scores_gemma":[0.007666476,0.00047350084,0.00005615069,0.02099758,0.0016734301,0.000002109537,0.000043013402,0.000016156406,0.000028474933,0.42793092,0.54076076,0.00035140518],"about_ca_topic_score_codex":0.00025979851,"about_ca_topic_score_gemma":0.0005428621,"teacher_disagreement_score":0.9720263,"about_ca_system_score_codex":0.00049760786,"about_ca_system_score_gemma":0.0025116985,"threshold_uncertainty_score":0.9942309},"labels":[],"label_agreement":null},{"id":"W2150700051","doi":"10.1016/j.ejca.2014.04.031","title":"Towards new methods for the determination of dose limiting toxicities and the assessment of the recommended dose for further studies of molecularly targeted agents – Dose-Limiting Toxicity and Toxicity Assessment Recommendation Group for Early Trials of Targeted therapies, an European Organisation for Research and Treatment of Cancer-led study","year":2014,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":122,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Queen's University","funders":"Cancer Research UK; National Cancer Institute; National Institute for Health and Care Research; Sanofi","keywords":"Toxicity; Limiting; Medicine; Pharmacology; Internal medicine; Engineering","score_opus":0.6365875789007553,"score_gpt":0.6253444966340245,"score_spread":0.011243082266730875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150700051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54164934,0.00069656776,0.45106682,0.0012428272,0.00029046996,0.0047483197,0.0002749119,0.0000047215594,0.000026008862],"genre_scores_gemma":[0.5873181,0.00058274,0.41172266,0.000027153468,0.00017733767,0.000120062265,0.0000020480795,0.00004070705,0.000009189394],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98253554,0.013633045,0.0028329478,0.0002971129,0.00046006162,0.00024131661],"domain_scores_gemma":[0.9413501,0.05253085,0.004273811,0.00029580426,0.0014806158,0.00006880104],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053503502,0.00024664318,0.001440955,0.00012760871,0.00023753008,0.00005140936,0.00031120266,0.000047779056,0.000012970696],"category_scores_gemma":[0.027215257,0.00013171406,0.00027578668,0.00015597863,0.00035989052,0.0001369874,0.0001185499,0.00015372476,3.2257226e-9],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00436555,0.0008607602,0.0016366605,0.0007216698,0.0020218424,1.8081222e-7,0.015665244,0.000017187693,0.08239502,0.0024141627,0.00004002862,0.8898617],"study_design_scores_gemma":[0.10529903,0.054575875,0.19535567,0.0022023076,0.0072641834,0.000004056037,0.037207395,0.02237829,0.33946437,0.23497313,0.0005010851,0.0007745973],"about_ca_topic_score_codex":0.000054685934,"about_ca_topic_score_gemma":0.000061328,"teacher_disagreement_score":0.8890871,"about_ca_system_score_codex":0.0001370854,"about_ca_system_score_gemma":0.0001622155,"threshold_uncertainty_score":0.9809789},"labels":[],"label_agreement":null},{"id":"W2150852620","doi":"10.1080/10601330802131451","title":"Evaluation of Bioequivalence of Highly Variable Drugs","year":2008,"lang":"en","type":"article","venue":"Clinical Research and Regulatory Affairs","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Pharmacology; Medicine; Pharmacokinetics","score_opus":0.8411408555136874,"score_gpt":0.6568679183698306,"score_spread":0.18427293714385684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150852620","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97496545,0.0005938905,0.0029118287,0.00022846214,0.0004294263,0.0009215196,0.000053546242,0.000037148133,0.019858718],"genre_scores_gemma":[0.81015265,0.0003487429,0.1889006,0.000006303887,0.0001807304,0.000021527827,6.690929e-7,0.000018816594,0.00036997246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877019,0.0060188905,0.002073147,0.0005501231,0.0032088866,0.0004470443],"domain_scores_gemma":[0.89552486,0.10015505,0.00044234894,0.00087389763,0.0026423682,0.0003614804],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08070463,0.00013554728,0.0008426121,0.00015528571,0.00012945144,0.00000712401,0.0003790044,0.00033925765,0.0002974181],"category_scores_gemma":[0.292734,0.00010603846,0.00015731947,0.00054395414,0.004371376,0.00007721531,0.00026647968,0.0005661343,0.000010545048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009871408,0.0024942702,0.0043672533,0.00090543565,0.00039948666,0.000013756518,0.0004398456,0.000007951939,0.0026956606,0.89489836,0.011276098,0.08151475],"study_design_scores_gemma":[0.0017683468,0.00096062303,0.0052207,0.00021885261,0.00011379209,0.0000033491353,0.0003330788,0.00067695294,0.0052274745,0.9851689,0.00019193148,0.00011605032],"about_ca_topic_score_codex":0.00000961132,"about_ca_topic_score_gemma":8.9383894e-7,"teacher_disagreement_score":0.21202937,"about_ca_system_score_codex":0.000044875243,"about_ca_system_score_gemma":0.00075244386,"threshold_uncertainty_score":0.99833816},"labels":[],"label_agreement":null},{"id":"W2150911897","doi":"10.1155/s0161171201005750","title":"Play‐the‐winner rule and adaptive designs of clinical trials","year":2001,"lang":"en","type":"article","venue":"International Journal of Mathematics and Mathematical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Manitoba","funders":"Faculty of Medicine, Memorial University of Newfoundland; Memorial University of Newfoundland","keywords":"Interchangeability; Regret; Simple (philosophy); Mathematics; Adaptive design; Mathematical optimization; Clinical trial; Artificial intelligence; Computer science; Statistics; Medicine","score_opus":0.8463739361824619,"score_gpt":0.6613213619018622,"score_spread":0.18505257428059974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150911897","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34765965,0.00033441797,0.64008623,0.0049905987,0.0011203544,0.0005870222,0.000034154025,0.000020328174,0.005167261],"genre_scores_gemma":[0.16378833,0.0005147076,0.83496565,0.00016112268,0.00046286403,0.0000060312786,7.975567e-8,0.0000143445195,0.000086857304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993045,0.0010478117,0.0041221757,0.00023202309,0.0013251642,0.0002278576],"domain_scores_gemma":[0.8853035,0.111307845,0.0024942702,0.00017312872,0.00051916146,0.0002020913],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04673035,0.00019954363,0.0014851096,0.00014331596,0.000105769315,0.00012815242,0.00078625383,0.00014267038,0.0003162058],"category_scores_gemma":[0.17823555,0.00010339624,0.00033824416,0.00018364571,0.0015020046,0.00018005002,0.00021857201,0.00034369738,0.000005136909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012902022,0.00065980025,0.00037713174,0.00007794647,0.00035374606,0.00003241359,0.00063649466,0.0000028747618,0.0002068962,0.96970594,0.0008488837,0.026968826],"study_design_scores_gemma":[0.00091493863,0.00042936538,0.00026446846,0.00041774168,0.00020729717,0.0003935855,0.0009460987,0.0029343846,0.00029256684,0.99290425,0.00017461173,0.00012066743],"about_ca_topic_score_codex":0.0000027151784,"about_ca_topic_score_gemma":0.0000010487081,"teacher_disagreement_score":0.19487946,"about_ca_system_score_codex":0.000014647982,"about_ca_system_score_gemma":0.000102416336,"threshold_uncertainty_score":0.9815917},"labels":[],"label_agreement":null},{"id":"W2151067943","doi":"10.1093/annonc/mdp478","title":"Influence of an independent review committee on assessment of response rate and progression-free survival in phase III clinical trials","year":2009,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Oncology; Clinical trial; Internal medicine; Progression-free survival; Overall survival","score_opus":0.7811995527025647,"score_gpt":0.7408788541978925,"score_spread":0.04032069850467224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151067943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9915898,0.00040809409,0.0007038002,0.0050411266,0.0001581528,0.00147436,0.00011842101,0.000012512683,0.00049371854],"genre_scores_gemma":[0.7946617,0.005085911,0.19810037,0.0019985286,0.0000789186,0.00004350422,0.000002454343,0.000017220238,0.000011406694],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9241662,0.066548176,0.007636964,0.000555201,0.0007338243,0.00035962183],"domain_scores_gemma":[0.76126385,0.23410174,0.0030863795,0.000900472,0.0004603684,0.00018721801],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19712624,0.00019986895,0.003709533,0.00014865061,0.000019738553,0.0000042055763,0.0005107609,0.00036939,0.00006316072],"category_scores_gemma":[0.48985198,0.00015084553,0.00023117308,0.00025154668,0.0004716717,0.00006947882,0.00015500713,0.00051504665,6.1908065e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.043127302,0.020619629,0.0025891226,0.0016130009,0.00026325986,0.00015439556,0.00015573094,0.000021900916,0.00428858,0.056788456,0.0028974079,0.86748123],"study_design_scores_gemma":[0.024209615,0.050553083,0.16395473,0.004785189,0.00026723812,0.000006160739,0.000047082965,0.00012424692,0.0042439555,0.75086033,0.00066503,0.00028332285],"about_ca_topic_score_codex":0.000008250718,"about_ca_topic_score_gemma":0.000009053223,"teacher_disagreement_score":0.8671979,"about_ca_system_score_codex":0.000021187316,"about_ca_system_score_gemma":0.00039856005,"threshold_uncertainty_score":0.8267275},"labels":[],"label_agreement":null},{"id":"W2151070032","doi":"10.3945/ajcn.115.113548","title":"Best (but oft-forgotten) practices: the multiple problems of multiplicity—whether and how to correct for many statistical tests","year":2015,"lang":"en","type":"article","venue":"American Journal of Clinical Nutrition","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":348,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Toronto","funders":"","keywords":"Multiple comparisons problem; Resampling; False discovery rate; Bonferroni correction; Statistical hypothesis testing; Null hypothesis; Multiplicity (mathematics); Statistics; Econometrics; Statistic; Mathematics; Computer science","score_opus":0.6155333581101351,"score_gpt":0.5890310654222888,"score_spread":0.02650229268784632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151070032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29341426,0.00009597672,0.69185144,0.0114763845,0.0009112267,0.0018250315,0.0003296429,0.000022002376,0.00007401558],"genre_scores_gemma":[0.34831253,0.00012297355,0.65024066,0.0004453929,0.0007526865,0.000053684074,0.0000014639335,0.000035464192,0.00003513899],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9938872,0.0022305148,0.0024695462,0.00035561013,0.0007157467,0.00034140245],"domain_scores_gemma":[0.79799074,0.19551185,0.0042879726,0.0003594494,0.0012923907,0.0005576125],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013342722,0.00023949335,0.0016389267,0.00009843972,0.00007040346,0.000067102344,0.00041650803,0.0001589849,0.000013717665],"category_scores_gemma":[0.5130425,0.0001562204,0.0003075441,0.000288968,0.0010280206,0.00017952008,0.00010339274,0.0006817201,0.000005194623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028656475,0.015328753,0.050001957,0.002017305,0.0015695562,0.00008079249,0.0015216128,0.00004901941,0.0031430228,0.022798797,0.087709874,0.78712285],"study_design_scores_gemma":[0.025040789,0.042125355,0.0091608865,0.0024968158,0.0017815024,0.00029915734,0.007232347,0.00484402,0.0009667644,0.8786159,0.026536265,0.00090017525],"about_ca_topic_score_codex":0.000043227523,"about_ca_topic_score_gemma":0.000025386486,"teacher_disagreement_score":0.85581714,"about_ca_system_score_codex":0.000039900515,"about_ca_system_score_gemma":0.00016510472,"threshold_uncertainty_score":0.6370483},"labels":[],"label_agreement":null},{"id":"W2151248340","doi":"10.1002/sim.5889","title":"Using confidence intervals to compare several correlated areas under the receiver operating characteristic curves","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Confidence interval; Statistics; Computer science; Mathematics","score_opus":0.5440103651787387,"score_gpt":0.569237814890378,"score_spread":0.02522744971163926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151248340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025243677,0.00010820476,0.96698016,0.003621644,0.0014603247,0.0015913195,0.00021868477,0.00006078491,0.000715229],"genre_scores_gemma":[0.2715498,0.000088636276,0.7212158,0.0062350947,0.00035201633,0.000093657356,0.000020728983,0.000056283567,0.0003880422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954056,0.001381882,0.0016391092,0.00044989004,0.00064336596,0.00048012618],"domain_scores_gemma":[0.9508122,0.047458023,0.00038901455,0.0005822801,0.0005139989,0.0002444562],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035809884,0.00031471666,0.0010352569,0.00010235075,0.0001447492,0.000057320034,0.0005040503,0.000081403174,0.0044047534],"category_scores_gemma":[0.11900029,0.00020543324,0.000039328537,0.00042456546,0.00052801205,0.00008311261,0.0001821871,0.00070629973,0.00013041569],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022209175,0.00046484632,0.0072143073,0.0020626353,0.00041146754,0.00025133352,0.0061292327,0.00068020105,0.0032878076,0.7011559,0.26493925,0.013180944],"study_design_scores_gemma":[0.0013280388,0.00022824504,0.028662547,0.006007723,0.0002111558,0.00003767393,0.0013479321,0.045760717,0.0000503817,0.9158216,0.000115005285,0.00042894302],"about_ca_topic_score_codex":0.00082992,"about_ca_topic_score_gemma":0.00009387428,"teacher_disagreement_score":0.26482424,"about_ca_system_score_codex":0.00014520639,"about_ca_system_score_gemma":0.000079148704,"threshold_uncertainty_score":0.9965054},"labels":[],"label_agreement":null},{"id":"W2151796218","doi":"10.2196/jmir.7.1.e5","title":"The Internet and Clinical Trials: Background, Online Resources, Examples and Issues","year":2005,"lang":"en","type":"review","venue":"Journal of Medical Internet Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton General Hospital; Hamilton Health Sciences","funders":"","keywords":"The Internet; Clinical trial; Randomized controlled trial; Medicine; Medical physics; Computer science; World Wide Web; Surgery; Pathology","score_opus":0.9320175324453995,"score_gpt":0.7712830913716275,"score_spread":0.160734441073772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151796218","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000124929,0.9912464,0.0018461094,0.004391005,0.0013207496,0.0008209611,0.000053239688,0.000016938602,0.0001796578],"genre_scores_gemma":[0.000003283226,0.9262315,0.060735684,0.00009255614,0.00959713,0.000017560766,0.0000025573352,0.00009070802,0.0032290309],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9110706,0.06800571,0.012800917,0.0008790289,0.0062387744,0.0010049883],"domain_scores_gemma":[0.29300314,0.6997663,0.003697257,0.0008718903,0.00093178346,0.001729681],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3333852,0.0005579311,0.0070682694,0.00043524237,0.00011935515,0.00072396605,0.0029698007,0.001839556,0.0014674522],"category_scores_gemma":[0.7446266,0.00026809284,0.0012656667,0.0003562424,0.0035804335,0.000096525866,0.00216541,0.010561508,0.000036966652],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021777129,0.00031885612,0.0000067434944,0.0022751924,0.0010156147,0.00020438497,0.00007962308,9.750208e-10,1.0256469e-8,0.010563566,0.10076301,0.8845552],"study_design_scores_gemma":[0.0011123812,0.0010470451,0.000006626954,0.027606042,0.0008597905,0.0006474208,0.00027762723,0.00008681889,1.14950154e-7,0.06462232,0.90351635,0.00021748431],"about_ca_topic_score_codex":0.000087855115,"about_ca_topic_score_gemma":0.00015908408,"teacher_disagreement_score":0.8843377,"about_ca_system_score_codex":0.0001800571,"about_ca_system_score_gemma":0.00075046154,"threshold_uncertainty_score":0.9999771},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2153109441","doi":"10.1093/bioinformatics/btu494","title":"STAMP: statistical analysis of taxonomic and functional profiles","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4314,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Python (programming language); Computer science; Graphical user interface; Software; R package; Exploratory data analysis; Statistical analysis; Data mining; Source code; Software package; Information retrieval; Programming language; Statistics; Mathematics","score_opus":0.36813942562374635,"score_gpt":0.47157612010780703,"score_spread":0.10343669448406068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153109441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020434024,0.000005060273,0.9747825,0.00004313407,0.0001487401,0.00021320638,0.00039560854,0.0000402408,0.0039374745],"genre_scores_gemma":[0.0913465,0.0000081555345,0.9084182,0.000075894735,0.000056776313,0.0000125826455,0.00001701913,0.00000982947,0.000055072942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806935,0.00019101046,0.0011188869,0.0001334977,0.0003010637,0.00018616764],"domain_scores_gemma":[0.97442913,0.024639,0.00039371612,0.00031026552,0.00010370498,0.0001241875],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002018413,0.0001383771,0.00068917905,0.00019041382,0.000046390425,0.000027807362,0.00009878015,0.00010868012,0.00045803256],"category_scores_gemma":[0.031612284,0.00011054218,0.00010242923,0.00029736137,0.00026113464,0.00007263636,0.00008472461,0.00011977053,0.000018826244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005949864,0.000080610975,0.0034277155,0.00032390252,0.00060715835,2.6810787e-7,0.00010386137,0.00001867224,0.000027307426,0.97087324,0.0035547158,0.020923045],"study_design_scores_gemma":[0.0008860613,0.00024512317,0.031729545,0.000038327278,0.0020599498,0.0000022257038,0.00017785763,0.24155574,0.00027330054,0.7214663,0.0012759755,0.00028961242],"about_ca_topic_score_codex":0.0000041450207,"about_ca_topic_score_gemma":0.0000028090585,"teacher_disagreement_score":0.24940696,"about_ca_system_score_codex":0.000019757708,"about_ca_system_score_gemma":0.00003331175,"threshold_uncertainty_score":0.97654486},"labels":[],"label_agreement":null},{"id":"W2153128783","doi":"10.18433/j35889","title":"Examining the Role of Metabolites in Bioequivalence Assessment","year":2010,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Cmax; Metabolite; Analyte; Pharmacokinetics; Chemistry; Active metabolite; Absorption (acoustics); Drug; Pharmacology; Chromatography; Mathematics; Medicine; Biochemistry; Materials science","score_opus":0.6540041474466444,"score_gpt":0.6478827242506174,"score_spread":0.006121423196026932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153128783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877075,0.00089703774,0.0030863967,0.0018053112,0.0016494347,0.00029785896,0.00001289822,0.000013802715,0.0045297868],"genre_scores_gemma":[0.73082155,0.00025851934,0.26839864,0.00017680935,0.00032639632,0.0000042759652,2.107012e-8,0.000007689424,0.0000061246174],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995358,0.0010829025,0.0016749996,0.00024070259,0.001215944,0.00042746033],"domain_scores_gemma":[0.96086276,0.037584007,0.00086614466,0.00019257652,0.00024247935,0.00025200858],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020263568,0.00017558344,0.00061658944,0.00017949076,0.00011883538,0.000070678594,0.0012771741,0.000053408603,0.0010423537],"category_scores_gemma":[0.026756657,0.00009825317,0.00017671952,0.0007954554,0.0014904249,0.00031277863,0.00019234476,0.0012757714,0.0000035666758],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012000274,0.00055433944,0.075731166,0.00005735028,0.00006285204,0.000021768807,0.00022985773,0.0000125535,0.5456773,0.14855434,0.000093015056,0.22888546],"study_design_scores_gemma":[0.0018722935,0.00022100745,0.0068011465,0.000088438996,0.00027850972,0.00007501872,0.00054379745,0.0071956394,0.2949808,0.6711298,0.016601272,0.00021224981],"about_ca_topic_score_codex":0.000011059239,"about_ca_topic_score_gemma":0.0000026113678,"teacher_disagreement_score":0.5225755,"about_ca_system_score_codex":0.000024504729,"about_ca_system_score_gemma":0.00028908366,"threshold_uncertainty_score":0.99987084},"labels":[],"label_agreement":null},{"id":"W2153537366","doi":"10.1111/1467-9574.00209","title":"A Bayesian adaptive design in clinical trials for continuous responses","year":2002,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bayesian probability; Computer science; Clinical trial; Convergence (economics); Covariate; Adaptive design; Bayesian inference; Mathematical optimization; Econometrics; Artificial intelligence; Machine learning; Mathematics; Medicine; Economics","score_opus":0.8210327105601135,"score_gpt":0.6167936388702271,"score_spread":0.20423907168988642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153537366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022683597,0.00011128014,0.99185044,0.0007162436,0.00075737113,0.0030341248,0.0015772225,0.00014671385,0.0015797426],"genre_scores_gemma":[0.052907392,0.00009413301,0.9444404,0.0003245239,0.000505701,0.0005407425,0.000005235094,0.000087424116,0.0010944457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9779856,0.01507437,0.0046752854,0.0008784235,0.0005564787,0.000829798],"domain_scores_gemma":[0.5546746,0.4436231,0.00074656494,0.00048652655,0.00014257783,0.00032660257],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04220437,0.00040140218,0.0027192761,0.00023980493,0.00011875772,0.000080995895,0.00042325922,0.0004384966,0.0021564546],"category_scores_gemma":[0.7128542,0.0003292764,0.0004233398,0.00033867016,0.0004636468,0.00006382864,0.000070997055,0.00060541794,0.00010836891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009402781,0.0016486805,0.00083454215,0.00019054925,0.00044787477,0.00034459983,0.0005294673,0.0000054639836,0.00005777034,0.51076674,0.2147413,0.26103023],"study_design_scores_gemma":[0.0063858978,0.0020346798,0.0007305237,0.00015943412,0.00031470982,0.000010746415,0.00009637342,0.022540318,0.000054152097,0.9649701,0.0022561278,0.0004469167],"about_ca_topic_score_codex":0.000011099943,"about_ca_topic_score_gemma":0.000011708994,"teacher_disagreement_score":0.6706498,"about_ca_system_score_codex":0.00008008563,"about_ca_system_score_gemma":0.00011003065,"threshold_uncertainty_score":0.99991596},"labels":[],"label_agreement":null},{"id":"W2154296834","doi":"10.1186/1745-6215-10-49","title":"Stopping randomized trials early for benefit: a protocol of the Study Of Trial Policy Of Interim Truncation-2 (STOPIT-2)","year":2009,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; St. Michael's Hospital; Western University; AIDS Vancouver; University of British Columbia; Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; McMaster University","funders":"Medical Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Interim; Medicine; Protocol (science); Interim analysis; Truncation (statistics); Randomized controlled trial; Data monitoring committee; Research design; Early stopping; Clinical trial; Medical physics; Alternative medicine; Statistics; Internal medicine; Computer science; Law; Artificial intelligence; Pathology; Mathematics","score_opus":0.8236072502114632,"score_gpt":0.6884190417043091,"score_spread":0.13518820850715407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154296834","genre_codex":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1895052,0.000013557343,0.04999102,0.00073403923,0.0011631728,0.75771105,0.00030135558,0.00005381564,0.00052677625],"genre_scores_gemma":[0.46409723,0.0000054365405,0.33694324,0.00011095103,0.0025333818,0.19592033,0.0000016879526,0.000077363715,0.0003103672],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9630056,0.02157004,0.013620643,0.00048281823,0.0009699424,0.00035092706],"domain_scores_gemma":[0.62349397,0.36370128,0.010722207,0.0012278018,0.00076244655,0.000092277056],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10524763,0.00031190552,0.008496558,0.0002511603,0.00006414007,0.000025666943,0.0007523415,0.0002457103,0.00012405784],"category_scores_gemma":[0.8124747,0.0001786075,0.0019813515,0.00051064073,0.00025046442,0.00006255472,0.00009413149,0.00018067648,7.2648055e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7782953,0.0028649552,0.000009956542,0.00031499023,0.0006773217,1.4932537e-7,0.0017430597,0.0000051673155,0.0041951835,0.18512262,0.00018859385,0.026582697],"study_design_scores_gemma":[0.4524802,0.0028016865,0.00007265158,0.00021148566,0.0007947704,1.5389143e-7,0.00010580145,0.000015824688,0.011484698,0.5319062,0.000027705799,0.00009883609],"about_ca_topic_score_codex":0.00010239409,"about_ca_topic_score_gemma":0.0000055900423,"teacher_disagreement_score":0.7072271,"about_ca_system_score_codex":0.000046806246,"about_ca_system_score_gemma":0.00030807668,"threshold_uncertainty_score":0.9213359},"labels":[],"label_agreement":null},{"id":"W2154632398","doi":"10.1177/1087057110377497","title":"Experimental Design and Statistical Methods for Improved Hit Detection in High-Throughput Screening","year":2010,"lang":"en","type":"article","venue":"SLAS DISCOVERY","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre; McGill University","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Replicate; Benchmark (surveying); Statistical power; Computer science; Preprocessor; Identification (biology); Statistical inference; Statistical hypothesis testing; Inference; Receiver operating characteristic; Statistics; Column (typography); Type I and type II errors; False positive rate; Word error rate; Data mining; Artificial intelligence; Mathematics; Machine learning","score_opus":0.35672579149214634,"score_gpt":0.5674295538723138,"score_spread":0.21070376238016741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154632398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029947624,0.000028018492,0.967699,0.00007430698,0.0009935696,0.0010618903,0.000086261534,0.00005737812,0.000051930907],"genre_scores_gemma":[0.12964381,0.0000033529277,0.86971426,0.00007169086,0.00022493528,0.00022885279,0.0000028005124,0.000047433798,0.00006283894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99733067,0.00092167454,0.00071291276,0.0005251042,0.00013221997,0.00037742805],"domain_scores_gemma":[0.9407291,0.058662184,0.00016402795,0.00029409112,0.000038647628,0.00011197407],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004289056,0.00022494374,0.00058551726,0.00007633282,0.00009436138,0.00012505447,0.00013995705,0.00023789324,0.00007995554],"category_scores_gemma":[0.047600087,0.000199872,0.00007642846,0.00011630908,0.00023954968,0.00024751524,0.00011530929,0.0004242047,0.0000021589078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001209944,0.00036164938,0.000055798337,0.000107943306,0.00008019048,0.0000055040273,0.00015616765,0.0000043343,0.36538926,0.38323623,0.00018835338,0.2492046],"study_design_scores_gemma":[0.0018586981,0.00037373824,0.0004463679,0.000023461693,0.000054434804,0.0000050742806,0.00007496406,0.011406294,0.19178079,0.79363793,0.000106467895,0.00023178731],"about_ca_topic_score_codex":0.00004846725,"about_ca_topic_score_gemma":0.000021657681,"teacher_disagreement_score":0.4104017,"about_ca_system_score_codex":0.000041784562,"about_ca_system_score_gemma":0.000042492255,"threshold_uncertainty_score":0.9604224},"labels":[],"label_agreement":null},{"id":"W2155086368","doi":"10.1016/j.cca.2005.11.007","title":"Testing experimental data for univariate normality","year":2006,"lang":"en","type":"review","venue":"Clinica Chimica Acta","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":236,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Normality; Statistics; Normality test; Kurtosis; Skewness; Anderson–Darling test; Sample size determination; Percentile; Mathematics; Quantile; Univariate; Goodness of fit; Statistical hypothesis testing; Econometrics; Kolmogorov–Smirnov test; Multivariate statistics","score_opus":0.8925548796379184,"score_gpt":0.6694180607045064,"score_spread":0.22313681893341197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155086368","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000089341465,0.942593,0.007419548,0.00020363639,0.005596362,0.009519531,0.022984216,0.0008972785,0.010777543],"genre_scores_gemma":[0.0000023958662,0.35490385,0.64156616,0.00007655108,0.0022338077,0.00023598286,0.00047823883,0.0002226987,0.00028031055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886574,0.0024087226,0.0055536646,0.002042739,0.00048697728,0.00085048215],"domain_scores_gemma":[0.725537,0.26700684,0.0026187147,0.004418594,0.00015185749,0.00026700686],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0108986795,0.00096592103,0.006032603,0.00011853948,0.00023205516,0.00015343363,0.0039346213,0.0012342996,0.00023531988],"category_scores_gemma":[0.3396956,0.00078284653,0.0011152284,0.00043898702,0.00040181685,0.00015749477,0.0022366212,0.0012950591,0.000057785146],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012363061,0.0024899105,0.0000037333114,0.036096405,0.0010869986,0.000018724988,0.000014342839,3.088966e-8,0.00001094944,0.0164206,0.16246806,0.7812666],"study_design_scores_gemma":[0.00085816975,0.00019398451,0.000002413004,0.006054173,0.0027307607,0.000014759728,0.0000039309657,0.00011962855,0.0000027940432,0.105463766,0.88373774,0.00081787165],"about_ca_topic_score_codex":0.000010844174,"about_ca_topic_score_gemma":0.000002517367,"teacher_disagreement_score":0.78044873,"about_ca_system_score_codex":0.00015521649,"about_ca_system_score_gemma":0.0006856197,"threshold_uncertainty_score":0.99946225},"labels":[],"label_agreement":null},{"id":"W2155212320","doi":"10.1093/jnci/djp401","title":"Response: Re: Dose Escalation Methods in Phase I Cancer Clinical Trials","year":2009,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Clinical trial; Medicine; De-escalation; Oncology; Cancer; Internal medicine","score_opus":0.8932938952765928,"score_gpt":0.7728696398865956,"score_spread":0.12042425538999713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155212320","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23581828,0.0023975298,0.5426978,0.15798174,0.05374603,0.0034382401,0.0008471757,0.00010070102,0.0029724769],"genre_scores_gemma":[0.087222256,0.0005483068,0.90126026,0.0049797976,0.00549569,0.000041692438,7.494872e-7,0.000028126884,0.0004230973],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97977096,0.013101194,0.005080922,0.00029301504,0.0014794641,0.00027442438],"domain_scores_gemma":[0.9192816,0.075591974,0.0035041752,0.00026914693,0.0011555479,0.00019755431],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.097478665,0.00022231741,0.0014042582,0.00025489082,0.00011720659,0.000057439778,0.00068661367,0.00030389114,0.00038798348],"category_scores_gemma":[0.5040477,0.00014055826,0.00070479146,0.00073886383,0.00023610958,0.00035205565,0.000062629355,0.0011291681,0.0000030057035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031169433,0.0025734166,0.0012705084,0.00007255398,0.0006791318,0.00005210677,0.00041224813,0.0029691427,0.012421514,0.11269856,0.0932862,0.74239516],"study_design_scores_gemma":[0.009333428,0.00036544967,0.015189558,0.00048800564,0.00027149945,0.000020546675,0.000011801365,0.0008901872,0.0024273933,0.942278,0.028510723,0.0002133757],"about_ca_topic_score_codex":0.000014066441,"about_ca_topic_score_gemma":0.00003549678,"teacher_disagreement_score":0.8295795,"about_ca_system_score_codex":0.000753751,"about_ca_system_score_gemma":0.0016761695,"threshold_uncertainty_score":0.92933565},"labels":[],"label_agreement":null},{"id":"W2155235311","doi":"10.1177/0091270009355155","title":"Operating Characteristics of a Partial‐Block Randomized Crossover Bioequivalence Study for Dutasteride, a Drug with a Long Half‐Life: Investigation Through Simulation and Comparison with Final Results","year":2010,"lang":"en","type":"article","venue":"The Journal of Clinical Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Bioequivalence; Crossover study; Dutasteride; Crossover; Medicine; Randomized controlled trial; Block (permutation group theory); Sample size determination; Mathematics; Computer science; Pharmacology; Statistics; Pharmacokinetics; Surgery; Internal medicine; Machine learning; Placebo","score_opus":0.5556653165397538,"score_gpt":0.6166235713161934,"score_spread":0.06095825477643957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155235311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9131724,0.000016565069,0.082695425,0.0013094951,0.0008869759,0.0018598419,0.000036454487,0.0000111467325,0.000011704843],"genre_scores_gemma":[0.8254018,0.000018091852,0.17335582,0.0003348039,0.0008265625,0.000023910303,7.8997635e-7,0.000023285054,0.000014933165],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9900211,0.0043892968,0.0046082553,0.00026626256,0.000461996,0.00025307687],"domain_scores_gemma":[0.7896844,0.20352508,0.0053081065,0.00027220693,0.0009996842,0.00021048919],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0246826,0.00023498923,0.002234624,0.0000467669,0.00014939296,0.000043431995,0.00031983617,0.00014389619,0.00003182161],"category_scores_gemma":[0.1082863,0.00012391794,0.00015808162,0.000148242,0.0015364903,0.00017685589,0.00009466806,0.0010540329,6.2361903e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.94413704,0.003453296,0.03120411,0.0004974963,0.002428699,0.000048105314,0.006466128,0.003156459,0.0033291036,0.0014305977,0.000940642,0.0029083195],"study_design_scores_gemma":[0.75352776,0.015438302,0.028272329,0.00066459156,0.01146119,0.00013750556,0.0008360814,0.120654166,0.0055980035,0.062512696,0.00016305548,0.0007343303],"about_ca_topic_score_codex":0.00001326157,"about_ca_topic_score_gemma":0.000016462129,"teacher_disagreement_score":0.20033668,"about_ca_system_score_codex":0.000009877831,"about_ca_system_score_gemma":0.0002600566,"threshold_uncertainty_score":0.899225},"labels":[],"label_agreement":null},{"id":"W2155947418","doi":"10.1016/j.jclinepi.2008.08.005","title":"Inadequate statistical power to detect clinically significant differences in adverse event rates in randomized controlled trials","year":2008,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":138,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Centre for Advancing Health Outcomes; Vancouver General Hospital","funders":"","keywords":"Statistical power; Adverse effect; Event (particle physics); Medicine; Randomized controlled trial; Statistics; Internal medicine; Mathematics; Physics","score_opus":0.8062677585673081,"score_gpt":0.6897538581019267,"score_spread":0.11651390046538146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155947418","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003793331,0.6987228,0.27696708,0.001680989,0.008816035,0.012867499,0.00025730152,0.000041849595,0.00026709962],"genre_scores_gemma":[0.00018178535,0.6542075,0.34331667,0.0006945436,0.0010763681,0.000389313,0.0000027684193,0.00008361112,0.000047438487],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.24804275,0.5712223,0.17501742,0.0021088375,0.0015665402,0.0020421618],"domain_scores_gemma":[0.027682789,0.91806865,0.051050726,0.0010404495,0.00065191375,0.0015054987],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.62694836,0.0015685541,0.18188745,0.001477038,0.000057027024,0.000026959304,0.0019453161,0.003636825,0.0008834405],"category_scores_gemma":[0.9954665,0.000827178,0.02024016,0.0008314476,0.0018441174,0.00008989358,0.000399279,0.007993931,0.00011897867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.26258272,0.0017740374,0.0010228761,0.0024952416,0.0044528195,0.0016194489,0.000054888947,0.000014950257,6.684055e-8,0.026953338,0.0033039015,0.69572574],"study_design_scores_gemma":[0.23246686,0.003054395,0.0005666367,0.018361604,0.00416348,0.00009260014,0.000021497372,0.00012934332,5.59017e-8,0.72655904,0.013733676,0.0008508079],"about_ca_topic_score_codex":0.00003061116,"about_ca_topic_score_gemma":0.000017732207,"teacher_disagreement_score":0.6996057,"about_ca_system_score_codex":0.0003021071,"about_ca_system_score_gemma":0.0030463901,"threshold_uncertainty_score":0.99970627},"labels":[],"label_agreement":null},{"id":"W2156520838","doi":"10.1158/1078-0432.ccr-09-1993","title":"An Overview of the Optimal Planning, Design, and Conduct of Phase I Studies of New Therapeutics","year":2010,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Clinical trial; Clinical study design; Medicine; Drug development; Research design; Clinical endpoint; Medical physics; Drug; Pharmacology; Pathology","score_opus":0.9926679819552562,"score_gpt":0.8542575059713408,"score_spread":0.13841047598391543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156520838","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051538594,0.9945278,0.0016695893,0.00008698593,0.00066555664,0.0022135729,0.00027860532,0.000010585262,0.000031887525],"genre_scores_gemma":[0.000014221297,0.8207671,0.17854135,0.000023491946,0.0004021041,0.00008085727,9.475081e-7,0.00006240941,0.00010750582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98134875,0.012058954,0.004265347,0.0006666847,0.0012189338,0.00044135007],"domain_scores_gemma":[0.7522355,0.24236524,0.0022237385,0.001728344,0.0011602904,0.0002869305],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033205815,0.00037738428,0.0054857205,0.00013386564,0.00007898638,0.000018081775,0.0014916534,0.0008767074,0.00019915485],"category_scores_gemma":[0.12033307,0.00020980573,0.0007621432,0.0006559658,0.0041367197,0.0000430292,0.0006582412,0.0028493938,0.0000014905567],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030965122,0.00069021643,0.000020308931,0.024775516,0.00097460963,0.0000030988463,0.00017092805,6.3168994e-7,0.000019944633,0.006049582,0.0016799568,0.96530557],"study_design_scores_gemma":[0.0041294037,0.006019283,0.000017327106,0.056838628,0.004925226,0.0000068703794,0.00020025675,0.00006467158,0.0006113243,0.44198108,0.48461616,0.00058975606],"about_ca_topic_score_codex":0.000030021476,"about_ca_topic_score_gemma":0.000004540398,"teacher_disagreement_score":0.9647158,"about_ca_system_score_codex":0.000045029876,"about_ca_system_score_gemma":0.0021632672,"threshold_uncertainty_score":0.9994511},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2156673479","doi":"10.1200/jco.2008.18.7393","title":"Heterogeneity and Power in Clinical Biomarker Studies","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Biomarker; Medicine; Outcome (game theory); Statistical power; Oncology; Internal medicine; Bioinformatics; Statistics; Biology; Genetics; Mathematics","score_opus":0.8560006059980471,"score_gpt":0.7383915548441444,"score_spread":0.11760905115390263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156673479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9813635,0.001004428,0.002810797,0.008727789,0.0039782003,0.00024770913,0.000004006613,0.000016525755,0.0018470953],"genre_scores_gemma":[0.5734432,0.0020408477,0.42022195,0.0034356967,0.0008053049,0.0000015153322,5.40327e-8,0.000014177644,0.000037261136],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98142344,0.0071231853,0.010246865,0.00039104896,0.00045300144,0.00036247616],"domain_scores_gemma":[0.747104,0.24758369,0.0038555379,0.0003686948,0.0005571623,0.0005309501],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.060786806,0.00021724621,0.003956576,0.00014160445,0.000034718527,0.000015201555,0.00035092176,0.00082618324,0.000059914],"category_scores_gemma":[0.5528802,0.00014664297,0.00073870365,0.00019870291,0.00080656377,0.0001119084,0.00013871989,0.0016914307,0.000010759386],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053167273,0.0057730847,0.12190486,0.000047094705,0.00091681833,0.0013559157,0.00012501018,7.432476e-7,0.000036095727,0.02072094,0.0189648,0.8248379],"study_design_scores_gemma":[0.0049866005,0.0073625087,0.3886976,0.00009904463,0.00016489554,0.00008244432,0.0000788568,0.000019577661,0.000010478655,0.59397477,0.004395707,0.00012754109],"about_ca_topic_score_codex":9.40655e-7,"about_ca_topic_score_gemma":0.000015306914,"teacher_disagreement_score":0.82471037,"about_ca_system_score_codex":0.000075341726,"about_ca_system_score_gemma":0.00038817863,"threshold_uncertainty_score":0.9671176},"labels":[],"label_agreement":null},{"id":"W2156778867","doi":"10.1093/jnci/djs141","title":"Assumptions of Expected Benefits in Randomized Phase III Trials Evaluating Systemic Treatments for Cancer","year":2012,"lang":"en","type":"review","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Confidence interval; Randomized controlled trial; Internal medicine; Clinical endpoint; Cancer; Clinical trial; Surgery","score_opus":0.9218299249129382,"score_gpt":0.7261335666871823,"score_spread":0.19569635822575593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156778867","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001631322,0.9755903,0.004858798,0.00009864964,0.010469457,0.005583495,0.0031423804,0.00000886158,0.000084921325],"genre_scores_gemma":[0.000110689805,0.91400576,0.07958548,0.00003271134,0.0036349392,0.0022498423,0.000011813116,0.00005776778,0.0003110066],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9845079,0.0053931535,0.007884288,0.0002701184,0.0016392602,0.00030523623],"domain_scores_gemma":[0.89499444,0.0899191,0.012837638,0.0002456935,0.001876493,0.0001266236],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03256237,0.00045384385,0.008534891,0.00046022475,0.0001000091,0.00003081978,0.0007142376,0.00041079402,0.0001593805],"category_scores_gemma":[0.21270359,0.00025035779,0.00292106,0.00055494095,0.00021129788,0.00020540346,0.000081153354,0.0006061668,0.000001272815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01492994,0.00083463953,0.0000035176656,0.010025975,0.0075995987,0.000001600457,0.00024149586,0.00047729042,0.000018315039,0.019083869,0.0010953473,0.9456884],"study_design_scores_gemma":[0.49056607,0.0002884576,0.000005066991,0.14666422,0.07208944,0.00014054269,0.000025038527,0.00035633266,0.00005660001,0.21523726,0.073650785,0.00092016475],"about_ca_topic_score_codex":0.00004751945,"about_ca_topic_score_gemma":0.000043802414,"teacher_disagreement_score":0.94476825,"about_ca_system_score_codex":0.0021993325,"about_ca_system_score_gemma":0.0040186266,"threshold_uncertainty_score":0.9999949},"labels":[],"label_agreement":null},{"id":"W2157977749","doi":"10.1093/annonc/mds174","title":"Comparison of absolute benefits of anticancer therapies determined by snapshot and area methods","year":2012,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; McMaster University","funders":"","keywords":"Medicine; Absolute risk reduction; Clinical trial; Colorectal cancer; Randomized controlled trial; Adjuvant therapy; Adjuvant; Internal medicine; Clinical endpoint; Oncology; Confidence interval; Cancer","score_opus":0.8201028135580092,"score_gpt":0.6917364243737233,"score_spread":0.1283663891842859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157977749","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9511856,0.0050418014,0.03745108,0.00095357466,0.0005112214,0.0004216735,0.00022719482,0.000016155924,0.004191702],"genre_scores_gemma":[0.45408335,0.00035800863,0.54536927,0.00011009397,0.000044802775,0.000008487191,0.0000011415748,0.000011116871,0.000013715136],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969759,0.0011123999,0.0012725561,0.00016428667,0.00018722753,0.00028762303],"domain_scores_gemma":[0.94697744,0.051448587,0.00094356434,0.00028425953,0.00024034196,0.000105828556],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047481665,0.00014284343,0.0015123182,0.00006461965,0.000018998568,0.0000022071783,0.00018378058,0.00023536156,0.00032357397],"category_scores_gemma":[0.022298738,0.000115299605,0.000115516836,0.00011794816,0.0005502195,0.000051901046,0.00010040416,0.00013691577,5.753007e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087593764,0.0028180568,0.024744308,0.0007181433,0.000736638,6.5772787e-7,0.002919451,0.0000022311622,0.05006893,0.09817205,0.017141728,0.80180186],"study_design_scores_gemma":[0.0019919323,0.0042949347,0.032983426,0.0001885427,0.00037906697,0.000005417029,0.00037755194,0.00024522442,0.4012055,0.5508833,0.007119007,0.00032607184],"about_ca_topic_score_codex":0.000015398653,"about_ca_topic_score_gemma":0.0000039402566,"teacher_disagreement_score":0.80147576,"about_ca_system_score_codex":0.0000070652077,"about_ca_system_score_gemma":0.00003488947,"threshold_uncertainty_score":0.9859369},"labels":[],"label_agreement":null},{"id":"W2158958298","doi":"10.1109/iembs.2008.4650242","title":"Learning brain connectivity with the false-discovery-rate-controlled PC-algorithm","year":2008,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"False discovery rate; Computer science; Bayesian probability; Artificial intelligence; Bayesian network; Artificial neural network; Machine learning; Functional magnetic resonance imaging; Algorithm; Pattern recognition (psychology); Neuroscience; Psychology","score_opus":0.29637268987540116,"score_gpt":0.470922395162117,"score_spread":0.17454970528671582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158958298","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07707609,0.000018513414,0.9055856,0.0036906446,0.00021002116,0.0010663241,0.000013416561,0.00026953727,0.012069876],"genre_scores_gemma":[0.24041179,0.000016415528,0.7376511,0.0014281725,0.00043963818,0.000159755,8.845393e-7,0.000074401876,0.019817816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948875,0.0031491788,0.00064414187,0.00044242333,0.00045695924,0.0004198552],"domain_scores_gemma":[0.8179476,0.18110219,0.00027917442,0.00043731421,0.0001321189,0.00010155119],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006779639,0.00027665182,0.0010555388,0.00004254458,0.00041021622,0.000089810404,0.00030245664,0.00014951346,0.00051540806],"category_scores_gemma":[0.13080154,0.00013777126,0.00021301789,0.00026896087,0.0004313014,0.00014996901,0.00010055383,0.0006603284,0.000081085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056022336,0.0016810503,0.0029974384,0.00015571476,0.0019911241,0.000519795,0.0022570433,0.0002744711,0.0015117462,0.8395004,0.0622309,0.08127807],"study_design_scores_gemma":[0.018807396,0.0013790098,0.0017184197,0.000066719906,0.00027172416,0.00009648634,0.00085002393,0.009345874,0.002067306,0.96225876,0.0024111061,0.0007271812],"about_ca_topic_score_codex":0.00004017957,"about_ca_topic_score_gemma":0.00002994778,"teacher_disagreement_score":0.177953,"about_ca_system_score_codex":0.000040270617,"about_ca_system_score_gemma":0.00010212128,"threshold_uncertainty_score":0.8765201},"labels":[],"label_agreement":null},{"id":"W2159272000","doi":"10.2106/jbjs.l.00243","title":"Efficient Designs: Factorial Randomized Trials","year":2012,"lang":"en","type":"article","venue":"Journal of Bone and Joint Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Factorial; Sample size determination; Randomized controlled trial; Factorial experiment; Computer science; Psychological intervention; Research design; Fractional factorial design; Management science; Statistics; Mathematics; Medicine; Machine learning; Engineering; Nursing","score_opus":0.7688911751858022,"score_gpt":0.5473559338146832,"score_spread":0.22153524137111902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159272000","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4073197,0.0029883364,0.5725496,0.0006924806,0.015197913,0.00075334526,0.00002118079,0.000033017586,0.0004444441],"genre_scores_gemma":[0.560234,0.00052018097,0.4324642,0.00015474467,0.006528124,0.000009767936,2.2028973e-7,0.00003386198,0.000054887394],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98689693,0.006677496,0.0053934073,0.0001108723,0.0005872035,0.00033409477],"domain_scores_gemma":[0.57325083,0.4218049,0.004090232,0.00018812079,0.0002587517,0.00040718573],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14341387,0.00017865286,0.0053763613,0.0002744475,0.000054874556,0.000042342974,0.00002728309,0.0001571356,0.00035340776],"category_scores_gemma":[0.65345174,0.00010730319,0.0015487341,0.00011075371,0.00015264595,0.000073631476,0.000038331196,0.00032540338,0.000007871496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3676227,0.0061203395,0.0032842509,0.001952511,0.0057302807,0.00047295654,0.0032871685,0.00003169211,0.016343284,0.19575092,0.25576344,0.14364044],"study_design_scores_gemma":[0.07312761,0.00013043078,0.00068678946,0.00071483536,0.0015877092,0.00025370342,0.00009932749,0.000090801856,0.0034929244,0.91796947,0.0014528949,0.00039352724],"about_ca_topic_score_codex":0.0000020250664,"about_ca_topic_score_gemma":4.641256e-8,"teacher_disagreement_score":0.7222185,"about_ca_system_score_codex":0.000030169702,"about_ca_system_score_gemma":0.0000943352,"threshold_uncertainty_score":0.8820357},"labels":[],"label_agreement":null},{"id":"W2159353629","doi":"10.1093/biostatistics/5.1.129","title":"Tests for multivariate recurrent events in the presence of a terminal event","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Univariate; Multivariate statistics; Medicine; Event (particle physics); Inference; Statistical hypothesis testing; Statistics; Breast cancer; Multivariate analysis; Econometrics; Cancer; Computer science; Internal medicine; Mathematics; Artificial intelligence","score_opus":0.5050057957657591,"score_gpt":0.5862204328749212,"score_spread":0.0812146371091621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159353629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02305116,0.0000307359,0.9727254,0.00047424974,0.0006638001,0.0017858462,0.001158879,0.000020141026,0.00008982123],"genre_scores_gemma":[0.31942186,0.000009469637,0.6803173,0.000048248043,0.00007419078,0.00009558794,0.000003803801,0.000014138836,0.000015399095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99770707,0.0004412963,0.0009458718,0.00025257602,0.00037783175,0.00027536682],"domain_scores_gemma":[0.9521536,0.046932787,0.00034869285,0.0003764613,0.00013126494,0.000057180365],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026459543,0.00015571465,0.00039677866,0.00005187522,0.000042555923,0.0000084239955,0.00038509312,0.00009030328,0.000015830226],"category_scores_gemma":[0.13393886,0.00010681761,0.000087029046,0.0001835357,0.00012631273,0.000025046309,0.000063238076,0.00016850106,0.000005104196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004986702,0.0020179981,0.0009090003,0.00083538285,0.00005502657,0.00003661433,0.00160107,0.000038463593,0.00050482433,0.95139277,0.0015691732,0.04054099],"study_design_scores_gemma":[0.0018181208,0.00046041064,0.010779195,0.00030913256,0.00006568938,0.0000061839537,0.00008097186,0.00046298653,0.00045518254,0.98527384,0.00015663754,0.00013165042],"about_ca_topic_score_codex":0.000032770626,"about_ca_topic_score_gemma":0.000033375334,"teacher_disagreement_score":0.29637071,"about_ca_system_score_codex":0.00005577249,"about_ca_system_score_gemma":0.000098598204,"threshold_uncertainty_score":0.87335634},"labels":[],"label_agreement":null},{"id":"W2159423483","doi":"10.1002/env.634","title":"Point sampling strategies for estimating coverage from benthic video transects","year":2004,"lang":"en","type":"article","venue":"Environmetrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Transect; Sampling (signal processing); Benthic zone; Environmental science; Statistics; Computer science; Geology; Mathematics; Oceanography; Telecommunications","score_opus":0.4612882854461509,"score_gpt":0.4985828738762995,"score_spread":0.0372945884301486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159423483","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060202334,0.00011349989,0.93742156,0.00018020239,0.0007078568,0.00061314687,0.00032026487,0.0001175318,0.00032360503],"genre_scores_gemma":[0.15809113,0.000033174863,0.8411109,0.00018605855,0.00043628027,0.000051377516,0.000010437868,0.0000625572,0.000018108902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975074,0.00019018131,0.0009225384,0.0005142092,0.00044763682,0.00041804186],"domain_scores_gemma":[0.9304209,0.06865595,0.0002851827,0.00045507198,0.000026261429,0.00015665274],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002091349,0.00026943884,0.0006335552,0.00014629395,0.00016854885,0.00011512082,0.00029632106,0.0002644822,0.00022812036],"category_scores_gemma":[0.08156068,0.00025705298,0.00023243384,0.00036568753,0.0001303009,0.0001626671,0.00006235056,0.00038025947,0.00004293851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003570222,0.001383612,0.0004391556,0.0009098225,0.0003597785,0.00005841312,0.0022747887,0.04182113,0.008241467,0.80970746,0.0004938973,0.13395345],"study_design_scores_gemma":[0.0018137112,0.00017800808,0.0007168447,0.00009895534,0.00014402682,0.0000017488954,0.000105415354,0.0013919293,0.0022868135,0.9928138,0.00015157321,0.00029715648],"about_ca_topic_score_codex":0.000041887728,"about_ca_topic_score_gemma":0.0000053647764,"teacher_disagreement_score":0.18310635,"about_ca_system_score_codex":0.00015477644,"about_ca_system_score_gemma":0.00006900523,"threshold_uncertainty_score":0.9999882},"labels":[],"label_agreement":null},{"id":"W2160212727","doi":"10.1080/02331880802497447","title":"On testing the bioequivalence of several treatments using the measure of distance","year":2009,"lang":"en","type":"article","venue":"Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia; National Science Council","keywords":"Mathematics; Studentized range; Bioequivalence; Statistics; Sample size determination; Null hypothesis; F-test of equality of variances; Null (SQL); p-value; Resampling; Variance (accounting); Measure (data warehouse); Range (aeronautics); Statistical hypothesis testing; Levene's test; Test statistic; Data mining; Standard error; Computer science","score_opus":0.7165878831731174,"score_gpt":0.5747739514518423,"score_spread":0.1418139317212751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160212727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009695575,0.00003474271,0.9872577,0.0001238789,0.00020219212,0.00039826872,0.0010063858,0.000018041803,0.0012631983],"genre_scores_gemma":[0.32679155,0.0000052058213,0.67301,0.000089860136,0.00004724402,0.0000025241916,5.340904e-7,0.0000109858365,0.000042109634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977156,0.0005567506,0.000750177,0.00018374366,0.00058282027,0.00021094436],"domain_scores_gemma":[0.94438285,0.054245498,0.0005341396,0.0005152766,0.00027531735,0.000046942492],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015783135,0.0001562572,0.00040796856,0.00001982874,0.000112769085,0.000013271947,0.00033611117,0.00006318123,0.000050869745],"category_scores_gemma":[0.10148726,0.0000824076,0.00006184015,0.00025881582,0.00037982935,0.000019750276,0.000033569795,0.00020216826,0.00000209706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014720747,0.00029207478,0.00022617767,0.00010411338,0.000086429856,0.0000092930895,0.00030367594,0.00017620751,0.0012804079,0.9544974,0.0010238366,0.04185316],"study_design_scores_gemma":[0.00040232152,0.00039757887,0.0018376984,0.00020729886,0.00020789815,0.000003162513,0.000057885667,0.0062374542,0.0010126636,0.98952687,0.000014369999,0.000094796174],"about_ca_topic_score_codex":0.000013049928,"about_ca_topic_score_gemma":0.0000018503206,"teacher_disagreement_score":0.317096,"about_ca_system_score_codex":0.000037811555,"about_ca_system_score_gemma":0.00008003016,"threshold_uncertainty_score":0.9060813},"labels":[],"label_agreement":null},{"id":"W2160269073","doi":"10.1002/1097-0258(20000730)19:14<1901::aid-sim514>3.0.co;2-v","title":"The generalization of the odds ratio, risk ratio and risk difference tor �k tables","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Odds ratio; Confidence interval; Statistics; Pooling; Generalization; Statistic; Mathematics; Relative risk; Standard error; Diagnostic odds ratio; Odds; Absolute risk reduction; Type I and type II errors; Econometrics; Computer science; Logistic regression; Artificial intelligence","score_opus":0.21131445457799014,"score_gpt":0.4951114708605551,"score_spread":0.283797016282565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160269073","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055317063,0.00036928293,0.94102484,0.00046546335,0.0005997391,0.00065140304,0.00083482196,0.000018326231,0.0007190333],"genre_scores_gemma":[0.12158923,0.0143546965,0.8608297,0.00021302963,0.0004959337,0.000069383255,0.000014270071,0.00004816056,0.0023856002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962225,0.0017404398,0.0010837236,0.00024148,0.0004955659,0.000216273],"domain_scores_gemma":[0.9498299,0.048993286,0.0004774862,0.00049572246,0.00013748731,0.000066120185],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038280406,0.00016643107,0.00048759545,0.000030857784,0.00024493458,0.000021593722,0.00028405408,0.00009243979,0.0006683361],"category_scores_gemma":[0.13022582,0.00008439568,0.000025803112,0.00026187152,0.0009325657,0.000021913378,0.000054858483,0.00035449813,0.0000024481828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012914302,0.00007848373,0.017137779,0.000109650755,0.00007072624,0.000002861987,0.0009966431,0.000085159634,0.00018218083,0.81534725,0.007913848,0.1579463],"study_design_scores_gemma":[0.001036535,0.00014622234,0.04575221,0.00013492443,0.00019372805,0.0000013851262,0.00010660894,0.01907642,0.00018493542,0.9327676,0.0004990021,0.00010038589],"about_ca_topic_score_codex":0.0003527236,"about_ca_topic_score_gemma":0.00054711965,"teacher_disagreement_score":0.15784591,"about_ca_system_score_codex":0.00003001906,"about_ca_system_score_gemma":0.000049777762,"threshold_uncertainty_score":0.87710065},"labels":[],"label_agreement":null},{"id":"W2160390730","doi":"10.1177/009286150804200112","title":"On the Applications of Fisher’s Least Significant Difference (LSD) Procedure in Three-Arm Clinical Trials with Survival Endpoints","year":2008,"lang":"en","type":"article","venue":"Drug Information Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Clinical trial; Medicine; Clinical endpoint; Statistics; Pharmacology; Mathematics; Internal medicine","score_opus":0.5600644604204658,"score_gpt":0.5263214434847089,"score_spread":0.033743016935756875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160390730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2988646,0.000012048708,0.68674946,0.0032800734,0.0006311768,0.0027088854,0.00017220178,0.000060711536,0.007520847],"genre_scores_gemma":[0.8840183,0.00011294451,0.114579886,0.0005431488,0.00041985104,0.00019222568,0.000005392899,0.000024832161,0.00010344366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99252176,0.0022586747,0.0038804135,0.00015789582,0.0009089399,0.00027229026],"domain_scores_gemma":[0.9260703,0.07038522,0.0024623629,0.00044954027,0.00043695117,0.00019562893],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021977765,0.00020861252,0.0009790764,0.0001544812,0.000205279,0.00006814735,0.0005123476,0.00014181805,0.0004356637],"category_scores_gemma":[0.10532323,0.00011332191,0.00022511157,0.0003906019,0.00035465404,0.00027157503,0.000049707312,0.0010935009,0.000045159984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005239266,0.003195462,0.04031486,0.00054998277,0.0005540955,0.000030372788,0.006108685,0.0003046884,0.000047588583,0.7863541,0.020132506,0.13716839],"study_design_scores_gemma":[0.004572686,0.0005172176,0.038742702,0.0004334694,0.0001081624,0.00010035637,0.0013232474,0.0016734909,0.00033282835,0.95117855,0.0006704192,0.00034684353],"about_ca_topic_score_codex":0.0000043896034,"about_ca_topic_score_gemma":0.000013000022,"teacher_disagreement_score":0.58515364,"about_ca_system_score_codex":0.00005204101,"about_ca_system_score_gemma":0.00033991408,"threshold_uncertainty_score":0.90221304},"labels":[],"label_agreement":null},{"id":"W2160929550","doi":"10.1198/016214504000002069","title":"Limited- and Full-Information Estimation and Goodness-of-Fit Testing in 2<i><sup>n</sup></i>Contingency Tables","year":2005,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":264,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of British Columbia","funders":"","keywords":"Statistics; Goodness of fit; Mathematics; Contingency table; Pooling; Estimator; Multivariate statistics; Statistical hypothesis testing; Parametric statistics; Econometrics; Computer science","score_opus":0.18925620646060193,"score_gpt":0.455272008541823,"score_spread":0.26601580208122105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160929550","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7400749,0.000046792342,0.25733325,0.001742432,0.0001255926,0.0002822471,0.00013008871,0.00001534439,0.0002494024],"genre_scores_gemma":[0.43591473,0.000031297765,0.56382704,0.000110823625,0.00009627156,0.0000026812768,6.860593e-7,0.000008343659,0.000008114723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966992,0.0007270435,0.0016442464,0.00011708806,0.00058384374,0.0002285612],"domain_scores_gemma":[0.9574437,0.038724612,0.0031898618,0.00013024035,0.00041319468,0.00009835237],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004302433,0.00014399819,0.0006834382,0.00012984939,0.00007577704,0.00006635112,0.00015135706,0.00007718996,0.000017201444],"category_scores_gemma":[0.20584695,0.00010620793,0.000058141082,0.00044786773,0.00017858087,0.0003914639,0.00008014996,0.00037513245,0.0000019839981],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033601726,0.00029436903,0.098242074,0.000233497,0.00015765698,0.000003330413,0.0012419322,0.0013842821,0.0004036869,0.031457495,0.0016001179,0.86464554],"study_design_scores_gemma":[0.0018851834,0.00068899523,0.22560965,0.0004305108,0.00039832623,0.00004387724,0.00066453,0.18382122,0.00016204857,0.58582175,0.00018640855,0.000287548],"about_ca_topic_score_codex":0.000041429656,"about_ca_topic_score_gemma":0.000010193943,"teacher_disagreement_score":0.864358,"about_ca_system_score_codex":0.00022283528,"about_ca_system_score_gemma":0.000071820345,"threshold_uncertainty_score":0.8008425},"labels":[],"label_agreement":null},{"id":"W2162300921","doi":"10.1177/1740774508096474","title":"A comprehensive comparison of the continual reassessment method to the standard 3 + 3 dose escalation scheme in Phase I dose-finding studies","year":2008,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":164,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"National Cancer Institute","keywords":"De-escalation; Phase (matter); Medicine; Medical physics; Computer science; Intensive care medicine; Chemistry","score_opus":0.9337735777746451,"score_gpt":0.7655472026703487,"score_spread":0.1682263751042964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162300921","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73719263,0.0005417982,0.2425062,0.0069427122,0.0045031644,0.0073669623,0.00040555166,0.00010523369,0.00043575064],"genre_scores_gemma":[0.304987,0.00012868573,0.6933195,0.00049246015,0.0007953374,0.00015663818,0.0000015799652,0.00003701807,0.00008175802],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9517269,0.03583797,0.009746145,0.0008517309,0.0012983176,0.00053892215],"domain_scores_gemma":[0.45427105,0.540097,0.003245986,0.001326534,0.0008113023,0.0002481103],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.073445104,0.00036055467,0.0045790076,0.00010001309,0.00025240553,0.000034580644,0.0007539479,0.00034563628,0.00009964092],"category_scores_gemma":[0.58708525,0.00019270722,0.00088751497,0.0007630432,0.00073488284,0.000065766115,0.00053348555,0.0009996628,0.000018033836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027706008,0.010317531,0.053519383,0.00085302396,0.004215291,0.00007354922,0.010411966,0.0002887315,0.0048351563,0.16068265,0.07969908,0.64739764],"study_design_scores_gemma":[0.05736508,0.00470884,0.058327153,0.0019242363,0.0015332496,0.000014516838,0.0058305496,0.002540961,0.009088401,0.8342251,0.023298368,0.0011435127],"about_ca_topic_score_codex":0.00001095761,"about_ca_topic_score_gemma":0.000014641296,"teacher_disagreement_score":0.6735425,"about_ca_system_score_codex":0.00013433472,"about_ca_system_score_gemma":0.00024732648,"threshold_uncertainty_score":0.95408326},"labels":[],"label_agreement":null},{"id":"W2162923130","doi":"","title":"Investigating the robustness of the nonparametric Levene test with more than two groups","year":2014,"lang":"en","type":"article","venue":"Redalyc (Universidad Autónoma del Estado de México)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"F-test of equality of variances; Nonparametric statistics; Levene's test; Statistics; Analysis of variance; Sample size determination; Mathematics; Type I and type II errors; Variance (accounting); Statistical hypothesis testing; Homogeneity (statistics); Population; One-way analysis of variance; Skewness; Statistical power; Econometrics; Demography; Test statistic","score_opus":0.13164832138675167,"score_gpt":0.37905781131965216,"score_spread":0.2474094899329005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162923130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7178603,0.000025206778,0.27707264,0.0016149522,0.00025166848,0.00063422736,0.00004463596,0.00011351579,0.0023828656],"genre_scores_gemma":[0.64668334,0.000004008345,0.3526002,0.00015782283,0.0001681735,0.000012519063,0.0000010912955,0.000055297827,0.00031757267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960337,0.0013340969,0.00072678475,0.0005297883,0.0007788845,0.0005967079],"domain_scores_gemma":[0.95077795,0.046185687,0.0009540277,0.0015426914,0.00028683202,0.00025280242],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003341183,0.00037745212,0.00078475307,0.00019911029,0.00041577604,0.00007479036,0.0013732242,0.00023193927,0.00006328412],"category_scores_gemma":[0.04392859,0.00023061965,0.00027486464,0.002086812,0.0012081899,0.00016289942,0.00042011216,0.00074775686,0.00000724675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002826901,0.0012928807,0.13975047,0.0010985907,0.0007332775,0.00007123846,0.0033399449,0.011060724,0.004284045,0.77712226,0.0019800656,0.0589838],"study_design_scores_gemma":[0.0059580323,0.0009006964,0.17879616,0.001216269,0.001377723,0.00019937781,0.0042702327,0.21495451,0.0048426953,0.5859369,0.00031028822,0.0012371369],"about_ca_topic_score_codex":0.0001374064,"about_ca_topic_score_gemma":0.00006920529,"teacher_disagreement_score":0.2038938,"about_ca_system_score_codex":0.00017714562,"about_ca_system_score_gemma":0.0002451243,"threshold_uncertainty_score":0.9641248},"labels":[],"label_agreement":null},{"id":"W2163071463","doi":"10.1002/sim.1121","title":"Sample size re‐estimation in cluster randomization trials","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; University of Toronto","funders":"","keywords":"Sample size determination; Randomization; Statistics; Cluster (spacecraft); Cluster randomised controlled trial; Computer science; Statistical power; Sample (material); Restricted randomization; Econometrics; Clinical trial; Mathematics; Randomized controlled trial; Medicine","score_opus":0.5611285954998531,"score_gpt":0.5843085060944774,"score_spread":0.02317991059462432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163071463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005430362,0.0000707675,0.9924818,0.002019197,0.00093671645,0.0012655573,0.00025796678,0.000049490976,0.002375441],"genre_scores_gemma":[0.026354782,0.00025424678,0.9720133,0.00059540384,0.00033552002,0.00009929096,0.00001668218,0.000040387786,0.00029038734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99166036,0.0036996983,0.0031973594,0.00041036893,0.00066116155,0.00037103577],"domain_scores_gemma":[0.6030126,0.39584044,0.0005656013,0.00036279627,0.000114852686,0.0001037008],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020180231,0.00024235032,0.0017577864,0.00023502237,0.000041883442,0.00001934165,0.0002030821,0.00020152968,0.0069457763],"category_scores_gemma":[0.87335247,0.00018996927,0.000053746622,0.0005463638,0.00025125538,0.000064999804,0.000045316167,0.00042038292,0.000038014365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00218767,0.00083640416,0.0018125776,0.0008021953,0.000108454515,0.00012505232,0.0038055254,0.00074260274,0.00009636153,0.64069,0.16727835,0.18151481],"study_design_scores_gemma":[0.016771475,0.00016692712,0.0005337466,0.00035620734,0.00009668407,0.0000017954179,0.00008702866,0.09702975,0.000017669796,0.88455397,0.00021442147,0.00017031879],"about_ca_topic_score_codex":0.00009411191,"about_ca_topic_score_gemma":0.00012569907,"teacher_disagreement_score":0.85317224,"about_ca_system_score_codex":0.00013970939,"about_ca_system_score_gemma":0.000021480508,"threshold_uncertainty_score":0.993962},"labels":[],"label_agreement":null},{"id":"W2164358237","doi":"10.1158/1078-0432.ccr-13-1222","title":"Phase III Trials of Targeted Anticancer Therapies: Redesigning the Concept","year":2013,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Clinical trial; Medicine; Drug development; Intensive care medicine; Phases of clinical research; Cancer; Clinical endpoint; Drug; Clinical study design; Anticancer drug; Drug trial; Standard of care; Randomized controlled trial; Oncology; Pharmacology; Internal medicine","score_opus":0.9689936851649781,"score_gpt":0.8078461069799944,"score_spread":0.1611475781849837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164358237","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010661215,0.98129094,0.0053497734,0.0004956725,0.002303383,0.008687522,0.0010115393,0.000082487124,0.0007680183],"genre_scores_gemma":[0.000012444352,0.93451375,0.056721933,0.00010627921,0.0040399767,0.0030284128,0.000013872235,0.00021219977,0.0013511067],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.91414315,0.0673845,0.012960392,0.0015191112,0.0026440236,0.0013488529],"domain_scores_gemma":[0.37241083,0.6186695,0.00434421,0.0024715625,0.0015997915,0.0005041243],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1636382,0.0008082213,0.013775814,0.00030403878,0.00035157992,0.00018547135,0.003066088,0.0016126233,0.012890871],"category_scores_gemma":[0.57354414,0.00041987823,0.0034034026,0.0016962001,0.0049582087,0.00009088316,0.00081347534,0.005644711,0.0001554788],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032391114,0.000740446,6.924416e-7,0.00465955,0.0016449911,0.000009103938,0.00011888447,6.82079e-8,0.0000033230021,0.016879579,0.0692152,0.90640426],"study_design_scores_gemma":[0.0047910037,0.0009574584,3.5957416e-7,0.013041024,0.0017439525,0.0000015786432,0.000111734225,0.000012274367,0.00003342023,0.21032448,0.76854485,0.0004378799],"about_ca_topic_score_codex":0.00018051855,"about_ca_topic_score_gemma":0.000006194359,"teacher_disagreement_score":0.90596634,"about_ca_system_score_codex":0.000269285,"about_ca_system_score_gemma":0.0030883902,"threshold_uncertainty_score":0.9998253},"labels":[],"label_agreement":null},{"id":"W2165682471","doi":"","title":"A model to select regimens for phase III trials for patients with advanced-stage non-small cell lung cancer.","year":2003,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Lung cancer; Stage (stratigraphy); Phases of clinical research; Clinical trial; Internal medicine; Cancer; Regimen; Oncology; Surgery; Biology","score_opus":0.47523369751072975,"score_gpt":0.5192202809645424,"score_spread":0.04398658345381268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165682471","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06138118,0.00003746581,0.9142337,0.00010313124,0.00048997725,0.02081191,0.0020123222,0.000076964636,0.0008533793],"genre_scores_gemma":[0.04316632,0.000012018576,0.9079715,0.00035399196,0.00015866471,0.045497485,0.000009837928,0.00011119309,0.0027189641],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99646014,0.00040394263,0.0012954293,0.00065166585,0.00030502575,0.00088377524],"domain_scores_gemma":[0.9628538,0.035149384,0.0006574763,0.0004988574,0.00042779537,0.00041269412],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006142654,0.00033019655,0.0013850143,0.000083800645,0.00012284674,0.000046125046,0.00025596414,0.00015763202,0.000026450036],"category_scores_gemma":[0.097472146,0.00025511085,0.0002511693,0.00023954874,0.000039129616,0.000068971705,0.00003235667,0.00014202428,9.349076e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07203375,0.014457327,0.0017188892,0.007915415,0.0025440208,0.000010502783,0.0020034523,0.007242398,0.00082063023,0.15341918,0.12070447,0.61713],"study_design_scores_gemma":[0.21811311,0.003712067,0.00029057456,0.00034655986,0.0036583582,6.173128e-7,0.00011186044,0.032865014,0.038645398,0.68354356,0.016007826,0.00270506],"about_ca_topic_score_codex":0.000004019825,"about_ca_topic_score_gemma":0.00001443447,"teacher_disagreement_score":0.6144249,"about_ca_system_score_codex":0.0001830176,"about_ca_system_score_gemma":0.00016436596,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W2166050184","doi":"10.1093/biostatistics/kxq041","title":"A multistate model for events defined by prolonged observation","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Duration (music); Event (particle physics); Spontaneous remission; Complete remission; State (computer science); Medicine; Computer science; Statistics; Mathematics; Internal medicine; Algorithm; Physics; Alternative medicine","score_opus":0.5493913029206225,"score_gpt":0.544768454180002,"score_spread":0.004622848740620578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166050184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016658118,0.000006156317,0.97503346,0.0004783812,0.0008827472,0.0012565318,0.005468068,0.00013662038,0.00007993528],"genre_scores_gemma":[0.028244812,0.0000074593327,0.96974057,0.00027084505,0.00015832268,0.00024616384,0.00010034527,0.000071427625,0.001160039],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99780715,0.00015759154,0.0008904955,0.00041535005,0.00032894328,0.00040047028],"domain_scores_gemma":[0.9722064,0.026461724,0.00037322522,0.0004485253,0.00033078957,0.0001793474],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016878496,0.0002419592,0.00046840945,0.000040639356,0.00013187222,0.00003725796,0.00026785204,0.00024982993,0.000057834513],"category_scores_gemma":[0.14238667,0.00022247985,0.000093869356,0.000119644785,0.00011699368,0.000058049893,0.000055522945,0.00031178602,0.000022071627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048960146,0.00089430134,0.00085691107,0.00047387768,0.0001169148,0.000004784389,0.00025373997,0.00001622899,0.028882684,0.8013471,0.12623717,0.040426698],"study_design_scores_gemma":[0.0013896237,0.00010443162,0.00030801876,0.000015805459,0.00009564103,0.0000011583256,0.0000050740655,0.20794438,0.0012016824,0.7876537,0.0010472125,0.00023329235],"about_ca_topic_score_codex":0.000007953976,"about_ca_topic_score_gemma":0.00003961045,"teacher_disagreement_score":0.20792815,"about_ca_system_score_codex":0.00003123379,"about_ca_system_score_gemma":0.00008466709,"threshold_uncertainty_score":0.90724653},"labels":[],"label_agreement":null},{"id":"W2166380979","doi":"10.1200/jco.2012.47.4957","title":"Evolution of Clinical Trial Design in Early Drug Development: Systematic Review of Expansion Cohort Use in Single-Agent Phase I Cancer Trials","year":2013,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Clinical trial; Cohort; Cohort study; Logistic regression; Internal medicine; Oncology; Intensive care medicine","score_opus":0.9252008630115631,"score_gpt":0.7254269325999303,"score_spread":0.19977393041163283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166380979","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019590817,0.9568084,0.017504282,0.000071308066,0.0077064713,0.015837945,0.00006354763,0.000012287899,0.00003666356],"genre_scores_gemma":[0.00004583405,0.74084413,0.25739616,0.00007913565,0.0010400552,0.000465024,0.0000025078605,0.00007451032,0.00005262672],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.68759257,0.17608342,0.1316426,0.0011965028,0.0026421116,0.0008428021],"domain_scores_gemma":[0.23571268,0.6754257,0.0850163,0.0011832855,0.0019633216,0.0006986855],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.3512823,0.000831803,0.05703247,0.00081514166,0.000027379983,0.00002670182,0.0013843845,0.0028846355,0.00029671023],"category_scores_gemma":[0.8766392,0.0005260966,0.005510323,0.0009800323,0.0005760416,0.0002695302,0.00027880943,0.0040945103,0.000021214193],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015223668,0.011674939,0.00012281412,0.54544395,0.0019913204,0.00015567934,0.000043936074,0.0000013024347,5.2206656e-7,0.0004687542,0.0015803627,0.42329273],"study_design_scores_gemma":[0.060406614,0.0099120205,0.00007697757,0.8886558,0.015637234,0.00002947085,0.00001688669,0.000015310754,0.00000360352,0.0136139905,0.011087072,0.00054502353],"about_ca_topic_score_codex":0.00005996812,"about_ca_topic_score_gemma":0.000045658977,"teacher_disagreement_score":0.5253569,"about_ca_system_score_codex":0.0012324709,"about_ca_system_score_gemma":0.012328556,"threshold_uncertainty_score":0.9997191},"labels":[],"label_agreement":null},{"id":"W2167008920","doi":"","title":"Comparison of Minimum Bias and Maximum Likelihood Methods for Claim Severity","year":2009,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Multiplicative function; Statistics; Maximum likelihood; Function (biology); Convergence (economics); Likelihood function; Applied mathematics; Algorithm; Econometrics; Mathematical analysis","score_opus":0.6566078927710173,"score_gpt":0.643769251551856,"score_spread":0.012838641219161229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167008920","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00901468,0.00007868471,0.9844523,0.0007530079,0.00025375927,0.00067003496,0.000037235102,0.000075105156,0.0046651694],"genre_scores_gemma":[0.024616273,0.000011340385,0.97482824,0.0002889756,0.00009595113,0.000015093298,8.942157e-7,0.000016665877,0.00012655933],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718857,0.0008558366,0.0011724473,0.0003232431,0.00017373261,0.00028616938],"domain_scores_gemma":[0.9238269,0.075198226,0.00031913316,0.0003607048,0.0001484731,0.00014656995],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0057418817,0.0001772303,0.0010824244,0.000052330117,0.00005038494,0.000021008036,0.00018250212,0.00021446965,0.00016779166],"category_scores_gemma":[0.08320065,0.00013989078,0.0001584332,0.00013411614,0.00012502208,0.000040019037,0.00005957797,0.00016853781,0.0000026912733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002518904,0.0006380165,0.0006462671,0.00024454325,0.00006471104,5.000037e-7,0.00020743057,1.2381803e-7,0.002041045,0.20144938,0.0064067054,0.7880494],"study_design_scores_gemma":[0.0009967976,0.00064019667,0.0010373665,0.00003497934,0.00013013843,0.0000014795646,0.00011428119,0.0026943085,0.019932678,0.97314847,0.0011028467,0.0001664758],"about_ca_topic_score_codex":0.0000034712516,"about_ca_topic_score_gemma":0.0000021071166,"teacher_disagreement_score":0.7878829,"about_ca_system_score_codex":0.000014233085,"about_ca_system_score_gemma":0.00002890724,"threshold_uncertainty_score":0.9245219},"labels":[],"label_agreement":null},{"id":"W2167123965","doi":"10.1200/jco.2010.31.9624","title":"Reporting of Serious Adverse Drug Reactions of Targeted Anticancer Agents in Pivotal Phase III Clinical Trials","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Drug; Adverse effect; Clinical trial; Pharmacology; Oncology; Anticancer drug; Intensive care medicine; Internal medicine","score_opus":0.82530059686524,"score_gpt":0.7434084139838205,"score_spread":0.08189218288141953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167123965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.980907,0.000031895222,0.0051594116,0.001121595,0.0105582485,0.0006860569,0.00005086851,0.000016011736,0.0014688923],"genre_scores_gemma":[0.62633204,0.00023119645,0.3715071,0.00018811428,0.0016131159,0.000006232854,7.810293e-7,0.000029144816,0.000092258284],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91335315,0.015236014,0.069282316,0.000546659,0.001069141,0.00051271473],"domain_scores_gemma":[0.34541962,0.53549963,0.114624895,0.0011504312,0.0022781778,0.0010272594],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.25353324,0.00027668578,0.009627188,0.0002845674,0.00004088845,0.000007126963,0.00060036,0.0012078368,0.0010377354],"category_scores_gemma":[0.9197891,0.0002053695,0.0024566662,0.00044584955,0.001165199,0.0001686365,0.00017708019,0.0042025954,0.0000059825875],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04653506,0.052814234,0.14190546,0.0006766058,0.0037521725,0.0026712005,0.00055524625,0.00004754908,0.015953222,0.02026852,0.018966056,0.69585466],"study_design_scores_gemma":[0.122320466,0.019128827,0.18539733,0.0012592324,0.0038924366,0.0004183523,0.0007187808,0.0015362432,0.004911718,0.64156014,0.017993432,0.0008630422],"about_ca_topic_score_codex":0.00005694648,"about_ca_topic_score_gemma":0.00010869844,"teacher_disagreement_score":0.69499165,"about_ca_system_score_codex":0.00006996134,"about_ca_system_score_gemma":0.0022559285,"threshold_uncertainty_score":0.9998754},"labels":[],"label_agreement":null},{"id":"W2167706052","doi":"10.1002/sim.4015","title":"Interval estimation for the area under the receiver operating characteristic curve when data are subject to error","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Confidence interval; Statistics; Variance (accounting); Computer science; Observational error; Interval (graph theory); Function (biology); Mathematics; Algorithm","score_opus":0.6034699099556665,"score_gpt":0.5849274279005707,"score_spread":0.018542482055095788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167706052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00322415,0.000017163544,0.97768635,0.012267271,0.0027207062,0.001702955,0.0021800355,0.000039760398,0.00016161407],"genre_scores_gemma":[0.061387938,0.00001322971,0.935059,0.0019881933,0.000950856,0.00020805949,0.00011800563,0.000056912577,0.00021780322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99670094,0.0005980328,0.0012313762,0.00054083654,0.0005403432,0.0003884703],"domain_scores_gemma":[0.8621573,0.13539508,0.0004306802,0.0015880729,0.00029968948,0.00012922165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010716652,0.00026575057,0.00069508335,0.000074402145,0.0002437709,0.000073873874,0.0012646929,0.00013059254,0.0007086526],"category_scores_gemma":[0.37864628,0.00014107849,0.000035056008,0.00021632662,0.0004929796,0.00007501252,0.00035201534,0.00087191194,0.000021656697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005127595,0.0003784597,0.0014254849,0.0006115377,0.00029735712,0.000042327512,0.0048748204,0.00011632599,0.0008134583,0.5970887,0.26244983,0.13138895],"study_design_scores_gemma":[0.0013283944,0.00023582696,0.011644579,0.00040146764,0.00027912867,0.0000093704775,0.0010982848,0.12808423,0.00002669049,0.85503066,0.001636464,0.00022489767],"about_ca_topic_score_codex":0.0001206143,"about_ca_topic_score_gemma":0.0011937126,"teacher_disagreement_score":0.3679296,"about_ca_system_score_codex":0.000052764484,"about_ca_system_score_gemma":0.00007934837,"threshold_uncertainty_score":0.7759249},"labels":[],"label_agreement":null},{"id":"W2167841915","doi":"10.1111/insr.12064","title":"Small‐scale Inference: Empirical Bayes and Confidence Methods for as Few as a Single Comparison","year":2014,"lang":"en","type":"preprint","venue":"International Statistical Review","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Canada Foundation for Innovation; University of Ottawa","keywords":"Inference; Statistics; Confidence interval; Null hypothesis; Bayes' theorem; Null (SQL); False discovery rate; Mathematics; Econometrics; Statistical inference; Group (periodic table); Multiple comparisons problem; Biology; Computer science; Bayesian probability; Artificial intelligence; Data mining; Chemistry","score_opus":0.7750999583842813,"score_gpt":0.7121616343933252,"score_spread":0.062938323990956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167841915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009062916,0.007307811,0.9784315,0.0043698847,0.001752327,0.002284645,0.0010057177,0.00011886764,0.004638597],"genre_scores_gemma":[0.0014330694,0.008292763,0.98472655,0.0036351301,0.0005220117,0.00079970097,0.00012581817,0.00008281167,0.00038216996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99155694,0.0027252927,0.003021503,0.0013541753,0.00083240203,0.00050966645],"domain_scores_gemma":[0.7913612,0.20541832,0.0011172367,0.0006958081,0.0009049209,0.0005024987],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077293008,0.00066046,0.0028764228,0.00009871995,0.000101377984,0.0002932675,0.001073914,0.00057685433,0.0026261196],"category_scores_gemma":[0.50794864,0.0005612549,0.0003885042,0.00010993984,0.00060498435,0.000047147198,0.0012201865,0.0012300892,0.00015336601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012353327,0.00035408116,0.00010144891,0.007647353,0.00026396356,0.000008862941,0.00004566687,0.0000012934698,0.000015640566,0.6103173,0.012537063,0.36858383],"study_design_scores_gemma":[0.0005000997,0.00038431905,0.000120764395,0.008557439,0.00070997915,0.000023168153,0.000008989849,0.0045573306,0.00008497833,0.9082012,0.07630298,0.0005487343],"about_ca_topic_score_codex":0.000060297825,"about_ca_topic_score_gemma":0.000015782554,"teacher_disagreement_score":0.50021935,"about_ca_system_score_codex":0.00018415667,"about_ca_system_score_gemma":0.00031427684,"threshold_uncertainty_score":0.9996839},"labels":[],"label_agreement":null},{"id":"W2167921963","doi":"10.1002/cjs.11197","title":"Nonparametric cure rate estimation with covariates","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Cancer Care South East; Ontario Institute for Cancer Research; Cancer Care Ontario; Institute for Clinical Evaluative Sciences; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Nonparametric statistics; Cure rate; Estimator; Parametric statistics; Statistics; Sample size determination; Econometrics; Mathematics; Estimation; Medicine; Surgery; Engineering","score_opus":0.27397385245959793,"score_gpt":0.4499953593536981,"score_spread":0.17602150689410018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167921963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004596297,0.000033929467,0.9930028,0.0007052041,0.00054497324,0.00028984412,0.00031125345,0.000009813937,0.00050593016],"genre_scores_gemma":[0.060247283,0.00001247207,0.939168,0.0002033494,0.00015247318,0.0000060105153,0.000002651475,0.000034766028,0.00017302361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978547,0.000376795,0.000977142,0.00013896308,0.0002913278,0.0003610637],"domain_scores_gemma":[0.97460383,0.022472894,0.00076174486,0.00023188864,0.0010542637,0.0008753912],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016668447,0.00017722246,0.0005441299,0.00032465288,0.00010742039,0.00017094125,0.00027175597,0.00011384452,0.0016271253],"category_scores_gemma":[0.072142094,0.00011762008,0.000051929794,0.0004497359,0.00022219213,0.000161586,0.0000088903125,0.00041292797,0.000095367905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089093955,0.00011103844,0.0050310744,0.00029544625,0.00041536448,0.0007239691,0.00045008532,0.0005300374,0.00003870456,0.64172834,0.20861915,0.1419677],"study_design_scores_gemma":[0.00076029374,0.00042155385,0.006200118,0.00012839264,0.00017748076,0.00009691917,0.00006066341,0.004397088,0.00006406646,0.9866705,0.0008321852,0.00019072658],"about_ca_topic_score_codex":0.0010795709,"about_ca_topic_score_gemma":0.0010245459,"teacher_disagreement_score":0.34494218,"about_ca_system_score_codex":0.00013876449,"about_ca_system_score_gemma":0.0010437927,"threshold_uncertainty_score":0.9992855},"labels":[],"label_agreement":null},{"id":"W2168627095","doi":"10.1348/000711004849222","title":"A note on preliminary tests of equality of variances","year":2004,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":313,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"F-test of equality of variances; Statistics; Test (biology); Type I and type II errors; Levene's test; Mathematics; Sample size determination; Econometrics; Nominal level; Statistical hypothesis testing; Test statistic","score_opus":0.38388052115437615,"score_gpt":0.5674083538348488,"score_spread":0.18352783268047262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168627095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06149862,0.00017128365,0.93387514,0.0006439546,0.00027741978,0.00024739784,0.0002872996,0.000011982938,0.002986924],"genre_scores_gemma":[0.37500483,0.000098416356,0.6246401,0.00014238714,0.00008170565,0.0000031979978,4.4101836e-7,0.000016688233,0.000012263302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995394,0.0008016667,0.00262454,0.00027985193,0.0006001014,0.0002998368],"domain_scores_gemma":[0.95701927,0.04111833,0.0010223745,0.00025286095,0.00032143298,0.00026570153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041274596,0.0001945669,0.0015177284,0.0000911515,0.00004219319,0.000017311875,0.00030976086,0.0002468731,0.0004698087],"category_scores_gemma":[0.09060911,0.00016664671,0.0001760292,0.00015606282,0.0011262054,0.000057390196,0.00006973734,0.0005707582,0.000007760424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010673302,0.0025500737,0.00003223445,0.0008726931,0.00011600378,0.00035311616,0.00013890292,0.0000029447422,0.00037749537,0.93040776,0.00070616073,0.06337528],"study_design_scores_gemma":[0.0026248405,0.0034836615,0.0071880273,0.001213235,0.00017252371,0.0014721175,0.000029021896,0.000024851137,0.00029148816,0.98332256,0.000029046816,0.00014861225],"about_ca_topic_score_codex":0.000006584369,"about_ca_topic_score_gemma":0.0000023449677,"teacher_disagreement_score":0.3135062,"about_ca_system_score_codex":0.000019866317,"about_ca_system_score_gemma":0.00007503292,"threshold_uncertainty_score":0.9170511},"labels":[],"label_agreement":null},{"id":"W2169204989","doi":"10.1177/070674370304801108","title":"Unicorns <i>Do</i> Exist: A Tutorial on “Proving” the Null Hypothesis","year":2003,"lang":"en","type":"article","venue":"The Canadian Journal of Psychiatry","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"","keywords":"Null hypothesis; Null (SQL); Context (archaeology); Statistical hypothesis testing; Alternative hypothesis; Sample size determination; Null model; Mathematics; Confidence interval; Statistics; Econometrics; Psychology; Computer science; Combinatorics; Data mining; Biology","score_opus":0.3659094334765383,"score_gpt":0.45211538248748134,"score_spread":0.08620594901094303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169204989","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16107127,0.004374751,0.014148564,0.2484115,0.19616726,0.0042081806,0.00068684085,0.00015082899,0.3707808],"genre_scores_gemma":[0.22037849,0.00003799896,0.7637333,0.006262138,0.00847823,0.000014257192,1.4453133e-7,0.00013082032,0.0009646122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960058,0.0018612706,0.0010255778,0.00017635112,0.00047755105,0.00045345322],"domain_scores_gemma":[0.97503895,0.022708269,0.00073813443,0.00078415824,0.00018500871,0.0005454883],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007497039,0.00021547123,0.00047713448,0.00009817287,0.00049695396,0.00015919386,0.0009463999,0.00016260445,0.000527737],"category_scores_gemma":[0.06689134,0.00011388063,0.00034452046,0.00028404346,0.0003584383,0.00004204872,0.000012469734,0.0009668708,0.00005801656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007403461,0.000050435545,0.000550916,0.000015885536,0.00010862448,0.000017803719,0.00019432661,0.000005771791,0.0000027073982,0.9341028,0.06270658,0.0021701183],"study_design_scores_gemma":[0.0006839567,0.00025074257,0.000281728,0.000115637515,0.00019314824,0.000107392814,0.00022050401,0.0000020699629,0.000035831086,0.97084975,0.027117452,0.0001418032],"about_ca_topic_score_codex":0.0005526206,"about_ca_topic_score_gemma":0.025112614,"teacher_disagreement_score":0.74958473,"about_ca_system_score_codex":0.00016523544,"about_ca_system_score_gemma":0.0028793612,"threshold_uncertainty_score":0.99267656},"labels":[],"label_agreement":null},{"id":"W2169368206","doi":"10.1080/03610926.2010.529527","title":"A Note on Testing Homogeneity of Several Exponential Location Parameters","year":2011,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Windsor","keywords":"Homogeneity (statistics); Exponential function; Estimator; Statistic; Monte Carlo method; Mathematics; Chen; Statistics; Applied mathematics; Computer science; Econometrics; Mathematical analysis","score_opus":0.6212194181360503,"score_gpt":0.5841964517999417,"score_spread":0.037022966336108576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169368206","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013591054,0.000087610366,0.98361874,0.000014891195,0.00017159863,0.00037014083,0.00007598777,0.00003697857,0.002032999],"genre_scores_gemma":[0.21305907,0.00005325144,0.7867143,0.000060865103,0.000013113093,0.000050223247,0.0000035993037,0.000020857298,0.000024739467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863349,0.011934913,0.0010663507,0.00028481224,0.00017202523,0.00020699076],"domain_scores_gemma":[0.87274903,0.12555696,0.0004996759,0.00089104276,0.00021917792,0.000084085965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017166542,0.0001821505,0.0005326098,0.0001299199,0.00010666028,0.000014790489,0.00039138852,0.00014801738,0.00008277541],"category_scores_gemma":[0.17086545,0.00017304478,0.000042011554,0.00031196146,0.0005768317,0.000064945656,0.00018946349,0.000369195,0.0000032554826],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048591604,0.00024712164,0.00031686775,0.00013467661,0.000026098325,0.0000013346199,0.0015737974,0.00001401585,0.00037148542,0.8225551,0.000022616789,0.17425095],"study_design_scores_gemma":[0.00064528646,0.00019004292,0.0072167427,0.00023132969,0.00008279634,0.0000030659555,0.00016038897,0.002048991,0.0052475836,0.98398745,0.000012563601,0.00017376966],"about_ca_topic_score_codex":0.00005819153,"about_ca_topic_score_gemma":0.000008758826,"teacher_disagreement_score":0.19946802,"about_ca_system_score_codex":0.000038670536,"about_ca_system_score_gemma":0.00005221579,"threshold_uncertainty_score":0.8361187},"labels":[],"label_agreement":null},{"id":"W2169548606","doi":"10.1016/j.cct.2010.08.010","title":"A web-based medical safety reporting system for a large multicenter clinical trial: The ALIAS experience","year":2010,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Medicine; Clinical trial; Patient safety; Relational database; Data management; Alias; Data collection; Computer science; Database; Health care","score_opus":0.8585179829869245,"score_gpt":0.6883359201567025,"score_spread":0.17018206283022197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169548606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18653439,0.00036213265,0.62801,0.02669429,0.10222941,0.044913527,0.0019401435,0.0026001672,0.006715988],"genre_scores_gemma":[0.7073658,0.00004221195,0.27359393,0.0041102204,0.012411229,0.0019339311,0.000021247171,0.00018640977,0.00033500986],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.88144875,0.05244108,0.058275096,0.0031130293,0.0030113682,0.0017106632],"domain_scores_gemma":[0.10224257,0.86978734,0.021607563,0.0034743408,0.0010770898,0.001811076],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.47698757,0.0007802709,0.007198819,0.00010857444,0.0005787023,0.000250573,0.0022381318,0.0022961367,0.0007561207],"category_scores_gemma":[0.9716465,0.0004676513,0.004778136,0.00041499178,0.0013734716,0.00019077201,0.0005375882,0.003450365,0.000094870265],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.36648756,0.012817454,0.03454042,0.0017117022,0.0025732354,0.0006822116,0.00035166234,5.6962506e-7,0.00029261372,0.30127344,0.16432303,0.11494612],"study_design_scores_gemma":[0.5330643,0.0038733613,0.0013367283,0.0016906234,0.0014489571,0.000035485773,0.00079481874,0.018799404,0.00041743214,0.14418048,0.29249677,0.0018616613],"about_ca_topic_score_codex":0.00001495536,"about_ca_topic_score_gemma":0.000028948933,"teacher_disagreement_score":0.8173463,"about_ca_system_score_codex":0.000057004545,"about_ca_system_score_gemma":0.0026152588,"threshold_uncertainty_score":0.9997775},"labels":[],"label_agreement":null},{"id":"W2170153043","doi":"10.1002/sim.4244","title":"Assessing noninferiority in a three‐arm trial using the Bayesian approach","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Bayesian probability; Parametric statistics; Computer science; Placebo; Statistical hypothesis testing; Clinical trial; Statistics; Machine learning; Medicine; Artificial intelligence; Mathematics; Alternative medicine","score_opus":0.7454022113351202,"score_gpt":0.6058046770374885,"score_spread":0.13959753429763166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170153043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012049367,0.000036318786,0.9748003,0.000098284174,0.0012095025,0.0011858476,0.00004106398,0.000036008547,0.010543318],"genre_scores_gemma":[0.15726788,0.000012595818,0.8419321,0.00012787036,0.00055224384,0.000048577615,0.0000028218578,0.000040524006,0.000015346719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99509656,0.0014756193,0.0017564923,0.00047682767,0.000673212,0.00052125857],"domain_scores_gemma":[0.9667728,0.031901173,0.00043347233,0.0006492859,0.000110777684,0.00013252499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0113572255,0.00028577045,0.0011018243,0.00018440121,0.00010200026,0.00003628254,0.00047101662,0.00021142833,0.0006029268],"category_scores_gemma":[0.10871535,0.00018718031,0.0000507309,0.00060600997,0.0008020882,0.00008906551,0.0001334576,0.0009935489,0.0000030295237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032732387,0.0011286394,0.0062622232,0.0003101361,0.000061056184,0.00023004357,0.0035393464,0.000007898449,0.00003997599,0.9655089,0.00044763598,0.019190924],"study_design_scores_gemma":[0.01644186,0.00032656203,0.003984314,0.00026622924,0.00011874118,0.000009462376,0.0008360042,0.019323386,0.000012195122,0.9584605,0.000012767568,0.0002079734],"about_ca_topic_score_codex":0.0006360086,"about_ca_topic_score_gemma":0.00031104055,"teacher_disagreement_score":0.14521852,"about_ca_system_score_codex":0.00015459646,"about_ca_system_score_gemma":0.0001676223,"threshold_uncertainty_score":0.8987923},"labels":[],"label_agreement":null},{"id":"W2170509755","doi":"10.1007/s10928-012-9258-0","title":"Application of a single-objective, hybrid genetic algorithm approach to pharmacokinetic model building","year":2012,"lang":"en","type":"article","venue":"Journal of Pharmacokinetics and Pharmacodynamics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto; Centre for Addiction and Mental Health","funders":"National Center for Research Resources; National Heart, Lung, and Blood Institute; Indiana Clinical and Translational Sciences Institute; National Institute of Mental Health; Eli Lilly and Company","keywords":"Covariate; Spurious relationship; Akaike information criterion; Lasso (programming language); NONMEM; Genetic algorithm; Model selection; Statistics; Mathematics; Feature selection; Population; Residual; Computer science; Algorithm; Machine learning; Mathematical optimization; Medicine","score_opus":0.20774451704765423,"score_gpt":0.4819784527793723,"score_spread":0.27423393573171806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170509755","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12568606,0.0005792438,0.8716489,0.00007280241,0.00072099647,0.000624708,0.00015717404,0.00002439864,0.0004857235],"genre_scores_gemma":[0.42591214,0.00032916918,0.5728366,0.00018727794,0.00064706476,0.000015686026,0.0000010058114,0.000056203284,0.000014867306],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587834,0.0004399908,0.0019781229,0.00032692932,0.00078480504,0.00059184246],"domain_scores_gemma":[0.9935342,0.0034666776,0.0013430208,0.00026239335,0.00062453264,0.0007691402],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027848657,0.00040594905,0.001004716,0.00037698974,0.00007635308,0.000037059548,0.0005165604,0.000105245796,0.000026144518],"category_scores_gemma":[0.0017306315,0.0003678372,0.0002655395,0.00046056518,0.00017049814,0.00018662882,0.00021683103,0.00061052176,0.0000018064103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006644385,0.003959419,0.00049902796,0.0008891538,0.000812072,0.0000139083595,0.0008148571,0.035323538,0.5494323,0.007608148,0.0017738342,0.39820933],"study_design_scores_gemma":[0.002843472,0.00026733012,0.0001758511,0.000072911665,0.001271943,0.00024224352,0.000034600398,0.88465685,0.046849005,0.062344328,0.00080015406,0.00044132074],"about_ca_topic_score_codex":0.0000024949136,"about_ca_topic_score_gemma":3.4919765e-8,"teacher_disagreement_score":0.8493333,"about_ca_system_score_codex":0.00011435882,"about_ca_system_score_gemma":0.00006294198,"threshold_uncertainty_score":0.99987733},"labels":[],"label_agreement":null},{"id":"W2170857766","doi":"10.1177/0962280210395739","title":"A generalized <i>p</i> -value approach for assessing noninferiority in a three-arm trial","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Confidence interval; Type I and type II errors; Statistics; Monte Carlo method; Sample size determination; Fraction (chemistry); Placebo; Mathematics; Value (mathematics); Medicine","score_opus":0.85810859778597,"score_gpt":0.7266962355247384,"score_spread":0.13141236226123165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170857766","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030692127,0.000065694556,0.9756126,0.00029113112,0.00079547166,0.0039990875,0.00010691018,0.00008285063,0.01597704],"genre_scores_gemma":[0.0041046403,0.000046705733,0.99257654,0.0002103201,0.0006380266,0.0022426655,0.000008907381,0.00011203723,0.00006015121],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.956814,0.031489577,0.003663327,0.0017587319,0.0038363305,0.002438041],"domain_scores_gemma":[0.61616546,0.38074696,0.00026792657,0.0010782718,0.00050041167,0.0012409522],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15566811,0.00047269097,0.0022960962,0.0006436325,0.00020482414,0.00013198033,0.0014274833,0.0011194664,0.0032242676],"category_scores_gemma":[0.7848223,0.00039136902,0.00025670032,0.0017380989,0.0021151954,0.00014243557,0.000700425,0.0039635366,0.000014155977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012349926,0.0025407374,0.0002790508,0.00044349424,0.000039239814,0.0001770148,0.00022785539,5.333892e-7,0.00005164461,0.7446031,0.00038985047,0.23889756],"study_design_scores_gemma":[0.03287898,0.00093542563,0.00088167994,0.00023170792,0.00004226842,0.000008192671,0.00014406606,0.039137978,0.00020505193,0.92490035,0.00023791935,0.0003963588],"about_ca_topic_score_codex":0.00053882593,"about_ca_topic_score_gemma":0.00010840852,"teacher_disagreement_score":0.62915415,"about_ca_system_score_codex":0.00038505375,"about_ca_system_score_gemma":0.0013233179,"threshold_uncertainty_score":0.99985385},"labels":[],"label_agreement":null},{"id":"W2171007688","doi":"10.1111/j.0006-341x.2004.00247.x","title":"Methods for the Statistical Analysis of Binary Data in Split‐Cluster Designs","year":2004,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Cancer Care Ontario; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistic; Generalization; Test statistic; Statistics; Binary data; Statistical hypothesis testing; Binary number; Cluster (spacecraft); Mathematics; Chi-square test; Computer science; Data mining; Algorithm; Arithmetic","score_opus":0.8597660708145176,"score_gpt":0.6874922533691127,"score_spread":0.17227381744540493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171007688","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013387398,0.0002595285,0.99524504,0.00037029086,0.0003191888,0.00073043257,0.0016572508,0.000022021348,0.00005749757],"genre_scores_gemma":[0.008641589,0.00006496254,0.99096924,0.00012310426,0.00006704488,0.000041728217,0.00003780866,0.000026186268,0.000028346138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964415,0.0010431467,0.0012909278,0.0004888657,0.00040191354,0.00033365504],"domain_scores_gemma":[0.7061752,0.29193038,0.00029289414,0.0013646565,0.00014539232,0.00009142991],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018224536,0.00016925679,0.00092570996,0.0016807512,0.000052063977,0.000032432643,0.0010507854,0.00018473246,0.00012712627],"category_scores_gemma":[0.3829158,0.00011273242,0.00017160164,0.011142483,0.00026998515,0.00005893201,0.0004322853,0.00018491247,0.000003910869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049698097,0.0015858829,0.0018501396,0.00047956215,0.0027074274,0.000012378935,0.00022184713,0.0002990204,0.0010388235,0.63767016,0.002223301,0.35141447],"study_design_scores_gemma":[0.001791641,0.00028504813,0.017908327,0.000028980685,0.0036785188,9.300562e-7,0.00008493357,0.03994025,0.00039035495,0.93438965,0.0012575913,0.00024379468],"about_ca_topic_score_codex":0.00006737349,"about_ca_topic_score_gemma":0.0000149552625,"teacher_disagreement_score":0.36469126,"about_ca_system_score_codex":0.00008923046,"about_ca_system_score_gemma":0.000101836136,"threshold_uncertainty_score":0.63162965},"labels":[],"label_agreement":null},{"id":"W2171549256","doi":"10.1111/1469-8986.00060","title":"A generally robust approach to hypothesis testing in independent and correlated groups designs","year":2003,"lang":"en","type":"article","venue":"Psychophysiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Heteroscedasticity; Type I and type II errors; Normality; Robustness (evolution); Statistic; Variance (accounting); Degrees of freedom (physics and chemistry); Statistics; Robust statistics; Econometrics; Standard error; Statistical power; Psychology; Mathematics","score_opus":0.6709965585225142,"score_gpt":0.48044187885248957,"score_spread":0.1905546796700246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171549256","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7105493,0.000034778026,0.27606615,0.00008612567,0.00053396216,0.0009787448,0.000013083909,0.000097911325,0.011639979],"genre_scores_gemma":[0.24509059,0.0000063881807,0.75426394,0.00039376612,0.00006793765,0.00009753208,3.4914308e-7,0.000030815798,0.000048695365],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967508,0.001386784,0.00070391945,0.0006172213,0.00014560147,0.0003956933],"domain_scores_gemma":[0.97200483,0.027256504,0.00014762867,0.0003635137,0.000060217368,0.00016731591],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017246433,0.00021659504,0.0006432281,0.00012910685,0.000053341348,0.000018241592,0.00019277276,0.0002636675,0.000046050576],"category_scores_gemma":[0.07832842,0.00018952524,0.000050661492,0.00044666228,0.00009975763,0.00002741992,0.000056325116,0.00034945164,0.000033180655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019990606,0.006364995,0.012922223,0.00072052464,0.0005351121,0.00012322173,0.0020093254,0.004715253,0.5038713,0.37799805,0.005498514,0.083242424],"study_design_scores_gemma":[0.0012426416,0.00025491693,0.009878693,0.00003353834,0.000030651478,0.000019302273,0.00005464233,0.0011575335,0.00040078862,0.9866556,0.000014726823,0.00025694992],"about_ca_topic_score_codex":0.000016585334,"about_ca_topic_score_gemma":0.000004101797,"teacher_disagreement_score":0.60865754,"about_ca_system_score_codex":0.00003920466,"about_ca_system_score_gemma":0.000028912958,"threshold_uncertainty_score":0.9294352},"labels":[],"label_agreement":null},{"id":"W2171999085","doi":"10.1002/sim.1336","title":"Improved up‐and‐down designs for phase I trials","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Estimator; Isotonic regression; Maximum tolerated dose; Sample size determination; Statistics; Computer science; Zero (linguistics); Sample (material); Mathematics; Clinical trial; Medicine","score_opus":0.7965506191140403,"score_gpt":0.6475064483633985,"score_spread":0.1490441707506418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171999085","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002763792,0.00024970382,0.9931621,0.0011842052,0.0014823986,0.0017561952,0.00104739,0.000059370217,0.0007822768],"genre_scores_gemma":[0.0056630843,0.00034616466,0.9912041,0.00048162165,0.00083941396,0.00023426297,0.000013384733,0.000055291675,0.0011627175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99521136,0.001205024,0.0022849808,0.00047366018,0.00036543582,0.00045951275],"domain_scores_gemma":[0.81319976,0.18561591,0.0004563694,0.00035709701,0.0001626865,0.00020814083],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014277091,0.00028075988,0.0018013542,0.00015979641,0.000080157544,0.000020259573,0.0002179133,0.0001897138,0.0021168026],"category_scores_gemma":[0.57650644,0.00020863337,0.00006975028,0.00021215586,0.0004817281,0.000034042572,0.00004880371,0.00033497633,0.000009129459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005009795,0.00037768626,0.00001842247,0.00045768303,0.00010694723,0.000029096858,0.00076170824,2.6271553e-7,0.0015197501,0.5930954,0.1197172,0.28341487],"study_design_scores_gemma":[0.015437975,0.001487097,0.000013004166,0.00018428054,0.00032734248,0.000005238471,0.00013702043,0.016758392,0.00025746663,0.9626739,0.002487878,0.0002304091],"about_ca_topic_score_codex":0.000016284224,"about_ca_topic_score_gemma":0.000014141954,"teacher_disagreement_score":0.5622294,"about_ca_system_score_codex":0.000054692322,"about_ca_system_score_gemma":0.000025614772,"threshold_uncertainty_score":0.9987954},"labels":[],"label_agreement":null},{"id":"W2175760929","doi":"10.1057/jors.2015.77","title":"Good Laboratory Practice for optimization research","year":2015,"lang":"en","type":"article","venue":"Journal of the Operational Research Society","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Management science; Set (abstract data type); Computer science; Engineering ethics; Operations research; Engineering management; Engineering","score_opus":0.8964348371194648,"score_gpt":0.7340319064664583,"score_spread":0.16240293065300648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2175760929","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059003728,0.0006108568,0.8308791,0.14651957,0.0029669255,0.0035300096,0.0002590888,0.000030939635,0.009303122],"genre_scores_gemma":[0.004018126,0.00010140951,0.9922849,0.0004365323,0.0017962301,0.000045115517,8.1406245e-7,0.000027811473,0.001289055],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98838824,0.0064087505,0.000863533,0.0001794818,0.003774035,0.00038597596],"domain_scores_gemma":[0.8045787,0.16801107,0.00043234346,0.0004665125,0.026135975,0.00037539788],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1123845,0.00009031969,0.00028597793,0.000068386355,0.00057382847,0.00023230456,0.0007463826,0.00017576934,0.00008043326],"category_scores_gemma":[0.64220184,0.0000557595,0.00025538407,0.000824235,0.0004695899,0.00042338416,0.00025437298,0.0015117445,0.000009651759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052072614,0.0006308062,0.000044282548,0.000063101266,0.00020966334,0.0000032867022,0.0009877416,0.006620184,0.0005279925,0.27796552,0.7120053,0.00042136267],"study_design_scores_gemma":[0.0023564897,0.0009420137,0.000026513573,0.00013294829,0.0000559117,0.000024331017,0.003503738,0.016159432,0.0013335885,0.89812344,0.07722323,0.00011835108],"about_ca_topic_score_codex":0.0000041193643,"about_ca_topic_score_gemma":8.6175055e-7,"teacher_disagreement_score":0.6347821,"about_ca_system_score_codex":0.0005284277,"about_ca_system_score_gemma":0.0028869596,"threshold_uncertainty_score":0.9139869},"labels":[],"label_agreement":null},{"id":"W2177271944","doi":"10.1111/poms.12514","title":"Designing Personalized Treatment: An Application to Anticoagulation Therapy","year":2015,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Polytechnique Montréal; McGill University","funders":"","keywords":"Partially observable Markov decision process; Unobservable; Warfarin; Sensitivity (control systems); Markov decision process; Computer science; Set (abstract data type); Medicine; Personalized medicine; Markov chain; Markov process; Machine learning; Markov model; Mathematics; Atrial fibrillation; Econometrics; Statistics; Internal medicine; Bioinformatics","score_opus":0.5810209444683472,"score_gpt":0.545120450267885,"score_spread":0.03590049420046215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177271944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044951215,0.000032951255,0.94941187,0.0023925537,0.00029204867,0.001849108,0.0000025878753,0.00013378808,0.0009339034],"genre_scores_gemma":[0.1776396,0.000091836446,0.8200516,0.00016655306,0.00026055222,0.0003891615,0.0000070306614,0.000015813335,0.0013778263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987552,0.00029489468,0.00028939862,0.0003704031,0.00018014012,0.000109962886],"domain_scores_gemma":[0.9992089,0.000189643,0.000040703835,0.00029459436,0.00013005381,0.00013607879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012255915,0.000111379944,0.0001680966,0.000094390394,0.00016519178,0.00009379307,0.000056433404,0.000032375505,0.000028157612],"category_scores_gemma":[0.0017777879,0.00009215937,0.000021320877,0.00020398412,0.000037202433,0.00015938595,0.00002096298,0.00003307913,0.000026107573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002957986,0.0008868202,0.0004536007,0.000030865158,0.00013047713,0.0000013767975,0.0032191828,0.0024445471,0.0025372584,0.5002275,0.0012272684,0.4885453],"study_design_scores_gemma":[0.0062295864,0.0023929863,0.004476849,0.00009164328,0.00044392323,0.000016790289,0.004853489,0.031695582,0.016606709,0.89219654,0.03992147,0.001074409],"about_ca_topic_score_codex":0.000014712045,"about_ca_topic_score_gemma":0.000018958526,"teacher_disagreement_score":0.48747087,"about_ca_system_score_codex":0.00007222537,"about_ca_system_score_gemma":0.00001297056,"threshold_uncertainty_score":0.37581497},"labels":[],"label_agreement":null},{"id":"W2178694734","doi":"10.1002/sim.6803","title":"Bias due to composite reference standards in diagnostic accuracy studies","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Statistics; Computer science; Data mining; Mathematics","score_opus":0.7570256031050993,"score_gpt":0.6499421358043234,"score_spread":0.10708346730077589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178694734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03802528,0.0011459389,0.9425698,0.0047663385,0.0030863695,0.0021316065,0.0023619046,0.00013871762,0.005774039],"genre_scores_gemma":[0.06618645,0.00039643236,0.9319358,0.00084365025,0.00033380036,0.00011674285,0.000013032691,0.00004618796,0.00012790709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99421614,0.0013998272,0.0020158188,0.00051630015,0.0013336814,0.00051823864],"domain_scores_gemma":[0.7136772,0.28425038,0.00031720015,0.00054640934,0.0008174087,0.00039137216],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013741654,0.00031209292,0.0015622356,0.00031215028,0.00003852756,0.000018770786,0.00040063844,0.00013115369,0.00017213197],"category_scores_gemma":[0.88697225,0.00024208793,0.000022075972,0.00073658297,0.00046762408,0.000051011993,0.00024541354,0.0006196013,0.000046559464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007405202,0.00047971052,0.008545923,0.00078351994,0.00012660844,0.002725663,0.0092445295,0.00008659883,0.000055972247,0.6948063,0.21547674,0.066927955],"study_design_scores_gemma":[0.003050093,0.0007318479,0.0041535688,0.0014658945,0.00007277916,0.000010961595,0.0014261091,0.00016947425,0.00004359719,0.9858708,0.0027308092,0.00027407147],"about_ca_topic_score_codex":0.0001708585,"about_ca_topic_score_gemma":0.00071375805,"teacher_disagreement_score":0.8732306,"about_ca_system_score_codex":0.0004985101,"about_ca_system_score_gemma":0.00023667731,"threshold_uncertainty_score":0.9872059},"labels":[],"label_agreement":null},{"id":"W2180417631","doi":"10.1016/j.cct.2015.11.010","title":"A small n sequential multiple assignment randomized trial design for use in rare disease research","year":2015,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Research Resources; National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases","keywords":"Medicine; Sample size determination; Randomized controlled trial; Research design; Clinical trial; Clinical study design; Statistics; Disease; Surgery; Pathology; Mathematics","score_opus":0.9838031589313935,"score_gpt":0.713887257317996,"score_spread":0.2699159016133975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180417631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014589881,0.0004976256,0.9246502,0.0021684198,0.007667257,0.048998162,0.0007192232,0.00025388948,0.00045534945],"genre_scores_gemma":[0.17623235,0.00010154954,0.8096468,0.00049817294,0.0048537017,0.007324792,0.000046229616,0.00017252681,0.0011238983],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.78709394,0.19421625,0.013983247,0.0018293684,0.0017319161,0.0011453135],"domain_scores_gemma":[0.06923567,0.9236731,0.0023340464,0.0016490014,0.0011491743,0.0019589951],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.48708466,0.000583695,0.007372598,0.00037689836,0.00014731531,0.00034744476,0.0009696174,0.00086824835,0.00012402468],"category_scores_gemma":[0.9749839,0.0004355905,0.0023466484,0.0005268494,0.0012104668,0.00030498928,0.000431101,0.0013490993,0.00006249042],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.93038964,0.0022572367,0.00030621846,0.00010086898,0.0003816051,0.00014002844,0.00006170696,0.000014338003,0.000009256572,0.013537441,0.04892969,0.0038719645],"study_design_scores_gemma":[0.5103683,0.001208265,0.000008086859,0.00019433316,0.00019333977,3.2814773e-7,0.000041233354,0.002598046,0.00004666975,0.48315445,0.0019002532,0.00028669534],"about_ca_topic_score_codex":0.00008131332,"about_ca_topic_score_gemma":0.000014400153,"teacher_disagreement_score":0.72945684,"about_ca_system_score_codex":0.0002316439,"about_ca_system_score_gemma":0.0027634434,"threshold_uncertainty_score":0.99980956},"labels":[],"label_agreement":null},{"id":"W2184630920","doi":"10.1017/s1481803500004917","title":"Understanding Equivalence Trials (and Why We Should Care)","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Emergency Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medicine; Equivalence (formal languages); Mathematics; Discrete mathematics","score_opus":0.9397717394312356,"score_gpt":0.6265422575982693,"score_spread":0.3132294818329663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184630920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04075096,0.06577307,0.5505135,0.11095548,0.07757431,0.002740826,0.0003936858,0.000106364074,0.15119179],"genre_scores_gemma":[0.6232381,0.04332214,0.3035315,0.0026001213,0.020900741,0.000019292296,0.0000035414353,0.0002730192,0.0061115636],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99556875,0.0009972735,0.0023877942,0.00019375923,0.00045385273,0.00039858895],"domain_scores_gemma":[0.9843179,0.0132722035,0.00064685347,0.00025665836,0.00023739332,0.0012689664],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0085579455,0.00020051264,0.0012263702,0.00024414144,0.00014647921,0.000009921578,0.00031054975,0.00015112224,0.04666621],"category_scores_gemma":[0.11276869,0.0001421208,0.00018287351,0.00030675525,0.00028728836,0.00008978298,0.000008510507,0.0004431939,0.000007987579],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035856006,0.000047627418,0.0023830393,0.00084308744,0.0006261555,0.00053337746,0.009254542,0.000015930214,0.00039260212,0.21247578,0.70474637,0.06832295],"study_design_scores_gemma":[0.0013211509,0.00055512536,0.000098655124,0.00087197905,0.00046877065,0.000027097083,0.0017278837,0.000015609,0.000032307587,0.94529355,0.049404453,0.00018341564],"about_ca_topic_score_codex":0.0006855657,"about_ca_topic_score_gemma":0.002469988,"teacher_disagreement_score":0.73281777,"about_ca_system_score_codex":0.00020894369,"about_ca_system_score_gemma":0.00040371215,"threshold_uncertainty_score":0.9542053},"labels":[],"label_agreement":null},{"id":"W2185911970","doi":"10.20982/tqmp.07.1.p015","title":"Randomization test of mean is compuationally inaccessible when the number of groups exceeds two","year":2011,"lang":"en","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Randomization; Statistics; Mathematics; Restricted randomization; Test (biology); Computer science; Medicine; Randomized controlled trial; Geology; Internal medicine","score_opus":0.7242500225447062,"score_gpt":0.6791121572757051,"score_spread":0.0451378652690011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185911970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009709952,0.00006856269,0.979265,0.00020123777,0.0030996455,0.0014970818,0.00013033982,0.00002513748,0.0060030865],"genre_scores_gemma":[0.01468526,0.000033037846,0.9844676,0.00019162548,0.00026466255,0.00024822095,0.0000039273887,0.000045893405,0.000059726466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886072,0.007619954,0.0026606848,0.0004937383,0.00030373837,0.00031464672],"domain_scores_gemma":[0.78715324,0.20993093,0.001560866,0.0005613029,0.00074415177,0.000049513714],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030758688,0.00025692108,0.0015899191,0.00018192145,0.000061833525,0.000010174128,0.00065654237,0.00024080506,0.00090329687],"category_scores_gemma":[0.18033947,0.00018485164,0.0002695922,0.00052161975,0.0007952043,0.00010943164,0.000096384676,0.00024645822,0.000008115999],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027113848,0.0007067573,0.0034781443,0.00015890267,0.00018333386,5.0766926e-7,0.0058244267,0.0000013076656,0.005247873,0.972768,0.0007565607,0.008162816],"study_design_scores_gemma":[0.008631805,0.00044223169,0.0018310365,0.00008735258,0.00018157483,0.0000024482567,0.00021637675,0.0003577122,0.013101938,0.9747444,0.00022392086,0.00017924549],"about_ca_topic_score_codex":0.0000636949,"about_ca_topic_score_gemma":0.00001335496,"teacher_disagreement_score":0.20231098,"about_ca_system_score_codex":0.00003109667,"about_ca_system_score_gemma":0.00007046658,"threshold_uncertainty_score":0.9980379},"labels":[],"label_agreement":null},{"id":"W2187089918","doi":"10.20982/tqmp.04.2.p061","title":"Confidence Intervals from Normalized Data: A correction to Cousineau (2005)","year":2008,"lang":"en","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2083,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confidence interval; Robust confidence intervals; Statistics; Mathematics","score_opus":0.8522175965034989,"score_gpt":0.719531494817121,"score_spread":0.13268610168637796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187089918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038227106,0.00018996774,0.9535991,0.000643205,0.038160983,0.001984017,0.0006853607,0.00014380319,0.0007708298],"genre_scores_gemma":[0.0006932145,0.00014189564,0.995872,0.0010696336,0.0013454154,0.00043754492,0.000037440474,0.000083150146,0.00031965735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98515534,0.009714324,0.002501835,0.0015139823,0.0003288114,0.0007856899],"domain_scores_gemma":[0.74124914,0.25543475,0.00078242697,0.0018245294,0.0004583908,0.0002507733],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02578625,0.00042768236,0.0020594357,0.0003231454,0.0001488712,0.00003668727,0.0012715971,0.0003656751,0.00053637446],"category_scores_gemma":[0.49566707,0.00039947877,0.00019022712,0.0005955325,0.0005248815,0.00023051804,0.0003225261,0.0005009152,0.00010740762],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0126575325,0.0015648804,0.00051501783,0.00014606559,0.00062990066,0.000082561935,0.0048107053,0.000018929282,0.055821262,0.63407046,0.24035622,0.049326476],"study_design_scores_gemma":[0.003633592,0.0008890323,0.00051143335,0.00015350863,0.0001218119,0.000020758842,0.000130717,0.0012359575,0.0039255093,0.9451931,0.04371529,0.00046928154],"about_ca_topic_score_codex":0.00039831523,"about_ca_topic_score_gemma":0.00016815438,"teacher_disagreement_score":0.46988082,"about_ca_system_score_codex":0.00013920081,"about_ca_system_score_gemma":0.00016138803,"threshold_uncertainty_score":0.9998457},"labels":[],"label_agreement":null},{"id":"W2188905245","doi":"10.1038/nmeth.3663","title":"ANOVA and the analysis of drug combination experiments","year":2015,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Government of Canada","keywords":"Analysis of variance; Computational biology; Computer science; Biology; Machine learning","score_opus":0.4638066355887606,"score_gpt":0.6384693616171507,"score_spread":0.17466272602839011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188905245","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033495648,0.0068402695,0.5875228,0.38254964,0.0065998845,0.002758569,0.0005944542,0.00017252237,0.012626896],"genre_scores_gemma":[0.00007221939,0.00004040053,0.912695,0.08493652,0.000775454,0.000052219442,0.00003205605,0.000051215597,0.0013449097],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9835282,0.013417693,0.0012583483,0.0005513875,0.0009787616,0.00026560895],"domain_scores_gemma":[0.84719706,0.15027826,0.0010042689,0.00096501125,0.00049868005,0.000056750236],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.025681762,0.0003642115,0.0024409662,0.00039964193,0.000055707496,0.000046157555,0.00059067167,0.002079322,0.00017072893],"category_scores_gemma":[0.17705244,0.0002179664,0.00050649315,0.001114033,0.00062269444,0.00003406705,0.00024363701,0.0039838348,0.0000014732323],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015088198,0.000071902236,0.00001668347,0.00025043378,0.0037091319,0.000011940718,0.00049415126,2.969824e-7,0.00002589852,0.05807186,0.9198304,0.01736642],"study_design_scores_gemma":[0.0017131148,0.000025734027,0.000044947177,0.000054388456,0.006670436,0.0000014900036,0.000038290575,0.00039698157,0.0007143373,0.9128308,0.07727757,0.00023185281],"about_ca_topic_score_codex":0.000015635438,"about_ca_topic_score_gemma":0.0000010805817,"teacher_disagreement_score":0.854759,"about_ca_system_score_codex":0.000064072025,"about_ca_system_score_gemma":0.000060946677,"threshold_uncertainty_score":0.9992162},"labels":[],"label_agreement":null},{"id":"W2194960242","doi":"10.1111/biom.12429","title":"False Discovery Rate Estimation for Large-Scale Homogeneous Discrete<i>p</i>-Values","year":2015,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneous; False discovery rate; Estimation; Scale (ratio); Statistics; Mathematics; Econometrics; Biology; Economics; Combinatorics; Geography; Cartography","score_opus":0.4759242506133713,"score_gpt":0.5376323145939031,"score_spread":0.06170806398053186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2194960242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018038385,0.00016821972,0.9775482,0.0002859481,0.0015695689,0.000884588,0.0010284035,0.00016526494,0.00031146704],"genre_scores_gemma":[0.028014448,0.000034414767,0.96919006,0.00017110659,0.00045803102,0.000111836656,0.000032676184,0.000067984365,0.0019194284],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971244,0.00047612778,0.0009044624,0.00046647625,0.00054134976,0.00048722423],"domain_scores_gemma":[0.96431583,0.03409061,0.00035897028,0.0005882582,0.00034265942,0.0003036846],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0069493097,0.00024946805,0.0006488034,0.0005362457,0.000109615474,0.0001837635,0.00035168094,0.00023595933,0.000019372761],"category_scores_gemma":[0.24330896,0.00018148597,0.00021852927,0.002125027,0.000100914905,0.00021027081,0.00016159947,0.00013503787,0.000057710015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017766538,0.0047342,0.0033133554,0.002299961,0.0007487528,0.00009090204,0.0021595133,0.00046397417,0.002520185,0.49856097,0.2574347,0.22589684],"study_design_scores_gemma":[0.0019229543,0.00038236048,0.00014418506,0.0000367306,0.00017745496,0.000005104975,0.00013314911,0.013874765,0.002946907,0.9750614,0.004973951,0.00034099826],"about_ca_topic_score_codex":0.000005988837,"about_ca_topic_score_gemma":0.0000026858884,"teacher_disagreement_score":0.47650045,"about_ca_system_score_codex":0.00012662215,"about_ca_system_score_gemma":0.00010340438,"threshold_uncertainty_score":0.763065},"labels":[],"label_agreement":null},{"id":"W2203142821","doi":"10.1158/1078-0432.ccr-15-0124","title":"Failures in Phase III: Causes and Consequences","year":2015,"lang":"en","type":"review","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Clinical trial; Randomized controlled trial; Drug development; Phases of clinical research; Population; Intensive care medicine; Cancer; Oncology; Pharmacology; Internal medicine; Drug","score_opus":0.9760698571292453,"score_gpt":0.8318534788750754,"score_spread":0.14421637825416989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2203142821","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045985642,0.99473894,0.00008775248,0.00044581786,0.0008347016,0.002444969,0.00040041524,0.000055175675,0.0009462239],"genre_scores_gemma":[0.000008222241,0.9667315,0.030211631,0.000053827804,0.001276472,0.00097464916,0.0000053084677,0.0000928845,0.0006455353],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9765964,0.015299574,0.004337791,0.0013579235,0.0014468591,0.0009614156],"domain_scores_gemma":[0.7588247,0.23851924,0.0005855362,0.0008597636,0.00054185785,0.00066890096],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055721767,0.00049495616,0.006051992,0.0004129699,0.00010983278,0.00016013315,0.0010261851,0.0012484115,0.0008185952],"category_scores_gemma":[0.32983065,0.00034849753,0.00045874505,0.0010389574,0.004338243,0.00007381505,0.000784234,0.0043193907,0.000095246425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018053855,0.0003794768,0.000017658727,0.008595966,0.00015026054,0.00018723037,0.000028495562,1.2830635e-8,6.156448e-8,0.015293325,0.01860501,0.956562],"study_design_scores_gemma":[0.0018752938,0.00034213706,9.4621987e-7,0.008541184,0.00022683959,0.0000067195588,0.00003148792,0.0000019425988,4.1539298e-7,0.37325728,0.6154557,0.0002600799],"about_ca_topic_score_codex":0.00046608335,"about_ca_topic_score_gemma":0.00039509492,"teacher_disagreement_score":0.95630187,"about_ca_system_score_codex":0.00031187222,"about_ca_system_score_gemma":0.0034262082,"threshold_uncertainty_score":0.9998967},"labels":[],"label_agreement":null},{"id":"W2205062739","doi":"10.1016/j.ctrv.2015.12.006","title":"Evolution in the eligibility criteria of randomized controlled trials for systemic cancer therapies","year":2015,"lang":"en","type":"review","venue":"Cancer Treatment Reviews","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Randomized controlled trial; Generalizability theory; Internal medicine; Logistic regression; Cancer","score_opus":0.8089890578173045,"score_gpt":0.6935839612305341,"score_spread":0.11540509658677034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2205062739","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017183961,0.924657,0.0043258313,0.00010775616,0.0011273096,0.06870759,0.00093842787,0.000022574754,0.00011180613],"genre_scores_gemma":[0.0000018852429,0.84009737,0.023049677,0.000031674284,0.0007993032,0.13579217,0.000017756916,0.000054776472,0.0001553845],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92770505,0.05841924,0.012268046,0.0007482135,0.00046937953,0.000390095],"domain_scores_gemma":[0.7178442,0.2706521,0.009650513,0.0013480916,0.00040909875,0.00009601514],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.114207275,0.0009500683,0.055287104,0.0001578456,0.000049986054,0.0000519256,0.0005788176,0.00047226108,0.00025960422],"category_scores_gemma":[0.20044748,0.00035479353,0.00857206,0.0003630066,0.00025613036,0.00004153787,0.000027922246,0.00022370237,0.0000071601376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01424767,0.00033534202,0.0000011601321,0.05453681,0.0029979502,0.0000013249088,0.000267734,1.8841352e-7,4.2134e-7,0.0068493197,0.0030211208,0.91774094],"study_design_scores_gemma":[0.15833063,0.00016954217,1.05562954e-7,0.057337083,0.038600683,0.0000040701866,0.000026200412,0.000010149525,5.2711476e-7,0.16441485,0.5807739,0.00033227616],"about_ca_topic_score_codex":0.00021428266,"about_ca_topic_score_gemma":0.000050841918,"teacher_disagreement_score":0.9174087,"about_ca_system_score_codex":0.001610757,"about_ca_system_score_gemma":0.0011250807,"threshold_uncertainty_score":0.9998904},"labels":[],"label_agreement":null},{"id":"W2215910533","doi":"","title":"Applying the Principles of Disease Screening to Prostate Cancer","year":2014,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"","keywords":"Prostate cancer; Medicine; Disease; Psychological intervention; Prostate cancer screening; Cancer; Intensive care medicine; Prostate-specific antigen; Nursing; Internal medicine","score_opus":0.6022014366444565,"score_gpt":0.570616342519582,"score_spread":0.031585094124874424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2215910533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009260127,0.00001577049,0.9814129,0.0015618623,0.00017700688,0.0017881814,0.00004160709,0.000069289505,0.0056732497],"genre_scores_gemma":[0.052505277,0.000005878908,0.94422317,0.00067350775,0.00016628472,0.00094062823,1.8381282e-7,0.000020995874,0.0014640692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846244,0.00037050803,0.000512547,0.00018954648,0.00028276295,0.00018219576],"domain_scores_gemma":[0.97179073,0.027392365,0.00014816468,0.00042103772,0.00008638425,0.00016132323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002774829,0.00009450554,0.00028121241,0.000022382816,0.000060737966,0.000018929262,0.00023820225,0.00002715709,0.00025762853],"category_scores_gemma":[0.07575907,0.000052691605,0.00007040028,0.00013071159,0.0000806506,0.000019939469,0.00015701236,0.00009557077,0.000011284374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018072268,0.000053125004,0.0042589204,0.00018226824,0.000039065766,5.186521e-7,0.00012816703,0.0002458728,0.00017860434,0.8128437,0.0008173277,0.1810717],"study_design_scores_gemma":[0.00045709743,0.0000687835,0.004398413,0.0002358365,0.000106844,1.2495819e-7,0.00007843788,0.005513977,0.0014177518,0.96626484,0.02128443,0.00017345512],"about_ca_topic_score_codex":0.000031438645,"about_ca_topic_score_gemma":0.000012349778,"teacher_disagreement_score":0.18089825,"about_ca_system_score_codex":0.000009044029,"about_ca_system_score_gemma":0.000024308762,"threshold_uncertainty_score":0.9320262},"labels":[],"label_agreement":null},{"id":"W2216819529","doi":"10.1016/j.ijrobp.2015.10.049","title":"NRG Oncology RTOG 0415: A Randomized Phase 3 Noninferiority Study Comparing 2 Fractionation Schedules in Patients With Low-Risk Prostate Cancer","year":2015,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McMaster University; Cancer Care Ontario","funders":"NRG Oncology","keywords":"Medicine; Oncology; Schedule; Prostate cancer; Internal medicine; Prostate; Cancer","score_opus":0.18329550255914662,"score_gpt":0.527530276123016,"score_spread":0.34423477356386933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2216819529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9121601,0.00006568733,0.08196211,0.00062355556,0.0034389829,0.0013591805,0.00013035678,0.00004202601,0.00021803248],"genre_scores_gemma":[0.8904951,0.00013859187,0.10772677,0.00018270555,0.0012633562,0.000119287666,0.000027503396,0.000038631253,0.000008056005],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99198157,0.0041317497,0.00245567,0.00038920328,0.00072619313,0.00031560805],"domain_scores_gemma":[0.97431856,0.018500607,0.004230819,0.00020980333,0.0025200103,0.00022019466],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008190208,0.00031773132,0.0017768156,0.00028847877,0.00008310879,0.000054253338,0.0005111583,0.00031615302,0.00006356736],"category_scores_gemma":[0.041886833,0.00024819336,0.00021411414,0.00030123268,0.0003815065,0.00045407255,0.000114798735,0.0011067429,0.0000142626],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06694405,0.007651989,0.7948684,0.000012253645,0.0012690468,0.000029924235,0.0016147275,0.001729826,0.00001602669,0.01524962,0.00018834179,0.11042576],"study_design_scores_gemma":[0.49174544,0.0045379642,0.034466267,0.00013408651,0.0005883903,0.0000095645755,0.00043261037,0.009100561,0.00012091783,0.45740137,0.0010523307,0.00041048977],"about_ca_topic_score_codex":0.0001254006,"about_ca_topic_score_gemma":0.00007856896,"teacher_disagreement_score":0.76040214,"about_ca_system_score_codex":0.0018360432,"about_ca_system_score_gemma":0.0011501944,"threshold_uncertainty_score":0.999997},"labels":[],"label_agreement":null},{"id":"W2216912048","doi":"10.1164/ajrccm.162.5.ed11-00c","title":"Dynamic Intrinsic PEEP (PEEPi,dyn)","year":2000,"lang":"en","type":"letter","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Medicine; Positive end-expiratory pressure; Cardiology; Mechanical ventilation; Anesthesia","score_opus":0.19298702889291047,"score_gpt":0.5056379734786564,"score_spread":0.3126509445857459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2216912048","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011082843,0.01769267,0.020559307,0.93834186,0.005115129,0.00081529794,0.00032817046,0.00014341694,0.0059212875],"genre_scores_gemma":[0.017356751,0.0007015204,0.13752872,0.827938,0.016062947,0.00001803362,0.0000072970106,0.00022750016,0.00015919696],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99214464,0.0026693845,0.0025236416,0.0005502124,0.0014583397,0.0006537645],"domain_scores_gemma":[0.9371459,0.059854288,0.0009559056,0.00060348015,0.00090731133,0.0005331423],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028946397,0.0005924022,0.003091685,0.000419538,0.00012455966,0.00004279369,0.0006052032,0.00058192795,0.0012367455],"category_scores_gemma":[0.087887965,0.00042315014,0.00037771347,0.00040070747,0.0049179266,0.00008909566,0.00009031758,0.004844766,0.000014499048],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041034556,0.00006253014,0.000060997994,0.0011693343,0.0002175793,0.0053461012,0.00042044994,1.1582971e-7,0.00001559086,0.0022768578,0.31551623,0.67450386],"study_design_scores_gemma":[0.0019383432,0.013541316,0.00014002052,0.0023624173,0.0020880976,0.00070817186,0.0016413961,0.0000033214615,0.000012690457,0.27235663,0.70448023,0.00072735106],"about_ca_topic_score_codex":0.00000741179,"about_ca_topic_score_gemma":0.0000016508653,"teacher_disagreement_score":0.6737765,"about_ca_system_score_codex":0.00014867264,"about_ca_system_score_gemma":0.00025997456,"threshold_uncertainty_score":0.999822},"labels":[],"label_agreement":null},{"id":"W2240321911","doi":"10.1200/jco.2009.27.15_suppl.6550","title":"Trends in the application of dynamic allocation methods in multiarm cancer clinical trials","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; London Health Sciences Centre","funders":"","keywords":"Medicine; Clinical trial; Randomization; Oncology; Medical physics; Internal medicine","score_opus":0.8598207331158435,"score_gpt":0.8010714738024179,"score_spread":0.05874925931342556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2240321911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13214532,0.0006525447,0.81858057,0.04042479,0.0045098583,0.0014088728,0.000026950484,0.000021833599,0.0022292908],"genre_scores_gemma":[0.3118966,0.00079521973,0.6850563,0.0013826905,0.0008073681,0.000022733831,8.1486087e-7,0.000013135772,0.000025083025],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8994354,0.07195773,0.026762078,0.0005441711,0.00085596915,0.000444671],"domain_scores_gemma":[0.5105754,0.4768828,0.011245002,0.00058744283,0.00049389794,0.00021548767],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29416162,0.00020743886,0.0047952393,0.00037515984,0.000021505872,0.000011313243,0.00084833964,0.0010530093,0.000115777795],"category_scores_gemma":[0.5544535,0.00012530202,0.0012003041,0.0007977036,0.00036689115,0.00010070848,0.00004687934,0.0023627093,0.000002803028],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018977524,0.0034274051,0.003838375,0.000017224318,0.00009807669,0.000020275571,0.00012462979,0.000029775434,0.00018209244,0.012235125,0.000640423,0.9774889],"study_design_scores_gemma":[0.008951329,0.004201981,0.30941558,0.00012381683,0.00044792716,0.000014844693,0.00013752092,0.0061566355,0.0000486549,0.6668636,0.0034824715,0.00015560874],"about_ca_topic_score_codex":0.00003752086,"about_ca_topic_score_gemma":0.0002383119,"teacher_disagreement_score":0.97733325,"about_ca_system_score_codex":0.00016904663,"about_ca_system_score_gemma":0.0006328181,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W2246470904","doi":"10.1200/jco.2007.25.18_suppl.2553","title":"Phase II stopping rules employing response rates and early progression","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Cancer Centre","funders":"","keywords":"Medicine; Relative risk; Phases of clinical research; Drug; Clinical endpoint; Drug development; Clinical trial; Oncology; Internal medicine; Pharmacology; Confidence interval","score_opus":0.7518050735852627,"score_gpt":0.7262127178139379,"score_spread":0.025592355771324793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2246470904","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95210296,0.00023960533,0.042946663,0.0022518085,0.0017470504,0.0002385684,0.0000043429823,0.000025966514,0.00044305835],"genre_scores_gemma":[0.348722,0.000099882665,0.6494699,0.0003657989,0.0012364428,0.0000018221374,6.7318865e-8,0.000023751953,0.000080322694],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9879961,0.004654337,0.0060927705,0.00029088327,0.0005494826,0.000416438],"domain_scores_gemma":[0.6971316,0.29800445,0.003592476,0.0002279447,0.0004798907,0.00056366343],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09140257,0.0001901854,0.0021020488,0.00017828657,0.00016215582,0.000029341885,0.00030087505,0.0006419313,0.000079123696],"category_scores_gemma":[0.52906233,0.00013093643,0.0003948003,0.00014821731,0.00055395835,0.00015522717,0.00021733719,0.001471871,0.000006784423],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03555992,0.0049193786,0.006335344,0.000048544716,0.0002241053,0.00090906175,0.00031776325,1.8434108e-7,0.0014482614,0.007946088,0.0012308946,0.9410605],"study_design_scores_gemma":[0.024815606,0.07006334,0.062012035,0.0006505233,0.00046911908,0.00027545975,0.00022330867,0.000046662357,0.0010796399,0.81778616,0.022243418,0.00033475578],"about_ca_topic_score_codex":0.0000016058262,"about_ca_topic_score_gemma":0.0000020588798,"teacher_disagreement_score":0.9407257,"about_ca_system_score_codex":0.00007315089,"about_ca_system_score_gemma":0.00047933645,"threshold_uncertainty_score":0.93559223},"labels":[],"label_agreement":null},{"id":"W2248705884","doi":"10.1200/jco.2009.27.15_suppl.e17515","title":"Comparison of randomized phase II studies (RP2s) and subsequent randomized controlled studies (RCTs) using identical systemic therapies","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; McMaster University; University of Toronto","funders":"","keywords":"Medicine; Concordance; Randomized controlled trial; Internal medicine; Meta-analysis; Clinical endpoint; MEDLINE; Relative risk; Confidence interval","score_opus":0.7604661029641409,"score_gpt":0.7133037812364109,"score_spread":0.04716232172772994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2248705884","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88845325,0.043177795,0.05640698,0.0042468677,0.0042157164,0.0033062028,0.0000071562263,0.000029764602,0.0001562882],"genre_scores_gemma":[0.6725219,0.012543802,0.3137086,0.0003261026,0.00082682824,0.000025248213,1.0951172e-7,0.000018943043,0.000028481374],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9423247,0.03184071,0.023924906,0.00040761687,0.0010656283,0.00043645868],"domain_scores_gemma":[0.2575087,0.71872675,0.02010644,0.00040446097,0.0028466429,0.00040699466],"candidate_categories":["metaresearch","metaepi_broad","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14064842,0.00044762122,0.036677472,0.00025289852,0.00015065723,0.000025334586,0.0003834145,0.0005875273,0.00004377823],"category_scores_gemma":[0.7928216,0.00024130094,0.0033949479,0.00017876989,0.0035151227,0.00015549289,0.00017218501,0.0012152654,0.0000013247568],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8680482,0.0038138868,0.00007140415,0.00022596643,0.014024701,0.00009492946,0.0016709511,0.0000115526755,0.00029362153,0.099651754,0.000277067,0.011815963],"study_design_scores_gemma":[0.54249734,0.0043049688,0.0000068840222,0.00059928355,0.0064214375,0.00006211368,0.0014657846,0.00092587643,0.000060324517,0.44351685,0.000013542583,0.000125627],"about_ca_topic_score_codex":0.0000019046536,"about_ca_topic_score_gemma":0.0000017568,"teacher_disagreement_score":0.6868861,"about_ca_system_score_codex":0.00014987447,"about_ca_system_score_gemma":0.0004797019,"threshold_uncertainty_score":0.99919677},"labels":[],"label_agreement":null},{"id":"W2249217595","doi":"","title":"Optimal personalized treatment rules for marketing interventions: A review of methods, a new proposal, and an insurance case study","year":2014,"lang":"en","type":"review","venue":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institució Catalana de Recerca i Estudis Avançats; Royal Bank of Canada","keywords":"Personalized medicine; Variety (cybernetics); Population; Psychological intervention; Set (abstract data type); Computer science; Actuarial science; Treatment and control groups; Outcome (game theory); Machine learning; Medicine; Artificial intelligence; Economics; Microeconomics; Bioinformatics; Psychiatry","score_opus":0.5773127238043168,"score_gpt":0.6079543282309487,"score_spread":0.030641604426631996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2249217595","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046757847,0.93535024,0.055317447,0.00008029945,0.0001501559,0.0072651515,0.0011645142,0.000104627645,0.000099976525],"genre_scores_gemma":[0.0000016621473,0.51419365,0.48511213,0.000014220923,0.000091587186,0.00015389292,0.000051416115,0.000079897494,0.00030150398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98296857,0.012662225,0.0023431696,0.0011581723,0.00026014715,0.00060773385],"domain_scores_gemma":[0.9484583,0.047335576,0.0020059785,0.0012271418,0.00038611775,0.000586844],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015721759,0.0008627468,0.005448767,0.00041742035,0.00023132737,0.000074023854,0.0006869799,0.0005603217,0.00022481046],"category_scores_gemma":[0.041776787,0.0007479709,0.001785481,0.00054687256,0.00030748785,0.00018167462,0.00030203152,0.0005262125,0.000004699906],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002038528,0.0008331966,0.000036146303,0.21659218,0.0015979742,0.0002452244,0.00040363456,2.642822e-7,3.291887e-7,0.0025333336,0.0007537506,0.7768001],"study_design_scores_gemma":[0.0091576055,0.0058143004,0.000020080453,0.37436002,0.05000056,0.0046860133,0.006147183,0.00024000245,0.000008630933,0.020507658,0.52636564,0.002692305],"about_ca_topic_score_codex":0.00056727394,"about_ca_topic_score_gemma":0.0000974115,"teacher_disagreement_score":0.7741078,"about_ca_system_score_codex":0.0008811113,"about_ca_system_score_gemma":0.00125857,"threshold_uncertainty_score":0.9994971},"labels":[],"label_agreement":null},{"id":"W2252455678","doi":"10.1158/1078-0432.ccr-15-0035","title":"Impact of the 2010 Consensus Recommendations of the Clinical Trial Design Task Force of the NCI Investigational Drug Steering Committee","year":2015,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre","funders":"National Center for Advancing Translational Sciences; National Cancer Institute","keywords":"Concordance; Medicine; Clinical trial; Drug development; Task force; Steering committee; Clinical study design; Randomized controlled trial; Medical physics; Research design; Oncology; Investigational Drugs; Drug; Internal medicine; Pharmacology","score_opus":0.9426179993832116,"score_gpt":0.7345665705338479,"score_spread":0.20805142884936367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2252455678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9522883,0.00015350888,0.0054932972,0.025327746,0.008257856,0.0061825607,0.0010338908,0.000031409672,0.0012313755],"genre_scores_gemma":[0.8956776,0.00010015457,0.10058645,0.0002626317,0.0013265823,0.0002120724,0.0000015518909,0.000071449824,0.0017614583],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96794873,0.024718873,0.0043570944,0.00047282627,0.001983014,0.00051948376],"domain_scores_gemma":[0.6622519,0.33043483,0.0021090093,0.0024550273,0.002335514,0.00041375207],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06826295,0.00021302303,0.001185668,0.000060113383,0.00023798223,0.000026178124,0.002197323,0.0003747007,0.00021149538],"category_scores_gemma":[0.5207225,0.000102871665,0.001160694,0.0010012417,0.0056704003,0.000042340464,0.0013980528,0.0024687436,0.0000071705244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030951418,0.00342385,0.11631773,0.00035154322,0.0013630962,0.000001658743,0.0008280137,0.0005782667,0.0005867694,0.0827606,0.747957,0.014880073],"study_design_scores_gemma":[0.0200624,0.0012978762,0.04492302,0.0005726587,0.00022196643,0.0000014044922,0.00018792285,0.0009015175,0.0014929619,0.9293329,0.0008201798,0.00018520051],"about_ca_topic_score_codex":0.00040722176,"about_ca_topic_score_gemma":0.0001263589,"teacher_disagreement_score":0.8465723,"about_ca_system_score_codex":0.00018495038,"about_ca_system_score_gemma":0.0042512743,"threshold_uncertainty_score":0.99983263},"labels":[],"label_agreement":null},{"id":"W2256121991","doi":"10.1093/jnci/djv292","title":"Benefit, Risk, and Outcomes in Drug Development: A Systematic Review of Sunitinib","year":2015,"lang":"en","type":"review","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Sunitinib; Medicine; Confidence interval; Internal medicine; Population; Clinical endpoint; Clinical trial; Drug development; Relative risk; Adverse effect; Drug; Intensive care medicine; Oncology; Cancer; Pharmacology; Environmental health","score_opus":0.6735981132024141,"score_gpt":0.6155997685026262,"score_spread":0.05799834469978793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256121991","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015514965,0.9959901,0.00015215427,0.00012053095,0.0015933871,0.0014554425,0.00037270228,0.0000042547636,0.00029590982],"genre_scores_gemma":[0.00000289387,0.9436725,0.05557216,0.00015826126,0.00025364145,0.00010107429,0.0000014495379,0.000027484546,0.00021057004],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99151367,0.0015926373,0.004812835,0.00018580961,0.0017285101,0.00016655288],"domain_scores_gemma":[0.971584,0.019323507,0.0072542746,0.00024513187,0.0014718036,0.00012125159],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016554656,0.0003405705,0.0050737304,0.00026939836,0.00005929548,0.000021913504,0.0008311354,0.00018041996,0.000032120985],"category_scores_gemma":[0.1687968,0.00018021493,0.0006011242,0.00049957476,0.00016651327,0.00012852273,0.00019158606,0.00092880556,0.0000027277763],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010092177,0.00009051213,0.000022769329,0.94561106,0.00065773353,0.000005424379,0.000071425995,0.0000016996981,1.1889553e-8,0.010250492,0.0013440347,0.04193475],"study_design_scores_gemma":[0.00047711676,0.000013749956,0.000015868365,0.7757621,0.0026807825,0.0000714406,0.0000045858587,8.100595e-7,7.455299e-7,0.09784787,0.12293857,0.00018639294],"about_ca_topic_score_codex":0.000015493197,"about_ca_topic_score_gemma":0.00007119056,"teacher_disagreement_score":0.169849,"about_ca_system_score_codex":0.00066463026,"about_ca_system_score_gemma":0.0024696044,"threshold_uncertainty_score":0.8382048},"labels":[],"label_agreement":null},{"id":"W2256391759","doi":"10.1007/978-94-017-7200-6_6","title":"Methodological Considerations for N-of-1 Trials","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Outcome (game theory); Computer science; Clinical trial; Binary number; Scale (ratio); Statistics; Econometrics; Mathematics; Medicine; Mathematical economics; Arithmetic","score_opus":0.9895071940284924,"score_gpt":0.7333257753082979,"score_spread":0.2561814187201945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256391759","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.03565405e-7,0.00009513414,0.539206,0.00034914757,0.0006830845,0.0015144785,0.00082143326,0.000069983544,0.45726064],"genre_scores_gemma":[0.0000032210462,0.00002785455,0.740566,0.00013794583,0.00058949867,0.000074462594,0.0000050103495,0.00005554451,0.25854045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99318624,0.0020628285,0.0035801008,0.00049127213,0.00046302966,0.0002165564],"domain_scores_gemma":[0.457243,0.5402994,0.0012135515,0.00046250297,0.00064385735,0.00013766531],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046724584,0.00036274918,0.0042528817,0.00010142728,0.00004396955,0.000022747663,0.00019327844,0.001070338,0.013046581],"category_scores_gemma":[0.8691034,0.00024742773,0.000951802,0.000016338983,0.00033109964,0.000019173838,0.00010623315,0.00036387003,0.00004753032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109525245,0.00002924548,6.6982295e-8,0.0001463462,0.00025586854,0.0000026327598,0.000008715027,2.520853e-7,0.000015889824,0.8356718,0.15931779,0.0044418857],"study_design_scores_gemma":[0.0010136561,0.0003216878,1.04750185e-7,0.000115872404,0.0008993512,0.000004693545,0.0000037532961,0.000012360615,0.00019631519,0.94484055,0.05233085,0.00026080952],"about_ca_topic_score_codex":0.0000014108167,"about_ca_topic_score_gemma":0.000003148312,"teacher_disagreement_score":0.82237875,"about_ca_system_score_codex":0.000041725794,"about_ca_system_score_gemma":0.00026655878,"threshold_uncertainty_score":0.9999978},"labels":[],"label_agreement":null},{"id":"W2257866789","doi":"10.2174/1574887110666150730120752","title":"Changes in and Impact of the Death Review Process in the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial","year":2015,"lang":"en","type":"review","venue":"Reviews on Recent Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Medicine; Death certificate; Cause of death; Prostate cancer; Colorectal cancer; Internal medicine; Lung cancer; Cancer; Oncology; Gynecology; Disease","score_opus":0.8960661393318761,"score_gpt":0.735743980328491,"score_spread":0.1603221590033851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2257866789","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008380841,0.9606175,0.000017999204,0.000884545,0.0009281432,0.03680324,0.0004958285,0.000016941656,0.00015202287],"genre_scores_gemma":[0.000002047677,0.98962384,0.00503373,0.0004655661,0.0009290057,0.003822567,0.0000116182555,0.00008786667,0.0000237793],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.88996595,0.09199014,0.014676552,0.0014519356,0.001176506,0.00073892396],"domain_scores_gemma":[0.6902066,0.29411778,0.012910491,0.0019117885,0.00039235552,0.00046102004],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22747135,0.0010228319,0.018901948,0.00018653275,0.0000724239,0.00008363508,0.0011761677,0.0009532255,0.00020300412],"category_scores_gemma":[0.6345211,0.00042683698,0.0020400344,0.0014647372,0.00041658347,0.000061307364,0.00033302692,0.0024285847,0.000004422641],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022117172,0.00046433613,0.00019144308,0.05386848,0.00024973627,0.0000058393293,0.000050739574,7.520247e-8,1.4662277e-8,0.00052181893,0.0023585837,0.9400772],"study_design_scores_gemma":[0.017889025,0.0015528717,0.00013755816,0.35785884,0.0044054105,0.000015014705,0.000012234927,0.000006987932,1.8060541e-7,0.028677417,0.58877397,0.0006704817],"about_ca_topic_score_codex":0.00003722343,"about_ca_topic_score_gemma":0.000070490954,"teacher_disagreement_score":0.93940675,"about_ca_system_score_codex":0.00020822357,"about_ca_system_score_gemma":0.0010372801,"threshold_uncertainty_score":0.99987286},"labels":[],"label_agreement":null},{"id":"W2262795364","doi":"10.69645/ebps6929","title":"Emerging trends in phase II trial design","year":2009,"lang":"en","type":"article","venue":"˜The œbiomedical & life sciences collection.","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Phase (matter); Physics","score_opus":0.4336698180243356,"score_gpt":0.5562438315899266,"score_spread":0.12257401356559106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262795364","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017999467,0.00016269431,0.937325,0.023750644,0.006652179,0.0017899717,0.000024480489,0.00036303862,0.011932526],"genre_scores_gemma":[0.29318726,0.00004296643,0.69690126,0.002593038,0.002536668,0.00017496473,0.0000021018468,0.000027602942,0.004534129],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944964,0.0016255564,0.0013576082,0.000605152,0.0012922834,0.00062302244],"domain_scores_gemma":[0.97803855,0.020840766,0.00030960556,0.0003622362,0.00006549374,0.00038332219],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013582967,0.00022693275,0.0006270097,0.0005652155,0.0010498341,0.00008341683,0.00079300365,0.00020871498,0.0013869274],"category_scores_gemma":[0.04225563,0.00014590347,0.00018064704,0.0058558807,0.0012017348,0.00012308199,0.00010474995,0.00049141224,0.000021116795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013358685,0.007352359,0.0000136173285,0.000017264252,0.000070938506,0.000044303684,0.0011832472,0.00006200534,0.00044330297,0.0382491,0.36707643,0.5721288],"study_design_scores_gemma":[0.034203332,0.010582876,0.00007638384,0.00004969298,0.00006678232,0.000011500647,0.00018930242,0.021025633,0.00007101549,0.92169726,0.011703253,0.00032298308],"about_ca_topic_score_codex":0.00002321868,"about_ca_topic_score_gemma":0.0000146929115,"teacher_disagreement_score":0.8834481,"about_ca_system_score_codex":0.000108035485,"about_ca_system_score_gemma":0.00038027388,"threshold_uncertainty_score":0.99952596},"labels":[],"label_agreement":null},{"id":"W2265497904","doi":"10.1200/jco.2007.25.18_suppl.6513","title":"Randomized trials in oncology stopped early for benefit: A systematic review","year":2007,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Randomized controlled trial; Sample size determination; Interim; Interim analysis; Internal medicine; Odds ratio; Oncology","score_opus":0.940011980333068,"score_gpt":0.7790016656310121,"score_spread":0.16101031470205585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2265497904","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001210766,0.943238,0.027804293,0.000867925,0.0072670667,0.019705711,0.000101188314,0.000025822495,0.0009887636],"genre_scores_gemma":[1.5195442e-7,0.6615704,0.33363137,0.0012089849,0.002484932,0.0007726762,0.0000026631276,0.0001091069,0.00021970787],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.63256943,0.21263391,0.14977339,0.0014211108,0.0020311885,0.0015709781],"domain_scores_gemma":[0.06520087,0.85487956,0.07648799,0.0010190551,0.0016011602,0.0008113657],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.64996517,0.0010599096,0.1511652,0.0008948037,0.00005478961,0.000039766714,0.0019400553,0.005172512,0.00026507393],"category_scores_gemma":[0.9774013,0.00059885596,0.023286428,0.0007668483,0.0007775292,0.00011177861,0.0002461451,0.0054089446,0.000057684767],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021860667,0.0011999034,1.5534908e-7,0.47105387,0.0027012806,0.00028402996,0.000013806789,4.2141632e-8,5.583545e-9,0.014044585,0.0018959156,0.48694575],"study_design_scores_gemma":[0.0968565,0.003554117,1.6357396e-7,0.3731712,0.041197542,0.00019218183,0.0000064158635,0.0000025237396,2.685345e-8,0.23445433,0.25024062,0.00032438672],"about_ca_topic_score_codex":0.0000051251286,"about_ca_topic_score_gemma":0.000017721079,"teacher_disagreement_score":0.64224565,"about_ca_system_score_codex":0.0009657874,"about_ca_system_score_gemma":0.006020595,"threshold_uncertainty_score":0.9996463},"labels":[],"label_agreement":null},{"id":"W2277638323","doi":"","title":"Neoadjuvant endocrine therapy and window of opportunity trials: new standards in the treatment of breast cancer?","year":2015,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Medicine; Neoadjuvant therapy; Breast cancer; Endocrine system; Window of opportunity; Oncology; Hormone therapy; Clinical trial; Chemotherapy; Hormonal therapy; Cancer; Intensive care medicine; Internal medicine; Bioinformatics; Hormone","score_opus":0.8235546235967922,"score_gpt":0.577538383601164,"score_spread":0.24601623999562816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2277638323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94875795,0.0058347117,0.006913302,0.014024269,0.0016111343,0.011952968,0.005759325,0.00007924755,0.0050671245],"genre_scores_gemma":[0.885838,0.008840521,0.10137646,0.00035442345,0.0009983847,0.00218417,0.0000037116163,0.000059342212,0.00034503758],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99614805,0.0018487744,0.0010834592,0.00017672373,0.00050773897,0.00023525239],"domain_scores_gemma":[0.9749079,0.0237462,0.00050396594,0.0003724988,0.00021730435,0.00025214703],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010416232,0.00014559887,0.001091458,0.000054623775,0.000012643533,0.000012650626,0.00016730712,0.00005795778,0.00007083162],"category_scores_gemma":[0.052419856,0.00007802602,0.00011070824,0.00016143003,0.00014890514,0.00003327153,0.000021277612,0.00008012148,1.0733071e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012916948,0.0005677082,0.0016247656,0.000028997132,0.000112748865,0.000008107214,0.0006884502,6.4626494e-7,0.000011810451,0.0054189297,0.0013408972,0.98890525],"study_design_scores_gemma":[0.017490914,0.0007602477,0.14289252,0.00005384056,0.0002355738,0.000016940627,0.00053655496,0.000013367504,0.00244141,0.8295672,0.0058040693,0.00018735988],"about_ca_topic_score_codex":0.00063289166,"about_ca_topic_score_gemma":0.000077772784,"teacher_disagreement_score":0.9887179,"about_ca_system_score_codex":0.000104674386,"about_ca_system_score_gemma":0.00030366157,"threshold_uncertainty_score":0.955562},"labels":[],"label_agreement":null},{"id":"W2281399600","doi":"10.1007/s40273-016-0388-x","title":"Cost Implications of Value-Based Pricing for Companion Diagnostic Tests in Precision Medicine","year":2016,"lang":"en","type":"article","venue":"PharmacoEconomics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Precision medicine; Companion diagnostic; Cost–benefit analysis; Medicine; Cost effectiveness; Health economics; Diagnostic test; Quality of Life Research; Personalized medicine; Medical physics; Actuarial science; Risk analysis (engineering); Public health; Pathology; Economics; Bioinformatics; Pediatrics","score_opus":0.6000055285187244,"score_gpt":0.6131922322189319,"score_spread":0.01318670370020758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281399600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11411137,0.000035037534,0.8775294,0.0049787727,0.0005714803,0.0020056502,0.0003174257,0.000045556808,0.0004053265],"genre_scores_gemma":[0.5755826,0.00008381898,0.4233715,0.00040666977,0.00022400758,0.0002759063,0.0000036224324,0.00003463654,0.000017240262],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979672,0.00024207668,0.0011904174,0.00029390748,0.00008056378,0.0002258305],"domain_scores_gemma":[0.79530686,0.20387723,0.00037430497,0.00026215424,0.00009086315,0.00008858364],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027981068,0.0001413597,0.00057462335,0.00011791631,0.000032796637,0.0000054739944,0.0002575713,0.00007163508,0.00020271224],"category_scores_gemma":[0.092545316,0.000101539394,0.00008043552,0.000102907215,0.00013967503,0.000060029022,0.000045647786,0.00008482776,0.000011515693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006780546,0.0011348261,0.044954184,0.0007016244,0.00011584419,0.0000016005401,0.00022075132,0.00040877893,0.05388307,0.3514375,0.014609975,0.5318538],"study_design_scores_gemma":[0.006017196,0.0001398144,0.012573472,0.000423103,0.00010889835,8.321329e-7,0.000008980564,0.0045880587,0.019737711,0.9552463,0.0009856302,0.00016997915],"about_ca_topic_score_codex":0.000011992913,"about_ca_topic_score_gemma":0.000007216022,"teacher_disagreement_score":0.6038088,"about_ca_system_score_codex":0.00016052523,"about_ca_system_score_gemma":0.00006523103,"threshold_uncertainty_score":0.91509855},"labels":[],"label_agreement":null},{"id":"W2284511997","doi":"10.1007/s11009-015-9477-0","title":"Piecewise Linear Approximations for Cure Rate Models and Associated Inferential Issues","year":2016,"lang":"en","type":"article","venue":"Methodology And Computing In Applied Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Censoring (clinical trials); Parametric statistics; Expectation–maximization algorithm; Event (particle physics); Piecewise; Independent and identically distributed random variables; Parametric model; Random variable; Applied mathematics; Algorithm; Statistics; Maximum likelihood","score_opus":0.7164409449664807,"score_gpt":0.5583159700148634,"score_spread":0.15812497495161726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284511997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11529075,0.000029891955,0.8822597,0.0007389733,0.00014857668,0.0010974999,0.00004292791,0.00009475236,0.00029692295],"genre_scores_gemma":[0.11730334,0.000017863978,0.8823552,0.00007084269,0.00009212023,0.00010209528,0.000001774964,0.000016571636,0.000040151153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947058,0.003395124,0.0008710622,0.00059736,0.000093558,0.0003370818],"domain_scores_gemma":[0.87893236,0.12032976,0.00027441164,0.00028070892,0.000100883786,0.00008186173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020205768,0.00020205938,0.00082574744,0.000057486803,0.00013634708,0.000018693916,0.0001370719,0.00035632364,0.00001979772],"category_scores_gemma":[0.072730444,0.00014434801,0.0000585695,0.00013228592,0.00043307373,0.00003653781,0.00020112043,0.00024885737,9.3529445e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003513937,0.00024595408,0.0015294704,0.00031001927,0.000066019515,4.0811338e-7,0.00041564973,0.00006900749,0.0007504731,0.8839959,0.0000632768,0.11220244],"study_design_scores_gemma":[0.0017125339,0.00007611046,0.0017178281,0.00005731,0.000052636384,8.8508455e-7,0.00001929438,0.01912056,0.00058712,0.9764295,0.00005296759,0.00017324326],"about_ca_topic_score_codex":0.0000049330247,"about_ca_topic_score_gemma":0.000012624499,"teacher_disagreement_score":0.116934635,"about_ca_system_score_codex":0.00003420856,"about_ca_system_score_gemma":0.00003383861,"threshold_uncertainty_score":0.93508035},"labels":[],"label_agreement":null},{"id":"W2288457759","doi":"10.1016/j.cjca.2016.02.067","title":"Composite End Points in Acute Heart Failure Research: Data Simulations Illustrate the Limitations","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"","keywords":"Medicine; Categorical variable; Context (archaeology); Weighting; Sample size determination; Statistical power; Statistics; Mathematics","score_opus":0.8055700487799716,"score_gpt":0.5765548994685809,"score_spread":0.22901514931139078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288457759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20139606,0.00040013352,0.3888319,0.38618594,0.0055772397,0.0017682823,0.007660287,0.000034395045,0.008145768],"genre_scores_gemma":[0.86751384,0.000031875166,0.13149989,0.00017005476,0.00070002273,0.0000028476154,0.0000029295998,0.000016630702,0.00006193796],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947992,0.00352103,0.0008076524,0.00019533679,0.000236399,0.00044040979],"domain_scores_gemma":[0.9119684,0.08636483,0.00017312253,0.000683253,0.00043406727,0.00037632987],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0077628754,0.00010052686,0.0005271402,0.00030178754,0.00016902611,0.000038601986,0.00085066434,0.00015737148,0.0000762671],"category_scores_gemma":[0.1072114,0.000057607616,0.000100654805,0.00029963083,0.0007737326,0.00013132647,0.00007878211,0.0006165812,0.000028178469],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000306659,0.00003524284,0.039388258,0.000037836802,0.0018841665,0.0010357967,0.00095822616,0.0012047117,0.006035203,0.33521575,0.5751613,0.038736872],"study_design_scores_gemma":[0.00090357946,0.00014498355,0.014146203,0.000100725556,0.00011096399,0.00021418504,0.00013562098,0.00005682041,0.000056380075,0.8970223,0.08699718,0.00011105384],"about_ca_topic_score_codex":0.00014430651,"about_ca_topic_score_gemma":0.0081455065,"teacher_disagreement_score":0.6661177,"about_ca_system_score_codex":0.00013305746,"about_ca_system_score_gemma":0.00096981553,"threshold_uncertainty_score":0.9003089},"labels":[],"label_agreement":null},{"id":"W2288666460","doi":"10.1002/sim.6907","title":"Inference on treatment‐covariate interaction based on a nonparametric measure of treatment effects and censored survival data","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Covariate; Nonparametric statistics; Statistics; Inference; Parametric statistics; Econometrics; Data set; Confidence interval; Survival analysis; Estimator; Computer science; Mathematics; Artificial intelligence","score_opus":0.5481851531616271,"score_gpt":0.5778375376790365,"score_spread":0.02965238451740937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288666460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011058366,0.000034210407,0.9813624,0.0006687237,0.0013727809,0.0012727033,0.0024296823,0.000048151953,0.0017529791],"genre_scores_gemma":[0.49102765,0.00024518286,0.5082875,0.00006867598,0.0001683354,0.000045455596,0.000034652207,0.000034030763,0.000088511864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966197,0.0011970584,0.0008746329,0.00055812544,0.00049128203,0.00025918882],"domain_scores_gemma":[0.8190564,0.17956339,0.000325547,0.00083398586,0.00010037208,0.00012031684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019544917,0.00031298652,0.0010924243,0.0003131701,0.00003137634,0.000008266367,0.00021520363,0.00012387944,0.00015500262],"category_scores_gemma":[0.21538246,0.0001643672,0.000029143906,0.0003226184,0.0002897661,0.00003701994,0.000046213183,0.00014022597,0.00001074837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003553564,0.002095566,0.0047688284,0.00050437433,0.00032854392,0.00015219649,0.00035743273,0.000021765089,0.0012046297,0.22821668,0.00096356455,0.7578329],"study_design_scores_gemma":[0.03199575,0.029831987,0.018061666,0.0046318234,0.000996268,0.0000035954931,0.00009840541,0.020194316,0.0021474743,0.89105046,0.00041770499,0.0005705388],"about_ca_topic_score_codex":0.0001505655,"about_ca_topic_score_gemma":0.000083853374,"teacher_disagreement_score":0.75726235,"about_ca_system_score_codex":0.0003564418,"about_ca_system_score_gemma":0.00009619048,"threshold_uncertainty_score":0.7912267},"labels":[],"label_agreement":null},{"id":"W2292012639","doi":"10.20982/tqmp.03.2.p060","title":"Computing the power of a t test","year":2007,"lang":"en","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Power (physics); Computer science; Physics; Geology","score_opus":0.7072139307535312,"score_gpt":0.7223390609533593,"score_spread":0.015125130199828085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292012639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008203747,0.00012211439,0.97945464,0.0003887738,0.0069136256,0.0012045725,0.000043902462,0.00004262716,0.0036260027],"genre_scores_gemma":[0.013547369,0.000009395487,0.98560745,0.00029734205,0.00041575555,0.000038718124,6.3113464e-7,0.00004505426,0.000038261845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99115115,0.005008101,0.0024554704,0.0005550505,0.00023244538,0.0005977561],"domain_scores_gemma":[0.47024006,0.5279231,0.00085406215,0.00059082836,0.0003272154,0.0000647017],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07745941,0.00024239316,0.0012291645,0.00020000912,0.00008246306,0.000011768943,0.000562748,0.00029238212,0.00009998556],"category_scores_gemma":[0.52117944,0.0001685991,0.00024656387,0.00062213093,0.0007564552,0.000035975016,0.000094601266,0.00040114138,0.000006903628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060020137,0.00041832138,0.0007421171,0.00007120847,0.00007845658,0.0000025887134,0.0016439907,9.83233e-7,0.014194169,0.9519912,0.00088984845,0.029366896],"study_design_scores_gemma":[0.0018097433,0.0010116954,0.002559941,0.00006261201,0.00005696885,0.0000048565544,0.0004340777,0.000090208654,0.0069215964,0.9827926,0.004071781,0.0001839158],"about_ca_topic_score_codex":0.000009661345,"about_ca_topic_score_gemma":0.000008181837,"teacher_disagreement_score":0.522915,"about_ca_system_score_codex":0.000040070387,"about_ca_system_score_gemma":0.00004125645,"threshold_uncertainty_score":0.9499497},"labels":[],"label_agreement":null},{"id":"W2292912771","doi":"10.1208/s12248-016-9873-6","title":"An Exact Procedure for the Evaluation of Reference-Scaled Average Bioequivalence","year":2016,"lang":"en","type":"article","venue":"The AAPS Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Bioequivalence; Replicate; Heteroscedasticity; Confidence interval; Mathematics; Statistics; Estimator; Food and drug administration; Computer science; Mathematical optimization; Medicine; Pharmacokinetics; Pharmacology","score_opus":0.7678424957344103,"score_gpt":0.6174819998177851,"score_spread":0.15036049591662526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2292912771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16282307,0.00016692143,0.82930255,0.004521853,0.00080789125,0.0014400567,0.000100944984,0.000030102541,0.0008066375],"genre_scores_gemma":[0.86667866,0.00014273127,0.13218495,0.0000892818,0.0006869762,0.000048403075,1.880351e-7,0.000020310914,0.00014851331],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99646556,0.001639055,0.0007269129,0.00015180244,0.0007962022,0.00022049111],"domain_scores_gemma":[0.95335543,0.044640366,0.0006335097,0.00055264146,0.0007336505,0.00008439471],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022389878,0.00011532958,0.0002824539,0.00002838119,0.00021830307,0.00004087385,0.0006844859,0.00008368697,0.0008249631],"category_scores_gemma":[0.09522816,0.000040882715,0.00012190609,0.0000941608,0.00023588618,0.000104277744,0.00004009315,0.00023413688,0.000009612868],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012958207,0.00045384775,0.00034962932,0.0001509265,0.00036400018,0.0000022640343,0.00096456043,0.000057871533,0.044356417,0.16532269,0.00788518,0.7787968],"study_design_scores_gemma":[0.001431139,0.0003029152,0.0017217917,0.00016244585,0.00036427408,0.000030861214,0.000083784005,0.0018475179,0.00439042,0.9894058,0.00017849605,0.00008056879],"about_ca_topic_score_codex":0.0000010409445,"about_ca_topic_score_gemma":0.0000021267174,"teacher_disagreement_score":0.8240831,"about_ca_system_score_codex":0.0000502892,"about_ca_system_score_gemma":0.00016962683,"threshold_uncertainty_score":0.9123931},"labels":[],"label_agreement":null},{"id":"W2298306261","doi":"10.1186/1745-6215-16-s2-o19","title":"The use of early decision modelling and value of information analysis in an adaptive trial design: results from the OPTIMA preliminary study","year":2015,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Ontario Institute for Cancer Research","funders":"","keywords":"Medicine; Value of information; Value (mathematics); Research design; Management science; Operations research; Medical physics; Risk analysis (engineering); Computer science; Machine learning; Artificial intelligence; Statistics; Mathematics; Engineering","score_opus":0.8936610273459658,"score_gpt":0.5946479136336955,"score_spread":0.29901311371227024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298306261","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4805485,0.000019969399,0.5169032,0.000023283372,0.00013271453,0.0022024908,0.0001563609,0.0000072753055,0.0000061630017],"genre_scores_gemma":[0.4019701,0.00001609928,0.59788215,0.0000060500406,0.00007373807,0.00004013282,0.0000024961957,0.0000069363496,0.0000022764518],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98175925,0.012836388,0.00418696,0.00025622966,0.0007943807,0.00016681977],"domain_scores_gemma":[0.62602323,0.37131232,0.0016042916,0.00066571636,0.00032050384,0.00007391885],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05373744,0.00015164033,0.0013070714,0.00013048423,0.0000611584,0.00009776221,0.0003397837,0.00013789067,0.0000034732468],"category_scores_gemma":[0.36041212,0.000079280144,0.00016050236,0.00053656305,0.00013733604,0.0003670269,0.00012611462,0.00017799264,0.000001067074],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.76953405,0.00068975514,0.0002518102,0.0000055265486,0.00084871874,0.0000018553565,0.009682821,0.18514508,0.000006645437,0.004528122,0.00021236105,0.029093258],"study_design_scores_gemma":[0.04823602,0.008316634,0.0014577775,0.00007814364,0.0020616725,1.0328934e-7,0.0019090752,0.332365,0.00015341204,0.60528094,0.0000060364987,0.0001351973],"about_ca_topic_score_codex":0.0006881803,"about_ca_topic_score_gemma":0.000030010846,"teacher_disagreement_score":0.72129804,"about_ca_system_score_codex":0.000027462696,"about_ca_system_score_gemma":0.00009472308,"threshold_uncertainty_score":0.97437644},"labels":[],"label_agreement":null},{"id":"W2300752603","doi":"10.1002/sim.6909","title":"Type‐II generalized family‐wise error rate formulas with application to sample size determination","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type I and type II errors; Sample size determination; False discovery rate; Null hypothesis; Statistical power; Word error rate; Statistics; Multiple comparisons problem; Statistical hypothesis testing; Computer science; Mathematics; Nominal level; Algorithm; Artificial intelligence; Confidence interval","score_opus":0.30340492714075973,"score_gpt":0.5395663056930371,"score_spread":0.23616137855227737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300752603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01839591,0.000009295434,0.97771376,0.001487116,0.00038874685,0.0010268359,0.0003892387,0.000069728216,0.0005193797],"genre_scores_gemma":[0.048715185,0.000041356892,0.9493572,0.00080654747,0.00030048031,0.00016820058,0.000009137397,0.00005373085,0.00054815185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972021,0.00044310823,0.0010056983,0.00046854795,0.0005073348,0.00037321445],"domain_scores_gemma":[0.92752725,0.07105046,0.00029711178,0.0005468799,0.00036614964,0.00021215148],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025374936,0.00024863216,0.0007043993,0.00012679964,0.000082254446,0.000009387872,0.0002576237,0.00012177166,0.00045801155],"category_scores_gemma":[0.21488649,0.0001469484,0.000022326802,0.00044025728,0.00024079646,0.000050526185,0.00008585716,0.00015870635,0.000040540057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019722306,0.00026258916,0.00080179574,0.00023859787,0.000058772726,0.000043305077,0.00066737656,0.000009896432,0.016458342,0.64916945,0.016136426,0.31418124],"study_design_scores_gemma":[0.0039038423,0.0012995276,0.0031087247,0.0003187944,0.000102009806,0.0000027160518,0.000055026,0.0012714452,0.0005051743,0.9870271,0.002147274,0.00025836623],"about_ca_topic_score_codex":0.00008033211,"about_ca_topic_score_gemma":0.00016447311,"teacher_disagreement_score":0.33785766,"about_ca_system_score_codex":0.00015157738,"about_ca_system_score_gemma":0.00007119902,"threshold_uncertainty_score":0.7917268},"labels":[],"label_agreement":null},{"id":"W2313243722","doi":"10.1177/1740774516634316","title":"Substantial risks associated with few clusters in cluster randomized and stepped wedge designs","year":2016,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Generalizability theory; Sample size determination; Cluster (spacecraft); Statistics; Statistical power; Computer science; Research design; Wedge (geometry); Type I and type II errors; Correlation; Cluster size; Contrast (vision); Econometrics; Mathematics; Artificial intelligence","score_opus":0.8556771333791159,"score_gpt":0.6453227649648124,"score_spread":0.21035436841430344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2313243722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38532737,0.00015613747,0.59455806,0.004279857,0.0030088178,0.010456798,0.00027188502,0.00032468216,0.0016164201],"genre_scores_gemma":[0.6898203,0.0006984149,0.3055158,0.0010643761,0.0012651534,0.00042028166,0.0000039510287,0.00016545402,0.0010462978],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9333732,0.05697376,0.007281194,0.0010231719,0.00063654815,0.00071212923],"domain_scores_gemma":[0.20505515,0.7911507,0.0023530698,0.000729624,0.00022869132,0.00048279864],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1765956,0.0004857042,0.0064864256,0.0001638444,0.00008609622,0.00009452566,0.00040139575,0.0008843074,0.0005111834],"category_scores_gemma":[0.8608698,0.00025105273,0.0007792021,0.00029644856,0.0015936483,0.00014154705,0.00019311294,0.0006599027,0.00005665598],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7965221,0.0029659732,0.013454882,0.00023004833,0.0035517348,0.00025840104,0.00031320273,0.0000039247484,0.00031049765,0.046442315,0.010364816,0.12558213],"study_design_scores_gemma":[0.48285717,0.00050897314,0.0017423126,0.0009074343,0.0009445113,0.000003195166,0.000026714915,0.00021652205,0.00010478834,0.5121175,0.00008286176,0.00048799327],"about_ca_topic_score_codex":0.000013143856,"about_ca_topic_score_gemma":0.00007126064,"teacher_disagreement_score":0.73417693,"about_ca_system_score_codex":0.000089891444,"about_ca_system_score_gemma":0.00017662402,"threshold_uncertainty_score":0.99999416},"labels":[],"label_agreement":null},{"id":"W2315610259","doi":"10.4172/2155-6180.1000167","title":"Number Needed to Treat for Recurrent Events","year":2013,"lang":"en","type":"article","venue":"Journal of Biometrics & Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Number needed to treat; Event (particle physics); Nonparametric statistics; Computer science; Medicine; Clinical trial; Randomized controlled trial; Parametric statistics; Statistics; Confidence interval; Relative risk; Mathematics; Surgery; Internal medicine","score_opus":0.49220853295056816,"score_gpt":0.5755920266585692,"score_spread":0.08338349370800108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315610259","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024049493,0.0000639425,0.96897966,0.0017164762,0.0029031131,0.0010924395,0.0008182129,0.00002547021,0.00035122482],"genre_scores_gemma":[0.014397558,0.000100887475,0.98382235,0.0005606622,0.0006495356,0.000029613877,0.0000038105047,0.000060621303,0.00037495192],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99578196,0.00032942268,0.0022256821,0.00026532265,0.00090262503,0.00049498887],"domain_scores_gemma":[0.942764,0.05300044,0.0012733326,0.00035381335,0.00196597,0.000642442],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032418557,0.00029005995,0.001011968,0.0010421838,0.00008634629,0.00010911037,0.00051951176,0.00021344547,0.00060188747],"category_scores_gemma":[0.2458879,0.00022375665,0.0003082763,0.0025180886,0.000074726995,0.00011824964,0.000106549625,0.0003058754,0.00020089316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053983135,0.0011379255,0.0005609673,0.00042626032,0.00023016738,0.000025499752,0.00019276894,0.0000014245747,0.0013459284,0.040951174,0.5829185,0.37166953],"study_design_scores_gemma":[0.0023333346,0.002256386,0.0008565547,0.00016289996,0.00036419946,0.00004836979,0.00016761356,0.00016974987,0.0024917547,0.98179394,0.008983819,0.00037135943],"about_ca_topic_score_codex":0.000013846949,"about_ca_topic_score_gemma":7.524595e-7,"teacher_disagreement_score":0.9408428,"about_ca_system_score_codex":0.00020780902,"about_ca_system_score_gemma":0.00011065982,"threshold_uncertainty_score":0.9124532},"labels":[],"label_agreement":null},{"id":"W2317487674","doi":"10.1097/jcp.0000000000000297","title":"Statistics Commentary Series","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; University of Toronto","funders":"","keywords":"Library science; Series (stratigraphy); Psychiatry; Psychology; Computer science; Geology","score_opus":0.8366553152807233,"score_gpt":0.7503061244825171,"score_spread":0.08634919079820624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2317487674","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017469621,0.9520632,0.011527344,0.0010832088,0.03276564,0.0009165107,0.000793511,0.000037244416,0.0008116017],"genre_scores_gemma":[3.0040624e-8,0.5896304,0.40230206,0.0013758644,0.0063363933,0.000013589321,0.000004645776,0.00008864864,0.00024832934],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9719744,0.012217001,0.013758406,0.00053558254,0.00095716154,0.00055750017],"domain_scores_gemma":[0.8268751,0.16071613,0.009860917,0.0005769562,0.0010145381,0.00095638615],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.029547887,0.0007248721,0.01198948,0.00030426038,0.00006208731,0.00004270065,0.0015590482,0.00145,0.0018316971],"category_scores_gemma":[0.11638612,0.00050836476,0.0022616296,0.00037673477,0.00085177645,0.00013599967,0.00027920384,0.004691188,0.00017160816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055877387,0.00054603984,0.0000027937165,0.0028928628,0.0010776742,0.00033024227,0.0000046960176,4.7307342e-8,1.9287853e-8,0.0014820602,0.48990077,0.50320405],"study_design_scores_gemma":[0.0027459608,0.0012484465,8.1013457e-7,0.0017687448,0.005013686,0.00030137453,0.0000060192065,8.1622295e-7,5.7189652e-8,0.36176246,0.6268761,0.00027549046],"about_ca_topic_score_codex":5.676793e-7,"about_ca_topic_score_gemma":0.0000011838256,"teacher_disagreement_score":0.50292856,"about_ca_system_score_codex":0.00016372121,"about_ca_system_score_gemma":0.0012424128,"threshold_uncertainty_score":0.99984634},"labels":[],"label_agreement":null},{"id":"W23195934","doi":"10.1007/bf03022005","title":"Sample size calculations in randomized trials: common pitfalls","year":2007,"lang":"en","type":"editorial","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; Vancouver Coastal Health Research Institute; University of British Columbia","funders":"","keywords":"Sample size determination; Sample (material); Randomized controlled trial; Statistics; Psychology; Medicine; Mathematics; Physics; Internal medicine; Thermodynamics","score_opus":0.19582435778012475,"score_gpt":0.45240315356812333,"score_spread":0.2565787957879986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W23195934","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01978813,0.003603888,0.0070454846,0.0056859064,0.9568411,0.0039597456,0.0012432028,0.00006936511,0.0017631744],"genre_scores_gemma":[0.0050468333,0.0007153726,0.2610487,0.00016017482,0.7316751,0.000037813392,0.000036770896,0.00050634175,0.0007729025],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9715549,0.01083147,0.011808286,0.0006764168,0.0029565487,0.0021723972],"domain_scores_gemma":[0.1458496,0.82177734,0.01635157,0.0015332692,0.0055864495,0.008901773],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13234782,0.001241863,0.0117799565,0.0028031636,0.00055032223,0.00072255795,0.0023030553,0.0029442185,0.0014016511],"category_scores_gemma":[0.779647,0.0010342519,0.0032058223,0.0012171555,0.0011029658,0.0003696167,0.000033773194,0.00831916,0.000018938548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00818734,0.00010794984,0.00008060981,0.00019050132,0.00067276135,0.33518666,0.00071227516,0.000053753323,4.9935784e-7,0.004435249,0.6477263,0.002646071],"study_design_scores_gemma":[0.06077913,0.00080572715,0.00010321848,0.0026296522,0.0025204986,0.25103062,0.00035878055,0.000040036906,0.000005378094,0.5264363,0.1538282,0.0014624271],"about_ca_topic_score_codex":0.032891296,"about_ca_topic_score_gemma":0.07856384,"teacher_disagreement_score":0.8257053,"about_ca_system_score_codex":0.003468108,"about_ca_system_score_gemma":0.020816337,"threshold_uncertainty_score":0.9995112},"labels":[],"label_agreement":null},{"id":"W2320209167","doi":"10.5414/cpp39162","title":"Evaluation of some properties of individual bioequivalence (IBE) from replicate-design studies","year":2001,"lang":"en","type":"article","venue":"International Journal of Clinical Pharmacology and Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Replicate; Econometrics; Aggregate (composite); Crossover; Cmax; Statistics; Variance (accounting); Set (abstract data type); Mathematics; Computer science; Economics; Bioavailability; Biology; Pharmacology; Machine learning","score_opus":0.8995036027209984,"score_gpt":0.691613292949327,"score_spread":0.20789030977167133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2320209167","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97697145,0.0045680525,0.011406321,0.0023883427,0.004282373,0.0003007762,0.000033824912,0.000008818757,0.000040029296],"genre_scores_gemma":[0.9222317,0.009278699,0.06644707,0.00086132175,0.0011501416,0.0000063520483,3.1978777e-7,0.000013103265,0.000011338779],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922665,0.0032301408,0.002874859,0.0001967911,0.0013059307,0.00012580329],"domain_scores_gemma":[0.9582048,0.03583028,0.0025399788,0.00014994961,0.0031937154,0.00008129699],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02206207,0.00013979612,0.00091141014,0.00011126199,0.000026408703,0.000010533761,0.00059488945,0.00019030378,0.00013393986],"category_scores_gemma":[0.029014155,0.000099221346,0.0002122042,0.000077603945,0.00087886077,0.0001395759,0.00014396846,0.00043249127,0.0000013805846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018452663,0.0065131425,0.026109455,0.00019544634,0.043512665,0.00010651891,0.0030209143,0.00031212278,0.07923127,0.023455732,0.0028550464,0.796235],"study_design_scores_gemma":[0.005075479,0.0008148609,0.0042798524,0.00021661857,0.0032380768,0.000023701547,0.00020920129,0.0008951507,0.032940537,0.9519051,0.0002830207,0.00011841605],"about_ca_topic_score_codex":0.0000019992158,"about_ca_topic_score_gemma":3.2471678e-7,"teacher_disagreement_score":0.92844933,"about_ca_system_score_codex":0.000030374193,"about_ca_system_score_gemma":0.0002441357,"threshold_uncertainty_score":0.9791649},"labels":[],"label_agreement":null},{"id":"W2323818785","doi":"10.5414/cpp41217","title":"Scaling or wider bioequivalence limits for highly variable drugs and for the special case of Cmax","year":2003,"lang":"en","type":"article","venue":"International Journal of Clinical Pharmacology and Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Toronto","funders":"","keywords":"Bioequivalence; Cmax; Geometric mean; Statistics; Scaling; Mathematics; Metric (unit); Drug; Econometrics; Pharmacology; Medicine; Pharmacokinetics","score_opus":0.6098432465095782,"score_gpt":0.6446210051782783,"score_spread":0.03477775866870003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2323818785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1962512,0.0010423749,0.76773894,0.008513604,0.024447827,0.0013026509,0.00030016995,0.000014586353,0.00038864577],"genre_scores_gemma":[0.32575426,0.002684246,0.66111076,0.0038571875,0.0063754776,0.000020583904,3.6494455e-7,0.000029171086,0.0001679584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970251,0.00062146975,0.0018034463,0.00017336429,0.00020775209,0.00016892185],"domain_scores_gemma":[0.8211114,0.17694923,0.000989894,0.00007822839,0.0007775139,0.00009372724],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008070412,0.00013116005,0.0006082007,0.00005375851,0.000094378156,0.000027483553,0.0002806876,0.00019111106,0.00014595375],"category_scores_gemma":[0.031935625,0.000078807505,0.00020121352,0.000058399324,0.0005260238,0.00007393492,0.000040422015,0.0003594906,3.051728e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019328361,0.0016898798,0.0012670367,0.00028333397,0.0066673695,0.00023040667,0.00070057064,0.000045792945,0.0016920312,0.6765287,0.006292259,0.28527427],"study_design_scores_gemma":[0.008093953,0.0009830929,0.00008463671,0.00006933173,0.0013600724,0.0006006626,0.00020089844,0.0014236297,0.0023267204,0.93506026,0.04966285,0.00013390159],"about_ca_topic_score_codex":9.653132e-7,"about_ca_topic_score_gemma":9.699659e-7,"teacher_disagreement_score":0.28514037,"about_ca_system_score_codex":0.000013753231,"about_ca_system_score_gemma":0.00017283268,"threshold_uncertainty_score":0.9762188},"labels":[],"label_agreement":null},{"id":"W2324253949","doi":"10.1097/nan.0b013e3182659950","title":"Building a Clinical Trial Process in Oncology","year":2012,"lang":"en","type":"review","venue":"Journal of Infusion Nursing","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nurses Association","funders":"","keywords":"Medicine; Clinical trial; Oncology nursing; Health care; MEDLINE; Intensive care medicine; Clinical Oncology; Cancer treatment; Medical physics; Oncology; Nursing; Cancer; Internal medicine; Nurse education","score_opus":0.8637669911056532,"score_gpt":0.7468416832305431,"score_spread":0.11692530787511013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324253949","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024299405,0.9688161,0.014452356,0.0001114778,0.013910158,0.0013802983,0.0000076158585,0.000020140295,0.0010588727],"genre_scores_gemma":[0.0000048666016,0.58320796,0.41233397,0.0000242213,0.0043568974,0.000009870367,2.1837052e-7,0.000052962052,0.00000901746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9827299,0.0064288834,0.009214969,0.00032663383,0.0007749952,0.0005246319],"domain_scores_gemma":[0.88232213,0.108821355,0.0077826222,0.00036195942,0.00032775867,0.00038418671],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.03192445,0.000435358,0.006848331,0.00062670873,0.000058862744,0.00004393492,0.0007265638,0.0014965408,0.00020094877],"category_scores_gemma":[0.18800259,0.00029925947,0.0015211786,0.0005914421,0.00024644175,0.00014928787,0.00009170382,0.003465525,0.0000132223095],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029995178,0.0014598664,0.0000017038876,0.003397821,0.000089037065,0.00008782807,0.00009987098,1.5671678e-7,1.6755665e-7,0.0029931276,0.00046941853,0.9884015],"study_design_scores_gemma":[0.017725987,0.0018419471,0.0000016275527,0.086041436,0.0027706295,0.00047826534,0.0000472626,0.0000056095596,5.97898e-7,0.4166413,0.47407955,0.00036579522],"about_ca_topic_score_codex":4.07155e-7,"about_ca_topic_score_gemma":3.5708294e-7,"teacher_disagreement_score":0.9880357,"about_ca_system_score_codex":0.00067325594,"about_ca_system_score_gemma":0.0013338958,"threshold_uncertainty_score":0.99994594},"labels":[],"label_agreement":null},{"id":"W2324998046","doi":"10.1136/oemed-2014-102362.352","title":"0381 Adjustment for multiple comparisons in a job and industry-title analysis of a case-control study of prostate cancer","year":2014,"lang":"en","type":"article","venue":"Occupational and Environmental Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Institut National de la Recherche Scientifique; Armand Frappier Museum; Université de Montréal","funders":"","keywords":"Confidence interval; Odds ratio; Demography; Logistic regression; Population; Bayes' theorem; Medicine; Statistics; Prostate cancer; Cancer; Mathematics; Internal medicine; Sociology","score_opus":0.2640537656905159,"score_gpt":0.48964540967163467,"score_spread":0.22559164398111875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2324998046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950176,0.00007846763,0.003945108,0.00005728493,0.00003605765,0.0004198726,0.0003936625,0.0000017084421,0.000050242124],"genre_scores_gemma":[0.98818946,0.00001204654,0.011638287,0.000029709634,0.000031532916,0.000056889607,0.000003980668,0.0000036722713,0.000034435103],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99932986,0.00008429237,0.0003160017,0.0001047499,0.000113615366,0.00005148039],"domain_scores_gemma":[0.995207,0.0045773727,0.00011057944,0.00006453459,0.0000058097794,0.00003470744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004532321,0.000053345746,0.0003350371,0.000058280846,0.00001269665,6.7657936e-7,0.000019085965,0.00003889324,0.00025163827],"category_scores_gemma":[0.0013599556,0.000038679435,0.000016689262,0.000059587554,0.00010012838,0.000008114486,0.000014698898,0.000054547036,1.6346361e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002204901,0.0003604584,0.9825816,0.0000514534,0.00030081382,0.0000016182901,0.00039589134,0.00006105972,0.00013189312,0.0007133754,0.00021443066,0.014966882],"study_design_scores_gemma":[0.0037115277,0.00046658283,0.97489977,0.00003332492,0.00086447666,0.0000014395569,0.0005854771,0.015540201,0.000017074439,0.0037753335,0.00005481481,0.000049959806],"about_ca_topic_score_codex":0.00014134121,"about_ca_topic_score_gemma":0.00012888428,"teacher_disagreement_score":0.015479141,"about_ca_system_score_codex":0.000013011153,"about_ca_system_score_gemma":0.0000034599345,"threshold_uncertainty_score":0.27552626},"labels":[],"label_agreement":null},{"id":"W2325128228","doi":"10.2316/j.2012.210-1029","title":"SAMPLE SIZE ESTIMATION FOR CANCER PROGRESSION MODELS","year":2012,"lang":"en","type":"article","venue":"International Journal of Computational Bioscience","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung","keywords":"Estimation; Sample size determination; Sample (material); Cancer; Medicine; Statistics; Oncology; Mathematics; Internal medicine; Engineering; Physics","score_opus":0.5373077102737298,"score_gpt":0.6291711456384945,"score_spread":0.09186343536476471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2325128228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013980856,0.00006418829,0.9806013,0.0019485115,0.0029746525,0.00019600322,0.00013416707,0.000015455546,0.000084837884],"genre_scores_gemma":[0.37366864,0.000009175176,0.62556505,0.00021324672,0.0005134805,0.000011813427,9.464168e-7,0.000006981982,0.000010670934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975857,0.00012872645,0.00083929085,0.00012747335,0.0011191677,0.0001996219],"domain_scores_gemma":[0.95404154,0.043561846,0.0008204035,0.00006880609,0.0013576987,0.00014970523],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026903138,0.00010605156,0.00023960027,0.00011098631,0.00007436119,0.000067343775,0.00048484092,0.000056674944,0.000102110884],"category_scores_gemma":[0.05951766,0.00008224299,0.00014094343,0.00014064189,0.00013729528,0.00061436626,0.00005985696,0.000118582524,0.0000024097483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052572927,0.000839379,0.0016890327,0.000053482152,0.00017474286,0.000003438779,0.00049464713,0.0540649,0.0010767928,0.7265732,0.0033361816,0.21116842],"study_design_scores_gemma":[0.0005910018,0.00008411426,0.0011488271,0.00010655913,0.000026275931,0.00002380281,0.000014394198,0.10027237,0.0009871027,0.8963511,0.0003064503,0.00008799275],"about_ca_topic_score_codex":0.0000028879288,"about_ca_topic_score_gemma":2.748054e-7,"teacher_disagreement_score":0.3596878,"about_ca_system_score_codex":0.00012538349,"about_ca_system_score_gemma":0.00018231822,"threshold_uncertainty_score":0.94840443},"labels":[],"label_agreement":null},{"id":"W2326081763","doi":"10.1016/j.cct.2016.04.001","title":"The win ratio approach to analyzing composite outcomes: An application to the EVOLVE trial","year":2016,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. John’s Health Sciences Centre","funders":"Amgen","keywords":"Medicine; Hazard ratio; Clinical endpoint; Placebo; Myocardial infarction; Confidence interval; Randomization; Randomized controlled trial; Internal medicine; Alternative medicine","score_opus":0.8144677085776505,"score_gpt":0.6428355406033506,"score_spread":0.17163216797429992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326081763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01104944,0.0000896717,0.9413995,0.028641641,0.003391138,0.012262343,0.00023053672,0.00026300523,0.0026726814],"genre_scores_gemma":[0.5102688,0.00007241956,0.46813315,0.006807111,0.009104523,0.003332065,0.000015958263,0.00018411299,0.0020818633],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9586014,0.029513462,0.00869768,0.0014443753,0.00106613,0.0006769523],"domain_scores_gemma":[0.520358,0.47301528,0.0020687596,0.003182002,0.00044125615,0.00093467644],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13602751,0.0005136763,0.0030352802,0.000103868304,0.00056671636,0.00033527322,0.0020780778,0.0004532476,0.000047408757],"category_scores_gemma":[0.5724475,0.0002110745,0.001172104,0.000618535,0.00042382308,0.00022736065,0.00043970125,0.00058058335,0.0004120811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08730465,0.003256357,0.00428936,0.000056844925,0.0016378982,0.000007054203,0.0004126907,0.000019131738,0.0011191182,0.2661616,0.15325274,0.48248258],"study_design_scores_gemma":[0.07149219,0.0031097713,0.003767041,0.00020857522,0.0006204522,0.0000021418953,0.00023307173,0.0006096637,0.0003633391,0.8123774,0.1060994,0.0011169616],"about_ca_topic_score_codex":0.000019992129,"about_ca_topic_score_gemma":0.000011615701,"teacher_disagreement_score":0.54621583,"about_ca_system_score_codex":0.00008778743,"about_ca_system_score_gemma":0.0003034801,"threshold_uncertainty_score":0.88964146},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2326187677","doi":"10.1080/03610918.2016.1152367","title":"A study of grouped failure time data and the misapplication of recurrent event modeling","year":2016,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Event (particle physics); Subject (documents); Event data; Clinical trial; Computer science; Medicine; Data mining; Internal medicine","score_opus":0.7149188315626711,"score_gpt":0.6272253548377682,"score_spread":0.08769347672490291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326187677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073760696,0.000080285885,0.924521,0.0003630088,0.00002420399,0.0009784352,0.00022204404,0.000014700134,0.00003559276],"genre_scores_gemma":[0.65068144,0.00007400394,0.34916747,0.0000057959696,0.000007105782,0.000027286966,0.000025185509,0.00000819203,0.000003534699],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968822,0.0013281293,0.0012174873,0.00024388869,0.00024378762,0.00008448885],"domain_scores_gemma":[0.9561597,0.04187259,0.000531959,0.0011220868,0.00028158643,0.0000320944],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027962108,0.000109692555,0.00038381197,0.000094091454,0.00009130961,0.000017257387,0.0004502945,0.000056189223,0.00000750435],"category_scores_gemma":[0.012788048,0.000073955336,0.000016337688,0.00020999555,0.0003149765,0.00008766314,0.00047961707,0.00011107192,9.983135e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065978855,0.0019281693,0.0016426676,0.00022288968,0.00015569304,3.974489e-7,0.005878303,0.024847481,0.00015637008,0.5134275,0.00013276153,0.45094797],"study_design_scores_gemma":[0.0019793343,0.00006336533,0.00054980477,0.000066407665,0.000062792606,3.2815848e-7,0.00031831852,0.6016444,0.000001828718,0.3952553,0.000007133345,0.00005099736],"about_ca_topic_score_codex":0.00002419878,"about_ca_topic_score_gemma":0.000059182614,"teacher_disagreement_score":0.57692075,"about_ca_system_score_codex":0.000025965099,"about_ca_system_score_gemma":0.000025460236,"threshold_uncertainty_score":0.9955277},"labels":[],"label_agreement":null},{"id":"W2326509145","doi":"10.5691/jjb.28.s75","title":"Contribution of Biostatistics in Clinical Trials to Human Society: Experience of a Quarter of a Century and the Future Prospects","year":2007,"lang":"en","type":"article","venue":"Japanese Journal of Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Biostatistics; Quarter (Canadian coin); Medicine; History; Epidemiology; Pathology","score_opus":0.32864406974793675,"score_gpt":0.5774501657966169,"score_spread":0.24880609604868015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326509145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9341076,0.00029717758,0.06413216,0.00028151786,0.0004728347,0.0006406948,0.00004597575,0.0000033075848,0.000018698922],"genre_scores_gemma":[0.7594741,0.00017105273,0.24007913,0.000053849122,0.00020985177,0.000002380062,2.695841e-7,0.000007788509,0.0000016007076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9906773,0.0018667346,0.006136554,0.00017984814,0.00088669354,0.00025288307],"domain_scores_gemma":[0.8753781,0.11843418,0.0043364223,0.0003077085,0.0013416068,0.00020198399],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0653403,0.00014667823,0.0019353912,0.0006284612,0.00003395495,0.000013791774,0.00031373586,0.00022324939,0.000021031741],"category_scores_gemma":[0.30943614,0.00008550776,0.00043692108,0.002964572,0.0006550078,0.00006417541,0.00007965316,0.00034629134,2.3674623e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025077399,0.008405239,0.1562027,0.0018336205,0.0014765783,0.000109329245,0.06218198,0.000005777854,0.13407087,0.46142662,0.0016444122,0.14756547],"study_design_scores_gemma":[0.042543013,0.007427087,0.21834311,0.00091289706,0.00082005473,0.00010416459,0.032562163,0.00025927866,0.046711266,0.6495669,0.00020999149,0.00054006657],"about_ca_topic_score_codex":0.000010742222,"about_ca_topic_score_gemma":0.000004747478,"teacher_disagreement_score":0.24409583,"about_ca_system_score_codex":0.00004573484,"about_ca_system_score_gemma":0.000056104796,"threshold_uncertainty_score":0.96242887},"labels":[],"label_agreement":null},{"id":"W2326733347","doi":"10.1515/sagmb-2014-0100","title":"Corrigendum to: Simple estimators of false discovery rates given as few as one or two p-values without strong parametric assumptions","year":2015,"lang":"en","type":"erratum","venue":"Statistical Applications in Genetics and Molecular Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; University of Ottawa","funders":"","keywords":"Estimator; Simple (philosophy); Parametric statistics; Econometrics; Mathematics; Statistics; Parametric model; Applied mathematics; Philosophy; Epistemology","score_opus":0.2888264089124639,"score_gpt":0.5600055300892997,"score_spread":0.27117912117683574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326733347","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001735363,0.0008944273,0.9860369,0.0001581772,0.0013639237,0.0023861425,0.0053609065,0.000042906133,0.0020212447],"genre_scores_gemma":[0.009787979,0.0007723893,0.98365945,0.00017826843,0.00027213848,0.00097401283,0.00090008083,0.00013291126,0.0033227922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951372,0.00092467136,0.0017375541,0.0011238777,0.00044706248,0.0006295929],"domain_scores_gemma":[0.98823553,0.009242403,0.0006081534,0.001036025,0.00040224913,0.00047566352],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013351877,0.0005651056,0.0017635787,0.00041906655,0.00010405186,0.00007927635,0.00059994153,0.0007444074,0.00015556139],"category_scores_gemma":[0.039098416,0.00048334306,0.00012107509,0.00076973904,0.00095764967,0.00002157516,0.0005189156,0.00081618695,0.00004158635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019678807,0.00084055634,0.0010201052,0.00046260495,0.00035915154,0.000022968468,0.000062546584,0.000028694072,0.00048764516,0.93189466,0.048488323,0.016135985],"study_design_scores_gemma":[0.0007458485,0.0009592973,0.0003860261,0.000114474846,0.0004924745,0.000008181403,0.0000765575,0.00084691553,0.00038795458,0.97510517,0.020333895,0.00054323155],"about_ca_topic_score_codex":0.00020063801,"about_ca_topic_score_gemma":0.00009064991,"teacher_disagreement_score":0.04321051,"about_ca_system_score_codex":0.00010965162,"about_ca_system_score_gemma":0.0006464718,"threshold_uncertainty_score":0.9997618},"labels":[],"label_agreement":null},{"id":"W2326789492","doi":"10.1097/ftd.0b013e318232bc61","title":"Performance of Different Population Pharmacokinetic Algorithms","year":2011,"lang":"en","type":"article","venue":"Therapeutic Drug Monitoring","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"NONMEM; Population; Algorithm; Statistics; Mathematics; Maximization; Residual; Mathematical optimization; Medicine","score_opus":0.5388029263656204,"score_gpt":0.5138796871841506,"score_spread":0.02492323918146988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326789492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99245286,0.00006378522,0.0040624496,0.000010820445,0.001689473,0.00026801322,0.0000038956955,0.00009386721,0.0013548223],"genre_scores_gemma":[0.8371278,0.00007073379,0.16230254,0.000006923606,0.00034113647,0.000022527214,2.7663557e-7,0.000031034604,0.00009701299],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982369,0.00029148994,0.0006781574,0.00021187622,0.00033152977,0.0002500671],"domain_scores_gemma":[0.99579144,0.0034753203,0.00025910823,0.0003302221,0.00006663776,0.00007728432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090043125,0.00017634904,0.00043307588,0.000063094056,0.00005086039,0.0000072558955,0.00024526287,0.00006162601,0.00019055358],"category_scores_gemma":[0.00064231706,0.00014111429,0.000093238996,0.00012418472,0.000064410335,0.00006223726,0.000057766225,0.00018440455,0.000010146984],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031836724,0.0006456145,0.30048794,0.00047913785,0.00026906948,0.0000036408176,0.002032613,0.000008199732,0.007397558,0.009016382,0.000011028825,0.67933047],"study_design_scores_gemma":[0.0011210253,0.00019286637,0.3845669,0.00028200238,0.0003081878,0.0000026167152,0.000105706706,0.0032403166,0.20169736,0.40814286,0.000009845173,0.0003302937],"about_ca_topic_score_codex":0.000022490938,"about_ca_topic_score_gemma":1.6967103e-7,"teacher_disagreement_score":0.6790002,"about_ca_system_score_codex":0.000038204544,"about_ca_system_score_gemma":0.000007144999,"threshold_uncertainty_score":0.5754474},"labels":[],"label_agreement":null},{"id":"W2330570680","doi":"10.1111/bmsp.12066","title":"Testing for negligible interaction: A coherent and robust approach","year":2016,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Contrast (vision); Type I and type II errors; Normality; Econometrics; Homoscedasticity; Statistical hypothesis testing; Interaction; Homogeneity (statistics); Statistics; Variance (accounting); Null hypothesis; Statistical power; Bootstrapping (finance); Computer science; Mathematics; Heteroscedasticity; Artificial intelligence; Economics","score_opus":0.5714294779352754,"score_gpt":0.5466511481811501,"score_spread":0.024778329754125306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2330570680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009491453,0.0001526475,0.98667306,0.0007723316,0.00025100756,0.00033933023,0.00012852561,0.000021928665,0.0021697222],"genre_scores_gemma":[0.02671371,0.0000795563,0.97255015,0.00020261222,0.0003021199,0.000028298009,4.2340193e-7,0.0000306228,0.00009252826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971574,0.00044851683,0.0014431108,0.00034385614,0.00025892718,0.00034816653],"domain_scores_gemma":[0.934677,0.06414041,0.00041965683,0.0001357024,0.000288462,0.00033879033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002797637,0.00018508312,0.0009287995,0.000064833774,0.00009877985,0.00008291579,0.00016153873,0.00017901123,0.0003003588],"category_scores_gemma":[0.10235773,0.00012844571,0.00008885696,0.000084700296,0.00059261714,0.00009926138,0.00006856401,0.00031234053,0.0000049808455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004346688,0.00074299023,0.000119964076,0.0005769439,0.00014202484,0.00013543178,0.000041589792,2.2715852e-7,0.00040485096,0.5404044,0.012080784,0.44491613],"study_design_scores_gemma":[0.0026160234,0.0009522566,0.0011032443,0.000581523,0.00014993237,0.006122453,0.00004476522,0.00034560284,0.000016137752,0.98751426,0.00037647935,0.00017733869],"about_ca_topic_score_codex":0.0000012427779,"about_ca_topic_score_gemma":6.433167e-7,"teacher_disagreement_score":0.44710985,"about_ca_system_score_codex":0.000020243433,"about_ca_system_score_gemma":0.000026682459,"threshold_uncertainty_score":0.9052035},"labels":[],"label_agreement":null},{"id":"W2330970282","doi":"10.1002/bimj.201200254","title":"Letter to the Editor","year":2013,"lang":"en","type":"letter","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Continuous variable; Binary number; Statistics; Sample (material); Mathematics; Latent variable; Econometrics; Computer science; Arithmetic; Physics","score_opus":0.5488640244462376,"score_gpt":0.5448566038001013,"score_spread":0.00400742064613635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2330970282","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000041553158,0.00008954693,0.13903446,0.82095075,0.038362917,0.00058980176,0.00010634824,0.000058190137,0.00080384914],"genre_scores_gemma":[0.000001150473,0.000015690111,0.27990082,0.44101128,0.2764299,0.000031736243,0.0000013309264,0.00006457129,0.0025435316],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920593,0.0022869771,0.0018100456,0.0005418534,0.0023275188,0.00097434025],"domain_scores_gemma":[0.88969845,0.1075963,0.0007729911,0.0009454284,0.0005101805,0.0004766479],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.0054698437,0.0005071879,0.0012204752,0.0013096629,0.00026706012,0.00067742186,0.0019965218,0.0017124778,0.0038618052],"category_scores_gemma":[0.23682338,0.00026781566,0.0006873626,0.002676706,0.00020194912,0.000068898014,0.00040327726,0.007713646,0.0039855586],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000114732175,0.000049060713,0.000002644329,0.000042680913,0.00015021402,0.00023663141,0.00001078331,5.074597e-8,0.0000057527795,0.00018856474,0.9787941,0.02050802],"study_design_scores_gemma":[0.00025736485,0.00018597751,0.000021263837,0.00007613431,0.00014799357,0.000098882476,0.0000016936793,0.0000044267326,0.000013800627,0.18329923,0.8155726,0.0003206339],"about_ca_topic_score_codex":0.0000047796816,"about_ca_topic_score_gemma":1.0892348e-7,"teacher_disagreement_score":0.37993944,"about_ca_system_score_codex":0.00024682368,"about_ca_system_score_gemma":0.00010941532,"threshold_uncertainty_score":0.9999774},"labels":[],"label_agreement":null},{"id":"W2338480338","doi":"10.1002/jrsm.1204","title":"Disconnected by design: analytic approach in treatment networks having no common comparator","year":2016,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of British Columbia","funders":"National Institutes of Health","keywords":"Computer science; Bayesian network; Risk analysis (engineering); Artificial intelligence; Medicine","score_opus":0.834068243143668,"score_gpt":0.6795690327267213,"score_spread":0.1544992104169467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338480338","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028607831,0.0002192436,0.9925253,0.00040568959,0.00017202293,0.0014173188,0.000060647108,0.00010274605,0.002236287],"genre_scores_gemma":[0.042372115,0.00022967231,0.9555378,0.000017097054,0.0002213519,0.0008253503,0.0000014622294,0.00008771884,0.0007074263],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9428677,0.052564196,0.0014191921,0.000987526,0.00086819544,0.0012931834],"domain_scores_gemma":[0.55087423,0.44737044,0.00018834068,0.0010132722,0.00019654531,0.00035713267],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052845914,0.0004041538,0.001813638,0.00036164772,0.00020495142,0.00011686402,0.0007774948,0.0003657561,0.00082500535],"category_scores_gemma":[0.27076873,0.00024144865,0.00024673963,0.0010232386,0.00059874146,0.00011844254,0.00024989748,0.0005630326,0.0000878776],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017454637,0.004148663,0.0029924836,0.00028804384,0.00077751145,0.0000742823,0.0002294546,0.00010440388,0.026121194,0.029310789,0.021100199,0.9131075],"study_design_scores_gemma":[0.0040807575,0.0013521742,0.0015162935,0.0014312061,0.00037279737,0.000014111279,0.0002824424,0.1463794,0.08137654,0.7592349,0.0025356596,0.0014237198],"about_ca_topic_score_codex":0.00009044328,"about_ca_topic_score_gemma":0.000008060801,"teacher_disagreement_score":0.9116838,"about_ca_system_score_codex":0.0007367457,"about_ca_system_score_gemma":0.00013586988,"threshold_uncertainty_score":0.98459905},"labels":[],"label_agreement":null},{"id":"W2339464282","doi":"10.1200/jco.2004.22.90140.6606","title":"RECIST (Response Evaluation Criteria in Solid Tumors) applied to response in lymphoma","year":2004,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Medicine; Response Evaluation Criteria in Solid Tumors; Nuclear medicine; Clinical trial; Cru; Cancer; Target lesion; Internal medicine; Phases of clinical research","score_opus":0.71470487039843,"score_gpt":0.6984320786943826,"score_spread":0.016272791704047385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339464282","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97314525,0.000024114834,0.013079356,0.009676232,0.002093322,0.00081207044,0.0000099675035,0.000014350541,0.0011453651],"genre_scores_gemma":[0.5932961,0.00001585873,0.4043505,0.0017304415,0.00051847036,0.000032735767,1.893201e-7,0.000026733542,0.000028975139],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9606497,0.024359696,0.012354925,0.0006137916,0.0013604509,0.0006614166],"domain_scores_gemma":[0.7253841,0.27017042,0.0027472822,0.0005060338,0.0006337471,0.000558411],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18271142,0.00024498248,0.0030473366,0.00056141027,0.00003243662,0.000026773037,0.00059259,0.0007408009,0.00039529894],"category_scores_gemma":[0.7665177,0.00020417388,0.00038017024,0.00063945795,0.00025441794,0.00010248608,0.00015979305,0.0010342015,0.00010011536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5436344,0.008295631,0.0008698915,0.000048725273,0.00013301345,0.0022409523,0.0010737024,0.0008498147,0.0045320564,0.010668537,0.0023221795,0.4253311],"study_design_scores_gemma":[0.025297925,0.009386841,0.18509758,0.00035457825,0.000108831504,0.00009617605,0.0001886516,0.00014093639,0.0004212433,0.7767027,0.0019602808,0.00024422916],"about_ca_topic_score_codex":0.000013221879,"about_ca_topic_score_gemma":0.000081029444,"teacher_disagreement_score":0.7660342,"about_ca_system_score_codex":0.001287638,"about_ca_system_score_gemma":0.004075038,"threshold_uncertainty_score":0.84157056},"labels":[],"label_agreement":null},{"id":"W2339892475","doi":"10.1109/tmi.2016.2554554","title":"Transformation Invariant Control ofVoxel-Wise False Discovery Rate","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; National Institute on Aging; Canadian Institutes of Health Research","keywords":"False discovery rate; Voxel; Mathematics; Transformation (genetics); Invariant (physics); Randomness; Artificial intelligence; Gaussian process; Gaussian; Measure (data warehouse); Statistical hypothesis testing; Pattern recognition (psychology); Algorithm; Computer science; Statistics; Data mining","score_opus":0.16387690117894177,"score_gpt":0.45452376861370153,"score_spread":0.29064686743475976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339892475","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002352256,0.000010518864,0.9811147,0.013378339,0.001540414,0.00050710724,0.00019164989,0.0002310097,0.0006739954],"genre_scores_gemma":[0.9551584,0.00012618957,0.041432172,0.0023733317,0.00027783195,0.00013493054,6.3284244e-7,0.00006150041,0.0004349703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99571574,0.0012235583,0.00121205,0.00044261524,0.0009085143,0.00049754756],"domain_scores_gemma":[0.9610657,0.037764847,0.00017528079,0.0004529425,0.000100622725,0.00044061863],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004495462,0.0002871913,0.00062849344,0.00015178995,0.00018035842,0.00007886652,0.00033877706,0.00018912811,0.001745778],"category_scores_gemma":[0.011819806,0.0001823087,0.0002860006,0.00022246197,0.00040750092,0.00055880914,0.0000019688948,0.0005429756,0.00021745561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095260417,0.0011720505,0.00003184267,0.00021493778,0.00029984495,0.00017528019,0.00038273187,0.000029587836,0.012127458,0.060336117,0.0017556256,0.92252195],"study_design_scores_gemma":[0.016513115,0.00023207658,0.00013581906,0.001751137,0.00065682566,0.000087648,0.00018709301,0.01575402,0.04410189,0.9182365,0.0013657404,0.0009781658],"about_ca_topic_score_codex":0.000015632726,"about_ca_topic_score_gemma":0.000013008289,"teacher_disagreement_score":0.9528062,"about_ca_system_score_codex":0.00011093147,"about_ca_system_score_gemma":0.00015254463,"threshold_uncertainty_score":0.9991668},"labels":[],"label_agreement":null},{"id":"W2339944052","doi":"10.1503/cmaj.1150088","title":"Minimal important difference is important","year":2016,"lang":"en","type":"letter","venue":"Canadian Medical Association Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Computer science; Significant difference; Data science; Medicine; Internal medicine","score_opus":0.1925851613701736,"score_gpt":0.4468041020082438,"score_spread":0.25421894063807016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339944052","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025703732,0.00016241966,0.0015356113,0.9873366,0.0058808895,0.00032596596,0.0016575642,0.00005450233,0.002789436],"genre_scores_gemma":[0.00003845353,0.0005673696,0.027234184,0.91242987,0.05059941,0.00002819698,0.000013987381,0.00013807217,0.008950444],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98700464,0.0017053165,0.003865237,0.0006537981,0.0050171814,0.0017538146],"domain_scores_gemma":[0.95656204,0.036263496,0.0029396624,0.0005413927,0.0008717538,0.0028216378],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.012641753,0.0005796186,0.0016454569,0.0003338443,0.00031671437,0.00024704728,0.0012137248,0.0049397135,0.04571982],"category_scores_gemma":[0.24120055,0.00041742163,0.00065435615,0.00023614049,0.0001935226,0.000070738795,0.00007794979,0.008450049,0.0004096344],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000748097,0.000013706219,0.0025886276,0.000049300677,0.00034027494,0.005541432,0.000049442882,5.02269e-10,0.0000014428252,0.0010109337,0.9769048,0.013492545],"study_design_scores_gemma":[0.0006779583,0.00006628536,0.00028920156,0.0003960166,0.00015255448,0.00031854113,0.000011695991,0.000009817244,0.0000050037074,0.30993798,0.68772894,0.00040601278],"about_ca_topic_score_codex":0.0004814033,"about_ca_topic_score_gemma":0.0018245265,"teacher_disagreement_score":0.30892706,"about_ca_system_score_codex":0.0022254803,"about_ca_system_score_gemma":0.007872132,"threshold_uncertainty_score":0.99982774},"labels":[],"label_agreement":null},{"id":"W2342819438","doi":"10.1016/j.jclinepi.2016.03.028","title":"N-of-1 trials to enhance patient outcomes: identifying effective therapies and reducing harms, one patient at a time","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health; University of Alberta","funders":"","keywords":"Medicine; Randomized controlled trial; N of 1 trial; Clinical trial; Alternative medicine; Intensive care medicine; MEDLINE; Physical therapy; Internal medicine; Pathology","score_opus":0.7547227347869369,"score_gpt":0.6748657510380461,"score_spread":0.07985698374889072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342819438","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8163019,0.00038678222,0.16749662,0.012529275,0.0021650873,0.00096636394,0.000057763213,0.00001868912,0.00007751933],"genre_scores_gemma":[0.26113677,0.0005276893,0.7356792,0.0019759277,0.00050233887,0.00003330369,1.8392242e-7,0.000038964492,0.00010562609],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9426396,0.039581828,0.016153932,0.0005966279,0.0005062312,0.00052176893],"domain_scores_gemma":[0.24153024,0.7462538,0.010702818,0.00048672853,0.0005169382,0.00050951145],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12065779,0.00031173322,0.008462949,0.00016636297,0.00006767567,0.000009009351,0.0003383354,0.00046143786,0.00036299185],"category_scores_gemma":[0.9296913,0.00016414069,0.0012246827,0.00013490052,0.0005267187,0.00010197476,0.00035330304,0.00060841354,0.000043652315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050211013,0.0009310865,0.033406608,0.00019042147,0.001876649,0.000029662073,0.0006806223,0.000005680319,0.00736078,0.0079126535,0.008323668,0.9342611],"study_design_scores_gemma":[0.0030817676,0.006806772,0.044175558,0.0019412879,0.00051461667,0.000032143074,0.000050750452,0.000017437103,0.0049581425,0.93640757,0.0016868198,0.00032711786],"about_ca_topic_score_codex":0.000006669831,"about_ca_topic_score_gemma":0.0000011378363,"teacher_disagreement_score":0.933934,"about_ca_system_score_codex":0.00010392034,"about_ca_system_score_gemma":0.00008644677,"threshold_uncertainty_score":0.90546787},"labels":[],"label_agreement":null},{"id":"W2344389180","doi":"10.1080/10543406.2018.1489401","title":"Stochastic optimization of adaptive enrichment designs for two subpopulations","year":2018,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; U.S. Food and Drug Administration; National Health Research Institutes; Patient-Centered Outcomes Research Institute; National Institute of Environmental Health Sciences; Canadian Institutes of Health Research; University of Southern California; National Institute for Health and Care Research; Northern California Institute for Research and Education; Foundation for the National Institutes of Health","keywords":"Interim; Simulated annealing; Adaptive design; Computer science; Computation; Mathematical optimization; Context (archaeology); Sequential analysis; Interim analysis; Decision rule; Mathematics; Statistics; Algorithm; Artificial intelligence; Randomized controlled trial; Clinical trial; Medicine","score_opus":0.673947311574328,"score_gpt":0.6092235239341564,"score_spread":0.06472378764017162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2344389180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009350729,0.00003849392,0.99644464,0.00014950325,0.0010284266,0.00058794435,0.0007341002,0.000014654059,0.00006713573],"genre_scores_gemma":[0.19169994,0.0000131143115,0.8074891,0.0000827733,0.0006479575,0.000009548558,0.0000026182743,0.000031029238,0.000023947592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641204,0.00047851706,0.0019766854,0.00019633381,0.00061071524,0.0003257228],"domain_scores_gemma":[0.96272427,0.033650517,0.0012943452,0.00019048597,0.0018390703,0.0003012877],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027899877,0.0002073697,0.00076940656,0.0001556199,0.00011023124,0.000025919766,0.00027277265,0.00011802088,0.0004508351],"category_scores_gemma":[0.04811645,0.00017094618,0.0001786919,0.0002805904,0.0004867143,0.000079312726,0.000055754008,0.0002793863,0.000005276594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003700972,0.0015937751,0.00015869703,0.0003142479,0.00078437425,0.00002482357,0.0003202912,0.01191535,0.0035045573,0.9403604,0.006940112,0.03038239],"study_design_scores_gemma":[0.0035542022,0.0019201295,0.00011380285,0.00012209683,0.0009847358,0.000024545461,0.000054898836,0.22027034,0.003798774,0.76883334,0.00010248064,0.00022067086],"about_ca_topic_score_codex":0.0000021472886,"about_ca_topic_score_gemma":0.0000013443537,"teacher_disagreement_score":0.20835498,"about_ca_system_score_codex":0.000114175346,"about_ca_system_score_gemma":0.00016524918,"threshold_uncertainty_score":0.9599017},"labels":[],"label_agreement":null},{"id":"W2363596501","doi":"10.22237/jmasm/1462075380","title":"Generalized Linear Model Analyses for Treatment Group Equality when Data are Non-Normal","year":2016,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Statistics; Test statistic; Type I and type II errors; Normality; Estimator; Null hypothesis; Statistic; Statistical hypothesis testing; Sample size determination; Econometrics","score_opus":0.8415148840633407,"score_gpt":0.6689807724260041,"score_spread":0.17253411163733667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2363596501","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037528892,0.00006721358,0.99356073,0.0005567601,0.00039837108,0.0008141509,0.0037588917,0.00004529972,0.00042326935],"genre_scores_gemma":[0.0072475746,0.0000914357,0.9910844,0.00023603438,0.00092576817,0.00008194726,0.000017040353,0.0001066059,0.00020917754],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99195,0.0023171692,0.0032830643,0.0008285115,0.00088864117,0.00073266093],"domain_scores_gemma":[0.88597584,0.109481566,0.0019631926,0.0014713657,0.00045437017,0.00065367424],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01505674,0.00054673577,0.002642243,0.00016770714,0.00015159302,0.000070354385,0.0011947408,0.00035691194,0.000266504],"category_scores_gemma":[0.06666642,0.00031698908,0.00040660927,0.00013345506,0.00034847,0.00019639166,0.00035936243,0.00029943397,0.000007224827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003691913,0.0011404218,0.000020203972,0.0002218944,0.0010586752,0.000024891368,0.00014918383,0.0001892389,0.026500827,0.35538888,0.004459701,0.6071542],"study_design_scores_gemma":[0.0053821877,0.0005053895,0.000039936695,0.00008190867,0.0011801714,0.000012236481,0.000020211628,0.18265142,0.0033106464,0.80583423,0.000631892,0.0003497523],"about_ca_topic_score_codex":0.0000073107026,"about_ca_topic_score_gemma":0.0000057980196,"teacher_disagreement_score":0.60680443,"about_ca_system_score_codex":0.00026198206,"about_ca_system_score_gemma":0.00024343519,"threshold_uncertainty_score":0.99992824},"labels":[],"label_agreement":null},{"id":"W2371137554","doi":"","title":"DEVELOPMENT AND USABILITY TESTING OF AN INTERACTIVE WEB-BASED DECISION AID FOR THE TREATMENT OF LOW-AND INTERMEDIATE RISK PROSTATE CANCER","year":2014,"lang":"en","type":"article","venue":"The 36th Annual Meeting of the Society for Medical Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Prostate cancer; Usability; Cancer; Medicine; Computer science; Risk analysis (engineering); Gynecology; Internal medicine; Human–computer interaction","score_opus":0.14756300070678124,"score_gpt":0.4888136394310966,"score_spread":0.3412506387243154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2371137554","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8378466,0.00014060146,0.15981281,0.0002500836,0.0003916525,0.0013261486,0.00021049034,0.000015209717,0.0000064567876],"genre_scores_gemma":[0.44240576,0.000048915474,0.5572565,0.000072589435,0.00009098133,0.00010320758,3.8483174e-7,0.0000187445,0.0000029083228],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641377,0.0006023209,0.0015626366,0.00036077827,0.0007824434,0.0002780414],"domain_scores_gemma":[0.6755341,0.32200563,0.0014113308,0.00048942515,0.0004489624,0.00011055968],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015552798,0.00021932971,0.0007249469,0.000021668762,0.00035873233,0.00001987691,0.0005189876,0.00015002933,0.000009363887],"category_scores_gemma":[0.28363138,0.00009733073,0.0004428627,0.00016908436,0.00090463244,0.00004473263,0.00025133704,0.00022453287,8.733124e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016744925,0.00028034742,0.0019923104,0.0004106329,0.00019603776,8.768945e-8,0.0056775883,0.00014155146,0.00010785562,0.0002917962,0.00007923292,0.9891481],"study_design_scores_gemma":[0.009714393,0.0020243446,0.0072428244,0.008968253,0.001017414,0.000002622219,0.0046671955,0.33452535,0.010773636,0.6192888,0.0014213644,0.00035377475],"about_ca_topic_score_codex":0.000021575646,"about_ca_topic_score_gemma":0.000037566853,"teacher_disagreement_score":0.98879427,"about_ca_system_score_codex":0.00007191252,"about_ca_system_score_gemma":0.00019120768,"threshold_uncertainty_score":0.7224029},"labels":[],"label_agreement":null},{"id":"W2399606097","doi":"10.1016/j.jval.2016.03.1496","title":"Reimbursement Recommendations Based on Phase II Clinical Evidence for Oncology Drugs in Canada","year":2016,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Formulary; Reimbursement; Medicine; Clinical trial; Oncology; Family medicine; Population; Listing (finance); Alternative medicine; Clinical Oncology; Internal medicine; Phases of clinical research; Intensive care medicine; Cancer; Pathology; Environmental health; Business; Health care","score_opus":0.8587800858823377,"score_gpt":0.69826068250283,"score_spread":0.16051940337950765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2399606097","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13603781,0.00013350189,0.33030924,0.5140121,0.008948023,0.008798792,0.0008718994,0.000103573686,0.0007850301],"genre_scores_gemma":[0.15031548,0.00026295835,0.8416066,0.0070158783,0.00028567505,0.0003919946,0.0000024823335,0.000031373664,0.00008756842],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99178827,0.004299734,0.0025906875,0.0005033487,0.00030985236,0.0005081229],"domain_scores_gemma":[0.7348604,0.26400897,0.00045860562,0.0004229447,0.00006058589,0.0001884559],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020361822,0.00014594558,0.00078799593,0.000107773325,0.000080902646,0.000004712916,0.00025211056,0.00012276869,0.00024399986],"category_scores_gemma":[0.20262642,0.00010788654,0.00008340675,0.00020860217,0.00006686716,0.000036430345,0.00005302086,0.00031179775,0.0000059397507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015371419,0.002832415,0.002968092,0.00036831398,0.000017941755,0.000011782347,0.0001618089,0.00012347517,0.0000070220926,0.061017018,0.05524024,0.8757147],"study_design_scores_gemma":[0.023699157,0.010269264,0.0013761884,0.005498937,0.000032144548,9.634773e-7,0.00016793128,0.028683135,0.000096009986,0.894327,0.035427332,0.00042195502],"about_ca_topic_score_codex":0.21642716,"about_ca_topic_score_gemma":0.20920728,"teacher_disagreement_score":0.8752928,"about_ca_system_score_codex":0.002814966,"about_ca_system_score_gemma":0.0060013034,"threshold_uncertainty_score":0.9996337},"labels":[],"label_agreement":null},{"id":"W2400385987","doi":"10.1002/sim.6986","title":"Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":177,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Computer science; Outcome (game theory); Ignorance; Calibration; Statistics; Econometrics; Machine learning; Mathematics","score_opus":0.6090490742207253,"score_gpt":0.5329850486829449,"score_spread":0.07606402553778036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400385987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39533547,0.000024558773,0.6026335,0.00029030695,0.00015506524,0.001030751,0.00041634616,0.000009793811,0.00010421063],"genre_scores_gemma":[0.85115314,0.00007501791,0.14847216,0.000013896793,0.00010366379,0.00011979564,0.0000020229245,0.000025470112,0.000034826167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997444,0.0004068706,0.001170678,0.00022469567,0.000470792,0.00028301045],"domain_scores_gemma":[0.8604295,0.13844524,0.0005214434,0.0004059188,0.00014896636,0.000048883783],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043846183,0.00020507547,0.0008513732,0.00006930033,0.000059866994,0.000004519154,0.00035253877,0.00007944301,0.000044545915],"category_scores_gemma":[0.15361683,0.00007045064,0.00008970518,0.000128932,0.00079478533,0.0000163228,0.000053945856,0.00020716648,4.573518e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009997964,0.00045833038,0.035522006,0.0009509864,0.0002925588,0.0000015943046,0.0015936876,0.00044794322,0.0012115198,0.92903996,0.001633613,0.027848015],"study_design_scores_gemma":[0.0021849317,0.0020554964,0.009312034,0.001963553,0.00020674332,8.396643e-7,0.00020923378,0.19864559,0.0009474216,0.784352,0.0000013350508,0.000120810764],"about_ca_topic_score_codex":0.000007620549,"about_ca_topic_score_gemma":0.000006848236,"teacher_disagreement_score":0.4558177,"about_ca_system_score_codex":0.000051110645,"about_ca_system_score_gemma":0.0000644866,"threshold_uncertainty_score":0.8535126},"labels":[],"label_agreement":null},{"id":"W2409630622","doi":"10.1007/978-1-59745-530-5_1","title":"Study Design: The Basics","year":2007,"lang":"en","type":"review","venue":"Methods in molecular biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Saskatchewan Health Authority","funders":"","keywords":"Blinding; Management science; Research design; Computer science; Interpretation (philosophy); Clinical study design; Data science; Selection (genetic algorithm); Artificial intelligence; Medicine; Statistics; Engineering; Mathematics; Clinical trial; Pathology","score_opus":0.859952979431288,"score_gpt":0.7398574072820376,"score_spread":0.12009557214925037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409630622","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6842415e-8,0.45989636,0.5363058,0.000012410974,0.00075102854,0.0024738468,0.000012178046,0.000037601156,0.00051078154],"genre_scores_gemma":[6.6225274e-9,0.43381944,0.56544584,0.00010356376,0.00014403128,0.00035419053,0.0000015757373,0.000084947606,0.00004641395],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90909463,0.08527256,0.0032905522,0.0011999215,0.00029819793,0.0008441446],"domain_scores_gemma":[0.75845873,0.23900442,0.0007747865,0.0015869765,0.000076781085,0.000098324876],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06932328,0.0007611046,0.004781581,0.00034082672,0.00007953036,0.00003422563,0.0016595653,0.0013316107,0.00012011328],"category_scores_gemma":[0.23416583,0.00044348213,0.00080080476,0.0011282564,0.00048087872,0.0000098021355,0.0006383172,0.0020850063,0.000038119942],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011400669,0.0002685332,0.0000020366483,0.00093738677,0.00028476902,0.00018024462,0.000039954874,2.1820918e-7,0.0000026218156,0.102381274,0.000048974787,0.8958426],"study_design_scores_gemma":[0.00026390416,0.00027587864,3.3586775e-7,0.00063831074,0.00093854894,0.000025342273,0.000026217802,0.000002644364,0.00001763017,0.64562696,0.35184228,0.00034192624],"about_ca_topic_score_codex":0.000005524633,"about_ca_topic_score_gemma":0.0000027689302,"teacher_disagreement_score":0.89550066,"about_ca_system_score_codex":0.00014387156,"about_ca_system_score_gemma":0.00022897676,"threshold_uncertainty_score":0.9999649},"labels":[],"label_agreement":null},{"id":"W2410408783","doi":"10.1016/j.clinthera.2010.02.009","title":"","year":2010,"lang":"en","type":"letter","venue":"Clinical Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Medicine; Medical physics; Pharmacology; Pharmacokinetics","score_opus":0.876935786707712,"score_gpt":0.6757686286756017,"score_spread":0.20116715803211027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410408783","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012791753,0.00013653934,0.07220646,0.8971124,0.023321943,0.0031449303,0.0007191403,0.0013613594,0.00071803835],"genre_scores_gemma":[0.000019705452,0.0004941894,0.44790843,0.5025024,0.04732828,0.00017597295,0.00003823336,0.00058342033,0.0009494137],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95587236,0.018411053,0.014794867,0.00425063,0.0034031377,0.0032679653],"domain_scores_gemma":[0.4574779,0.52900535,0.004880963,0.006742812,0.0011895129,0.0007034893],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.037429236,0.002796024,0.009782285,0.0003541564,0.0005350096,0.0005372208,0.0061372467,0.0470534,0.00065551326],"category_scores_gemma":[0.35343856,0.0022996871,0.0051754806,0.00083508604,0.005394887,0.00019516078,0.0013445942,0.109906614,0.00014646584],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004152901,0.0011647787,0.00077854434,0.00065735064,0.0026023872,0.0015875513,0.000059838145,1.1887262e-7,0.00003449313,0.008026936,0.909088,0.075584695],"study_design_scores_gemma":[0.0022472143,0.0007792296,0.00009599373,0.00020595593,0.0021653622,0.00003827127,0.0000078350295,0.000056326982,0.000054052765,0.5145257,0.47838274,0.001441311],"about_ca_topic_score_codex":0.000010736084,"about_ca_topic_score_gemma":0.000017347655,"teacher_disagreement_score":0.51059425,"about_ca_system_score_codex":0.00015485297,"about_ca_system_score_gemma":0.0008141387,"threshold_uncertainty_score":0.99924004},"labels":[],"label_agreement":null},{"id":"W2410992638","doi":"10.1002/sim.6996","title":"Bayesian adjustment for the misclassification in both dependent and independent variables with application to a breast cancer study","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; American Cancer Society","keywords":"Concordance; Covariate; Logistic regression; Breast cancer; Statistics; Medicine; Econometrics; Internal medicine; Oncology; Cancer; Mathematics","score_opus":0.18434440924207227,"score_gpt":0.501049341478635,"score_spread":0.3167049322365627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410992638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020234059,0.000053434298,0.9891391,0.004408217,0.00018935,0.0036069548,0.00051021035,0.000016149552,0.000053181542],"genre_scores_gemma":[0.51419073,0.00014691407,0.48218492,0.00026152068,0.0002666405,0.0027791983,0.000002778679,0.000037283895,0.0001299965],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99764645,0.0003350231,0.000791964,0.00046450275,0.00049406965,0.00026796653],"domain_scores_gemma":[0.9711017,0.028018517,0.0002185498,0.000412356,0.00013108602,0.00011780073],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037114986,0.00018384973,0.00047223998,0.00011483509,0.00005449093,0.000011941926,0.0002104202,0.00006695285,0.00010276844],"category_scores_gemma":[0.010254235,0.0000893518,0.0000094981615,0.00022556944,0.00015927124,0.000026630052,0.000054111137,0.00014509527,0.0000013649264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017633713,0.0011471894,0.04898826,0.0002906732,0.00017723528,0.000017226428,0.002513377,0.000055249067,0.0008344949,0.35625768,0.0027862617,0.58516896],"study_design_scores_gemma":[0.0075805155,0.0008611238,0.31059578,0.00055799715,0.00026725695,0.00000751572,0.0016737141,0.002483693,0.000024860938,0.6755612,0.00015130095,0.00023503965],"about_ca_topic_score_codex":0.00046429716,"about_ca_topic_score_gemma":0.0041187196,"teacher_disagreement_score":0.58493394,"about_ca_system_score_codex":0.00021992851,"about_ca_system_score_gemma":0.000073198484,"threshold_uncertainty_score":0.9980828},"labels":[],"label_agreement":null},{"id":"W2411964580","doi":"10.1158/1078-0432.ccr-15-2644","title":"Rendering the 3 + 3 Design to Rest: More Efficient Approaches to Oncology Dose-Finding Trials in the Era of Targeted Therapy","year":2016,"lang":"en","type":"editorial","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University College of the North","funders":"Bristol-Myers Squibb; American Association for Cancer Research","keywords":"Medicine; Clinical trial; Maximum tolerated dose; Dosing; Adaptive design; Pharmacodynamics; Oncology; Medical physics; Pharmacokinetics; Pharmacology; Internal medicine","score_opus":0.9658752865274041,"score_gpt":0.7506138417031166,"score_spread":0.21526144482428744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2411964580","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040067527,0.0018362047,0.087585784,0.058242146,0.8131582,0.032194365,0.0015538174,0.00012852527,0.0012941927],"genre_scores_gemma":[0.0027687575,0.0028183972,0.21475798,0.00066807686,0.76830477,0.009936489,0.000008658113,0.00028515668,0.0004517102],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8828403,0.09981094,0.008007864,0.002030553,0.0054759285,0.0018344541],"domain_scores_gemma":[0.14363213,0.8509437,0.0014484971,0.00252856,0.0009582767,0.00048887444],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.36316845,0.0005817266,0.0043827607,0.00040965472,0.00031075504,0.00015733852,0.0042596557,0.002129004,0.00035893303],"category_scores_gemma":[0.83225155,0.0002719267,0.00083820155,0.0018000241,0.0014087779,0.00003054371,0.0010511313,0.007663295,0.00005861384],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00907457,0.0007412325,0.000017702067,0.00017651379,0.0002978048,0.000032991742,0.0018621574,0.00013075108,0.00011192561,0.0028386158,0.82945997,0.15525578],"study_design_scores_gemma":[0.009841944,0.006652737,0.0005628344,0.0035479341,0.00026292316,0.0000014169339,0.0012541814,0.00019001811,0.0013469479,0.2921776,0.683099,0.001062495],"about_ca_topic_score_codex":0.00020784783,"about_ca_topic_score_gemma":0.000090419744,"teacher_disagreement_score":0.7511327,"about_ca_system_score_codex":0.00078721176,"about_ca_system_score_gemma":0.0032781756,"threshold_uncertainty_score":0.9999733},"labels":[],"label_agreement":null},{"id":"W2412646424","doi":"10.1158/0008-5472.can-15-3455","title":"Design and Reporting of Targeted Anticancer Preclinical Studies: A Meta-Analysis of Animal Studies Investigating Sorafenib Antitumor Efficacy","year":2016,"lang":"en","type":"review","venue":"Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Canadian Institutes of Health Research","keywords":"Sorafenib; Medicine; Meta-analysis; Oncology; Internal medicine; Publication bias; Hepatocellular carcinoma; Cancer; Renal cell carcinoma; External validity; Subgroup analysis; Clinical study design; Clinical trial","score_opus":0.9843123348499394,"score_gpt":0.7927409852617976,"score_spread":0.19157134958814181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2412646424","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041134507,0.9934565,0.0025766566,0.00014480844,0.00017410763,0.0028396833,0.00033582546,0.000038503633,0.000022577577],"genre_scores_gemma":[0.00012348185,0.748342,0.2504084,0.000009071564,0.00018275563,0.0007674347,0.0000015275558,0.000084039915,0.00008128856],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9710098,0.013227165,0.011426131,0.0015253135,0.0019497733,0.0008618039],"domain_scores_gemma":[0.49154842,0.48890984,0.01337842,0.0017972367,0.0039991625,0.00036692226],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.074327886,0.00067267625,0.021626612,0.0009260205,0.00018648492,0.000036247242,0.00077716855,0.00045873973,0.00035757077],"category_scores_gemma":[0.7308551,0.00038627285,0.0028153255,0.0032597214,0.0039222427,0.00007959031,0.0011027664,0.0013110719,0.0000035091414],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029281026,0.0003066819,0.000027897597,0.09007347,0.6868017,0.000068466776,0.0008063582,0.0000040756313,0.00021857386,0.0052045244,0.001096219,0.21509923],"study_design_scores_gemma":[0.0012479243,0.0015329367,0.000018424837,0.03678455,0.8155025,0.0000076718425,0.00044894178,0.00006807827,0.0010772165,0.13628586,0.0058744554,0.0011514267],"about_ca_topic_score_codex":0.000026946123,"about_ca_topic_score_gemma":0.0000063321836,"teacher_disagreement_score":0.6565272,"about_ca_system_score_codex":0.0002584045,"about_ca_system_score_gemma":0.00137552,"threshold_uncertainty_score":0.9998589},"labels":[],"label_agreement":null},{"id":"W2416416514","doi":"","title":"Principles of clinical trial design.","year":2002,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Clinical trial; Intensive care medicine; Internal medicine","score_opus":0.9500416021478778,"score_gpt":0.6186003152805594,"score_spread":0.33144128686731844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2416416514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07365225,0.00021953078,0.74245113,0.0015429623,0.009931863,0.013226536,0.0000928714,0.0005075668,0.15837526],"genre_scores_gemma":[0.072075754,0.00004874485,0.9229912,0.00009267802,0.0010303331,0.0009802185,1.4621236e-7,0.00002976083,0.0027511683],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945799,0.001978117,0.0023807304,0.0003133955,0.00040366733,0.0003441735],"domain_scores_gemma":[0.890633,0.10790367,0.0006346503,0.00053157576,0.000086671156,0.00021046892],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01406711,0.00012699382,0.00088721636,0.00004298347,0.000025948315,0.000014306629,0.00032054624,0.00021514433,0.0005336581],"category_scores_gemma":[0.44404024,0.0000996435,0.0002817949,0.0001548614,0.00022947903,0.000035708836,0.000091997936,0.00025235506,0.00003745805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009018632,0.0014789222,0.00037887855,0.00007890639,0.000165603,0.000010745123,0.000030531322,0.0000019400254,0.0000013797588,0.1974506,0.006697293,0.78468657],"study_design_scores_gemma":[0.04590445,0.00053242093,0.008354384,0.000021539736,0.00022430619,0.000002161214,0.000007942519,0.0006370866,0.0005262529,0.9333168,0.010199054,0.00027358043],"about_ca_topic_score_codex":0.0000010295045,"about_ca_topic_score_gemma":3.598515e-7,"teacher_disagreement_score":0.784413,"about_ca_system_score_codex":0.000013615871,"about_ca_system_score_gemma":0.000013585192,"threshold_uncertainty_score":0.58431816},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2417291824","doi":"10.1002/9781118445112.stat08040","title":"Dynamic Treatment Regimes","year":2017,"lang":"en","type":"letter","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Psychological intervention; Class (philosophy); Treatment effect; Randomized controlled trial; Econometrics; Operations research; Medicine; Artificial intelligence; Mathematics; Psychiatry; Surgery","score_opus":0.5431801025688237,"score_gpt":0.5601618703280155,"score_spread":0.0169817677591918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2417291824","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007309005,0.00077568745,0.47365183,0.17856358,0.005535742,0.0034720292,0.32985082,0.0009098993,0.007167332],"genre_scores_gemma":[0.000015348443,0.0035601023,0.90903676,0.034266923,0.0027783855,0.00020992958,0.007270389,0.00043896894,0.042423196],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901137,0.001595594,0.002795739,0.0020935596,0.0017178952,0.0016835448],"domain_scores_gemma":[0.9452829,0.046629865,0.00277702,0.004089862,0.0007932246,0.00042714467],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0012431646,0.0017380487,0.0036553468,0.00034899754,0.0005332246,0.00043080814,0.0021059858,0.0023335454,0.001921523],"category_scores_gemma":[0.054339293,0.0014147043,0.0004042671,0.00017367527,0.0011944931,0.00013492015,0.00043427135,0.0040154294,0.00049240433],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010389295,0.00050205254,0.000009142738,0.0006839731,0.00058694865,0.0025062943,0.00005553681,7.4766666e-7,0.0000054279494,0.026645405,0.89903027,0.06987033],"study_design_scores_gemma":[0.0010584905,0.00070323184,0.000022854767,0.0006221274,0.00075489626,0.000031502375,0.000013765237,0.0004154166,0.000006161984,0.550627,0.4448124,0.0009321949],"about_ca_topic_score_codex":0.00020285494,"about_ca_topic_score_gemma":0.00022554968,"teacher_disagreement_score":0.5239816,"about_ca_system_score_codex":0.00087560393,"about_ca_system_score_gemma":0.0010313762,"threshold_uncertainty_score":0.9995366},"labels":[],"label_agreement":null},{"id":"W2418770449","doi":"10.1186/s12874-016-0166-7","title":"Evaluation of a multi-arm multi-stage Bayesian design for phase II drug selection trials – an example in hemato-oncology","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut National Du Cancer; CNIB","keywords":"Sample size determination; Bayes' theorem; Bayesian probability; Statistics; Decision rule; Interim analysis; Computer science; Medicine; Mathematics; Randomized controlled trial; Surgery","score_opus":0.9863969453268049,"score_gpt":0.7938781117172434,"score_spread":0.19251883360956146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2418770449","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014287604,0.00010596653,0.9785431,0.00062984275,0.0005863,0.0056498903,0.000075826916,0.00006703599,0.000054436543],"genre_scores_gemma":[0.012539185,0.0000968888,0.9840139,0.00007893764,0.00045038585,0.0024820606,0.00000488155,0.00007277283,0.000261001],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.39750397,0.58686775,0.0061235144,0.0019191836,0.005608144,0.0019774183],"domain_scores_gemma":[0.0985032,0.8960858,0.001005922,0.0008647149,0.0026488977,0.00089149113],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7471657,0.00032296695,0.0029321099,0.0008065608,0.00020464374,0.000015448644,0.0008802612,0.0011061559,0.0036239277],"category_scores_gemma":[0.9751024,0.00021456362,0.00032419825,0.0007912522,0.0012456867,0.00013708824,0.00032020084,0.0008946568,0.000011675814],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069693434,0.008421285,0.00007213695,0.00054632785,0.00019521087,0.00001543544,0.0013525306,0.000023086854,0.040442966,0.051139202,0.001241429,0.889581],"study_design_scores_gemma":[0.040481754,0.0054720254,0.0000366253,0.00029934247,0.00023950363,0.00001092307,0.0006100783,0.1605206,0.03820771,0.75331086,0.0005440382,0.00026656795],"about_ca_topic_score_codex":0.00036411107,"about_ca_topic_score_gemma":0.0024258774,"teacher_disagreement_score":0.8893145,"about_ca_system_score_codex":0.00063126866,"about_ca_system_score_gemma":0.005019238,"threshold_uncertainty_score":0.9972869},"labels":[],"label_agreement":null},{"id":"W2431958829","doi":"10.1097/jcp.0000000000000447","title":"Statistics Commentary Series","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; University of Toronto","funders":"","keywords":"Library science; Series (stratigraphy); Psychiatry; Psychology; Computer science","score_opus":0.7440903335648084,"score_gpt":0.6988603449131224,"score_spread":0.045229988651685926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2431958829","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20705694,0.0006082684,0.58933866,0.079156905,0.11156778,0.0012797836,0.00046966536,0.00016518311,0.010356811],"genre_scores_gemma":[0.009703348,0.00031318143,0.9721413,0.012166297,0.0053197853,0.000004584166,8.285326e-7,0.00004085025,0.0003097757],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99053156,0.0035660022,0.0047062407,0.00023939156,0.0006208761,0.00033590174],"domain_scores_gemma":[0.9283753,0.06729771,0.0022874726,0.00028384785,0.0008996321,0.0008560527],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017291727,0.00021223741,0.0016233989,0.00010566253,0.00004123237,0.000022465472,0.0005991236,0.00030220184,0.0009716293],"category_scores_gemma":[0.12219465,0.00016331844,0.00036189434,0.00017871229,0.000556763,0.00015978026,0.0001102762,0.0013312584,0.000069926486],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058063036,0.0010236577,0.0030984462,0.000032961132,0.00038565174,0.00031407934,0.00004611726,0.0000032333683,0.00003634035,0.011489943,0.9561361,0.02162717],"study_design_scores_gemma":[0.010308407,0.00254553,0.0008294805,0.000028698456,0.00036900726,0.0001454312,0.00007922858,0.000034296885,0.000059789727,0.87492186,0.11051629,0.00016197344],"about_ca_topic_score_codex":0.0000012188995,"about_ca_topic_score_gemma":0.000002400487,"teacher_disagreement_score":0.86343193,"about_ca_system_score_codex":0.000052290856,"about_ca_system_score_gemma":0.0002663255,"threshold_uncertainty_score":0.99994165},"labels":[],"label_agreement":null},{"id":"W2435640307","doi":"","title":"Bioequivalence and interchangeability of narrow therapeutic range drugs. Canadian Society for Pharmaceutical Sciences discussion.","year":2000,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Interchangeability; Bioequivalence; Medicine; Pharmaceutical sciences; Pharmacology; Computer science; Pharmacokinetics","score_opus":0.5770432396117128,"score_gpt":0.5236744621771628,"score_spread":0.05336877743454993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2435640307","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8081032,0.0046799616,0.043893617,0.08155424,0.0035374311,0.026864855,0.004003023,0.00052261015,0.02684104],"genre_scores_gemma":[0.80396545,0.0001316417,0.19358397,0.0007698041,0.00014879814,0.00093129766,7.0896925e-7,0.000020177706,0.0004481472],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981031,0.00031335498,0.000495913,0.00035677722,0.00024136179,0.00048953376],"domain_scores_gemma":[0.9868984,0.0124295615,0.000078983016,0.00020885748,0.000051238232,0.00033290868],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059325416,0.000131361,0.0003821139,0.00003667061,0.00015058521,0.00002897504,0.0002676243,0.00010857458,0.00039504847],"category_scores_gemma":[0.008573665,0.00007995688,0.0001844044,0.00019864007,0.0011584918,0.00006842477,0.000036304227,0.00013460557,0.0000014344123],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012163004,0.000085743406,0.0010876466,0.00027930844,0.000046336096,3.631441e-7,0.0006426245,2.2615687e-7,0.000012655102,0.012207627,0.00067330233,0.98484254],"study_design_scores_gemma":[0.0014472215,0.00010258873,0.011089475,0.000044437493,0.00020456391,0.0000024048452,0.0003080428,0.00089743995,0.00076495897,0.97701967,0.007852159,0.00026703294],"about_ca_topic_score_codex":0.00037971276,"about_ca_topic_score_gemma":0.00030997806,"teacher_disagreement_score":0.9845755,"about_ca_system_score_codex":0.00006777444,"about_ca_system_score_gemma":0.00006924588,"threshold_uncertainty_score":0.99977756},"labels":[],"label_agreement":null},{"id":"W2443086342","doi":"","title":"The number remaining at risk: an adjunct to the number needed to treat.","year":2002,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Number needed to treat; Medicine; Absolute risk reduction; Odds ratio; Adjunct; Adverse effect; Confidence interval; Event (particle physics); Number needed to harm; Relative risk; Statistics; Internal medicine; Mathematics","score_opus":0.5203457045445028,"score_gpt":0.48972298675955095,"score_spread":0.030622717784951847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2443086342","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6383023,0.0000645382,0.038763274,0.035093468,0.0042899624,0.008816886,0.0002784565,0.0006220185,0.27376905],"genre_scores_gemma":[0.3772515,0.000077811164,0.55253154,0.0073576123,0.0031298653,0.00714185,0.0000019187173,0.00023179223,0.052276067],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99539816,0.0017942104,0.0008388399,0.00050345407,0.0005949258,0.0008704348],"domain_scores_gemma":[0.9463535,0.05143125,0.00022558862,0.0013235009,0.0001107258,0.0005554415],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007257411,0.00026950377,0.0005087583,0.000023197877,0.00055786193,0.00016848657,0.00073781,0.00014792573,0.0014260944],"category_scores_gemma":[0.15660986,0.00014308777,0.00017753619,0.00045619448,0.0001243445,0.00006382782,0.00032259553,0.00036437303,0.0022404531],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035173868,0.00024179858,0.004509467,0.000022243445,0.00012308937,0.000017346665,0.0019079464,0.000011150213,0.000008167159,0.03207341,0.33801368,0.62271994],"study_design_scores_gemma":[0.0024042889,0.00011389864,0.054802734,0.000046759455,0.0005123076,0.000047263304,0.001049935,0.0005023924,0.0008850465,0.7579792,0.18070814,0.00094804325],"about_ca_topic_score_codex":0.000075134245,"about_ca_topic_score_gemma":0.0001172032,"teacher_disagreement_score":0.7259058,"about_ca_system_score_codex":0.00014385686,"about_ca_system_score_gemma":0.000007907703,"threshold_uncertainty_score":0.99948674},"labels":[],"label_agreement":null},{"id":"W2460537066","doi":"10.1007/s40471-016-0079-3","title":"SMART Thinking: a Review of Recent Developments in Sequential Multiple Assignment Randomized Trials","year":2016,"lang":"en","type":"review","venue":"Current Epidemiology Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Randomized controlled trial; Identification (biology); Data science; Computer science; Management science; Medicine; Intensive care medicine; Engineering; Pathology; Biology","score_opus":0.8959304626455019,"score_gpt":0.6849616236723068,"score_spread":0.21096883897319507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460537066","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0515587e-7,0.9304864,0.048796494,0.0002142168,0.009411562,0.010396418,0.00012573473,0.00007248577,0.000496521],"genre_scores_gemma":[1.5222926e-7,0.8047157,0.19215305,0.00013598945,0.0003943489,0.0023724346,0.000092561444,0.00008659198,0.00004914671],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7725242,0.16711527,0.054287333,0.0030256722,0.0013450334,0.0017025333],"domain_scores_gemma":[0.2506941,0.71379083,0.032403816,0.002188778,0.0004998463,0.000422648],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32183126,0.0011736421,0.041746464,0.0004035153,0.00006243328,0.000008690718,0.0006968597,0.001201996,0.0013947457],"category_scores_gemma":[0.9485889,0.0006677863,0.0041484456,0.00048249832,0.0006754414,0.000053199186,0.0006094759,0.0013604485,0.00004500815],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006697527,0.00031356205,0.0000661821,0.12556918,0.00093752606,0.00009428452,0.00001138672,3.4642888e-8,6.336555e-8,0.006606867,0.0077197943,0.85801136],"study_design_scores_gemma":[0.0069644055,0.000017869002,8.588103e-7,0.22586748,0.0019654443,0.00007323588,3.0072812e-7,5.279637e-7,7.0674554e-7,0.3006788,0.4640911,0.00033930741],"about_ca_topic_score_codex":0.000007419738,"about_ca_topic_score_gemma":0.0000012249646,"teacher_disagreement_score":0.85767204,"about_ca_system_score_codex":0.00060337584,"about_ca_system_score_gemma":0.0014983455,"threshold_uncertainty_score":0.99957734},"labels":[],"label_agreement":null},{"id":"W2462507877","doi":"10.1371/journal.pone.0158798","title":"Time Varying Apparent Volume of Distribution and Drug Half-Lives Following Intravenous Bolus Injections","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Memorial University of Newfoundland","funders":"University of Saskatchewan","keywords":"Volume of distribution; Bolus (digestion); Intravenous bolus; Extracellular fluid; Distribution Volume; Population; Distribution (mathematics); Mathematics; Gamma distribution; Renal function; Chemistry; Statistics; Medicine; Pharmacokinetics; Internal medicine; Extracellular; Mathematical analysis; Biochemistry","score_opus":0.267731070730653,"score_gpt":0.41417309935037017,"score_spread":0.14644202861971717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2462507877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8150328,0.00008287177,0.18225855,0.00068601256,0.00017663748,0.00057612837,0.00032677743,0.0001423066,0.0007179094],"genre_scores_gemma":[0.67187196,0.00003661857,0.3272377,0.000013320808,0.00013522196,0.00003064287,0.0000041339176,0.000022688002,0.000647733],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983139,0.0003303886,0.00059177354,0.00024358754,0.0003089847,0.00021138068],"domain_scores_gemma":[0.98601323,0.013337805,0.00020019736,0.000262678,0.00008594916,0.0001001607],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010955911,0.00012249706,0.0005336178,0.000036750414,0.00008681436,0.000015310683,0.00010607822,0.00006999232,0.00017955023],"category_scores_gemma":[0.038177084,0.00009263395,0.00008628953,0.00011176994,0.00014724983,0.000070135065,0.000096144126,0.00011259383,0.000045429824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012877939,0.032548312,0.020959638,0.004944732,0.009473364,0.00012038627,0.006019121,0.000005666348,0.52176297,0.1529644,0.007971961,0.24194165],"study_design_scores_gemma":[0.001969669,0.00039200665,0.0018180911,0.0020626457,0.0012400653,0.000004455609,0.00008599094,0.00090492255,0.04949157,0.94155896,0.00006209667,0.00040954677],"about_ca_topic_score_codex":0.000013407091,"about_ca_topic_score_gemma":0.0000014657411,"teacher_disagreement_score":0.78859454,"about_ca_system_score_codex":0.00005808409,"about_ca_system_score_gemma":0.00002572772,"threshold_uncertainty_score":0.96992475},"labels":[],"label_agreement":null},{"id":"W2463735421","doi":"10.1177/0272989x16655346","title":"Quantitative Framework for Retrospective Assessment of Interim Decisions in Clinical Trials","year":2016,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Interim; Management science; Neglect; Clinical trial; Interim analysis; Set (abstract data type); Dimension (graph theory); Outcome (game theory); Probabilistic logic; Focus (optics); Computer science; Epistemology; Psychology; Medicine; Political science; Artificial intelligence; Economics; Mathematics; Law","score_opus":0.8337389509473252,"score_gpt":0.7541194232979128,"score_spread":0.07961952764941238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463735421","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026657969,0.000028821136,0.96814704,0.0009834196,0.00240813,0.0011616374,0.00012336853,0.00004248669,0.00044710052],"genre_scores_gemma":[0.2725462,0.00012633686,0.72670186,0.00019781836,0.0002873598,0.00009335938,2.9899584e-7,0.000033778317,0.000013005449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9827325,0.0065632476,0.0073135253,0.0008744065,0.002026045,0.0004903182],"domain_scores_gemma":[0.09947795,0.89707834,0.0017753255,0.0008309261,0.00048904534,0.00034844494],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10251212,0.0002672101,0.002819442,0.00026359968,0.00006130564,0.000027093147,0.000769648,0.0007779209,0.0019498039],"category_scores_gemma":[0.9722494,0.00015157404,0.00078078976,0.0004794307,0.00053475663,0.00008209972,0.00039633366,0.0007626604,0.000017824612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007442065,0.00034572027,0.0033393197,0.000014217928,0.00005757794,0.000014866611,0.00002691746,1.673559e-7,0.000035547313,0.56010354,0.0009773131,0.43434063],"study_design_scores_gemma":[0.0034333253,0.0011178879,0.02069575,0.006726179,0.000070851806,0.0000022131924,0.000064742155,0.001482004,0.000045879166,0.96600586,0.00016631707,0.00018899766],"about_ca_topic_score_codex":0.0000012703431,"about_ca_topic_score_gemma":0.000013011111,"teacher_disagreement_score":0.8905151,"about_ca_system_score_codex":0.00018119384,"about_ca_system_score_gemma":0.00030985038,"threshold_uncertainty_score":0.9989625},"labels":[],"label_agreement":null},{"id":"W2470860284","doi":"10.1037/met0000036","title":"Planning sample sizes when effect sizes are uncertain: The power-calibrated effect size approach.","year":2015,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Sample size determination; Statistical power; Sample (material); Statistics; Replication (statistics); Computer science; Power (physics); Confidence interval; Econometrics; Mathematics","score_opus":0.6449695789679178,"score_gpt":0.6157682207415001,"score_spread":0.029201358226417784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470860284","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023378694,0.00035600952,0.94609797,0.001460722,0.0021277752,0.0042526913,0.00007790025,0.00094130076,0.02130696],"genre_scores_gemma":[0.020096174,0.0000046791115,0.97634995,0.0014940037,0.00058846385,0.0011992861,0.0000030480605,0.000106948566,0.00015743972],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96092165,0.03429405,0.0015082697,0.0013418744,0.0009009516,0.0010332108],"domain_scores_gemma":[0.5883963,0.4090869,0.00059579295,0.0012547178,0.0001465317,0.0005197146],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03699339,0.0008121863,0.0023127173,0.00007406262,0.00027891324,0.00023592275,0.0014571028,0.0008329925,0.0010221609],"category_scores_gemma":[0.62264806,0.00041885886,0.00057028054,0.00074094784,0.000851589,0.00011737971,0.0004246324,0.0015363006,0.000074093776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025730183,0.006119605,0.043043915,0.0018986379,0.002922186,0.00061781483,0.0049744095,0.00040777033,0.004628019,0.12923418,0.22464047,0.5557828],"study_design_scores_gemma":[0.0041719875,0.0032445826,0.0052533415,0.00016929177,0.00027163196,0.00004551326,0.00021963644,0.00068087305,0.0011659334,0.9807897,0.0032977865,0.0006897219],"about_ca_topic_score_codex":0.000018556677,"about_ca_topic_score_gemma":3.4278904e-7,"teacher_disagreement_score":0.8515555,"about_ca_system_score_codex":0.00009207883,"about_ca_system_score_gemma":0.00003153883,"threshold_uncertainty_score":0.99989104},"labels":[],"label_agreement":null},{"id":"W2475258578","doi":"10.1002/bimj.201500231","title":"A simple procedure to estimate the optimal sample size in case of conjunctive coprimary endpoints","year":2016,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"","keywords":"Sample size determination; Statistics; Type I and type II errors; Mathematics; Statistical power; Null hypothesis; Independence (probability theory); Sample (material); Flexibility (engineering); Binomial distribution; Econometrics","score_opus":0.3276058476212865,"score_gpt":0.5636369010409312,"score_spread":0.23603105341964475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475258578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45884743,0.000058946393,0.5363833,0.0026385079,0.00048378282,0.00081022916,0.00042521252,0.00003804575,0.00031456692],"genre_scores_gemma":[0.4010322,0.00001107485,0.59850276,0.0001956899,0.00018575203,0.00001681176,1.0782992e-7,0.000023491337,0.000032098353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99644965,0.0008186338,0.0013699529,0.0003121125,0.0005664568,0.00048319006],"domain_scores_gemma":[0.8057319,0.1927472,0.00046612773,0.00034158613,0.00031882987,0.00039436115],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051977583,0.00021152625,0.0007461955,0.0005250294,0.00010222767,0.000048572256,0.00042763536,0.00016282983,0.00076821377],"category_scores_gemma":[0.5446983,0.00010350067,0.00019445455,0.0024729439,0.00026094573,0.00008330558,0.00023420344,0.00039154224,0.000026804666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071628154,0.0047623436,0.027912967,0.00053839997,0.0009900093,0.008762064,0.0013541646,0.000034682213,0.026605092,0.06682283,0.048563115,0.8064915],"study_design_scores_gemma":[0.003908394,0.0013040095,0.014597095,0.0002472595,0.00012694973,0.0025572104,0.00016655368,0.00015058022,0.0053958823,0.9704586,0.00073223363,0.0003552321],"about_ca_topic_score_codex":0.000019025603,"about_ca_topic_score_gemma":0.000006544674,"teacher_disagreement_score":0.9036358,"about_ca_system_score_codex":0.00020263303,"about_ca_system_score_gemma":0.00017227702,"threshold_uncertainty_score":0.8411402},"labels":[],"label_agreement":null},{"id":"W2475271839","doi":"10.2310/8000.2014.141405","title":"Critically appraising noninferiority randomized controlled trials: a primer for emergency physicians","year":2015,"lang":"en","type":"review","venue":"Canadian Journal of Emergency Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; McGill University Health Centre","funders":"","keywords":"Medicine; Randomized controlled trial; Protocol (science); Intensive care medicine; Clinical trial; Assay sensitivity; Alternative medicine; Gold standard (test); Critically ill; Medical emergency; Surgery; Internal medicine; Pathology","score_opus":0.8134235510217568,"score_gpt":0.6595537318429862,"score_spread":0.15386981917877063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475271839","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.1547994e-7,0.8216644,0.12393488,0.0007990525,0.043768775,0.0065143676,0.00030592733,0.000018828288,0.0029932396],"genre_scores_gemma":[0.0000010811535,0.8846128,0.099194326,0.000059759925,0.014438664,0.00039528086,0.000014292744,0.00018710352,0.0010966839],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9635738,0.013987979,0.019666344,0.00058328436,0.0011506322,0.0010379219],"domain_scores_gemma":[0.72553074,0.24124809,0.019300807,0.0013321233,0.008839863,0.0037483948],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11696394,0.0011231047,0.04397156,0.0009510198,0.00020975403,0.000023206872,0.0011423543,0.0008463132,0.007197174],"category_scores_gemma":[0.8870208,0.0006593536,0.008826902,0.0007343073,0.0005771338,0.00011831551,0.000033854227,0.0014656857,0.000015443085],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012959769,0.00019949434,0.0000011485573,0.019597067,0.010850323,0.00012051818,0.0005461107,3.61934e-7,0.0000011195732,0.06137826,0.34006488,0.55428094],"study_design_scores_gemma":[0.07780146,0.00037971576,6.81483e-8,0.012786224,0.030812737,0.00001619028,0.000060831273,0.000014832266,9.642427e-8,0.32085592,0.5568391,0.00043282818],"about_ca_topic_score_codex":0.00036888133,"about_ca_topic_score_gemma":0.00053335226,"teacher_disagreement_score":0.7700569,"about_ca_system_score_codex":0.00037224314,"about_ca_system_score_gemma":0.0054855905,"threshold_uncertainty_score":0.99958575},"labels":[],"label_agreement":null},{"id":"W2505707497","doi":"10.14288/1.0135586","title":"Informing selective screening through more robust estimation of STI risk","year":2015,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Estimation; Computer science; Risk analysis (engineering); Medicine; Economics","score_opus":0.2556070586823056,"score_gpt":0.3873188887084527,"score_spread":0.13171183002614711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2505707497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48577145,0.000016850852,0.51213795,0.00002226842,0.00008506737,0.0002458759,0.00021541538,0.00005235952,0.0014527797],"genre_scores_gemma":[0.4561449,0.000012813407,0.543731,0.000007951598,0.000020247433,3.2874522e-7,0.0000029411785,0.000010356563,0.0000694933],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984045,0.00027445538,0.00038736087,0.0002725609,0.0004502457,0.00021089782],"domain_scores_gemma":[0.99405456,0.0043819607,0.0006217982,0.00028369372,0.0005297516,0.00012824974],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015087154,0.00005536496,0.0005551303,0.00003519335,0.00012545547,0.000033927332,0.00028416683,0.00016800534,0.00004882511],"category_scores_gemma":[0.02323981,0.00017242778,0.00013359866,0.0003793893,0.00039639065,0.0003953564,0.00016483507,0.00024078217,0.0000052871223],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008643958,0.00021152956,0.0065640328,0.00024656628,0.00018302652,0.000059092825,0.0015226512,0.0016072652,0.000011538828,0.00022017694,0.004561267,0.9847264],"study_design_scores_gemma":[0.0033190798,0.00033757964,0.51914746,0.00063559663,0.00037922387,0.000039315542,0.0049616797,0.020232573,0.000015793623,0.45055768,0.000034993136,0.00033904554],"about_ca_topic_score_codex":0.03873142,"about_ca_topic_score_gemma":0.010207286,"teacher_disagreement_score":0.98438734,"about_ca_system_score_codex":0.000074740434,"about_ca_system_score_gemma":0.000111636655,"threshold_uncertainty_score":0.98498785},"labels":[],"label_agreement":null},{"id":"W2507014214","doi":"","title":"Advanced Methods and Measures for Studying Complex Drug Utilization Patterns with Patient-Level Databases","year":2012,"lang":"en","type":"article","venue":"Data Archiving and Networked Services (DANS)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Medicine; Pharmacoepidemiology; Database; Drug; Medical emergency; Pharmacology; Computer science","score_opus":0.7289686360686757,"score_gpt":0.5647178292047377,"score_spread":0.164250806863938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507014214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15989368,0.00029954492,0.83589244,0.000035207657,0.00018555789,0.0006770771,0.0028684596,0.00007661767,0.00007142218],"genre_scores_gemma":[0.21279147,0.00018489998,0.7860231,0.00014742052,0.00021077682,0.000052491218,0.00053654396,0.000045414392,0.000007914493],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9968054,0.0012705816,0.0005966486,0.00057958456,0.00026680675,0.0004809721],"domain_scores_gemma":[0.9693724,0.0291477,0.0003155276,0.00088351255,0.00005967962,0.0002212057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037555967,0.00028316138,0.000573302,0.00005231745,0.0003273905,0.00007890397,0.00045258243,0.000038467555,0.000010752715],"category_scores_gemma":[0.002297259,0.000209162,0.000027429627,0.00012584911,0.00011678733,0.00042961026,0.000751326,0.00016915103,4.3813225e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007074646,0.00035712396,0.07374039,0.00209346,0.00032827197,0.000002228141,0.0066766175,0.00005405237,0.0006138118,0.004666178,0.0004668059,0.9102936],"study_design_scores_gemma":[0.010769616,0.0011017302,0.3723436,0.006856155,0.0033109467,0.00008505118,0.022339715,0.35825303,0.0016988494,0.19634162,0.023290504,0.0036091672],"about_ca_topic_score_codex":0.00008007844,"about_ca_topic_score_gemma":0.00041612523,"teacher_disagreement_score":0.90668446,"about_ca_system_score_codex":0.000010296029,"about_ca_system_score_gemma":0.000012398759,"threshold_uncertainty_score":0.8529379},"labels":[],"label_agreement":null},{"id":"W2510561985","doi":"10.1177/0962280216660127","title":"A two-stage model in a Bayesian framework to estimate a survival endpoint in the presence of confounding by indication","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut National Du Cancer","keywords":"Prostate-specific antigen; Prostate cancer; Medicine; Oncology; Biomarker; Prostate; Hormonal therapy; Clinical endpoint; Hormone therapy; Internal medicine; Randomized controlled trial; Cancer; Biology","score_opus":0.6285155508790987,"score_gpt":0.7340032660082315,"score_spread":0.1054877151291328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510561985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061325002,0.000025535946,0.9844503,0.005488424,0.00018008245,0.0015260645,0.0002699098,0.000022861776,0.0019043394],"genre_scores_gemma":[0.11863387,0.000048511465,0.88041776,0.00018219402,0.00006837233,0.0005386165,0.00000197535,0.000043151354,0.0000655421],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95115995,0.037366074,0.0032614553,0.0012366382,0.0051949346,0.0017809583],"domain_scores_gemma":[0.38697532,0.61080647,0.00023201463,0.0010412339,0.00023976096,0.0007052086],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13694763,0.00030257695,0.0012637693,0.00065530237,0.00007457783,0.000057021465,0.001742415,0.0005118166,0.0012962656],"category_scores_gemma":[0.8684334,0.00018532659,0.00007804556,0.0021799284,0.0016996918,0.00008889746,0.0006278428,0.0026666948,0.000022318809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005149454,0.0005212306,0.0011635892,0.00022247154,0.000011313074,0.00012938416,0.0009209224,0.00001303884,0.0009882941,0.8261719,0.00030779326,0.16903515],"study_design_scores_gemma":[0.0014491022,0.00024617914,0.0017429815,0.0012757757,0.000008512661,0.0000021473338,0.000369549,0.04510296,0.00043486478,0.94907385,0.00008467452,0.00020940616],"about_ca_topic_score_codex":0.00023536671,"about_ca_topic_score_gemma":0.0003062088,"teacher_disagreement_score":0.7314858,"about_ca_system_score_codex":0.00033853075,"about_ca_system_score_gemma":0.0006311197,"threshold_uncertainty_score":0.9996342},"labels":[],"label_agreement":null},{"id":"W2510746161","doi":"10.1111/bcp.13119","title":"Understanding and applying pharmacometric modelling and simulation in clinical practice and research","year":2016,"lang":"en","type":"review","venue":"British Journal of Clinical Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Medical Research Council","keywords":"Physiologically based pharmacokinetic modelling; Medicine; Computer science; Intensive care medicine; Medical physics; Pharmacology; Pharmacokinetics","score_opus":0.949349178115599,"score_gpt":0.7655469293470311,"score_spread":0.183802248768568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510746161","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029410553,0.8958416,0.099321395,0.00023522675,0.002593346,0.0014163808,0.00003845621,0.000016002587,0.00024350113],"genre_scores_gemma":[0.000508791,0.84796333,0.14830072,0.00018649844,0.0029176644,0.000025240673,4.5799672e-7,0.00007612017,0.000021186363],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96430594,0.023710128,0.009572122,0.00087715714,0.0008825556,0.0006520913],"domain_scores_gemma":[0.49511907,0.50038046,0.003238585,0.00014179817,0.00052289927,0.00059718825],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11248741,0.00039140106,0.0054944707,0.0009052949,0.00019707598,0.00018366874,0.0004164066,0.0012445749,0.00009696621],"category_scores_gemma":[0.31643194,0.00034347706,0.0005123468,0.0007936702,0.0013884628,0.00039136474,0.00055328093,0.006281874,0.00000430615],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003832513,0.00041754436,0.000051831288,0.0034641647,0.0005181812,0.001108126,0.000012720844,0.000020152385,1.0524104e-7,0.00091251754,0.0012674625,0.99184394],"study_design_scores_gemma":[0.010415064,0.0010447702,0.00003287185,0.024518605,0.0035750077,0.0031197423,0.000080331585,0.0055260747,1.6859987e-7,0.38527802,0.56572586,0.0006835022],"about_ca_topic_score_codex":0.000005596628,"about_ca_topic_score_gemma":0.00000105199,"teacher_disagreement_score":0.99116045,"about_ca_system_score_codex":0.0001811061,"about_ca_system_score_gemma":0.00047726865,"threshold_uncertainty_score":0.9999017},"labels":[],"label_agreement":null},{"id":"W2515516029","doi":"10.5539/ijsp.v5n5p16","title":"Considering Both Statistical and Clinical Significance","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Null hypothesis; Type I and type II errors; Statistical significance; Statistical power; Statistical hypothesis testing; Sample size determination; Statistics; Confidence interval; Null (SQL); Equivalence (formal languages); Mathematics; Clinical significance; Alternative hypothesis; Interpretation (philosophy); Interval estimation; Econometrics; Computer science; Data mining","score_opus":0.3992486955807552,"score_gpt":0.5445952669216005,"score_spread":0.14534657134084533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515516029","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047545135,0.00004546791,0.9487677,0.0013830735,0.0010626693,0.00016674049,0.000850027,0.000011236032,0.00016791098],"genre_scores_gemma":[0.2189096,0.00036548544,0.7802825,0.00010240436,0.00029923898,0.0000021395294,3.884514e-7,0.000011484185,0.000026737123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968415,0.000615112,0.0016329462,0.00026474652,0.000478287,0.0001674316],"domain_scores_gemma":[0.93079007,0.06755088,0.0006317843,0.00014126216,0.0006427137,0.00024328956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005057891,0.00014178567,0.0005311106,0.000049923645,0.000038557242,0.00006636225,0.00020687871,0.00009507979,0.0002605502],"category_scores_gemma":[0.113675214,0.00008943069,0.000060152728,0.000030288318,0.0008127265,0.00009980542,0.000121909514,0.00024861295,0.0000023898724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041934967,0.00020416197,0.03611026,0.000055408673,0.00022575518,0.00010422725,0.000036709676,1.7089914e-7,0.000113257505,0.6834994,0.0019745778,0.27725676],"study_design_scores_gemma":[0.0013420824,0.00032245775,0.031027954,0.00012019545,0.000074104995,0.000089421825,0.00001098986,0.0000761697,0.00004847609,0.9657541,0.0010170791,0.000116987],"about_ca_topic_score_codex":0.000006287048,"about_ca_topic_score_gemma":0.000008799048,"teacher_disagreement_score":0.2822547,"about_ca_system_score_codex":0.000054881395,"about_ca_system_score_gemma":0.0001333017,"threshold_uncertainty_score":0.89379066},"labels":[],"label_agreement":null},{"id":"W2519385594","doi":"10.1177/2168479016666586","title":"Current Practices in Choosing Estimands and Sensitivity Analyses in Clinical Trials: Results of the ICH E9 Survey","year":2016,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Clinical trial; Medicine; Family medicine; Pharmacy; Population; Addendum; Stakeholder; Quarter (Canadian coin); Internal medicine; Environmental health; Geography; Public relations; Political science","score_opus":0.9071316686951898,"score_gpt":0.707854031508543,"score_spread":0.19927763718664682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519385594","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820438,0.00007126871,0.015920157,0.0007345142,0.0006583774,0.00045489092,0.000028517778,0.000015585108,0.00007287784],"genre_scores_gemma":[0.9782272,0.00003029152,0.021559462,0.000089576984,0.00006638585,0.000005665228,3.2153386e-7,0.000008626434,0.000012443753],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9837758,0.011202511,0.0033148197,0.0006010427,0.00081160356,0.00029424066],"domain_scores_gemma":[0.7103079,0.2806535,0.006251453,0.0014227203,0.0012678005,0.00009660339],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19423887,0.00015198354,0.00078258984,0.00037205414,0.00009250178,0.000044765533,0.00027780456,0.000115689596,0.000006963238],"category_scores_gemma":[0.5567326,0.000081881466,0.000060069335,0.003611481,0.0018417662,0.00032995435,0.0001513,0.00031800213,0.0000010800596],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00124451,0.00049510156,0.27331936,0.00006194118,0.00003568629,0.0000020585303,0.00029238535,0.00000901252,0.05248619,0.071556725,0.000042375363,0.6004546],"study_design_scores_gemma":[0.0014952789,0.000055744527,0.79912245,0.00026958916,0.000023020993,0.0000016554553,0.000022179564,0.0011465256,0.004324534,0.1934151,0.000021415952,0.00010248438],"about_ca_topic_score_codex":0.000056486984,"about_ca_topic_score_gemma":0.00012000591,"teacher_disagreement_score":0.60035217,"about_ca_system_score_codex":0.000088679124,"about_ca_system_score_gemma":0.0004606137,"threshold_uncertainty_score":0.82970065},"labels":[],"label_agreement":null},{"id":"W2519427156","doi":"10.1177/2168479016665434","title":"DIA’s Adaptive Design Scientific Working Group (ADSWG): Best Practices Case Studies for “Less Well-understood” Adaptive Designs","year":2016,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"inVentiv Health Clinical","funders":"","keywords":"Toolbox; Clinical study design; Adaptive design; Computer science; Clinical trial; Research design; Risk analysis (engineering); Management science; Pharmacy; Data science; Medicine; Engineering; Family medicine","score_opus":0.8818243861039051,"score_gpt":0.5764153350103045,"score_spread":0.3054090510936006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519427156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059795506,0.00017643409,0.9348122,0.00073378615,0.001962058,0.0019836868,0.000018094765,0.00015427751,0.00036395405],"genre_scores_gemma":[0.55758286,0.0000069681373,0.44138095,0.00020180714,0.00017779361,0.0001733522,3.0821394e-7,0.000034982095,0.00044100892],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939957,0.0011953522,0.0014192635,0.0012925501,0.0012472919,0.00084979564],"domain_scores_gemma":[0.9315485,0.06229939,0.0024154736,0.0010727022,0.0025088333,0.00015512187],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.02460542,0.0004155001,0.0007048207,0.0006584271,0.0015722142,0.00030056428,0.0008111065,0.00018479778,0.000038330167],"category_scores_gemma":[0.040285494,0.00028891358,0.000106983105,0.0035437406,0.0053408532,0.0010539617,0.00019216668,0.00024569177,0.000036194895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005175451,0.00023872673,0.00003349963,0.000044627104,0.00017628065,0.000032454962,0.0012656407,0.000010940841,0.06349788,0.8205114,0.00039274446,0.113278285],"study_design_scores_gemma":[0.0013381287,0.0008209488,0.000092417766,0.00037276416,0.00021031944,0.000096038224,0.005574915,0.0012761219,0.018747238,0.9704552,0.00047977403,0.0005361161],"about_ca_topic_score_codex":0.0000054818206,"about_ca_topic_score_gemma":0.000019749492,"teacher_disagreement_score":0.49778733,"about_ca_system_score_codex":0.0005581075,"about_ca_system_score_gemma":0.0006585762,"threshold_uncertainty_score":0.9999563},"labels":[],"label_agreement":null},{"id":"W2519808874","doi":"10.1111/biom.12583","title":"Estimation of Diagnostic Accuracy of a Combination of Continuous Biomarkers Allowing for Conditional Dependence Between the Biomarkers and the Imperfect Reference-Test","year":2016,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Imperfect; Computer science; Statistics; Econometrics; Mathematics","score_opus":0.2859670164302872,"score_gpt":0.4834837546288036,"score_spread":0.1975167381985164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519808874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4274089,0.0002007027,0.5683406,0.0006701608,0.00016250504,0.0016640541,0.0014530302,0.00001854652,0.00008149409],"genre_scores_gemma":[0.88942105,0.000115806666,0.11034544,0.000009662331,0.000022987419,0.000056607263,0.000010895923,0.000012318249,0.000005222389],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974806,0.00055245217,0.0011196632,0.00020299945,0.00048372746,0.00016061524],"domain_scores_gemma":[0.4837425,0.5146769,0.000943234,0.0002573162,0.00034114663,0.00003884978],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0068810456,0.00013436584,0.00058147433,0.00035299986,0.000069583904,0.000015145233,0.0003176735,0.00013407439,0.000020274383],"category_scores_gemma":[0.6673185,0.00006642827,0.00013739042,0.0011632977,0.0008684734,0.0000882094,0.00009320863,0.00006193405,7.6650116e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082438294,0.00056080887,0.052093536,0.0012776284,0.0012510988,0.0000012081675,0.00023258333,0.000001436427,0.012623892,0.28313014,0.0012804628,0.6467228],"study_design_scores_gemma":[0.0062230504,0.00061437435,0.08627595,0.00035454953,0.00063004764,0.0000024332646,0.0000895992,0.0010301367,0.026464641,0.8781227,0.000029607294,0.0001629031],"about_ca_topic_score_codex":0.000028303153,"about_ca_topic_score_gemma":9.223644e-7,"teacher_disagreement_score":0.6604375,"about_ca_system_score_codex":0.000030440942,"about_ca_system_score_gemma":0.0000625281,"threshold_uncertainty_score":0.33548376},"labels":[],"label_agreement":null},{"id":"W2521539014","doi":"10.1002/cpt.515","title":"“Threshold‐crossing”: A Useful Way to Establish the Counterfactual in Clinical Trials?","year":2016,"lang":"en","type":"article","venue":"Clinical Pharmacology & Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"Medical Research Council","keywords":"Counterfactual thinking; Harm; Outcome (game theory); Randomized controlled trial; Clinical trial; Counterfactual conditional; Computer science; Randomized experiment; Actuarial science; Econometrics; Medicine; Psychology; Economics; Social psychology; Microeconomics","score_opus":0.8085835664795291,"score_gpt":0.6822660510648504,"score_spread":0.12631751541467873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521539014","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8205868,0.00025168815,0.070286825,0.07866784,0.024428708,0.004161401,0.0003075482,0.00039734377,0.000911824],"genre_scores_gemma":[0.60961515,0.0019712518,0.13115959,0.24285638,0.011727219,0.0005346018,0.0000029271416,0.00035410753,0.0017787725],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9680453,0.020090673,0.008499589,0.0014014607,0.00071528764,0.0012476692],"domain_scores_gemma":[0.53085774,0.46509704,0.0015114938,0.0014024241,0.00041289037,0.00071839645],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08901188,0.00063016993,0.0032292823,0.00016012757,0.0002923594,0.00020043463,0.0019172222,0.0011819336,0.0018950843],"category_scores_gemma":[0.12380791,0.0003325144,0.0011280818,0.0006175171,0.003427092,0.00016638968,0.0006428541,0.0022525592,0.0006349345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013456223,0.007684753,0.07028135,0.000097373464,0.0034132048,0.00025203227,0.0009215652,0.000008781391,0.004253296,0.008082651,0.35768867,0.53386015],"study_design_scores_gemma":[0.025698869,0.0031129532,0.04155818,0.0003540379,0.0030688618,0.000023943394,0.00017320906,0.00048805677,0.0020555756,0.5648133,0.3572365,0.0014164832],"about_ca_topic_score_codex":0.0000040891186,"about_ca_topic_score_gemma":0.000033149543,"teacher_disagreement_score":0.5567307,"about_ca_system_score_codex":0.00017227317,"about_ca_system_score_gemma":0.00043519607,"threshold_uncertainty_score":0.9999127},"labels":[],"label_agreement":null},{"id":"W2527117517","doi":"10.1002/sim.7137","title":"Choosing appropriate analysis methods for cluster randomised cross‐over trials with a binary outcome","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"National Institute for Health and Care Research; National Institute on Handicapped Research","keywords":"Statistics; Type I and type II errors; Cluster (spacecraft); Correlation; Cluster analysis; Outcome (game theory); Hierarchical clustering; Random effects model; Binary number; Cluster randomised controlled trial; Regression; Mathematics; Computer science; Meta-analysis; Medicine; Randomized controlled trial","score_opus":0.5289356418669582,"score_gpt":0.6556294378967649,"score_spread":0.12669379602980668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527117517","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019569558,0.00006226625,0.99244773,0.00095436355,0.00082617585,0.0026362673,0.0006977358,0.000070506685,0.00034800387],"genre_scores_gemma":[0.0045674164,0.000046004363,0.99297196,0.00045048483,0.00056609896,0.00043134313,0.000016212383,0.00008605609,0.0008644489],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883741,0.0054650605,0.0040710038,0.0007969505,0.0006546286,0.00063826557],"domain_scores_gemma":[0.6786235,0.3191183,0.0010845591,0.0006545623,0.0003113569,0.0002077444],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054562595,0.0004513198,0.004115792,0.0005333356,0.00010470161,0.000041726933,0.00039385143,0.00026056299,0.0013740971],"category_scores_gemma":[0.5677755,0.00022358735,0.00030910206,0.0008928839,0.0007849655,0.000076844,0.00009408881,0.00031733577,0.0000061962874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09122325,0.00092934584,0.02864546,0.0021631825,0.008640903,0.0001204094,0.0013895737,0.00010917315,0.0040406613,0.39027107,0.012788282,0.4596787],"study_design_scores_gemma":[0.08453471,0.00059839233,0.0029477132,0.00036439134,0.004276812,0.0000024387584,0.000038227085,0.0045860894,0.00016788811,0.9016105,0.00048048748,0.00039236815],"about_ca_topic_score_codex":0.000025968,"about_ca_topic_score_gemma":0.000024548941,"teacher_disagreement_score":0.5132129,"about_ca_system_score_codex":0.00015951849,"about_ca_system_score_gemma":0.00008564524,"threshold_uncertainty_score":0.9995388},"labels":[],"label_agreement":null},{"id":"W2528587226","doi":"10.1080/02664763.2016.1238054","title":"A likelihood-based approach for multivariate one-sided tests with missing data","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate statistics; Missing data; Multivariate analysis; Anesthesiology; Statistics; Medicine; Library science; Computer science; Mathematics","score_opus":0.5821130806050215,"score_gpt":0.5298083091860011,"score_spread":0.05230477141902046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528587226","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020521333,0.000008981115,0.9957931,0.00032063198,0.0001759015,0.000699827,0.0021767844,0.00003303496,0.00058651174],"genre_scores_gemma":[0.017100872,0.00000637465,0.9820429,0.0001873961,0.0005070269,0.000021649235,0.00001536239,0.00008996609,0.000028425853],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641573,0.00022728303,0.0016948575,0.00042633832,0.00076515385,0.0004706337],"domain_scores_gemma":[0.9130518,0.083538264,0.0016705178,0.00084052235,0.0005782749,0.00032065008],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0048781456,0.0002968408,0.0010818343,0.000123056,0.00011055925,0.00008031427,0.0008142213,0.00016666386,0.00006239256],"category_scores_gemma":[0.07227664,0.00017485945,0.00008032642,0.00016824035,0.00023429068,0.000100520134,0.00011306145,0.0003229693,0.0000042613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011329493,0.003234556,0.00014287097,0.0014803137,0.0013458354,0.00010278807,0.00024510568,0.00011776863,0.021131467,0.46126267,0.032897204,0.46670994],"study_design_scores_gemma":[0.008390291,0.0006699043,0.0001471917,0.00045400957,0.0007643743,0.000016520835,0.00004571081,0.0074202907,0.0022175615,0.9789718,0.0005422816,0.00036005714],"about_ca_topic_score_codex":0.0000017189519,"about_ca_topic_score_gemma":0.0000022777267,"teacher_disagreement_score":0.51770914,"about_ca_system_score_codex":0.00009550479,"about_ca_system_score_gemma":0.00047139195,"threshold_uncertainty_score":0.935538},"labels":[],"label_agreement":null},{"id":"W2530757763","doi":"10.5489/cuaj.4163","title":"Is it time to end lone-wolf medicine?","year":2016,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; University of Toronto","funders":"","keywords":"Dead end; Psychology; Social psychology","score_opus":0.34481615177333064,"score_gpt":0.4776553675382122,"score_spread":0.13283921576488156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530757763","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014023369,0.00003153887,0.03343258,0.90923667,0.0014790745,0.0004651156,0.000356894,0.00007923532,0.04089555],"genre_scores_gemma":[0.31852508,0.00011972586,0.3507996,0.22570486,0.011405305,0.00006446348,0.0000037353545,0.00014947675,0.09322775],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963199,0.0010339505,0.0009623366,0.00030329896,0.00067895406,0.00070156937],"domain_scores_gemma":[0.9670135,0.030337999,0.00044677808,0.0002184259,0.00038437013,0.0015989761],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0063251,0.00018729395,0.0005805097,0.0001739078,0.00020907387,0.00005857149,0.0003912061,0.00039540755,0.07927223],"category_scores_gemma":[0.23868835,0.00010983689,0.00015597718,0.0002539113,0.00008929677,0.000073086965,0.000037511913,0.00045162946,0.0042276834],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033724977,0.000026838474,0.0072338157,0.0000026023904,0.000098655444,0.00005151831,0.0001143907,2.8929497e-7,0.00022169543,0.00822859,0.9620348,0.021953054],"study_design_scores_gemma":[0.0008795033,0.0003489849,0.014764149,0.0000484013,0.00007120256,0.0000345973,0.00001462839,0.0000103219,0.000036080917,0.6917079,0.29188165,0.00020256035],"about_ca_topic_score_codex":0.000123291,"about_ca_topic_score_gemma":0.00012917878,"teacher_disagreement_score":0.68353176,"about_ca_system_score_codex":0.0009956063,"about_ca_system_score_gemma":0.00025916798,"threshold_uncertainty_score":0.99654764},"labels":[],"label_agreement":null},{"id":"W2531230258","doi":"10.1002/sim.7148","title":"Understanding the effects of conditional dependence in research studies involving imperfect diagnostic tests","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Econometrics; Covariance; Statistics; Mathematics; Conditional variance; Autoregressive conditional heteroskedasticity","score_opus":0.8096974943345971,"score_gpt":0.6540817036197748,"score_spread":0.15561579071482234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2531230258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028084295,0.0014916807,0.96477777,0.002155628,0.0012819922,0.0015534216,0.00019057644,0.000029097046,0.00043553085],"genre_scores_gemma":[0.8668494,0.0017504347,0.13098621,0.000073478106,0.0001628103,0.00011079842,0.0000013371008,0.000024002366,0.000041501877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99422586,0.002738546,0.0011331027,0.00034282668,0.001102967,0.0004567101],"domain_scores_gemma":[0.43293917,0.5663451,0.0001677442,0.0002727597,0.00021680871,0.000058445603],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015056978,0.00017014674,0.0007528466,0.00029051487,0.00009253649,0.00000666086,0.0003442947,0.00009951,0.00012035758],"category_scores_gemma":[0.85910296,0.00008774078,0.000025417647,0.0005985211,0.0022525925,0.000045331828,0.0001797686,0.00054105785,0.0000068467198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005768141,0.00010396706,0.016934957,0.0009880018,0.00005921549,0.00023946009,0.0012544461,0.000001567761,0.0015977304,0.97002447,0.0059924643,0.0027460414],"study_design_scores_gemma":[0.0019515157,0.00050487387,0.015270624,0.004624893,0.00004274158,0.0000043062605,0.001169251,0.00007852559,0.000335363,0.97591096,0.0000050649464,0.00010186823],"about_ca_topic_score_codex":0.0000474845,"about_ca_topic_score_gemma":0.00048080756,"teacher_disagreement_score":0.844046,"about_ca_system_score_codex":0.00043242762,"about_ca_system_score_gemma":0.00010801817,"threshold_uncertainty_score":0.8299771},"labels":[],"label_agreement":null},{"id":"W2533485695","doi":"10.1016/j.jclinepi.2016.08.007","title":"Odds ratios deconstructed: A new way to understand and explain odds ratios as conditional risk ratios","year":2016,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Odds; Odds ratio; Diagnostic odds ratio; Medicine; Statistics; Mathematics; Confidence interval; Logistic regression","score_opus":0.7361257878273237,"score_gpt":0.6429549873686936,"score_spread":0.09317080045863013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2533485695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1219192,0.00009651453,0.85139626,0.023617767,0.0018559616,0.00048676942,0.0001220238,0.00003089048,0.00047463417],"genre_scores_gemma":[0.1660327,0.00085071794,0.8223008,0.0067414287,0.0034861015,0.000010322718,0.0000018488884,0.000049274448,0.0005268473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9707547,0.017088497,0.010304572,0.0006841618,0.00053204765,0.00063606055],"domain_scores_gemma":[0.41521403,0.57711643,0.005193816,0.0005188624,0.00052392005,0.0014329503],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053489726,0.0003969704,0.004165511,0.00020597062,0.00016073108,0.00003413835,0.0004857285,0.0008364478,0.0023345768],"category_scores_gemma":[0.8640758,0.00024474453,0.0007387592,0.0001961602,0.0009778223,0.00025548445,0.00016708956,0.0012287749,0.00013729322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022444755,0.000265241,0.032543007,0.000044613542,0.0006910085,0.00007784712,0.00014124493,0.000018214127,0.00017760387,0.7853825,0.08115572,0.097258516],"study_design_scores_gemma":[0.005682642,0.0022111053,0.0177256,0.00023202352,0.00029098394,0.0002773562,0.000134333,0.00012842556,0.00010303943,0.9704912,0.0024244173,0.0002989202],"about_ca_topic_score_codex":0.000013086306,"about_ca_topic_score_gemma":0.00004043934,"teacher_disagreement_score":0.81058604,"about_ca_system_score_codex":0.00010592785,"about_ca_system_score_gemma":0.00070427585,"threshold_uncertainty_score":0.9985774},"labels":[],"label_agreement":null},{"id":"W2536899752","doi":"10.2196/medinform.6437","title":"Population Analysis of Adverse Events in Different Age Groups Using Big Clinical Trials Data","year":2016,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Adverse effect; Clinical trial; Medicine; Population; Adverse drug event; Intensive care medicine; Internal medicine; Environmental health","score_opus":0.8073965431513741,"score_gpt":0.6622115404118676,"score_spread":0.14518500273950652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2536899752","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69411904,0.0000033831118,0.30391884,0.00011375709,0.0007151004,0.0006866602,0.00031720664,0.00004065533,0.00008534229],"genre_scores_gemma":[0.6909282,0.00007621967,0.30806968,0.00022253358,0.0005306868,0.000028038725,0.00009068051,0.000028834871,0.000025125459],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98448396,0.0039569214,0.00906777,0.0003119477,0.0017660466,0.0004133435],"domain_scores_gemma":[0.8906233,0.10479874,0.002456629,0.0015670309,0.00010014451,0.00045420774],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03532219,0.00027878545,0.0031173178,0.00049232395,0.00003296097,0.0000053291665,0.0010337317,0.0006179961,0.00064624246],"category_scores_gemma":[0.3395251,0.00015396187,0.00054267416,0.0009167242,0.00026935883,0.00024719743,0.0007151721,0.0004483771,0.000013306259],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012048486,0.0040092138,0.4499558,0.0014330678,0.005238112,0.00006146677,0.0013772884,0.000019554765,0.00007266809,0.038527668,0.0012151138,0.4968852],"study_design_scores_gemma":[0.0121524185,0.00033064213,0.35028875,0.00235811,0.0051129777,0.000004879732,0.0005179887,0.15641813,0.00004219811,0.4717814,0.00018010606,0.00081237365],"about_ca_topic_score_codex":0.000026081845,"about_ca_topic_score_gemma":0.00007529687,"teacher_disagreement_score":0.49607286,"about_ca_system_score_codex":0.00010704639,"about_ca_system_score_gemma":0.0001071699,"threshold_uncertainty_score":0.9933388},"labels":[],"label_agreement":null},{"id":"W2547489879","doi":"","title":"A method for IPD meta-analysis of treatment-covariate interaction with a continuous predictor in randomised trials","year":2014,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Biostatistics; Epidemiology; Medicine; Covariate; Clinical trial; Clinical epidemiology; Health informatics; Public health; Statistics; Pathology; Mathematics","score_opus":0.7464045979269598,"score_gpt":0.6130974183423201,"score_spread":0.13330717958463967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547489879","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00168911,0.000012533497,0.9934107,0.00017282729,0.000103061364,0.002894472,0.00022473,0.000048126403,0.001444438],"genre_scores_gemma":[0.023248065,0.0000041694857,0.9747804,0.00007980808,0.00007631555,0.0011683825,0.000006970873,0.00002914884,0.00060677144],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.98894024,0.0074516865,0.0026703908,0.00045985804,0.00024201353,0.00023581911],"domain_scores_gemma":[0.67863584,0.31937304,0.0012377811,0.00047973805,0.0001935863,0.00008002973],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027624287,0.0002728893,0.006808365,0.00036908497,0.000022651164,0.000030053841,0.00014913018,0.00015262168,0.0012529993],"category_scores_gemma":[0.18476103,0.00014356652,0.0022575601,0.0005547224,0.000050678256,0.00005756417,0.00001923675,0.000089853,0.0000018331626],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06531047,0.0018127706,0.00012367769,0.00022863095,0.65894353,0.0000031422114,0.0008039446,0.0005496421,0.0018816176,0.24206947,0.00035763258,0.027915489],"study_design_scores_gemma":[0.048800558,0.0016236602,0.000029706647,0.000012058389,0.51323605,8.23782e-7,0.00008798406,0.03929987,0.004327006,0.392096,0.0002821141,0.0002041895],"about_ca_topic_score_codex":0.00017545583,"about_ca_topic_score_gemma":0.00020432037,"teacher_disagreement_score":0.31192136,"about_ca_system_score_codex":0.00006958166,"about_ca_system_score_gemma":0.000049679285,"threshold_uncertainty_score":0.99966},"labels":[],"label_agreement":null},{"id":"W2549196472","doi":"10.1002/ajmg.c.31533","title":"Alternative designs for clinical trials in rare diseases","year":2016,"lang":"en","type":"review","venue":"American Journal of Medical Genetics Part C Seminars in Medical Genetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Clinical study design; Randomized controlled trial; Clinical trial; Computer science; Research design; Narrative review; Medicine; Adaptive design; Medical physics; Management science; Risk analysis (engineering); Intensive care medicine; Engineering; Surgery; Pathology; Mathematics","score_opus":0.7319805827812529,"score_gpt":0.681855876041094,"score_spread":0.0501247067401589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549196472","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010922745,0.8751572,0.11557458,0.0010218546,0.005275685,0.0022300577,0.0005631116,0.000023959732,0.000044323715],"genre_scores_gemma":[0.000010472068,0.79865,0.19469257,0.00060929725,0.0055309436,0.0002277648,0.000012187296,0.00022402099,0.000042698433],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92545694,0.03899796,0.024287427,0.0015576758,0.007949584,0.0017504337],"domain_scores_gemma":[0.4112803,0.56897086,0.01289473,0.0015424407,0.00076409645,0.0045475834],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.12615609,0.0013153934,0.018121148,0.0009360448,0.00007068165,0.000077604556,0.004672148,0.002451951,0.0015120977],"category_scores_gemma":[0.74444014,0.00086617563,0.0037330077,0.0012370633,0.0039748484,0.000046493264,0.00080265035,0.004388424,0.000025843552],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032978132,0.0012236033,0.00024099779,0.0027397943,0.0007370273,0.0013156403,0.00006537983,0.0000013099541,6.490726e-8,0.00064000464,0.013891863,0.97881454],"study_design_scores_gemma":[0.005515638,0.0036397032,0.00001700891,0.105337866,0.0026408774,0.00037502687,0.00013276316,0.00032398672,0.0000027409617,0.13337833,0.7475242,0.0011118858],"about_ca_topic_score_codex":0.0000038730323,"about_ca_topic_score_gemma":0.000010416654,"teacher_disagreement_score":0.9777027,"about_ca_system_score_codex":0.00041508884,"about_ca_system_score_gemma":0.006206027,"threshold_uncertainty_score":0.99995977},"labels":[],"label_agreement":null},{"id":"W2550638838","doi":"10.1146/annurev-statistics-060116-054139","title":"<i>p</i>-Values: The Insight to Modern Statistical Inference","year":2016,"lang":"en","type":"article","venue":"Annual Review of Statistics and Its Application","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalar (mathematics); Mathematics; Inference; Applied mathematics; Statistical inference; Range (aeronautics); Exponential function; Statistical model; Computer science; Statistics; Mathematical analysis; Artificial intelligence","score_opus":0.22918720550015687,"score_gpt":0.5231912735818536,"score_spread":0.2940040680816967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550638838","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015734356,0.0022901376,0.98939073,0.0020765888,0.00006401271,0.001175878,0.004212929,0.000022041622,0.0006103261],"genre_scores_gemma":[0.054376107,0.05339734,0.88845336,0.0028949333,0.00017267466,0.0004139457,0.00001570951,0.00004661744,0.00022933498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976581,0.00035065576,0.0010008354,0.0003528931,0.0004273417,0.00021018996],"domain_scores_gemma":[0.9680354,0.030400332,0.0003532726,0.00046217823,0.0005777113,0.00017107943],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020413972,0.00017700311,0.0005627934,0.000028330978,0.00007345162,0.000012640957,0.00028133826,0.00006432318,0.00011893906],"category_scores_gemma":[0.06277407,0.00009100314,0.000036529455,0.00017878959,0.00017368214,0.000059604816,0.00014010463,0.0001067085,0.000061016424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001277143,0.000039008926,0.0000074350933,0.0011201401,0.0000128729735,3.9894005e-7,0.000090799695,4.7054318e-8,0.0002592658,0.64366364,0.0062845233,0.3485091],"study_design_scores_gemma":[0.00021935532,0.00017455428,0.0003964968,0.0018254566,0.000121324156,0.0000018085948,0.000014587035,0.00022657857,0.00026422364,0.9762824,0.020309612,0.00016360343],"about_ca_topic_score_codex":0.000005078987,"about_ca_topic_score_gemma":0.0000021595342,"teacher_disagreement_score":0.3483455,"about_ca_system_score_codex":0.000019306179,"about_ca_system_score_gemma":0.000053635136,"threshold_uncertainty_score":0.9451206},"labels":[],"label_agreement":null},{"id":"W2551343228","doi":"10.1186/s12874-016-0251-y","title":"Autoregressive transitional ordinal model to test for treatment effect in neurological trials with complex endpoints","year":2016,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; International Collaboration On Repair Discoveries; Vancouver Coastal Health","funders":"International Foundation for Research in Paraplegia","keywords":"Statistical power; Clinical trial; Computer science; Statistical model; Autoregressive model; Statistical hypothesis testing; Econometrics; Statistics; Medicine; Data mining; Artificial intelligence; Mathematics","score_opus":0.9662030711366986,"score_gpt":0.7484280647731535,"score_spread":0.21777500636354508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551343228","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043053284,0.000013903906,0.94321865,0.009650578,0.00016268293,0.0032751495,0.00034060926,0.00006549735,0.0002196627],"genre_scores_gemma":[0.025450949,0.000029004199,0.9705542,0.00045765968,0.00056894345,0.0026549841,0.0000048727256,0.00005212547,0.00022729515],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9233817,0.07028244,0.001825442,0.0011593613,0.002011755,0.0013393053],"domain_scores_gemma":[0.12283748,0.8749487,0.0002142223,0.0005492078,0.00038147334,0.001068959],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14105572,0.00038615448,0.00299701,0.00040660118,0.00013482242,0.000023574927,0.00069224404,0.00063032814,0.002093849],"category_scores_gemma":[0.9352511,0.00017412602,0.00036087024,0.00037320034,0.001113224,0.000041630516,0.00018243569,0.00050560135,0.000048129496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08363462,0.004307845,0.0057154032,0.00074508536,0.00037072788,0.0008572266,0.00040713666,0.00009493718,0.0127278855,0.28947887,0.008981752,0.59267855],"study_design_scores_gemma":[0.014532013,0.016349116,0.0021644824,0.00036367515,0.00009676308,0.000047931127,0.000017453882,0.010794269,0.002374869,0.95259,0.0003889231,0.00028052964],"about_ca_topic_score_codex":0.000019885685,"about_ca_topic_score_gemma":0.00028793194,"teacher_disagreement_score":0.8046662,"about_ca_system_score_codex":0.00019105767,"about_ca_system_score_gemma":0.0012379191,"threshold_uncertainty_score":0.9988184},"labels":[],"label_agreement":null},{"id":"W2555459351","doi":"10.12688/f1000research.8680.1","title":"Three general concepts to improve risk prediction: good data, wisdom of the crowd, recalibration","year":2016,"lang":"en","type":"preprint","venue":"F1000Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics","funders":"Deutsche Forschungsgemeinschaft; European Commission","keywords":"Interim; Prostate cancer; Automatic summarization; Clinical trial; Computer science; Data collection; Medicine; Data science; Medical physics; Artificial intelligence; Cancer; Statistics; Internal medicine","score_opus":0.6250446288852266,"score_gpt":0.6063474123778936,"score_spread":0.018697216507333025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555459351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011450145,0.00010683095,0.9377361,0.0042073573,0.0055452078,0.0055446783,0.02987337,0.00017534744,0.005360995],"genre_scores_gemma":[0.010680591,0.00014518043,0.97969246,0.000116776486,0.005291607,0.00057528354,0.00007361814,0.00017258486,0.0032518823],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99131733,0.0031617903,0.0017307643,0.0012542688,0.0019473505,0.00058851694],"domain_scores_gemma":[0.9547692,0.03807527,0.00076838303,0.0054109264,0.0006600208,0.0003162011],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011997165,0.00035452785,0.0009447253,0.00012222835,0.0001804438,0.00012546298,0.0036068948,0.0007122001,0.0010708465],"category_scores_gemma":[0.16839288,0.00021752133,0.00025782918,0.0003259726,0.0007673823,0.000115222414,0.008862173,0.0017503077,0.0000954077],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015315405,0.00084546703,0.01351746,0.002102694,0.0012964576,0.000016258668,0.0004963965,0.000104653765,0.0073335064,0.29816604,0.48509833,0.18949118],"study_design_scores_gemma":[0.0008537363,0.00021408267,0.004238454,0.00047231183,0.00015437948,0.0000011204565,0.000013752272,0.0049281335,0.0056127887,0.98013276,0.0031406076,0.00023787317],"about_ca_topic_score_codex":0.00018997835,"about_ca_topic_score_gemma":0.00009535992,"teacher_disagreement_score":0.6819667,"about_ca_system_score_codex":0.00014428797,"about_ca_system_score_gemma":0.0007365215,"threshold_uncertainty_score":0.9998423},"labels":[],"label_agreement":null},{"id":"W2559407777","doi":"10.1007/s10985-016-9386-8","title":"Two-phase outcome-dependent studies for failure times and testing for effects of expensive covariates","year":2016,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Sample size determination; Outcome (game theory); Econometrics; Cohort; Measure (data warehouse); Computer science; Mathematics; Data mining","score_opus":0.5370032129490003,"score_gpt":0.5969984575793092,"score_spread":0.05999524463030892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559407777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050501623,0.00027969098,0.98601985,0.0007280516,0.00015892062,0.0012577455,0.0064341216,0.000057436257,0.000014024203],"genre_scores_gemma":[0.030146422,0.000019461731,0.96911263,0.00007155047,0.00017383376,0.00015557751,0.000058491198,0.000030804666,0.00023123244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972571,0.00037956945,0.0011639474,0.00066144305,0.0002578019,0.00028009687],"domain_scores_gemma":[0.7615313,0.23645453,0.00056184945,0.0009603233,0.00039951366,0.00009247342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002883451,0.00023524452,0.0016088303,0.00016513193,0.00009605874,0.000030185167,0.00045850783,0.00008037432,0.000044344284],"category_scores_gemma":[0.44139057,0.00014600235,0.00021420188,0.00032976034,0.00019772841,0.00012532024,0.0004699544,0.000058132744,0.000004235902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004725812,0.004754423,0.04586934,0.01878363,0.15242864,0.000116746385,0.0019318524,0.000042246465,0.08747564,0.29722497,0.11081719,0.2758295],"study_design_scores_gemma":[0.012623635,0.0010094185,0.0002215488,0.00042467928,0.030345527,0.0000024886492,0.0004855383,0.0061732405,0.017166529,0.9306987,0.00025561173,0.0005930678],"about_ca_topic_score_codex":0.000014153772,"about_ca_topic_score_gemma":0.000019437985,"teacher_disagreement_score":0.63347375,"about_ca_system_score_codex":0.000020548077,"about_ca_system_score_gemma":0.000023351733,"threshold_uncertainty_score":0.59538025},"labels":[],"label_agreement":null},{"id":"W2561882864","doi":"10.5539/ijsp.v6n1p142","title":"Statistical Monitoring of Clinical Trials Using Brownian Bridges","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Brownian bridge; Interim; Sample size determination; Computer science; Interim analysis; Bridge (graph theory); Brownian motion; Mathematics; Statistics; Randomized controlled trial; Medicine; Surgery","score_opus":0.7551291555293425,"score_gpt":0.6488733003722469,"score_spread":0.10625585515709557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561882864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21050669,0.00003859871,0.7850962,0.00033471157,0.0023000801,0.00016887492,0.0015069665,0.000006257173,0.000041603846],"genre_scores_gemma":[0.31859905,0.00017605166,0.680423,0.0000126002615,0.0007649083,0.0000012234593,4.2450668e-7,0.000012239531,0.000010451639],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9907216,0.0028688207,0.005042651,0.00026012765,0.0009185491,0.00018824608],"domain_scores_gemma":[0.85370123,0.14151898,0.0026590019,0.00020103766,0.0016770669,0.00024269655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0281489,0.00016819825,0.0014005087,0.00009551532,0.000031649033,0.000043658274,0.0003666956,0.00014629001,0.00025952316],"category_scores_gemma":[0.43105334,0.00010258223,0.00021771129,0.000052821484,0.0005717788,0.000118004566,0.0001223581,0.00028040193,0.000001370667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014132262,0.0005279492,0.18477458,0.00014719857,0.0006070166,0.000069030684,0.00006386105,0.0000033090787,0.00096454186,0.34533215,0.0005712534,0.4655259],"study_design_scores_gemma":[0.0018683745,0.00033178268,0.064359844,0.00035954118,0.00018808425,0.000045643937,0.000020947815,0.00015925372,0.0007613349,0.9315994,0.00018757279,0.00011822719],"about_ca_topic_score_codex":0.000015452337,"about_ca_topic_score_gemma":0.0000018316805,"teacher_disagreement_score":0.58626723,"about_ca_system_score_codex":0.000077248595,"about_ca_system_score_gemma":0.0002499946,"threshold_uncertainty_score":0.9755903},"labels":[],"label_agreement":null},{"id":"W2563085254","doi":"10.1345/aph.1e017","title":"Book Review: Design and Analysis of Clinical Trials: Concepts and Methodologies, 2nd Edition","year":2004,"lang":"en","type":"article","venue":"Annals of Pharmacotherapy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"","keywords":"Medicine; Medical physics; Clinical trial; Intensive care medicine; Internal medicine","score_opus":0.9295336380232716,"score_gpt":0.763468060645814,"score_spread":0.16606557737745764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563085254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016329527,0.18060678,0.8118362,0.004021798,0.00034050125,0.0012474847,0.00020453102,0.00004157157,0.00006821559],"genre_scores_gemma":[0.0002286602,0.36939293,0.6189796,0.011146136,0.00017227129,0.000026501277,0.0000022604356,0.00001713703,0.000034520566],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.984097,0.011718642,0.0032456128,0.00039474032,0.00034046316,0.00020353605],"domain_scores_gemma":[0.83261657,0.16472326,0.001857789,0.0003218434,0.0003107074,0.0001698114],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059855707,0.0002054312,0.0031540347,0.00015603402,0.00003135465,0.00000977819,0.00018023269,0.00017865564,0.0012520471],"category_scores_gemma":[0.13916261,0.00015558592,0.0005456097,0.0004317944,0.0005603718,0.00009910339,0.00003893477,0.00022884717,7.945623e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003253924,0.00095614017,0.00021329857,0.0022135035,0.012642538,0.000013372146,0.00033949365,0.00006730684,0.025971765,0.017064778,0.40676206,0.53050184],"study_design_scores_gemma":[0.0058455574,0.0010798188,0.000537851,0.00095780916,0.0060351756,0.00000227295,0.000024303505,0.00039806394,0.17857796,0.7828473,0.023335507,0.00035841853],"about_ca_topic_score_codex":0.000008635469,"about_ca_topic_score_gemma":2.6202696e-7,"teacher_disagreement_score":0.7657825,"about_ca_system_score_codex":0.0000048800343,"about_ca_system_score_gemma":0.0000659453,"threshold_uncertainty_score":0.99966097},"labels":[],"label_agreement":null},{"id":"W2563343870","doi":"10.1111/bcp.13225","title":"Modelling the dose–response relationship: the fair share of pharmacokinetic and pharmacodynamic information","year":2016,"lang":"en","type":"article","venue":"British Journal of Clinical Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; inVentiv Health Clinical","funders":"","keywords":"Pharmacokinetics; Pharmacodynamics; Drug; Pharmacology; Chemistry; Mathematics; Medicine","score_opus":0.43787091721917804,"score_gpt":0.5661294216487494,"score_spread":0.12825850442957132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563343870","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80859077,0.0006154986,0.17724416,0.008885811,0.0034114637,0.00073578744,0.0001995187,0.000028898903,0.00028812137],"genre_scores_gemma":[0.9650594,0.0022278277,0.030353786,0.0012013242,0.0010084445,0.000018138679,5.0277555e-7,0.00002490622,0.00010565489],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9888558,0.0061710416,0.003965143,0.00018596026,0.00051864947,0.00030342492],"domain_scores_gemma":[0.817085,0.17970513,0.0022392618,0.00017532686,0.0005987073,0.00019656819],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02062004,0.00018122507,0.0008617307,0.000091223614,0.00018696548,0.00004457585,0.0007100503,0.00020640132,0.00068860094],"category_scores_gemma":[0.07369663,0.00010022842,0.00038179828,0.00022035735,0.000995285,0.00041141015,0.00018255449,0.001142853,0.00001469052],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021241453,0.001430813,0.0030548002,0.00040769766,0.0016230816,0.0002944283,0.00058977766,0.003311584,0.0036018754,0.014603577,0.097452104,0.8523888],"study_design_scores_gemma":[0.03393423,0.0020043072,0.022318626,0.0012206893,0.0030714227,0.0025775125,0.0002485329,0.05785665,0.001480388,0.8366842,0.037881646,0.0007217612],"about_ca_topic_score_codex":0.0000058903843,"about_ca_topic_score_gemma":8.3014504e-7,"teacher_disagreement_score":0.85166705,"about_ca_system_score_codex":0.000033794044,"about_ca_system_score_gemma":0.00020055217,"threshold_uncertainty_score":0.934106},"labels":[],"label_agreement":null},{"id":"W2563861885","doi":"10.3768/rtipress.2009.mr.0009.0903","title":"A mixed model approach for intent-to-treat analysis in longitudinal clinical trials with missing values","year":2009,"lang":"en","type":"report","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":297,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Missing data; Imputation (statistics); Post hoc; Clinical trial; Confusion; Population; Longitudinal data; Mixed model; Protocol (science); Medicine; Statistics; Computer science; Data mining; Psychology; Mathematics; Alternative medicine","score_opus":0.9271468758360674,"score_gpt":0.6894751672155476,"score_spread":0.23767170862051978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563861885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038179028,0.000095768235,0.9723491,0.000264856,0.00039514192,0.0041113594,0.00039644024,0.00016659238,0.021838939],"genre_scores_gemma":[0.001380383,0.00017583481,0.9895896,0.00015918039,0.0011350459,0.00044538864,0.000093910865,0.00015533209,0.0068653817],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97902745,0.005951077,0.009720458,0.0023511876,0.001993512,0.00095632777],"domain_scores_gemma":[0.7893006,0.20366144,0.0030241262,0.0018031893,0.0015026662,0.00070798525],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10782237,0.0010094643,0.0114279725,0.0011428983,0.00009904133,0.00020772149,0.0007852017,0.0016257683,0.00013788232],"category_scores_gemma":[0.6193176,0.0006580187,0.0030567513,0.0015187428,0.00025910852,0.00007034794,0.00019715502,0.001282114,0.000005354772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018603561,0.01363315,0.01263885,0.007618111,0.028938038,0.00029087876,0.00031084567,0.010222468,0.000019931083,0.03759201,0.18514872,0.68498343],"study_design_scores_gemma":[0.0049145934,0.001268602,0.0008926746,0.00092788984,0.032055512,0.00001935204,0.00010597804,0.17382625,0.000052123938,0.78425646,0.00017298793,0.0015075923],"about_ca_topic_score_codex":0.00009012686,"about_ca_topic_score_gemma":0.00007820493,"teacher_disagreement_score":0.7466644,"about_ca_system_score_codex":0.00047018047,"about_ca_system_score_gemma":0.0014164073,"threshold_uncertainty_score":0.9996703},"labels":[],"label_agreement":null},{"id":"W2564423956","doi":"10.6339/jds.201407_12(3).0001","title":"Factorial ANOVA with unbalanced data: A fresh look at the types of sums of squares","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Confusion; Factorial; Factorial analysis; Analysis of variance; Statistics; Type (biology); Econometrics; Mathematics; Factorial experiment; Explained sum of squares; Lack-of-fit sum of squares; Generalized least squares; Computer science; Arithmetic; Psychology; Non-linear least squares","score_opus":0.7074570963113356,"score_gpt":0.5968141994031163,"score_spread":0.11064289690821927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564423956","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55755675,0.0008891036,0.4217253,0.0019054568,0.0059185424,0.0005733939,0.009597329,0.000018548455,0.0018155571],"genre_scores_gemma":[0.20522629,0.0000989788,0.79411256,0.000044310444,0.00045632612,3.2227874e-7,0.00000754377,0.000009523447,0.00004416821],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970808,0.00030091076,0.0009388548,0.0002832031,0.0012210042,0.00017520972],"domain_scores_gemma":[0.9769497,0.018956238,0.001209696,0.002039701,0.0007513733,0.00009330993],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007997203,0.00008831879,0.0005194033,0.000047902267,0.000070435955,0.000044924593,0.002866848,0.00004080647,0.00022160732],"category_scores_gemma":[0.11479868,0.00004559166,0.0000371144,0.00060632377,0.0014719588,0.0006638664,0.0014303633,0.00021942417,0.0000019082518],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004687378,0.0024142563,0.036660336,0.0014186723,0.0012628728,0.0005066034,0.0016824164,0.00010755562,0.5707844,0.17813545,0.15383235,0.04850769],"study_design_scores_gemma":[0.0068426738,0.0022103528,0.010255878,0.0019791613,0.0011855724,0.00044950724,0.0014986453,0.0015431829,0.37851304,0.58486634,0.010013839,0.00064180285],"about_ca_topic_score_codex":0.00001093551,"about_ca_topic_score_gemma":0.00005547603,"teacher_disagreement_score":0.4067309,"about_ca_system_score_codex":0.00002700373,"about_ca_system_score_gemma":0.0007903302,"threshold_uncertainty_score":0.89265776},"labels":[],"label_agreement":null},{"id":"W2564611563","doi":"10.1345/aph.1e289","title":"Book Review: Bayesian Approaches to Clinical Trials and Health-Care Evaluation","year":2004,"lang":"en","type":"article","venue":"Annals of Pharmacotherapy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"","keywords":"Medicine; Bayesian probability; Clinical trial; Intensive care medicine; Medical physics; Internal medicine; Artificial intelligence; Computer science","score_opus":0.9567938797757775,"score_gpt":0.7489904644587767,"score_spread":0.20780341531700075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564611563","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067646964,0.6457065,0.1420545,0.20076703,0.0010095361,0.008765356,0.00019092271,0.00012118418,0.0007085108],"genre_scores_gemma":[0.0017890765,0.22363484,0.52978736,0.24320117,0.0010930771,0.00032259634,0.0000065290164,0.000078296565,0.00008706067],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98874515,0.0065377727,0.003199287,0.0005122453,0.00067642244,0.0003291168],"domain_scores_gemma":[0.98080385,0.016862271,0.0011333448,0.00046210765,0.00030914764,0.00042928048],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059122164,0.00023753975,0.0019186788,0.00008655297,0.00006368193,0.000019234052,0.00024815244,0.0001268429,0.0012457569],"category_scores_gemma":[0.043955933,0.00019022715,0.00039031525,0.00022012874,0.00012928704,0.00008489541,0.000041145886,0.00025277358,0.000014277673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031691426,0.00034786566,0.000027343474,0.0012456785,0.0002505753,0.0000010703669,0.00041074117,0.000005912587,0.00018550728,0.00600312,0.39946264,0.59174263],"study_design_scores_gemma":[0.010008747,0.002079883,0.0002746935,0.0034565907,0.00049137993,0.0000041506237,0.00009460792,0.00013028321,0.031199768,0.73231065,0.21931833,0.0006309288],"about_ca_topic_score_codex":0.000007899041,"about_ca_topic_score_gemma":0.0000013925991,"teacher_disagreement_score":0.7263075,"about_ca_system_score_codex":0.000032095024,"about_ca_system_score_gemma":0.0002521166,"threshold_uncertainty_score":0.9996672},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2566423486","doi":"10.5539/ijsp.v6n1p78","title":"Inverse Sampling for McNemar's Test","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; McNemar's test; Statistics; Negative binomial distribution; Continuity correction; Binomial distribution; Sampling (signal processing); Binomial test; Binomial proportion confidence interval; Binomial (polynomial); Poisson sampling; Beta-binomial distribution; Slice sampling; Poisson distribution; Importance sampling; Computer science","score_opus":0.4781346160748784,"score_gpt":0.5445036897344046,"score_spread":0.06636907365952616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566423486","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011911591,0.000012244174,0.98348594,0.0017531036,0.0009927704,0.0002052698,0.0015244024,0.0000079745505,0.000106711545],"genre_scores_gemma":[0.034845605,0.00007091215,0.9644551,0.00010375841,0.00044318725,0.0000067794113,7.774086e-7,0.000011877016,0.000061949315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982496,0.00012378086,0.0009750992,0.00015527595,0.00036520607,0.0001310407],"domain_scores_gemma":[0.92148983,0.0764596,0.0005632127,0.00011406234,0.0012532321,0.000120060264],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032092147,0.00010400035,0.00032527203,0.000053750133,0.000035710993,0.00004259319,0.00024105258,0.00006404233,0.00015936636],"category_scores_gemma":[0.2061853,0.000064173015,0.000084313106,0.000029876437,0.00019539136,0.00008325013,0.00006350563,0.00010374963,0.0000019489305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005814314,0.0003763,0.009007213,0.00014112743,0.00021841863,0.000016567777,0.00008616134,0.0000015440368,0.0011687967,0.7054994,0.007260581,0.27564248],"study_design_scores_gemma":[0.0013339691,0.00027932823,0.0022907432,0.00012926907,0.00005244578,0.0000260997,0.0000083142595,0.00008485917,0.000250734,0.99244004,0.0030169305,0.000087291504],"about_ca_topic_score_codex":0.0000020571408,"about_ca_topic_score_gemma":0.0000067449446,"teacher_disagreement_score":0.28694063,"about_ca_system_score_codex":0.000077433986,"about_ca_system_score_gemma":0.00008771478,"threshold_uncertainty_score":0.80050135},"labels":[],"label_agreement":null},{"id":"W2567636536","doi":"10.1093/ije/dyw320","title":"An introduction to multiplicity issues in clinical trials: the what, why, when and how","year":2016,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":379,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Ottawa Hospital; University of Ottawa; Population Health Research Institute; McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Confusion; Multiplicity (mathematics); Clinical trial; Population; Computer science; Risk analysis (engineering); Medicine; Intensive care medicine; Psychology; Mathematics; Pathology","score_opus":0.7812381245744865,"score_gpt":0.6905686159584271,"score_spread":0.09066950861605938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567636536","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07302389,0.00024209054,0.3876085,0.53362584,0.00524608,0.00022158881,0.00001529207,0.000009087292,0.00000763318],"genre_scores_gemma":[0.084740624,0.0020623116,0.8895917,0.007744205,0.015707674,0.000015246467,6.345091e-7,0.000022636992,0.000114992275],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9717935,0.023928547,0.0033767605,0.00035605946,0.00030594517,0.00023924171],"domain_scores_gemma":[0.57855934,0.41787374,0.0022021316,0.00039546084,0.0007171807,0.00025217535],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12642542,0.00013605614,0.0013134193,0.00016189044,0.000024063327,0.000049963634,0.00065897364,0.00020811489,0.00018843317],"category_scores_gemma":[0.8324124,0.00006441595,0.00022885538,0.000053614156,0.00032920437,0.0003829055,0.00011495415,0.0004283934,0.000005728033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015957924,0.00029659888,0.024521915,0.000006401518,0.00030938836,0.0000231025,0.00019674258,0.0000074077902,0.0007901813,0.16719648,0.09654795,0.7085081],"study_design_scores_gemma":[0.0015130677,0.00048378864,0.013085577,0.00012358923,0.000040577874,0.00007328436,0.00011500978,0.00012188033,0.00011203616,0.94444066,0.039805293,0.000085221924],"about_ca_topic_score_codex":0.000013952847,"about_ca_topic_score_gemma":0.000036779616,"teacher_disagreement_score":0.7772442,"about_ca_system_score_codex":0.00007363212,"about_ca_system_score_gemma":0.000038985414,"threshold_uncertainty_score":0.89952886},"labels":[],"label_agreement":null},{"id":"W2569798057","doi":"10.1016/j.jclinepi.2016.12.005","title":"Response to the letter by Guogen Shan and Hua Zhang (response to letter commenting: J Clin Epidemiol. 2015;68:733-739)","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; SickKids Foundation; Institute for Clinical Evaluative Sciences; Women's College Hospital; Hospital for Sick Children","funders":"Canadian Institutes of Health Research","keywords":"Gee; Sample size determination; Categorical variable; Type I and type II errors; Statistic; Statistics; Generalized estimating equation; Contingency table; Binary number; Zhàng; Mathematics; Binary data; Inference; Subject (documents); Econometrics; Computer science; Artificial intelligence; Library science; Geography; Arithmetic","score_opus":0.7665830285238733,"score_gpt":0.6658356382063745,"score_spread":0.1007473903174988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569798057","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063095586,0.00048565015,0.07456879,0.90716326,0.009346103,0.0014876737,0.00048219904,0.000049020073,0.00010775306],"genre_scores_gemma":[0.00012703033,0.00021599344,0.29124382,0.6784945,0.026321264,0.00006875959,0.000007992018,0.00018553373,0.0033351192],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.7222983,0.23933454,0.030314313,0.0028256169,0.0019006785,0.00332651],"domain_scores_gemma":[0.28282437,0.6988999,0.0131819965,0.0030258044,0.00074504997,0.0013228512],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.42149356,0.0013705969,0.013327373,0.0005173137,0.0005361172,0.00016854398,0.004418581,0.0048629143,0.0006856498],"category_scores_gemma":[0.9514895,0.0008743574,0.002982742,0.00024884247,0.0016801676,0.00018042319,0.0018209417,0.013991841,0.00060688896],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015116631,0.00017810505,0.0020160635,0.000121805264,0.0008445584,0.00075400225,0.0000764619,0.0000049632913,0.00008404291,0.0001415322,0.9726828,0.00797908],"study_design_scores_gemma":[0.0023859518,0.0024776557,0.0035375904,0.0008297027,0.000737862,0.00020907234,0.000010047774,0.000041776308,0.000014747991,0.11250394,0.8764513,0.0008003724],"about_ca_topic_score_codex":0.000038828486,"about_ca_topic_score_gemma":0.000007569696,"teacher_disagreement_score":0.5299959,"about_ca_system_score_codex":0.00020993182,"about_ca_system_score_gemma":0.00043697451,"threshold_uncertainty_score":0.99990445},"labels":[],"label_agreement":null},{"id":"W2570893302","doi":"10.1345/aph.1e234","title":"Book Review: Textbook of Clinical Trials","year":2004,"lang":"en","type":"article","venue":"Annals of Pharmacotherapy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Medical physics; Clinical trial; Intensive care medicine; Internal medicine","score_opus":0.9018041130801897,"score_gpt":0.761129861643926,"score_spread":0.14067425143626366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570893302","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004284736,0.7896437,0.1328026,0.047823343,0.0040790546,0.007941595,0.0009015913,0.00033708563,0.012186272],"genre_scores_gemma":[0.00064330664,0.55323464,0.3353836,0.107937194,0.0011607306,0.00007613392,0.0000020390873,0.00009744842,0.0014649262],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98810977,0.004578686,0.006005594,0.0003793934,0.0006131545,0.0003134167],"domain_scores_gemma":[0.9261937,0.06939413,0.002972537,0.00067584857,0.0005096598,0.0002541227],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041460402,0.00025065272,0.0032129618,0.000079120706,0.000025415518,0.0000058118794,0.0004989077,0.00018550993,0.008581947],"category_scores_gemma":[0.12241581,0.0001895446,0.0012653272,0.00022157728,0.00037352426,0.00009215465,0.000043725864,0.00034926343,0.000044886714],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007675478,0.0011981893,0.000028624074,0.001525275,0.0006704803,0.0000073375886,0.00004815754,0.00000217712,0.013399153,0.020394627,0.8506589,0.11129956],"study_design_scores_gemma":[0.0037823308,0.00045520198,0.000026492651,0.0015357456,0.00021140446,0.0000015352657,0.0000029598532,0.0000047740264,0.27067104,0.48554772,0.23757328,0.00018748586],"about_ca_topic_score_codex":0.0000063760012,"about_ca_topic_score_gemma":1.7938011e-7,"teacher_disagreement_score":0.61308557,"about_ca_system_score_codex":0.0000066705247,"about_ca_system_score_gemma":0.0001812769,"threshold_uncertainty_score":0.99232435},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2573716001","doi":"10.1177/0962280216688031","title":"An efficient test based on the inferential model for the non-inferiority of odds ratio in matched-pairs design","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Odds ratio; Test (biology); Sample size determination; Odds; Statistics; Score test; Computer science; Type I and type II errors; Inference; Function (biology); Mathematics; Medicine; Statistical hypothesis testing; Logistic regression; Artificial intelligence","score_opus":0.7979925770576195,"score_gpt":0.7224137239264271,"score_spread":0.07557885313119239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573716001","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080053083,0.0000071121203,0.9907001,0.004425477,0.00032735252,0.002825813,0.00024070713,0.000020161755,0.00065274263],"genre_scores_gemma":[0.29915044,0.000013719072,0.6997835,0.00014438923,0.00014641686,0.0006992128,0.0000015957665,0.000040365052,0.000020356742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9761662,0.016300183,0.002039092,0.00086061255,0.0034455683,0.0011883483],"domain_scores_gemma":[0.31463915,0.6818939,0.00031419058,0.0021210206,0.00054427754,0.00048746984],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1514196,0.00031947318,0.0011471843,0.00023212213,0.00061160355,0.0002006244,0.0027104614,0.000517504,0.0010847627],"category_scores_gemma":[0.8827624,0.00017957753,0.00015227815,0.00042371693,0.0037644529,0.000051470102,0.00045120815,0.002677925,0.000008396378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019723277,0.0025740182,0.0004355001,0.00040999064,0.000036849375,0.000044699576,0.00041137432,0.0035949918,0.000463554,0.7936212,0.00087446946,0.19556107],"study_design_scores_gemma":[0.0011011678,0.0004394764,0.0033602302,0.00018146996,0.00002000003,3.0949036e-7,0.00007042371,0.5429936,0.00057634467,0.4511445,0.0000061583287,0.00010636691],"about_ca_topic_score_codex":0.00015390155,"about_ca_topic_score_gemma":0.00010547021,"teacher_disagreement_score":0.73134273,"about_ca_system_score_codex":0.00017525027,"about_ca_system_score_gemma":0.0012982002,"threshold_uncertainty_score":0.9998284},"labels":[],"label_agreement":null},{"id":"W2575904277","doi":"10.1161/circheartfailure.116.003222","title":"Composite End Points in Clinical Trials of Heart Failure Therapy","year":2017,"lang":"en","type":"article","venue":"Circulation Heart Failure","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"Servier; Canadian Institutes of Health Research; Alberta Innovates; Alberta Innovates - Health Solutions; Amgen","keywords":"Statistics; Composite index; Clinical trial; Rank (graph theory); Heart failure; Consistency (knowledge bases); Mann–Whitney U test; Medicine; Composite number; Index (typography); Mathematics; Physical therapy; Computer science; Econometrics; Composite indicator; Internal medicine; Artificial intelligence; Algorithm","score_opus":0.6457514187604767,"score_gpt":0.6072940481127969,"score_spread":0.038457370647679845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2575904277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92795813,0.00013790233,0.026655467,0.03879652,0.001992116,0.0034270685,0.0002460188,0.00017346271,0.00061329117],"genre_scores_gemma":[0.5724573,0.0000108977665,0.42670783,0.00027589448,0.00045166205,0.000027566373,0.0000056489757,0.000035365767,0.000027832195],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886318,0.005793766,0.0039759004,0.00060780696,0.00061815506,0.00037261174],"domain_scores_gemma":[0.94422877,0.052296277,0.001526763,0.0014793182,0.0002600472,0.00020883397],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028808156,0.00028675198,0.0022939614,0.00015199684,0.00021418308,0.00012897712,0.00046524836,0.00057829113,0.0012008421],"category_scores_gemma":[0.18066466,0.0002485438,0.00071580225,0.00015912615,0.00044934405,0.0002300814,0.00011837025,0.00064035127,0.00007987822],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080509594,0.0015121103,0.82110065,0.00035265496,0.00036791875,0.000015160404,0.00034631084,0.00003659892,0.023996938,0.075444795,0.048600398,0.02742137],"study_design_scores_gemma":[0.0052409885,0.00015761616,0.41406804,0.00034151846,0.00007090681,0.000009412517,0.00004181461,0.0004128957,0.0029130762,0.56000346,0.01638866,0.00035161703],"about_ca_topic_score_codex":0.000041804313,"about_ca_topic_score_gemma":0.00004619854,"teacher_disagreement_score":0.48455867,"about_ca_system_score_codex":0.000043053937,"about_ca_system_score_gemma":0.00011993282,"threshold_uncertainty_score":0.99999666},"labels":[],"label_agreement":null},{"id":"W2579129885","doi":"10.1016/j.jclinepi.2016.12.017","title":"Response to letter to the editor by A. Huitfeldt Re: Odds ratios deconstructed: a new way to understand and explain odds ratios as conditional risk ratios","year":2017,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Odds ratio; Odds; Counterexample; Section (typography); Paragraph; Statement (logic); Relative risk; Mathematics; Statistics; Medicine; Combinatorics; Confidence interval; Computer science; Linguistics; Philosophy; Logistic regression","score_opus":0.591890600401322,"score_gpt":0.6058424513978082,"score_spread":0.013951850996486215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579129885","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020586564,0.00006513921,0.38373673,0.6003158,0.0116371475,0.001254668,0.0008048752,0.00002334509,0.00010364571],"genre_scores_gemma":[0.00030455686,0.00010772433,0.32691634,0.5838891,0.08658219,0.000052009265,0.000021069884,0.000101296966,0.002025672],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9263931,0.0553963,0.013908567,0.001563114,0.0014414529,0.001297462],"domain_scores_gemma":[0.41420597,0.57420754,0.007761821,0.001584327,0.0007472254,0.0014931011],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.10869166,0.0009424642,0.0072254976,0.0003905779,0.0005549876,0.00023197771,0.0020488657,0.0035410703,0.0014257807],"category_scores_gemma":[0.91684437,0.00063376164,0.0012945725,0.00023716279,0.0011047248,0.00022408969,0.0005538991,0.008717129,0.00035120497],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049585057,0.00008407827,0.00037796565,0.000054585336,0.0006812314,0.00025463893,0.00020429271,0.000021174634,0.00003212153,0.0029914354,0.9861342,0.0042057945],"study_design_scores_gemma":[0.0022094646,0.002818743,0.00063461275,0.0003257743,0.00045189692,0.00015509315,0.00006024193,0.000026176345,0.000015835783,0.3946908,0.5981147,0.0004966294],"about_ca_topic_score_codex":0.000043168326,"about_ca_topic_score_gemma":0.00007384035,"teacher_disagreement_score":0.8081527,"about_ca_system_score_codex":0.00024808702,"about_ca_system_score_gemma":0.0013009302,"threshold_uncertainty_score":0.9996114},"labels":[],"label_agreement":null},{"id":"W2579663487","doi":"10.1002/sim.7215","title":"Accounting for competing risks in randomized controlled trials: a review and recommendations for improvement","year":2017,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":152,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Randomized controlled trial; Cumulative incidence; Incidence (geometry); Outcome (game theory); Event (particle physics); Survival analysis; Medicine; Relative risk; Actuarial science; Confidence interval; Cohort; Internal medicine","score_opus":0.8315391831852751,"score_gpt":0.7107421776711227,"score_spread":0.1207970055141524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579663487","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.17117835e-8,0.63250124,0.33634475,0.0008899962,0.0008931131,0.02712273,0.0020865402,0.000015228124,0.00014638541],"genre_scores_gemma":[5.440304e-8,0.52876306,0.46131414,0.00017830383,0.00042305427,0.009068119,0.00012806125,0.0000561188,0.00006906847],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9755104,0.008749117,0.01383447,0.0008662472,0.00043373677,0.00060603226],"domain_scores_gemma":[0.41351634,0.5783305,0.0071986145,0.00053257204,0.000321333,0.0001006024],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20009318,0.0007115617,0.039821856,0.0004235818,0.0001681697,0.000066490495,0.00048389297,0.00038478302,0.00018371595],"category_scores_gemma":[0.94162685,0.00043480695,0.0009916383,0.00015902321,0.0004564319,0.000038227456,0.00013556144,0.00078436785,0.0000012320187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028343138,0.00006227433,2.230432e-7,0.12129552,0.000597849,0.0000028684817,0.000040538587,1.631567e-8,2.7833277e-8,0.08028455,0.005893324,0.7889885],"study_design_scores_gemma":[0.17983185,0.00014031646,6.98928e-8,0.1361159,0.014998064,0.0000017255388,0.000030642816,0.00026436712,1.8423625e-8,0.5131682,0.1551688,0.000280026],"about_ca_topic_score_codex":0.00006427499,"about_ca_topic_score_gemma":0.00005271671,"teacher_disagreement_score":0.78870845,"about_ca_system_score_codex":0.00017544924,"about_ca_system_score_gemma":0.00029486258,"threshold_uncertainty_score":0.9998104},"labels":[],"label_agreement":null},{"id":"W2583136411","doi":"10.1208/s12248-017-0048-x","title":"The Two Main Goals of Bioequivalence Studies","year":2017,"lang":"en","type":"article","venue":"The AAPS Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Canada Research Chairs","funders":"","keywords":"Bioequivalence; Harmonization; Equivalence (formal languages); Product (mathematics); Risk analysis (engineering); Management science; Actuarial science; Psychology; Computer science; Medicine; Pharmacology; Business; Pharmacokinetics; Economics; Mathematics","score_opus":0.8314813567239242,"score_gpt":0.6843529059429423,"score_spread":0.1471284507809819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583136411","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6769128,0.010611041,0.16869247,0.09180209,0.01809221,0.0020311326,0.0001990855,0.00012486854,0.031534307],"genre_scores_gemma":[0.4366411,0.004046201,0.5546309,0.00023296502,0.0020926928,0.000012526435,2.6453709e-8,0.000038125032,0.0023055093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972336,0.0011556044,0.0008074486,0.000103547405,0.00043583487,0.00026390658],"domain_scores_gemma":[0.9343293,0.06318396,0.0011862468,0.0010101898,0.00021922549,0.00007112205],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.015726853,0.000112800255,0.00041923847,0.000015313297,0.0013565904,0.00016343665,0.0014805172,0.000037154485,0.00006282073],"category_scores_gemma":[0.22796953,0.000046658923,0.00016596666,0.00003694365,0.0013302739,0.00006601565,0.00034182664,0.0004451465,0.000021401376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023721383,0.000092133785,0.00057700963,0.00007146449,0.00067006133,0.000049987946,0.00093764317,0.0000027496415,0.0016001869,0.86615306,0.023480803,0.10612767],"study_design_scores_gemma":[0.0005051168,0.00007775838,0.0006892715,0.000134546,0.00012251252,0.00006182784,0.00042150842,0.000020836236,0.002041715,0.99503446,0.00082706177,0.000063366024],"about_ca_topic_score_codex":0.0000032705007,"about_ca_topic_score_gemma":0.00000573862,"teacher_disagreement_score":0.38593838,"about_ca_system_score_codex":0.000026244437,"about_ca_system_score_gemma":0.00004733497,"threshold_uncertainty_score":0.9999435},"labels":[],"label_agreement":null},{"id":"W2583584334","doi":"","title":"PERSPECTIVA FUTURA DE LA FARMACOEPIDEMIOLOGÍA EN LA ERA DEL “BIG DATA” Y LA EXPANSIÓN DE LAS FUENTES DE INFORMACIÓN","year":2016,"lang":"es","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.710781057381665,"score_gpt":0.7101378047294562,"score_spread":0.00064325265220877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583584334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5817328,0.022527426,0.33246627,0.004143562,0.003619691,0.0027389815,0.0044937185,0.0004184457,0.047859073],"genre_scores_gemma":[0.55981594,0.108314544,0.32490876,0.0016961101,0.003907829,0.00017179825,0.00001732812,0.000367245,0.0008004411],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9713633,0.020805698,0.0038536876,0.0011873373,0.0011835137,0.0016064831],"domain_scores_gemma":[0.7743947,0.21987246,0.002511176,0.0017503696,0.00047502533,0.0009962842],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05147467,0.0009847638,0.002999977,0.0007642025,0.00040266718,0.0021595529,0.008508999,0.0011475565,0.0074408944],"category_scores_gemma":[0.2694464,0.00072724436,0.00062923785,0.0008555834,0.0014410542,0.0023144146,0.0043702815,0.0024763579,0.00008165324],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018324549,0.0015660342,0.43393514,0.001393126,0.002469471,0.00052339875,0.0015341958,0.000055583812,0.061247107,0.04599488,0.14893547,0.30051315],"study_design_scores_gemma":[0.00309516,0.00004730885,0.2841974,0.0036199472,0.001050057,0.00030269753,0.0005784385,0.0004215142,0.010023241,0.64867747,0.046772007,0.0012147684],"about_ca_topic_score_codex":0.00083337916,"about_ca_topic_score_gemma":0.000015937201,"teacher_disagreement_score":0.6026826,"about_ca_system_score_codex":0.0006914794,"about_ca_system_score_gemma":0.0014710092,"threshold_uncertainty_score":0.99982494},"labels":[],"label_agreement":null},{"id":"W2587412035","doi":"10.1002/sim.7242","title":"Quantifying the bias in the estimated treatment effect in randomized trials having interim analyses and a rule for early stopping for futility","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Interim; Interim analysis; Early stopping; Treatment effect; Econometrics; Randomized controlled trial; Statistics; Computer science; Medicine; Mathematics; Law; Artificial intelligence; Surgery","score_opus":0.9144447875273284,"score_gpt":0.717800957027186,"score_spread":0.19664383050014234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587412035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19711831,0.00034096788,0.7918386,0.0015667952,0.00070251,0.007900658,0.00042158677,0.000019326117,0.00009124239],"genre_scores_gemma":[0.50876683,0.00012528557,0.48964074,0.00008051566,0.0001603824,0.0011808681,0.000009483428,0.000023272056,0.000012585235],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894207,0.007008751,0.0024321307,0.0004303505,0.00031521704,0.0003928468],"domain_scores_gemma":[0.56111085,0.43741563,0.00081190234,0.0005403384,0.00007726091,0.00004402097],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07987711,0.0003025834,0.0032791113,0.00016885014,0.00025522444,0.000121394805,0.00042246107,0.00012186553,0.0000200861],"category_scores_gemma":[0.7910778,0.00013567935,0.00017139144,0.00012991908,0.000823119,0.000048975056,0.0000701411,0.00027964983,3.8779933e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15504335,0.0010959095,0.03795758,0.00395612,0.0013182171,0.00017651272,0.023124099,0.000036839225,0.0013952554,0.2928916,0.0017040374,0.4813005],"study_design_scores_gemma":[0.12082438,0.0008141121,0.015339726,0.0013107812,0.0008470198,0.0000018246477,0.0005338018,0.02738866,0.00015502912,0.8326129,0.000013664207,0.00015814461],"about_ca_topic_score_codex":0.0010745818,"about_ca_topic_score_gemma":0.0013422198,"teacher_disagreement_score":0.71120065,"about_ca_system_score_codex":0.000103676124,"about_ca_system_score_gemma":0.000050475704,"threshold_uncertainty_score":0.9474602},"labels":[],"label_agreement":null},{"id":"W2587637943","doi":"10.1002/cncr.30579","title":"Determinants of the recommended phase 2 dose of molecular targeted agents","year":2017,"lang":"en","type":"review","venue":"Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Dosing; Internal medicine; Clinical endpoint; Pharmacokinetics; Pharmacodynamics; Confidence interval; Odds ratio; Surrogate endpoint; Oncology; Clinical trial; Pharmacology","score_opus":0.8369433527983116,"score_gpt":0.7032770405706433,"score_spread":0.13366631222766823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587637943","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000671756,0.99393,0.00046805717,0.0000147704195,0.0019955358,0.001472522,0.0014461352,0.000012203804,0.0005936174],"genre_scores_gemma":[0.000016907694,0.9501204,0.049141914,0.000030066753,0.00012640817,0.00017916154,0.0000020518985,0.00006515568,0.00031795888],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962255,0.0011793021,0.001720096,0.00032353878,0.00032822564,0.00022334709],"domain_scores_gemma":[0.98655236,0.008598573,0.0030802262,0.0015507111,0.0001372955,0.00008083511],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015421573,0.00030828116,0.0031597372,0.000045450255,0.000046531393,0.000010193598,0.0011118931,0.00036526768,0.00066862494],"category_scores_gemma":[0.05096793,0.0001838686,0.0008749501,0.0001273682,0.00022664396,0.000018733223,0.00027555856,0.00035092037,0.0000055341925],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000150598225,0.00013576946,0.0000032151302,0.015978964,0.00019302109,0.000007677805,0.000012402257,1.9516413e-8,0.0000049206938,0.00044821357,0.0016417823,0.981559],"study_design_scores_gemma":[0.0016492925,0.00009909786,0.000006436022,0.038712107,0.0034926212,0.000003205514,0.0000021723963,0.000009882292,0.0011092827,0.14849298,0.8060462,0.000376747],"about_ca_topic_score_codex":0.000011710189,"about_ca_topic_score_gemma":0.0000030053527,"teacher_disagreement_score":0.9811822,"about_ca_system_score_codex":0.000073383584,"about_ca_system_score_gemma":0.00036188628,"threshold_uncertainty_score":0.9570262},"labels":[],"label_agreement":null},{"id":"W2589026107","doi":"10.1111/pan.13088","title":"Sequential allocation trial design in anesthesia: an introduction to methods, modeling, and clinical applications","year":2017,"lang":"en","type":"review","venue":"Pediatric Anesthesia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"","keywords":"Sample size determination; Medicine; Range (aeronautics); Confidence interval; Statistics; Population; Mathematical optimization; Mathematics","score_opus":0.7422750650565006,"score_gpt":0.6444602135530432,"score_spread":0.09781485150345748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589026107","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022254131,0.2630569,0.72837055,0.0005548933,0.00032680776,0.0075048767,0.0000053862027,0.00014595827,0.000012378789],"genre_scores_gemma":[7.700252e-7,0.4779006,0.5126063,0.000032797405,0.008002185,0.0012849797,0.000016225144,0.00010168898,0.000054406824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98089385,0.011919691,0.0041811187,0.0018806851,0.0005346226,0.00059005065],"domain_scores_gemma":[0.9668298,0.028210448,0.0019285313,0.002222213,0.00024712645,0.00056192564],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.028373824,0.0007725177,0.004290176,0.0006011648,0.00024296695,0.00024214998,0.0010992803,0.0014509443,0.000041473384],"category_scores_gemma":[0.044670437,0.00068218046,0.00056074,0.0006201548,0.00016824575,0.00021448881,0.00011961411,0.0011917677,0.00007142666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009702422,0.0006115785,0.0000075923463,0.0025484015,0.000066431094,0.000047396832,0.000028102622,0.000012271353,2.5689147e-8,0.009391801,0.00076914026,0.985547],"study_design_scores_gemma":[0.008296676,0.0017996649,0.000007514038,0.00061300804,0.008678603,0.0005847654,0.000018759218,0.0027727876,2.5686774e-7,0.31135595,0.66401345,0.0018585647],"about_ca_topic_score_codex":0.000023653143,"about_ca_topic_score_gemma":0.0000042135507,"teacher_disagreement_score":0.9836885,"about_ca_system_score_codex":0.0001772259,"about_ca_system_score_gemma":0.00072774285,"threshold_uncertainty_score":0.9998454},"labels":[],"label_agreement":null},{"id":"W2590824379","doi":"10.5539/ijsp.v6n2p106","title":"Tests of Independence for a $2 \\times 2$ Contingency Table with Random Margins","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Contingency table; Mathematics; Exact test; Statistics; Multinomial distribution; Hypergeometric distribution; Chi-square test; Independence (probability theory); Test (biology); Econometrics","score_opus":0.26226651942224183,"score_gpt":0.5096757922651235,"score_spread":0.24740927284288167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590824379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05197441,0.000042717616,0.94445163,0.00039030006,0.0007722088,0.000451689,0.0012610027,0.00000415969,0.0006518543],"genre_scores_gemma":[0.31923968,0.00003405897,0.6805106,0.000013309681,0.00014168891,0.000006343159,7.076777e-7,0.000007308466,0.000046314337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818814,0.00012360176,0.00091045763,0.0001468021,0.0005134191,0.00011756103],"domain_scores_gemma":[0.976443,0.018319994,0.0016360474,0.00022043062,0.0032970707,0.00008345263],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036943338,0.00010594007,0.0005015085,0.00003976936,0.00008628917,0.00009563551,0.00044563596,0.00006438257,0.00008794127],"category_scores_gemma":[0.15183654,0.00007408614,0.00006006016,0.000018226854,0.00035720805,0.0001261875,0.00008121527,0.00017072355,2.3308151e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057033235,0.00069830276,0.06829916,0.0005647047,0.0007346355,0.000042579588,0.00023052069,0.000013165488,0.00029198296,0.858577,0.0024571682,0.062387444],"study_design_scores_gemma":[0.003391624,0.00043564,0.025398167,0.00019344476,0.00010157866,0.000018825047,0.000013952035,0.00026951783,0.0003933952,0.9694115,0.00028965605,0.00008268646],"about_ca_topic_score_codex":0.000025824223,"about_ca_topic_score_gemma":0.00003671663,"teacher_disagreement_score":0.26726526,"about_ca_system_score_codex":0.00002701971,"about_ca_system_score_gemma":0.00016406427,"threshold_uncertainty_score":0.8553079},"labels":[],"label_agreement":null},{"id":"W2592303047","doi":"10.6000/1929-6029.2017.06.01.3","title":"ROC Analysis for Phase II Group Sequential Basket Clinical Trial","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Nonparametric statistics; Parametric statistics; Clinical trial; Computer science; Group (periodic table); Receiver operating characteristic; Randomized controlled trial; Statistics; Econometrics; Artificial intelligence; Machine learning; Mathematics; Medicine; Surgery; Internal medicine","score_opus":0.8643649198917347,"score_gpt":0.7766170149383429,"score_spread":0.0877479049533918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592303047","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041179907,0.00002499795,0.9463867,0.0042158975,0.006078624,0.00064599345,0.000846077,0.000008490757,0.0006133158],"genre_scores_gemma":[0.29843184,0.0004424574,0.6950561,0.00016155205,0.005562857,0.000046561567,0.00001778952,0.000035550565,0.00024530914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985406,0.002850162,0.0042088693,0.00046209194,0.006470248,0.0006026537],"domain_scores_gemma":[0.8429207,0.15036207,0.0017631239,0.00066275586,0.0035363273,0.0007550184],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07938781,0.00020022498,0.0013331912,0.0008659521,0.00036374838,0.0003253577,0.0034888838,0.0004417908,0.0024611545],"category_scores_gemma":[0.76400065,0.00016292468,0.00061316683,0.00026961634,0.0013979347,0.0001895771,0.00080798764,0.0023144665,0.000009984997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06962823,0.006801051,0.0020134132,0.00006918733,0.003349958,0.0020702642,0.00012639443,0.0000043118553,0.000022693366,0.4584686,0.028796252,0.42864966],"study_design_scores_gemma":[0.079503305,0.004473938,0.0010606064,0.00020726124,0.0003197219,0.000019049408,0.000045124652,0.0070845676,0.000023840572,0.9010854,0.006014017,0.00016319517],"about_ca_topic_score_codex":0.000045908342,"about_ca_topic_score_gemma":0.00016473846,"teacher_disagreement_score":0.6846129,"about_ca_system_score_codex":0.00025285463,"about_ca_system_score_gemma":0.00093480235,"threshold_uncertainty_score":0.99998724},"labels":[],"label_agreement":null},{"id":"W2593515265","doi":"10.1136/ebmed-2017-110685","title":"Reflections on using non-inferiority randomised placebo controlled trials in assessing cardiovascular safety of new agents for treatment of type 2 diabetes","year":2017,"lang":"en","type":"article","venue":"Evidence-Based Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Diabetes Canada; Women and Children’s Health Research Institute; University of Alberta","funders":"","keywords":"Medicine; Placebo; Clinical trial; Harm; Intensive care medicine; Randomized controlled trial; Number needed to harm; Food and drug administration; Number needed to treat; Alternative medicine; Internal medicine; Pharmacology; Psychology; Pathology","score_opus":0.8078595663444346,"score_gpt":0.6425220915176343,"score_spread":0.16533747482680028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593515265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31565535,0.0025638219,0.6579192,0.002686526,0.004029444,0.016027419,0.00007220077,0.00004564279,0.0010004021],"genre_scores_gemma":[0.61218196,0.0005682537,0.3856247,0.00007468242,0.0012222118,0.00019909031,0.0000028929287,0.000042013577,0.00008419763],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9927392,0.0030774863,0.0029061278,0.00037886406,0.00061407045,0.00028427498],"domain_scores_gemma":[0.79886997,0.19787914,0.0018562758,0.0009407096,0.00031326566,0.00014067258],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03253219,0.00028038947,0.00614434,0.00020795756,0.000161309,0.000024418887,0.0002491192,0.00018593852,0.00012401657],"category_scores_gemma":[0.6795017,0.0001794207,0.0010797236,0.0001685681,0.00029285217,0.00010806017,0.000021808764,0.00010526275,7.042607e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.61571175,0.004084863,0.014342072,0.005965343,0.015516098,0.000068709,0.0019361898,0.0057422784,0.10090138,0.0064510005,0.001603584,0.22767676],"study_design_scores_gemma":[0.7615359,0.007626657,0.0070354333,0.025974935,0.013492627,8.882667e-7,0.00017821707,0.016910672,0.056245506,0.10995491,0.00047055617,0.000573734],"about_ca_topic_score_codex":0.00026215322,"about_ca_topic_score_gemma":0.000011844188,"teacher_disagreement_score":0.6469695,"about_ca_system_score_codex":0.00024887704,"about_ca_system_score_gemma":0.00060334255,"threshold_uncertainty_score":0.9962117},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2593604058","doi":"10.1371/journal.pbio.2001307","title":"Increasing efficiency of preclinical research by group sequential designs","year":2017,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Bundesministerium für Bildung und Forschung","keywords":"Biomedicine; Sample size determination; Frequentist inference; Clinical study design; Sample (material); Sequential analysis; Block (permutation group theory); Design of experiments; Computer science; Biology; Clinical trial; Risk analysis (engineering); Statistics; Bioinformatics; Artificial intelligence; Mathematics; Bayesian probability; Medicine; Bayesian inference","score_opus":0.9064160519764929,"score_gpt":0.6900746953585928,"score_spread":0.2163413566179001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593604058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87602675,0.00010985384,0.11412098,0.0005714147,0.0007411519,0.00082373153,0.00019660078,0.00007406486,0.007335436],"genre_scores_gemma":[0.61685073,0.000026247837,0.38275596,0.000027856586,0.00024962777,0.000023178587,0.0000023677258,0.000017933791,0.000046079975],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922332,0.00545044,0.0010114033,0.0004943213,0.00031333716,0.0004972908],"domain_scores_gemma":[0.89215964,0.10606842,0.00043695417,0.0009844914,0.000219263,0.00013123314],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015669888,0.00013354576,0.0007220134,0.00006630258,0.000310982,0.000037268554,0.0009944928,0.00041460048,0.00033967965],"category_scores_gemma":[0.4685031,0.00010548454,0.00012036816,0.00007480915,0.0019411871,0.000041487117,0.0005248348,0.0005666547,0.000045116758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011660573,0.002566411,0.023837574,0.00030835398,0.00028073476,0.000015803798,0.0001307025,7.2824164e-8,0.47916073,0.47096846,0.004295189,0.0172699],"study_design_scores_gemma":[0.0008418448,0.0008463774,0.00070909574,0.000089367924,0.000060202095,0.0000037465552,0.000012053703,0.00015506384,0.024221767,0.97263235,0.0002941146,0.00013401436],"about_ca_topic_score_codex":0.00009743798,"about_ca_topic_score_gemma":0.0000059989225,"teacher_disagreement_score":0.50166386,"about_ca_system_score_codex":0.000031682783,"about_ca_system_score_gemma":0.00006768208,"threshold_uncertainty_score":0.7152385},"labels":[],"label_agreement":null},{"id":"W2593926725","doi":"10.1016/j.jclinepi.2017.02.010","title":"Simple randomization did not protect against bias in smaller trials","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"Canadian Institutes of Health Research; All-India Institute of Medical Sciences","keywords":"Randomization; Simple (philosophy); Clinical trial; Medicine; Statistics; Mathematics; Computer science; Internal medicine","score_opus":0.9542001172518783,"score_gpt":0.7341474733553284,"score_spread":0.22005264389654988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593926725","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38708428,0.00014217167,0.5753973,0.02467541,0.008021634,0.0022106837,0.000048531503,0.00004303792,0.002376946],"genre_scores_gemma":[0.34645608,0.0011991643,0.64442647,0.0033125766,0.004394879,0.000034655044,0.0000011967411,0.000051244107,0.00012375432],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85358506,0.109767064,0.03439738,0.00074922276,0.0006406838,0.00086059206],"domain_scores_gemma":[0.12841472,0.8441493,0.02535212,0.0011138031,0.00051110226,0.00045893804],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45908257,0.00030407787,0.011223513,0.00017615416,0.00015221132,0.00004442075,0.0011168298,0.0009898753,0.00028506826],"category_scores_gemma":[0.99394923,0.0001943993,0.0020646644,0.000089986905,0.0006816835,0.00017785317,0.00023214844,0.0020504885,0.000029915078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042326048,0.0020666139,0.33377033,0.0003571268,0.0013187067,0.00040728858,0.00007429855,0.0004707063,0.00015488768,0.14271136,0.022856357,0.45348626],"study_design_scores_gemma":[0.020182298,0.0006670496,0.06867382,0.0002570155,0.00017173999,0.0000140338225,0.000007916007,0.0012158295,0.000077988145,0.9058105,0.002727029,0.00019479368],"about_ca_topic_score_codex":0.000018497763,"about_ca_topic_score_gemma":0.000027747023,"teacher_disagreement_score":0.76309913,"about_ca_system_score_codex":0.000058724094,"about_ca_system_score_gemma":0.0002801973,"threshold_uncertainty_score":0.8908466},"labels":[],"label_agreement":null},{"id":"W2595956641","doi":"10.1159/000362525","title":"Unvollständige Daten in randomisierten dermatologischen Studien: Auswirkungen und statistische Methoden","year":2014,"lang":"de","type":"article","venue":"Kompass Dermatologie","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Amgen (Canada); University of Waterloo","funders":"","keywords":"Gynecology; Medicine; Art","score_opus":0.4725614789157605,"score_gpt":0.5476027252835461,"score_spread":0.07504124636778564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2595956641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076530855,0.019039562,0.9211179,0.019205872,0.009120177,0.0063285446,0.0012356729,0.0010912431,0.015207948],"genre_scores_gemma":[0.10419691,0.0020409275,0.89028883,0.0015548101,0.0006895799,0.0005384415,0.00006587287,0.0002702274,0.00035442703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97029746,0.017730454,0.0055103432,0.0022635001,0.001408681,0.0027895507],"domain_scores_gemma":[0.83764744,0.1570623,0.0017049361,0.0024679995,0.00035605684,0.0007612903],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.015499338,0.0015751014,0.0061728153,0.00059570384,0.00040734388,0.00038026564,0.0026018242,0.0017058146,0.00043175233],"category_scores_gemma":[0.2096572,0.0013643517,0.0006681687,0.001222316,0.0013803071,0.0003937718,0.0015857824,0.0023543886,0.0019651335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005211609,0.0047858017,0.049421534,0.0067265234,0.011039212,0.0049862904,0.0033067309,0.00034182952,0.00024649675,0.49606758,0.328952,0.08891439],"study_design_scores_gemma":[0.024889255,0.00034978898,0.004621796,0.00086939585,0.0041232496,0.00012800493,0.0004934043,0.024533004,0.0020756656,0.8694942,0.065903075,0.0025191798],"about_ca_topic_score_codex":0.00019379347,"about_ca_topic_score_gemma":0.00016890967,"teacher_disagreement_score":0.37342662,"about_ca_system_score_codex":0.00040609654,"about_ca_system_score_gemma":0.0004528572,"threshold_uncertainty_score":0.99994725},"labels":[],"label_agreement":null},{"id":"W2599014587","doi":"","title":"Confidence Intervals for a Discrete Population Median","year":2007,"lang":"fr","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Confidence interval; Robust confidence intervals; CDF-based nonparametric confidence interval; Statistics; Population; Confidence region; Statistic; Confidence distribution; Sign test; Credible interval; Sign (mathematics); Mathematics; Computer science; Mann–Whitney U test; Wilcoxon signed-rank test; Medicine","score_opus":0.6035152429956283,"score_gpt":0.6237787561512848,"score_spread":0.020263513155656443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599014587","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055497664,0.00023051533,0.97466373,0.008289702,0.0059353607,0.0013845039,0.00022152642,0.000087379,0.008632283],"genre_scores_gemma":[0.032423582,0.000037443544,0.9449331,0.00077554455,0.0015294448,0.000035798806,0.00000767064,0.000052487165,0.020204885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99610466,0.00051699416,0.001887605,0.00045293444,0.00038713173,0.00065065717],"domain_scores_gemma":[0.86020195,0.13840123,0.00040323933,0.00044041994,0.00022142258,0.00033174388],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013247206,0.00025577683,0.00078431075,0.00007597634,0.00008464889,0.000075377386,0.000288032,0.00043728485,0.0037315076],"category_scores_gemma":[0.24210007,0.00022701528,0.00031177248,0.00018602044,0.00027609966,0.00013632509,0.00009375247,0.0002716162,0.00020018537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016152536,0.00009312619,0.00022760252,0.00049358886,0.0000662657,0.00000821915,0.0001572267,6.2203424e-7,0.00006776388,0.87000144,0.0052449703,0.123477675],"study_design_scores_gemma":[0.0009715622,0.00031866351,0.0011560138,0.00052267214,0.00023659131,0.0000069204684,0.00015462619,0.002217894,0.0017400014,0.98805714,0.0043313787,0.0002865577],"about_ca_topic_score_codex":0.00027343156,"about_ca_topic_score_gemma":0.00037412666,"teacher_disagreement_score":0.22885287,"about_ca_system_score_codex":0.00012518646,"about_ca_system_score_gemma":0.00003817013,"threshold_uncertainty_score":0.9971792},"labels":[],"label_agreement":null},{"id":"W2599407426","doi":"10.1200/jco.2014.32.15_suppl.2549","title":"Correlation between phase 2 clinical trial design and subsequent phase 3 outcome.","year":2014,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Juravinski Cancer Centre; Queen's University; Baker Hughes (Canada)","funders":"","keywords":"Medicine; Clinical trial; Outcome (game theory); Discontinuation; Clinical endpoint; Internal medicine; Randomized controlled trial; Surrogate endpoint","score_opus":0.8939519433398854,"score_gpt":0.736351741187874,"score_spread":0.15760020215201131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599407426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23707935,0.000032063024,0.7526297,0.0020637517,0.0068368814,0.00075675023,0.000014923797,0.00002944988,0.00055713125],"genre_scores_gemma":[0.2576253,0.00014602559,0.73214775,0.0009499893,0.008984288,0.000009326732,0.000001524661,0.000043311844,0.00009249841],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9625444,0.020086622,0.01563567,0.00050979276,0.0007838036,0.00043974578],"domain_scores_gemma":[0.46586755,0.5227184,0.009071609,0.00052700244,0.0006593037,0.0011561274],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1264511,0.0003141023,0.0050567216,0.00015105311,0.000094503994,0.000043407796,0.00043905314,0.0014030499,0.00027777013],"category_scores_gemma":[0.6664466,0.00022581773,0.001116644,0.00017702222,0.0008591521,0.00017411615,0.00014472683,0.0027076288,0.00004199888],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10573394,0.008038549,0.006447926,0.00003904384,0.0005554908,0.00019110237,0.000030372437,0.000008015029,0.0000075426747,0.0157619,0.007164452,0.85602164],"study_design_scores_gemma":[0.29822525,0.08455633,0.002040201,0.00006614982,0.0015728301,0.00006736892,0.000015796024,0.002821232,0.000012737422,0.58487415,0.025471998,0.00027595923],"about_ca_topic_score_codex":0.0000017951409,"about_ca_topic_score_gemma":0.0000011482622,"teacher_disagreement_score":0.85574573,"about_ca_system_score_codex":0.00009518699,"about_ca_system_score_gemma":0.0007155255,"threshold_uncertainty_score":0.99989337},"labels":[],"label_agreement":null},{"id":"W2601443004","doi":"10.1027/1614-2241/a000122","title":"Using the Errors-in-Variables Method in Two-Group Pretest-Posttest Designs","year":2017,"lang":"en","type":"article","venue":"Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Analysis of covariance; Covariate; Statistics; Reliability (semiconductor); Covariance; Mathematics; Econometrics; Observational error; Sample size determination; Psychology; Power (physics)","score_opus":0.918746052008132,"score_gpt":0.6893558059739121,"score_spread":0.22939024603421987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601443004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019684441,0.00006100656,0.9745602,0.00093818794,0.0012795521,0.0008113489,0.000018068584,0.000049915692,0.0025972626],"genre_scores_gemma":[0.011537647,0.000012488499,0.9874957,0.0003922417,0.0003236956,0.00008618701,5.414395e-7,0.00006075435,0.00009074742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96869993,0.027970333,0.0014699107,0.0007637896,0.00029260822,0.000803408],"domain_scores_gemma":[0.7083924,0.28918856,0.0006824357,0.0015651174,0.000075968375,0.00009553904],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057018254,0.00032289018,0.0013902866,0.00016759479,0.0003006976,0.00009650548,0.0013363241,0.00033581755,0.00026299374],"category_scores_gemma":[0.5003332,0.0002321059,0.0001619683,0.00023338845,0.0005796097,0.00012472279,0.00050940766,0.00091876456,0.00001241675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049298967,0.00037697793,0.027431192,0.00017323527,0.00012281492,0.00020868666,0.00096596166,0.00033186714,0.037690688,0.89356923,0.0002013432,0.038435023],"study_design_scores_gemma":[0.0015061626,0.00009365105,0.0062399125,0.00010506544,0.00011257035,0.000041325904,0.00013001563,0.0067690844,0.003294202,0.98130476,0.00013677073,0.00026646644],"about_ca_topic_score_codex":0.00092512276,"about_ca_topic_score_gemma":0.0007141522,"teacher_disagreement_score":0.4433149,"about_ca_system_score_codex":0.000112645575,"about_ca_system_score_gemma":0.00010154634,"threshold_uncertainty_score":0.97099817},"labels":[],"label_agreement":null},{"id":"W2601953228","doi":"10.1200/jco.2007.25.18_suppl.6532","title":"The quality of phase I trial (P1T) abstracts submitted to ASCO meetings","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Family medicine; Limiting; Quality (philosophy); Quality Score; Rating scale; Medical physics; Statistics","score_opus":0.8494559102098228,"score_gpt":0.7573544482863453,"score_spread":0.09210146192347746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2601953228","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9389261,0.000047078476,0.041278873,0.0055674566,0.007357613,0.00073981745,0.000015553078,0.000017983062,0.006049543],"genre_scores_gemma":[0.4789698,0.000073959156,0.5155545,0.001256007,0.003960026,0.0000042630127,1.7887041e-7,0.000028433276,0.0001528505],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96981573,0.0070642424,0.020646485,0.0003531335,0.0014803752,0.0006400042],"domain_scores_gemma":[0.2979868,0.6858439,0.012973794,0.0006421262,0.0016306915,0.00092269614],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2126922,0.00020723286,0.003214487,0.00010279122,0.00009404952,0.000022513754,0.0008661805,0.0007372049,0.00016038533],"category_scores_gemma":[0.8068952,0.00012326565,0.0011300188,0.00028339704,0.00063725683,0.000069803835,0.00015277904,0.0017136765,0.000027407803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3237376,0.008611908,0.0005601896,0.00006407338,0.0006864507,0.000185305,0.00016330645,0.000003009937,0.0007206357,0.045591496,0.014402212,0.60527384],"study_design_scores_gemma":[0.13828436,0.03076473,0.01971559,0.00012394733,0.00049895927,0.000029265222,0.0002737435,0.000008476724,0.0012154569,0.75337046,0.05544374,0.000271265],"about_ca_topic_score_codex":0.000017294407,"about_ca_topic_score_gemma":0.000058055368,"teacher_disagreement_score":0.707779,"about_ca_system_score_codex":0.00010863234,"about_ca_system_score_gemma":0.000929659,"threshold_uncertainty_score":0.81069905},"labels":[],"label_agreement":null},{"id":"W2603868241","doi":"10.1200/jco.2012.30.15_suppl.e14706","title":"Multistage phase II design for mixed tumor response and time-to-event endpoints: An application for screening new drugs in hepatocellular carcinoma (HCC).","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Aegera Therapeutics (Canada)","funders":"","keywords":"Medicine; Sorafenib; Clinical endpoint; Surrogate endpoint; Oncology; Internal medicine; Early stopping; Progression-free survival; Hepatocellular carcinoma; Hazard ratio; Phases of clinical research; Randomized controlled trial; Clinical trial; Overall survival; Confidence interval; Machine learning","score_opus":0.590656214930436,"score_gpt":0.6152416354378769,"score_spread":0.024585420507440947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603868241","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4068635,0.000049616792,0.5898266,0.0013303872,0.0003618071,0.0015128282,0.000036264002,0.000010674677,0.000008363799],"genre_scores_gemma":[0.2696607,0.000005334221,0.72824764,0.00054230733,0.0012361435,0.00010357242,0.000001613851,0.000042793767,0.00015987548],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9892331,0.0047526187,0.004757484,0.00038637672,0.00033295323,0.000537471],"domain_scores_gemma":[0.8088386,0.18718459,0.0023065917,0.00031908645,0.0003222342,0.0010289213],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06279633,0.0002429228,0.002210897,0.00019506825,0.00009872671,0.000017921227,0.0003634542,0.0004367276,0.000076211836],"category_scores_gemma":[0.28617993,0.00020354119,0.00040905623,0.00015196466,0.00015154333,0.00019454374,0.00011828111,0.0006030297,0.00000894493],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15643838,0.011018379,0.0033348864,0.00017981212,0.00027612908,0.00006269009,0.0013172865,0.000036812875,0.008010218,0.005982799,0.012199943,0.80114263],"study_design_scores_gemma":[0.112544745,0.1156442,0.016116677,0.00044344825,0.0016021193,0.000177209,0.0008020112,0.083922006,0.008252286,0.5724588,0.08681631,0.0012201727],"about_ca_topic_score_codex":0.0000073839806,"about_ca_topic_score_gemma":0.0000023873336,"teacher_disagreement_score":0.79992247,"about_ca_system_score_codex":0.00014648703,"about_ca_system_score_gemma":0.0006561793,"threshold_uncertainty_score":0.96504843},"labels":[],"label_agreement":null},{"id":"W2604913116","doi":"10.1093/ectj/utz006","title":"A simple, graphical approach to comparing multiple treatments","year":2019,"lang":"en","type":"article","venue":"Econometrics Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Toronto Metropolitan University","funders":"","keywords":"Spurious relationship; Graphical model; Resampling; Computer science; Simple (philosophy); Multiple comparisons problem; Jackknife resampling; Algorithm; Zero (linguistics); Mathematics; Statistics; Artificial intelligence; Machine learning","score_opus":0.6608640137915875,"score_gpt":0.5200311668773503,"score_spread":0.14083284691423725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604913116","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66864187,0.000044166023,0.30067402,0.00008806416,0.0011191732,0.00063900824,0.000032650263,0.000056487672,0.028704593],"genre_scores_gemma":[0.5223706,0.000014054017,0.47701904,0.00012151426,0.00023762153,0.000011036809,9.80096e-7,0.000027376887,0.0001978041],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735785,0.0003313049,0.0011114982,0.0003812906,0.00034285124,0.00047518435],"domain_scores_gemma":[0.97858995,0.019972706,0.0003589408,0.00040647163,0.00010942008,0.0005625345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003374046,0.00021431308,0.00085954263,0.00086428225,0.000117828626,0.00018331934,0.00045315237,0.00014034261,0.0005678058],"category_scores_gemma":[0.045408092,0.00018013678,0.00027432095,0.0012782234,0.000038157847,0.00012151679,0.0001517073,0.0005650676,0.00040153787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029424138,0.0022629916,0.8418559,0.00013084213,0.0007854642,0.00002702813,0.00025338578,0.00041756968,0.000067773086,0.12251327,0.008797952,0.022593603],"study_design_scores_gemma":[0.004118696,0.00047027125,0.0687779,0.00003226615,0.00011999586,0.00009974243,0.000108329165,0.006017767,0.00007829194,0.9173448,0.0023846643,0.00044728376],"about_ca_topic_score_codex":0.0000030919432,"about_ca_topic_score_gemma":6.5509767e-7,"teacher_disagreement_score":0.7948315,"about_ca_system_score_codex":0.00017561189,"about_ca_system_score_gemma":0.000039264363,"threshold_uncertainty_score":0.96263283},"labels":[],"label_agreement":null},{"id":"W2605062205","doi":"10.1158/1078-0432.ccr-16-2354","title":"Use of Expansion Cohorts in Phase I Trials and Probability of Success in Phase II for 381 Anticancer Drugs","year":2017,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Center for Advancing Translational Sciences; National Cancer Institute; National Institutes of Health","keywords":"Medicine; Cohort; Confidence interval; Internal medicine; Clinical trial; Cohort study; Logistic regression; Phases of clinical research; Oncology","score_opus":0.935117757440753,"score_gpt":0.7769513201782015,"score_spread":0.15816643726255153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605062205","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9918848,0.00015851503,0.0016690338,0.0010163666,0.00042987024,0.0040980414,0.00066505844,0.000009850887,0.0000684176],"genre_scores_gemma":[0.9083074,0.00101643,0.08966181,0.000029753981,0.00025971272,0.0006218148,0.0000022311037,0.00003393378,0.00006691867],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98632145,0.0061649396,0.0049879476,0.00089564006,0.0010068245,0.00062322844],"domain_scores_gemma":[0.7582783,0.23780954,0.0013301469,0.001421021,0.0008886888,0.00027231083],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09633612,0.00020559793,0.003057814,0.00020786555,0.00016658717,0.00006537418,0.0006787531,0.00040691555,0.00023103945],"category_scores_gemma":[0.66285944,0.00016210534,0.00028756663,0.00029024683,0.0026078087,0.00023483323,0.0006257729,0.00087947166,5.378539e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.046391353,0.019023485,0.13302107,0.0042187218,0.00023334238,0.000029114948,0.0008060846,0.0000057161847,0.0038651177,0.026884414,0.002353184,0.7631684],"study_design_scores_gemma":[0.036739483,0.00419836,0.017719768,0.0017012623,0.00012077582,3.0336443e-7,0.00006479455,0.0014163903,0.012544171,0.92475903,0.00044909675,0.00028659185],"about_ca_topic_score_codex":0.001068904,"about_ca_topic_score_gemma":0.0005704527,"teacher_disagreement_score":0.8978746,"about_ca_system_score_codex":0.00011253251,"about_ca_system_score_gemma":0.00063017866,"threshold_uncertainty_score":0.960858},"labels":[],"label_agreement":null},{"id":"W2606817843","doi":"","title":"Geographical Distribution and Trends of Clinical Trial Recruitment Sites in Developing and Developed Countries","year":2017,"lang":"en","type":"article","venue":"Journal of health informatics in developing countries","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Clinical trial; Geography; Distribution (mathematics); China; Demography; Medicine; Socioeconomics; Internal medicine","score_opus":0.6694972395972644,"score_gpt":0.6147420041857606,"score_spread":0.05475523541150373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606817843","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8976924,0.0005463196,0.086427495,0.01277704,0.0014136251,0.0009511303,0.000078396006,0.000016322587,0.000097257514],"genre_scores_gemma":[0.10171417,0.01859385,0.8785989,0.0008518903,0.0001817989,0.000024594392,0.000005295251,0.000020682144,0.000008807532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9881768,0.0008481609,0.009489979,0.00018888866,0.0007973752,0.0004987784],"domain_scores_gemma":[0.9733069,0.018900443,0.0066871047,0.00035020453,0.0005817962,0.0001735862],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034293365,0.00028279176,0.0021495302,0.00048022458,0.0003399616,0.0002077567,0.00043249674,0.00034265613,0.000008994602],"category_scores_gemma":[0.07895729,0.00022987911,0.00010258314,0.00029312796,0.0008143326,0.00057517225,0.0002933178,0.0007103017,6.254448e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011605947,0.00024036488,0.3016544,0.0049104113,0.00025539502,0.00003459216,0.0048864014,0.000002562316,1.7515151e-7,0.53615236,0.0014998128,0.13875756],"study_design_scores_gemma":[0.042581033,0.0013851369,0.51038086,0.005657324,0.00007909469,0.00009448914,0.00066272327,0.00036084888,0.00005079989,0.40681824,0.03129945,0.00063000235],"about_ca_topic_score_codex":0.000024911322,"about_ca_topic_score_gemma":0.00012820325,"teacher_disagreement_score":0.79597825,"about_ca_system_score_codex":0.00026831395,"about_ca_system_score_gemma":0.001599707,"threshold_uncertainty_score":0.9943982},"labels":[],"label_agreement":null},{"id":"W2609113350","doi":"10.5539/ijsp.v6n3p204","title":"A New Margin Function for Anti-infective Trials","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Comisión de Operación y Fomento de Actividades Académicas, Instituto Politécnico Nacional; Consejo Nacional de Ciencia y Tecnología","keywords":"Margin (machine learning); Context (archaeology); Food and drug administration; Clinical trial; Medicine; Sample size determination; Selection (genetic algorithm); Drug trial; Statistics; Computer science; Medical physics; Mathematics; Machine learning; Risk analysis (engineering); Geography; Pathology","score_opus":0.5299838594816128,"score_gpt":0.5780388171269906,"score_spread":0.048054957645377816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609113350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008919566,0.000025815516,0.9856888,0.0010356603,0.0028726838,0.00043271307,0.0007658154,0.0000065919053,0.00025234665],"genre_scores_gemma":[0.09752099,0.000057641366,0.9011984,0.00004592213,0.0010867945,0.000007392985,0.0000018071298,0.000011902947,0.00006912962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975105,0.00040620216,0.0013584292,0.00018225648,0.00041707625,0.00012554109],"domain_scores_gemma":[0.95920926,0.037054546,0.0020337054,0.00022549446,0.0013288514,0.00014815715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009975618,0.00012688183,0.0007099885,0.00005751655,0.0001294322,0.00024729507,0.00035941106,0.00009046946,0.00020411848],"category_scores_gemma":[0.30483478,0.000095610616,0.00017286479,0.000015586054,0.0001470851,0.00015643727,0.00008598534,0.0001915892,0.0000014172459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013700563,0.00016491355,0.004434908,0.00008238763,0.0005279314,0.000010719098,0.0000648573,0.0000026211017,0.00013153342,0.7120008,0.00921412,0.27199516],"study_design_scores_gemma":[0.0022523075,0.00039264094,0.034507558,0.00007206545,0.00020788691,0.000016149792,0.000007744245,0.0001561419,0.00017089005,0.96027845,0.0018452739,0.00009286954],"about_ca_topic_score_codex":0.000022634707,"about_ca_topic_score_gemma":0.000011200148,"teacher_disagreement_score":0.29485914,"about_ca_system_score_codex":0.00006392787,"about_ca_system_score_gemma":0.00017961544,"threshold_uncertainty_score":0.7010209},"labels":[],"label_agreement":null},{"id":"W2614396497","doi":"10.1177/2168479017700679","title":"Reference Limits for Outlier Analyses in Randomized Clinical Trials","year":2017,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"inVentiv Health Clinical","funders":"Eli Lilly and Company","keywords":"Percentile; Outlier; Confidence interval; Statistics; Clinical trial; Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.933678491744073,"score_gpt":0.7282545952392478,"score_spread":0.20542389650482518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614396497","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40049183,0.000105907675,0.5809165,0.0026500328,0.003808002,0.0053297565,0.000046981026,0.0001709707,0.006479981],"genre_scores_gemma":[0.7263279,0.00001683631,0.2722126,0.00060375885,0.0002719122,0.00016102935,0.000001188611,0.000020965774,0.00038380222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886995,0.0044362345,0.0046263216,0.00081881514,0.00090664986,0.0005124787],"domain_scores_gemma":[0.7859482,0.20318763,0.0055793244,0.0029446373,0.0021584642,0.00018173497],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21557339,0.00025311337,0.0023900082,0.0004940772,0.0005984173,0.00032133787,0.0014083182,0.00025838663,0.00010437689],"category_scores_gemma":[0.6255826,0.00018149274,0.0003055428,0.0009719965,0.003673753,0.0004508749,0.000122013436,0.00036462757,0.000016257558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061039613,0.00014073255,0.0005068059,0.000028840816,0.00007020587,7.973944e-7,0.00007416922,0.0000023746575,0.0059849834,0.85710067,0.000099595774,0.12988684],"study_design_scores_gemma":[0.03700267,0.00008485644,0.01438256,0.000086785665,0.00013121871,7.962168e-7,0.000036918194,0.0025976514,0.0035205516,0.94163734,0.00028097825,0.00023767394],"about_ca_topic_score_codex":0.000008144114,"about_ca_topic_score_gemma":0.000005043685,"teacher_disagreement_score":0.41000918,"about_ca_system_score_codex":0.00008807935,"about_ca_system_score_gemma":0.0005539828,"threshold_uncertainty_score":0.9990377},"labels":[],"label_agreement":null},{"id":"W2616229279","doi":"10.1371/journal.pone.0177785","title":"Feasibility study of TSPO quantification with [18F]FEPPA using population-based input function","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University of Toronto; Centre for Addiction and Mental Health","funders":"National Institute of Mental Health; Canadian Institutes of Health Research","keywords":"Function (biology); Population; Chemistry; Medicine; Biology; Cell biology; Environmental health","score_opus":0.8490679195996129,"score_gpt":0.5658021164938113,"score_spread":0.28326580310580163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616229279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9206882,0.000001969158,0.077727556,0.000056359917,0.000088784196,0.001238573,0.000022922353,0.000048890826,0.00012675178],"genre_scores_gemma":[0.655854,2.3607828e-7,0.34401932,0.000008168039,0.00006221988,0.000019604795,0.00000235003,0.000017384027,0.000016720678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975906,0.0005565658,0.00074656407,0.00035936266,0.00060601323,0.00014091794],"domain_scores_gemma":[0.99060977,0.0066622007,0.00094264525,0.0013672303,0.00035330976,0.000064859305],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022591804,0.00013372407,0.000568879,0.000055978704,0.00024503816,0.000055034518,0.00022635635,0.00007950618,0.00011548912],"category_scores_gemma":[0.050586507,0.000110770656,0.000045251643,0.00009417909,0.00009389031,0.00010597541,0.000041734602,0.00015768166,0.0000057016946],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012940364,0.016835965,0.9668725,0.0005670096,0.00033731596,0.000002261636,0.0001138507,0.000059517653,0.007231588,0.005702072,0.000008049771,0.00097584684],"study_design_scores_gemma":[0.0027538538,0.0010076719,0.7762738,0.00038144106,0.0011304024,1.8552544e-7,0.00011920167,0.008836132,0.005418546,0.20386454,1.9986558e-7,0.00021401956],"about_ca_topic_score_codex":0.00023751838,"about_ca_topic_score_gemma":0.00011271526,"teacher_disagreement_score":0.26629177,"about_ca_system_score_codex":0.000056281042,"about_ca_system_score_gemma":0.000047013284,"threshold_uncertainty_score":0.9574108},"labels":[],"label_agreement":null},{"id":"W2616530926","doi":"10.1016/j.conctc.2017.05.005","title":"Sharing some interim data in trial monitoring can mislead or unmask trial investigators: A scenario-based survey of trial experts","year":2017,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"Canadian Institutes of Health Research","keywords":"Interim; Interim analysis; Event (particle physics); Placebo; Clinical trial; Psychology; Medicine; Computer science; Econometrics; Statistics; Mathematics; Alternative medicine; Internal medicine; Political science; Law","score_opus":0.9806808221974505,"score_gpt":0.73176877105737,"score_spread":0.24891205114008041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616530926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9039925,0.0012680743,0.005481577,0.012899106,0.031710796,0.036342017,0.0057280366,0.0006103741,0.0019675582],"genre_scores_gemma":[0.8372923,0.00046455776,0.15722999,0.0002477412,0.0032640966,0.00095424516,0.00023141349,0.00015753874,0.00015812238],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9287307,0.049121063,0.018122075,0.001989479,0.0012091963,0.0008274789],"domain_scores_gemma":[0.29316592,0.6569112,0.0141740525,0.033698194,0.00088190474,0.0011687069],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16372141,0.00074567023,0.006358258,0.00036957112,0.00069413666,0.0005069633,0.014317429,0.0011396651,0.000114004375],"category_scores_gemma":[0.9055377,0.00061578467,0.00097293564,0.0004956271,0.0027373242,0.0008389423,0.0058575966,0.0019955868,0.0000124935705],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.96789765,0.006089183,0.010927376,0.00013884183,0.00053184223,0.000022869332,0.00015639,7.6305025e-7,0.00004866322,0.0036976524,0.002703973,0.0077848206],"study_design_scores_gemma":[0.887219,0.0041006324,0.0020538839,0.0017033556,0.00033252407,5.9808366e-7,0.00014023074,0.0012096273,0.00021670252,0.101339266,0.00086977397,0.00081436813],"about_ca_topic_score_codex":0.0028931121,"about_ca_topic_score_gemma":0.001104816,"teacher_disagreement_score":0.7418163,"about_ca_system_score_codex":0.00015762898,"about_ca_system_score_gemma":0.0034634497,"threshold_uncertainty_score":0.99997663},"labels":[],"label_agreement":null},{"id":"W2620592310","doi":"10.1515/cttr-2017-0008","title":"Analysis of the Effect of Multiple Testing in Assessing Tobacco Product Differences","year":2017,"lang":"en","type":"article","venue":"Beiträge zur Tabakforschung international","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bonferroni correction; Type I and type II errors; Multiple comparisons problem; Statistical power; Null hypothesis; Statistical hypothesis testing; Null (SQL); Statistics; Product type; Computer science; Econometrics; Alternative hypothesis; Product (mathematics); Mathematics; Data mining","score_opus":0.45794994001306577,"score_gpt":0.5563287913655769,"score_spread":0.09837885135251112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620592310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907633,0.000010304447,0.004420721,0.00015565296,0.00088153005,0.00034145112,0.00008994377,0.000015719394,0.0033213699],"genre_scores_gemma":[0.8886448,0.0000014956295,0.111104645,0.00000619042,0.00012610343,0.00002337958,0.0000018685661,0.000012515247,0.00007896116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99717396,0.00052470976,0.0011522956,0.00032177483,0.0006331679,0.00019410772],"domain_scores_gemma":[0.9628935,0.0345344,0.0015269818,0.0007597732,0.00024760852,0.000037767542],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037417228,0.00016759541,0.0008331558,0.00020097874,0.00012113423,0.00009276605,0.0011439066,0.000080102065,0.00009192654],"category_scores_gemma":[0.32849172,0.00010744224,0.0002979818,0.00035780415,0.00028216373,0.00019695956,0.00037814683,0.0002490872,0.0000011418498],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004927637,0.000085186926,0.98074645,0.000057344456,0.00045150646,0.0000017287318,0.00004428889,0.00004663078,0.0019421106,0.0037328082,0.000017526385,0.012825165],"study_design_scores_gemma":[0.0007490029,0.000046259887,0.9584295,0.00031833787,0.00046126757,8.722812e-7,0.000018792862,0.012780749,0.012229295,0.014847853,0.000005776854,0.00011225469],"about_ca_topic_score_codex":0.00022324502,"about_ca_topic_score_gemma":0.00014208778,"teacher_disagreement_score":0.32475,"about_ca_system_score_codex":0.000046464556,"about_ca_system_score_gemma":0.000045308094,"threshold_uncertainty_score":0.6771647},"labels":[],"label_agreement":null},{"id":"W2620799017","doi":"10.1111/bmsp.12103","title":"<scp>ANOVA</scp> and the variance homogeneity assumption: Exploring a better gatekeeper","year":2017,"lang":"en","type":"article","venue":"British Journal of Mathematical and Statistical Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Homogeneity (statistics); Analysis of variance; F-test of equality of variances; Null hypothesis; Statistics; Mathematics; Levene's test; One-way analysis of variance; Equivalence (formal languages); Statistical hypothesis testing; Variance (accounting); Econometrics; Mixed-design analysis of variance; Population variance; Population; Test statistic; Demography; Discrete mathematics","score_opus":0.4557394537833383,"score_gpt":0.5102854334071317,"score_spread":0.05454597962379343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620799017","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14614898,0.0005507852,0.84445906,0.0035035328,0.0007243465,0.0003628835,0.00009386559,0.000023410938,0.004133147],"genre_scores_gemma":[0.12042548,0.001467063,0.8758939,0.0010985973,0.0008085318,0.000044824912,5.447311e-7,0.00004908578,0.0002120119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959061,0.0011371337,0.0015917497,0.00040619227,0.0005006839,0.0004581281],"domain_scores_gemma":[0.9511646,0.04692145,0.0008096529,0.0005083604,0.00023204797,0.00036387658],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.007023971,0.00025080223,0.0012925473,0.000047924666,0.0005870883,0.00042027206,0.0005672998,0.0002235423,0.00043796934],"category_scores_gemma":[0.14463721,0.00018096923,0.00015735583,0.000050762326,0.0028913228,0.0002111681,0.0002459436,0.00094207196,0.00003019243],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019794193,0.00035880628,0.00035019874,0.00027785898,0.00024583968,0.0008252288,0.00018074691,8.320208e-8,0.000045003417,0.8660449,0.008514993,0.12295843],"study_design_scores_gemma":[0.0040667127,0.00020618149,0.022372559,0.00031996437,0.0002523027,0.004559471,0.00004850178,0.0001393582,0.000013174567,0.9669433,0.0009742418,0.00010419202],"about_ca_topic_score_codex":0.0000069976054,"about_ca_topic_score_gemma":0.0000035697133,"teacher_disagreement_score":0.13761324,"about_ca_system_score_codex":0.000013585396,"about_ca_system_score_gemma":0.000025159274,"threshold_uncertainty_score":0.99982226},"labels":[],"label_agreement":null},{"id":"W2621276102","doi":"10.1007/s40264-017-0549-7","title":"Using Simulated Data to Assess Case-Crossover Designs for Studying Less Transient Effects of Drugs","year":2017,"lang":"en","type":"letter","venue":"Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Transient (computer programming); Crossover study; Crossover; Pharmacology; Intensive care medicine; Artificial intelligence; Alternative medicine; Pathology","score_opus":0.8589573799309084,"score_gpt":0.6137502789181453,"score_spread":0.2452071010127631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621276102","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054119476,0.00005134966,0.9623951,0.013353101,0.0036746007,0.0070011704,0.007822213,0.00011967237,0.00017085967],"genre_scores_gemma":[0.0077568525,0.000007867094,0.9675758,0.020890808,0.0028128272,0.00004470125,0.00018397073,0.00032695578,0.00040020834],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9929187,0.0020172573,0.0020416419,0.0013448398,0.000866555,0.00081094966],"domain_scores_gemma":[0.8191245,0.17587793,0.0011436929,0.0033331832,0.00036443095,0.00015627123],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007652702,0.0006797583,0.0026098278,0.00015162253,0.0004229073,0.00015658993,0.001988029,0.0009615836,0.000034841938],"category_scores_gemma":[0.08376496,0.00061074825,0.00040053212,0.00016559118,0.00024237335,0.00015267792,0.00072122423,0.0014126633,0.0000058616783],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020691527,0.0010218933,0.00003201845,0.03229389,0.0035152687,0.008718102,0.0044504954,0.0011922441,0.00097153685,0.0017476216,0.91907316,0.02491462],"study_design_scores_gemma":[0.0456186,0.0014005327,0.00013527855,0.027481994,0.027480403,0.0006208133,0.0012342468,0.085230514,0.011188737,0.4276407,0.36102575,0.010942406],"about_ca_topic_score_codex":0.00013999082,"about_ca_topic_score_gemma":0.000010534121,"teacher_disagreement_score":0.5580474,"about_ca_system_score_codex":0.00019223786,"about_ca_system_score_gemma":0.0002382383,"threshold_uncertainty_score":0.9996344},"labels":[],"label_agreement":null},{"id":"W2623675967","doi":"10.22237/jmasm/1146456300","title":"Multiple Comparison Procedures, Trimmed Means And Transformed Statistics","year":2006,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Truncated mean; Mathematics; Statistics; Pairwise comparison; Heteroscedasticity; Robust statistics; Statistical hypothesis testing; Type I and type II errors; Normality; Estimator","score_opus":0.3306211837292218,"score_gpt":0.5463877821994243,"score_spread":0.21576659847020252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623675967","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077178184,0.00029600377,0.99514747,0.00018382017,0.0003901207,0.00068577676,0.0005815776,0.00005700854,0.0018864354],"genre_scores_gemma":[0.10240288,0.00005005317,0.8968649,0.00010405195,0.0003987557,0.000029750197,0.0000076236374,0.00008708451,0.000054926117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924629,0.0017680757,0.0035560052,0.00050147396,0.0010374407,0.00067414105],"domain_scores_gemma":[0.88772464,0.10994606,0.0011763482,0.00031961373,0.0003698852,0.00046345618],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0082435915,0.00048607317,0.002157568,0.00021124548,0.00016220493,0.00011324972,0.0004010594,0.00035066332,0.00017244792],"category_scores_gemma":[0.06643675,0.00038767842,0.00016283871,0.0002448191,0.0005707953,0.000088139845,0.00007412366,0.0010827645,0.000004719721],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013536238,0.0007302824,0.00021561839,0.0004732712,0.00017578616,0.000046230605,0.00021416652,0.00004645411,0.0054483614,0.6225259,0.0058548125,0.36291555],"study_design_scores_gemma":[0.0041106055,0.0004068764,0.001927504,0.000079470985,0.000586375,0.000073289644,0.0000808044,0.01959216,0.002876589,0.9690522,0.00079837063,0.00041573474],"about_ca_topic_score_codex":0.000011113825,"about_ca_topic_score_gemma":0.00002251725,"teacher_disagreement_score":0.3624998,"about_ca_system_score_codex":0.00012072127,"about_ca_system_score_gemma":0.00026739933,"threshold_uncertainty_score":0.9998575},"labels":[],"label_agreement":null},{"id":"W2624012514","doi":"10.1186/s13063-017-1995-3","title":"A comparison of approaches for adjudicating outcomes in clinical trials","year":2017,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Robarts Clinical Trials","funders":"","keywords":"Adjudication; Outcome (game theory); Medicine; Statistics; Range (aeronautics); Mathematics; Law; Political science","score_opus":0.9840235320840289,"score_gpt":0.7880445275755948,"score_spread":0.19597900450843408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624012514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3508222,0.00032891775,0.6031937,0.0052690865,0.00795865,0.023350185,0.0013236305,0.0002405066,0.0075131403],"genre_scores_gemma":[0.38003835,0.000010942604,0.61891097,0.000026707155,0.00055111933,0.00033195142,0.0000017041973,0.000031807736,0.00009642945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96363175,0.018571232,0.016057104,0.00071198586,0.00054489536,0.0004830251],"domain_scores_gemma":[0.22265904,0.7632227,0.011958269,0.0018217539,0.0001561069,0.00018213109],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2740973,0.00026669653,0.008904374,0.00010578969,0.00015175495,0.00008957997,0.00096580957,0.00031397142,0.00013077684],"category_scores_gemma":[0.9685236,0.00018851121,0.0014024528,0.00006565655,0.00041988664,0.00008263023,0.00020731265,0.00036992662,0.000010427802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030675477,0.0026794756,0.17734818,0.00065121474,0.000884306,0.0000042272336,0.00028610817,0.0000044059734,0.00023009379,0.40780744,0.0039264057,0.4031106],"study_design_scores_gemma":[0.009995652,0.00033018264,0.019380908,0.00020414575,0.0005343345,3.9339452e-7,0.00012372625,0.0010372034,0.0017890624,0.9661986,0.00017294133,0.00023284732],"about_ca_topic_score_codex":0.000021143622,"about_ca_topic_score_gemma":0.000022097389,"teacher_disagreement_score":0.7446515,"about_ca_system_score_codex":0.00002578672,"about_ca_system_score_gemma":0.00011335558,"threshold_uncertainty_score":0.7687264},"labels":[],"label_agreement":null},{"id":"W267145578","doi":"10.22237/jmasm/1146456060","title":"Confidence Intervals For An Effect Size When Variances Are Not Equal","year":2006,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Mathematics; Statistics; Confidence interval; Robust confidence intervals; CDF-based nonparametric confidence interval; Econometrics; Credible interval","score_opus":0.47460601032463207,"score_gpt":0.5929059697711583,"score_spread":0.11829995944652621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W267145578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005107903,0.00007204508,0.99506503,0.00024132548,0.00093592843,0.00094543817,0.00041913227,0.00006233462,0.0017479857],"genre_scores_gemma":[0.08381053,0.0000060996426,0.9143294,0.0003597368,0.0012313523,0.00009181964,0.000002084118,0.00008944557,0.000079543555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9900417,0.004581708,0.0031216207,0.00061601395,0.0009616037,0.00067739014],"domain_scores_gemma":[0.70793617,0.28911167,0.0016938604,0.0004530312,0.00043510812,0.0003701747],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025602615,0.0004899888,0.0024126857,0.00011525562,0.00014718974,0.00018300602,0.0008015903,0.00037660563,0.0003617239],"category_scores_gemma":[0.1776193,0.00037210426,0.00036679325,0.00013707127,0.00042731423,0.00016429425,0.00011727019,0.0008443932,0.000007636541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026222256,0.0004212788,0.0000137989,0.0004105498,0.00016371724,0.000031293053,0.000090834124,0.000036379653,0.013283018,0.8016207,0.002619972,0.17868623],"study_design_scores_gemma":[0.0029560472,0.0016605248,0.00030382682,0.00017583932,0.00060773594,0.000042723117,0.000028766031,0.007618338,0.0112602115,0.9746025,0.00033540398,0.00040808812],"about_ca_topic_score_codex":0.000009675737,"about_ca_topic_score_gemma":0.0000046247915,"teacher_disagreement_score":0.28452998,"about_ca_system_score_codex":0.00012209213,"about_ca_system_score_gemma":0.0001315522,"threshold_uncertainty_score":0.9998731},"labels":[],"label_agreement":null},{"id":"W2692859861","doi":"10.3324/haematol.2017.168815","title":"Center-level variation in accuracy of adverse event reporting in a clinical trial for pediatric acute myeloid leukemia: a report from the Children’s Oncology Group","year":2017,"lang":"en","type":"letter","venue":"Haematologica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute","keywords":"Medicine; Adverse effect; Myeloid leukemia; Clinical trial; Oncology; Internal medicine; Event (particle physics); Pediatric oncology; Center (category theory); Pediatrics; Cancer","score_opus":0.5675975619002257,"score_gpt":0.5693340134520334,"score_spread":0.0017364515518076828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2692859861","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69677544,0.00018948225,0.10817607,0.14308268,0.017523605,0.028841002,0.004305592,0.0002933078,0.0008128383],"genre_scores_gemma":[0.03568246,0.00054540875,0.9128032,0.030455297,0.016075274,0.0032465926,0.00077163236,0.00021872274,0.00020145018],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9757267,0.0050472445,0.015877685,0.0016984997,0.0008113231,0.00083849725],"domain_scores_gemma":[0.77740777,0.19251643,0.027610263,0.0021472762,0.00022724945,0.0000910374],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.027759617,0.0006372075,0.0049075987,0.00021130314,0.0001470917,0.000036756104,0.0014945624,0.0036993586,0.000098968085],"category_scores_gemma":[0.69393206,0.00043639357,0.0013581006,0.00022554015,0.00033798767,0.0001073893,0.00063025934,0.0040920586,0.000010208126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.046256952,0.005718794,0.10068389,0.001736607,0.0023347922,0.043439943,0.0008867104,0.000003971173,0.000009896277,0.0057888576,0.77313524,0.020004315],"study_design_scores_gemma":[0.073875844,0.0017544153,0.12998994,0.0007473717,0.0023080658,0.001089236,0.00003393387,0.00011949434,0.000008727001,0.7783873,0.0106585575,0.0010271318],"about_ca_topic_score_codex":0.00039807937,"about_ca_topic_score_gemma":0.00016386286,"teacher_disagreement_score":0.8046271,"about_ca_system_score_codex":0.00046858037,"about_ca_system_score_gemma":0.0010208472,"threshold_uncertainty_score":0.9998088},"labels":[],"label_agreement":null},{"id":"W2726694079","doi":"10.22237/jmasm/1288584600","title":"A Flexible Method for Testing Independence in Two-Way Contingency Tables","year":2010,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Contingency table; Mathematics; Ordinal data; Independence (probability theory); Statistics; Ordinal regression; Ordinal optimization; Simple (philosophy); Association (psychology); Econometrics; Psychology","score_opus":0.4627845410539772,"score_gpt":0.6170332364692402,"score_spread":0.15424869541526304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726694079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074092206,0.000044943754,0.9930604,0.00013458884,0.0010647249,0.00086700637,0.00015232962,0.000052729916,0.0038823148],"genre_scores_gemma":[0.017672194,0.0000047827734,0.98122025,0.00016852518,0.0006770505,0.000103990125,0.0000011252628,0.00009707401,0.000054989294],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99211204,0.0020901677,0.0034092313,0.00062943465,0.0009165123,0.0008426236],"domain_scores_gemma":[0.71062124,0.2860341,0.0015841955,0.0005109201,0.0007862906,0.0004632455],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042231772,0.00043263077,0.0019885716,0.0003191295,0.00013340221,0.000115669915,0.00077115407,0.00037576378,0.00031148602],"category_scores_gemma":[0.3591644,0.0003583147,0.00022231827,0.0005106825,0.00026809066,0.00012822775,0.00017452548,0.0023577192,0.0000042017464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000400756,0.00024073203,0.00010140098,0.00014253856,0.000056793564,0.000021792262,0.000105304694,0.000040748255,0.07354331,0.44121286,0.00015534436,0.48397842],"study_design_scores_gemma":[0.0031106826,0.00025626578,0.0003683424,0.00010749519,0.00023297926,0.00008668949,0.00005526374,0.037095964,0.013532949,0.9444528,0.00032830014,0.00037222248],"about_ca_topic_score_codex":0.000021183745,"about_ca_topic_score_gemma":0.000026110707,"teacher_disagreement_score":0.50324,"about_ca_system_score_codex":0.00008606377,"about_ca_system_score_gemma":0.00033197086,"threshold_uncertainty_score":0.99994385},"labels":[],"label_agreement":null},{"id":"W2732894280","doi":"10.1371/journal.pbio.2002212","title":"Can cancer researchers accurately judge whether preclinical reports will reproduce?","year":2017,"lang":"en","type":"article","venue":"PLoS Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Replication (statistics); Pace; Optimism; Biology; Cancer; Cognitive psychology; Psychology; Statistics; Computer science; Data science; Social psychology; Mathematics","score_opus":0.8966954757372453,"score_gpt":0.6814503299149918,"score_spread":0.21524514582225351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732894280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85205233,0.00070259784,0.0029836127,0.090611145,0.009178306,0.0038525537,0.0006364943,0.000676013,0.039306965],"genre_scores_gemma":[0.6652522,0.00048253482,0.3245658,0.0009768,0.002794384,0.00047244,0.000006900495,0.00013092425,0.0053179907],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99477637,0.0017837272,0.0013135726,0.001175823,0.00028710064,0.0006634357],"domain_scores_gemma":[0.9682922,0.027043317,0.001016747,0.0030332548,0.00032075236,0.00029372977],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075808,0.00024568243,0.0009639082,0.00005131613,0.0003097743,0.00008362895,0.0008236825,0.0005493701,0.0016125878],"category_scores_gemma":[0.5132942,0.00018449302,0.00017767205,0.000069374066,0.0011391622,0.000088069086,0.0005524986,0.0007904748,0.000048502356],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024583894,0.0035404467,0.35359272,0.00094090693,0.003150496,0.0012695149,0.0012705823,0.0000018880912,0.04175447,0.24955179,0.09496996,0.24749885],"study_design_scores_gemma":[0.00051424187,0.00024241842,0.006283748,0.000093832045,0.00010253995,0.00001285284,0.000013008736,0.000025644067,0.0054267296,0.979056,0.007964864,0.00026410722],"about_ca_topic_score_codex":0.0003284287,"about_ca_topic_score_gemma":0.00021402258,"teacher_disagreement_score":0.7295042,"about_ca_system_score_codex":0.00008149531,"about_ca_system_score_gemma":0.00024391925,"threshold_uncertainty_score":0.99930006},"labels":[],"label_agreement":null},{"id":"W2737529060","doi":"10.1136/jclinpath-2017-204520","title":"Improving validation methods for molecular diagnostics: application of Bland-Altman, Deming and simple linear regression analyses in assay comparison and evaluation for next-generation sequencing","year":2017,"lang":"en","type":"article","venue":"Journal of Clinical Pathology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Princess Margaret Cancer Foundation; Genome Canada","keywords":"Linear regression; Simple linear regression; Simple (philosophy); Computer science; Computational biology; Data mining; Statistics; Medicine; Biology; Mathematics; Machine learning","score_opus":0.8698920011840419,"score_gpt":0.7294773631251671,"score_spread":0.14041463805887477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737529060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35546243,0.00024154424,0.64333653,0.00013173258,0.00023341409,0.0005781021,0.000008818326,0.0000029780344,0.000004454336],"genre_scores_gemma":[0.42931142,0.000103859085,0.57022536,0.000025778569,0.0002852574,0.00003165216,0.0000044496255,0.000011642991,5.498961e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932415,0.0029508977,0.0030831487,0.00032152332,0.000235741,0.00016719529],"domain_scores_gemma":[0.9106751,0.08319627,0.0047727586,0.0003305399,0.00092615094,0.00009914743],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042471174,0.0001413652,0.0012186698,0.00013219476,0.00013882735,0.000050587867,0.00017942437,0.0003583632,0.0000019271506],"category_scores_gemma":[0.5196288,0.000112017435,0.00017648326,0.00005011307,0.00018810692,0.00019897337,0.00007872755,0.00030702376,7.156736e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044317052,0.00015827849,0.017077364,0.00028794134,0.0000669893,0.000003373038,0.00015592626,0.0002928497,0.16313176,0.0036694498,0.000032992906,0.8146799],"study_design_scores_gemma":[0.0028509973,0.0007013846,0.0045855716,0.00013157124,0.0006147238,0.000010633541,0.000081356695,0.5359199,0.034083996,0.42088038,0.000022759375,0.000116722316],"about_ca_topic_score_codex":0.0000090522035,"about_ca_topic_score_gemma":0.000011589303,"teacher_disagreement_score":0.81456316,"about_ca_system_score_codex":0.000044933982,"about_ca_system_score_gemma":0.000113601265,"threshold_uncertainty_score":0.9859774},"labels":[],"label_agreement":null},{"id":"W2738359971","doi":"10.1007/s10957-017-1139-7","title":"Optimal Timing to Initiate Medical Treatment for a Disease Evolving as a Semi-Markov Process","year":2017,"lang":"en","type":"article","venue":"Journal of Optimization Theory and Applications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Theory of computation; Mathematics; Process (computing); Markov process; Markov decision process; Mathematical optimization; Markov chain; Calculus (dental); Applied mathematics; Computer science; Medicine; Algorithm; Statistics","score_opus":0.2880180947609726,"score_gpt":0.5617737587265674,"score_spread":0.2737556639655948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738359971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020954534,0.00004999528,0.9950666,0.0012004104,0.00007514695,0.0007795738,0.00004202076,0.000015868894,0.00067496736],"genre_scores_gemma":[0.093072265,0.000119991484,0.90534467,0.00027377493,0.00054291036,0.0003931848,0.0000024453188,0.000029127794,0.000221619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984953,0.00022065212,0.00068939145,0.00018431987,0.00026228276,0.00014806566],"domain_scores_gemma":[0.98575306,0.012321952,0.0007310458,0.00031085793,0.00041186708,0.0004712381],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002967459,0.00012908663,0.00035391602,0.00007226378,0.00047360876,0.00014281782,0.00030500855,0.000081256825,0.0002461918],"category_scores_gemma":[0.060434792,0.00009928583,0.00011059349,0.00006176987,0.00012684212,0.00017430387,0.000051756044,0.000107560125,0.0000025131287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033534747,0.0014862177,0.00027274774,0.00041110464,0.0004444129,0.00003330317,0.0010833931,0.02636348,0.000040342944,0.84247583,0.0006986204,0.123337045],"study_design_scores_gemma":[0.0014676285,0.00028017245,0.000048936272,0.00023732663,0.00033322492,0.000026461545,0.00013214393,0.024382623,0.00013854554,0.9723593,0.00044476482,0.00014884872],"about_ca_topic_score_codex":4.5680585e-7,"about_ca_topic_score_gemma":2.0650702e-7,"teacher_disagreement_score":0.12988347,"about_ca_system_score_codex":0.000038345464,"about_ca_system_score_gemma":0.00019970565,"threshold_uncertainty_score":0.94747955},"labels":[],"label_agreement":null},{"id":"W2739089105","doi":"10.22237/jmasm/1430453100","title":"Per Family or Familywise Type I Error Control: \"Eether, Eyether, Neether, Nyther, Let's Call the Whole Thing Off!\"","year":2015,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Type I and type II errors; False discovery rate; Multiple comparisons problem; Statistics; Mathematics; Context (archaeology); Word error rate; Computer science; Biology; Artificial intelligence; Genetics","score_opus":0.5655361585975405,"score_gpt":0.574170741845323,"score_spread":0.008634583247782546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739089105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012473544,0.0014306706,0.9865324,0.0013832918,0.0021531389,0.0009959864,0.00017320283,0.000110655994,0.0059733125],"genre_scores_gemma":[0.016906181,0.00013563037,0.97768825,0.0030306764,0.0012277254,0.000050208313,0.0000019885576,0.00023780894,0.00072153244],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9848088,0.007925451,0.0034600727,0.0007253059,0.0020197714,0.0010605857],"domain_scores_gemma":[0.8753403,0.1194513,0.0018256673,0.0011550352,0.0011832629,0.001044458],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031815033,0.0007840159,0.002581827,0.00019044794,0.00023239704,0.00023797942,0.0015557748,0.0006366665,0.0004482377],"category_scores_gemma":[0.11368562,0.00044819753,0.00042825998,0.00048073565,0.000908654,0.00017287531,0.0002709326,0.002503328,0.000117722346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0100701535,0.0010859572,0.00002934919,0.00017526312,0.0011406378,0.00022881998,0.0032071674,0.0005057007,0.016559836,0.18444343,0.03614641,0.7464073],"study_design_scores_gemma":[0.0059022238,0.0010390981,0.00014555689,0.00011198838,0.00091116613,0.0001061389,0.00113374,0.013366031,0.00019899364,0.9484024,0.02807662,0.00060601346],"about_ca_topic_score_codex":0.000018758554,"about_ca_topic_score_gemma":0.000006043958,"teacher_disagreement_score":0.763959,"about_ca_system_score_codex":0.00028293265,"about_ca_system_score_gemma":0.00082007475,"threshold_uncertainty_score":0.99979794},"labels":[],"label_agreement":null},{"id":"W2743251916","doi":"10.1177/0141076817721131","title":"The history and development of N-of-1 trials","year":2017,"lang":"en","type":"article","venue":"Journal of the Royal Society of Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":146,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; McMaster University","funders":"","keywords":"Data science; Computer science; World Wide Web; Medicine","score_opus":0.6698808734972078,"score_gpt":0.5654760536393612,"score_spread":0.10440481985784666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743251916","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4365905,0.034416836,0.363587,0.11591292,0.03631427,0.0032289273,0.000063978565,0.000028283917,0.009857301],"genre_scores_gemma":[0.08886833,0.0006289476,0.9082926,0.00017360116,0.00092355744,0.0000017403588,3.8575937e-8,0.000017401579,0.001093792],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99624634,0.00064377167,0.002236166,0.000065570915,0.00070502155,0.00010314084],"domain_scores_gemma":[0.9549699,0.03828664,0.0059290472,0.00040811815,0.0003343529,0.00007197102],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030447302,0.00009290579,0.0011721468,0.000010749139,0.00015404215,0.000003373607,0.0006470292,0.00009394948,0.00009295862],"category_scores_gemma":[0.17514616,0.000038438364,0.000339597,0.00001847652,0.0015594319,0.000017641285,0.00015037418,0.0002802357,1.4123901e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013997424,0.0005043341,0.0031484973,0.001957385,0.0032864863,0.000003127392,0.014148348,0.000007985129,0.0068410435,0.01737138,0.64221203,0.30911964],"study_design_scores_gemma":[0.014978337,0.0012919425,0.033378087,0.0048722764,0.0018676599,0.00001651083,0.0025618994,0.00034164044,0.012529022,0.86253226,0.06537602,0.00025434585],"about_ca_topic_score_codex":0.000010705047,"about_ca_topic_score_gemma":0.0000012533573,"teacher_disagreement_score":0.8451609,"about_ca_system_score_codex":0.00006544995,"about_ca_system_score_gemma":0.00022108763,"threshold_uncertainty_score":0.99835855},"labels":[],"label_agreement":null},{"id":"W2746145072","doi":"10.18433/j39s6z","title":"Analysis of Non-Pivotal Bioequivalence Studies Submitted in Abbreviated New Drug Submissions for Delayed-Release Drug Products","year":2017,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Drug; Cmax; Medicine; Pharmacology; Pharmacokinetics; Generic drug","score_opus":0.6937152983738399,"score_gpt":0.6617007900323524,"score_spread":0.03201450834148756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2746145072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97676027,0.0023484027,0.007662694,0.010310423,0.0015817647,0.000993764,0.00012207493,0.000024741465,0.00019585542],"genre_scores_gemma":[0.8369339,0.0014927888,0.16073376,0.00019392477,0.0004303372,0.000012594039,5.1671924e-7,0.000018477918,0.00018371985],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9942395,0.0007545723,0.002541008,0.0005545541,0.0012310398,0.0006793195],"domain_scores_gemma":[0.97222006,0.023201631,0.002403652,0.0004689694,0.0010262562,0.0006794255],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013872351,0.00033502904,0.0017111757,0.0006090669,0.0004685365,0.00014062632,0.0018589585,0.000057190657,0.0002535562],"category_scores_gemma":[0.103957765,0.00023273098,0.00060909014,0.0016414982,0.0015640691,0.0006424711,0.00032523114,0.0005938937,0.0000035614416],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009639346,0.008590622,0.20263852,0.0035108267,0.014778335,0.0005434959,0.0059815757,0.0014002643,0.18520403,0.017058017,0.06993531,0.48071966],"study_design_scores_gemma":[0.027205182,0.0012394167,0.030154452,0.0019950133,0.026517285,0.00006469199,0.0016816069,0.16192578,0.43688872,0.30018654,0.010094591,0.0020467087],"about_ca_topic_score_codex":0.0001048123,"about_ca_topic_score_gemma":0.00003564536,"teacher_disagreement_score":0.47867295,"about_ca_system_score_codex":0.000103322986,"about_ca_system_score_gemma":0.00062847836,"threshold_uncertainty_score":0.9490494},"labels":[],"label_agreement":null},{"id":"W2746482145","doi":"10.1016/j.conctc.2017.08.003","title":"Sensitivity of adaptive enrichment trial designs to accrual rates, time to outcome measurement, and prognostic variables","year":2017,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; H. Lundbeck A/S; Patient-Centered Outcomes Research Institute; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Accrual; Leverage (statistics); Estimator; Sample size determination; Baseline (sea); Statistics; Population; Computer science; Clinical study design; Econometrics; Clinical trial; Medicine; Mathematics; Internal medicine; Accounting; Economics","score_opus":0.9370810160194082,"score_gpt":0.6566860927908064,"score_spread":0.2803949232286018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2746482145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0397949,0.0008478673,0.8379757,0.0406021,0.004036318,0.046457585,0.003321932,0.00062583655,0.02633776],"genre_scores_gemma":[0.5236098,0.000047637568,0.47481158,0.00042925417,0.00035728174,0.00041730673,0.000006459093,0.000046812467,0.00027388995],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9515554,0.03808837,0.007947281,0.00096643233,0.0009571969,0.00048536505],"domain_scores_gemma":[0.5348004,0.4518236,0.0042120134,0.0068330346,0.0013288993,0.0010020499],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15728988,0.00044660195,0.0036829673,0.00015643072,0.0006671619,0.0002272227,0.0020018874,0.0004148262,0.00012416861],"category_scores_gemma":[0.8507592,0.0003792885,0.00058624335,0.00022692746,0.00089548196,0.00023274112,0.0023781292,0.0007185822,0.00015226341],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17404892,0.023607504,0.055385057,0.0006614147,0.007619105,0.000083418214,0.0011922184,0.000012037424,0.010109126,0.27736762,0.09753979,0.3523738],"study_design_scores_gemma":[0.116798155,0.011075386,0.044032346,0.002209983,0.0027519225,0.0000080080345,0.00026282333,0.0017470011,0.0013167281,0.7990108,0.018341359,0.0024454785],"about_ca_topic_score_codex":0.00007741365,"about_ca_topic_score_gemma":0.00003997887,"teacher_disagreement_score":0.69346935,"about_ca_system_score_codex":0.00008427548,"about_ca_system_score_gemma":0.0005994599,"threshold_uncertainty_score":0.9998659},"labels":[],"label_agreement":null},{"id":"W2749146004","doi":"10.1002/cncr.30919","title":"Drug development for breast, colorectal, and non–small cell lung cancers from 1979 to 2014","year":2017,"lang":"en","type":"article","venue":"Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Western University; University of Calgary","funders":"University of Calgary","keywords":"Medicine; Breast cancer; Colorectal cancer; Oncology; Lung cancer; Internal medicine; Cancer; Clinical trial; Drug development; Drug; Pharmacology","score_opus":0.28176829251449925,"score_gpt":0.5075090988175017,"score_spread":0.22574080630300247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749146004","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83553404,0.00038846396,0.15272303,0.0015010752,0.0030381347,0.0023915078,0.0017313842,0.00007030363,0.0026220782],"genre_scores_gemma":[0.08698633,0.00007305164,0.90944105,0.0004277674,0.0006975239,0.0007600432,0.0000019717104,0.000048608574,0.0015636348],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986281,0.00006657356,0.00041853258,0.00042786766,0.00014803626,0.0003109309],"domain_scores_gemma":[0.9916414,0.0073188487,0.0002562842,0.00042356673,0.00011457534,0.00024534372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008295495,0.00018125463,0.00049433956,0.000023851453,0.00026638468,0.00010152389,0.0003518895,0.000098247896,0.00038883457],"category_scores_gemma":[0.004536236,0.00015847155,0.000057035373,0.000023158898,0.00009732997,0.000041791096,0.00017758552,0.00011773304,0.00002086901],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001662456,0.00021346925,0.035198446,0.0014141598,0.0006052867,0.000018771116,0.00468099,0.000027668204,0.005815742,0.0036920062,0.5552853,0.39138576],"study_design_scores_gemma":[0.012457478,0.00028078054,0.17202239,0.0018935797,0.0011003457,0.0000035265505,0.00040052022,0.00231513,0.12286555,0.59649956,0.08753319,0.002627933],"about_ca_topic_score_codex":0.00058703066,"about_ca_topic_score_gemma":0.0010122205,"teacher_disagreement_score":0.75671804,"about_ca_system_score_codex":0.00023666126,"about_ca_system_score_gemma":0.00031063575,"threshold_uncertainty_score":0.6462282},"labels":[],"label_agreement":null},{"id":"W2749388036","doi":"10.1177/0022034517725049","title":"Impact of Selection Bias on Treatment Effect Size Estimates in Randomized Trials of Oral Health Interventions: A Meta-epidemiological Study","year":2017,"lang":"en","type":"review","venue":"Journal of Dental Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics; University of Alberta","funders":"","keywords":"Selection bias; Meta-analysis; Epidemiology; Randomized controlled trial; Psychological intervention; Medicine; Sample size determination; Oral health; Effect modification; Environmental health; Selection (genetic algorithm); Statistics; Dentistry; Confidence interval; Internal medicine; Computer science; Mathematics; Psychiatry; Pathology","score_opus":0.9859906141623999,"score_gpt":0.8396295782838669,"score_spread":0.146361035878533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749388036","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076722484,0.97808415,0.00088828965,0.000031580068,0.00039732805,0.012621342,0.00025895936,0.000008245147,0.000037842365],"genre_scores_gemma":[0.002802078,0.9369317,0.059576582,0.0000012082081,0.00016026704,0.00042151322,0.0000022138886,0.0000480612,0.000056319088],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.7887486,0.19320612,0.015055876,0.00047628113,0.001915487,0.0005976062],"domain_scores_gemma":[0.24072504,0.7440867,0.013790346,0.0005592316,0.00055051665,0.00028820452],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.39669845,0.00063443935,0.040490534,0.0012410365,0.00009446629,0.00006680262,0.0007997012,0.00040295382,0.0005341789],"category_scores_gemma":[0.9190332,0.00025548902,0.017764425,0.000551915,0.0004685759,0.00007477305,0.00018820264,0.0017164019,0.00000618795],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05611753,0.009903557,0.000677562,0.014773244,0.031560622,0.00009783376,0.000049734546,0.000004180853,0.0000012565476,0.0002918303,0.00037921764,0.88614345],"study_design_scores_gemma":[0.29510933,0.22264238,0.0013809913,0.13310225,0.06186797,0.00035107715,0.000110126704,0.00007055094,0.000049664348,0.28395683,0.00063206814,0.0007267734],"about_ca_topic_score_codex":0.0004981416,"about_ca_topic_score_gemma":0.000067591514,"teacher_disagreement_score":0.8854166,"about_ca_system_score_codex":0.0013414948,"about_ca_system_score_gemma":0.0010153367,"threshold_uncertainty_score":0.99998975},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad","metaepi_narrow"],"domain":"methods","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2752127454","doi":"10.1002/sim.7440","title":"Algorithms for evaluating reference scaled average bioequivalence: power, bias, and consumer risk","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Computer science; Statistics; Econometrics; Sample size determination; Statistical power; Mathematics; Medicine","score_opus":0.7233084269583646,"score_gpt":0.6410520296377792,"score_spread":0.08225639732058543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752127454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013167807,0.0002688239,0.9791681,0.0004929342,0.0013080041,0.00124927,0.0023934755,0.00004860527,0.0019029838],"genre_scores_gemma":[0.053495836,0.00083623204,0.94485235,0.00012383853,0.00022453944,0.00008921942,0.000011909843,0.000043214,0.00032284655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99612904,0.00081004185,0.0013334651,0.0006074937,0.00064955145,0.00047041746],"domain_scores_gemma":[0.9087291,0.088851176,0.00097162393,0.0008841884,0.00035635845,0.00020754838],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013381693,0.00028887126,0.0010424008,0.00010902139,0.0004243693,0.00006922319,0.00048207477,0.00020383149,0.0004873788],"category_scores_gemma":[0.57324785,0.0002255301,0.00003658815,0.00007690348,0.0014445771,0.000066574336,0.00019658302,0.000557314,0.000009823902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005269368,0.00021105242,0.014743194,0.00092799217,0.00017138946,0.000094315576,0.00088180474,0.0000020474479,0.00034187204,0.5531629,0.014554517,0.41438198],"study_design_scores_gemma":[0.004779784,0.0007759284,0.011406591,0.00055193336,0.00023629666,0.000005752645,0.00012296635,0.00913182,0.00005475599,0.9722644,0.0004032659,0.00026650605],"about_ca_topic_score_codex":0.00014830248,"about_ca_topic_score_gemma":0.000049697428,"teacher_disagreement_score":0.5598662,"about_ca_system_score_codex":0.00005200998,"about_ca_system_score_gemma":0.00008058419,"threshold_uncertainty_score":0.91968507},"labels":[],"label_agreement":null},{"id":"W2752464292","doi":"10.1177/0962280217720947","title":"Competing risks modeling of cumulative effects of time-varying drug exposures","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Hazard; Computer science; Statistics; Econometrics; Risk analysis (engineering); Medicine; Mathematics","score_opus":0.7693399576326204,"score_gpt":0.7370097003486988,"score_spread":0.03233025728392158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752464292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025094936,0.00012848097,0.9649021,0.00028424038,0.00039396196,0.00092256046,0.00007337731,0.000031641706,0.00816868],"genre_scores_gemma":[0.2577915,0.00008241385,0.74183017,0.000016711609,0.000151111,0.000040253602,0.000001185927,0.000047923942,0.000038729973],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96474546,0.025665559,0.0031539965,0.00090584287,0.004333894,0.0011952689],"domain_scores_gemma":[0.4376161,0.5591952,0.0006047667,0.0012374625,0.00075537123,0.00059109053],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.087793246,0.00031252857,0.0020566215,0.00037470364,0.00034692924,0.00006260649,0.0017970235,0.00045933053,0.0014083947],"category_scores_gemma":[0.91993684,0.00025885552,0.00018487657,0.0003969546,0.0033269392,0.00010474653,0.001381592,0.002552289,0.000014894545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009583378,0.0011407795,0.0022298037,0.0045626718,0.00022401674,0.00038634875,0.0013654429,0.00013404229,0.0020673897,0.34327474,0.00042400716,0.6432324],"study_design_scores_gemma":[0.0013244897,0.00022267403,0.0007955291,0.002070523,0.000042352687,0.0000019242614,0.000107278094,0.24750398,0.004067642,0.7436844,0.0000050475946,0.00017412326],"about_ca_topic_score_codex":0.0005612015,"about_ca_topic_score_gemma":0.000011039991,"teacher_disagreement_score":0.8321436,"about_ca_system_score_codex":0.00010032963,"about_ca_system_score_gemma":0.0004092146,"threshold_uncertainty_score":0.99998635},"labels":[],"label_agreement":null},{"id":"W2752545986","doi":"10.1002/sim.7453","title":"Improving phase II oncology trials using best observed RECIST response as an endpoint by modelling continuous tumour measurements","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Cancer Research UK; AstraZeneca","keywords":"Response Evaluation Criteria in Solid Tumors; Sample size determination; Clinical endpoint; Clinical trial; Estimator; Medicine; Oncology; Outcome (game theory); Complete response; Computer science; Statistics; Internal medicine; Phases of clinical research; Mathematics; Chemotherapy","score_opus":0.8504567930226415,"score_gpt":0.6474845982302354,"score_spread":0.20297219479240614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752545986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120083526,0.00011160245,0.87391126,0.0006187667,0.002094568,0.0013372721,0.00117072,0.000058602473,0.0006136931],"genre_scores_gemma":[0.110947594,0.00006676291,0.8874193,0.00022493373,0.00076086476,0.000057318375,0.000033286324,0.00010451992,0.00038542258],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9852203,0.0076897703,0.004076589,0.00095245277,0.0012449083,0.00081597816],"domain_scores_gemma":[0.9195884,0.07474177,0.0030329425,0.0014847446,0.0006196282,0.0005325479],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06316792,0.0005162362,0.0031005854,0.00020451858,0.00075882766,0.00011154463,0.00097554026,0.0004051194,0.00055670977],"category_scores_gemma":[0.65066653,0.0004389139,0.00010913484,0.00013214143,0.0009182497,0.00018015545,0.00030496175,0.00091462315,0.000011824708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06065699,0.010826881,0.0003967336,0.0011528439,0.0008279409,0.002847681,0.005255764,0.0002770263,0.36416683,0.0864288,0.015968623,0.45119387],"study_design_scores_gemma":[0.025001619,0.0087303715,0.000030981555,0.0009559603,0.00089885667,0.00002661865,0.00073642563,0.065172054,0.0042337407,0.8925462,0.0009959247,0.00067124603],"about_ca_topic_score_codex":0.0015404961,"about_ca_topic_score_gemma":0.0001377277,"teacher_disagreement_score":0.8061174,"about_ca_system_score_codex":0.0005306067,"about_ca_system_score_gemma":0.00044799125,"threshold_uncertainty_score":0.9998063},"labels":[],"label_agreement":null},{"id":"W2754566416","doi":"10.1007/s10637-017-0510-8","title":"Comparison of reporting phase I trial results in ClinicalTrials.gov and matched publications","year":2017,"lang":"en","type":"review","venue":"Investigational New Drugs","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Clinical trial; Interquartile range; Adverse effect; Internal medicine; Clinical endpoint; MEDLINE","score_opus":0.9371062626576229,"score_gpt":0.7366516816469256,"score_spread":0.20045458101069724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754566416","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005908707,0.9701888,0.0027321095,0.004092772,0.0033448057,0.010477428,0.0020285642,0.00024489695,0.0062997537],"genre_scores_gemma":[0.000031503532,0.4421112,0.55453575,0.000045207318,0.001740661,0.00025599482,0.0002025971,0.000082203136,0.000994864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9782745,0.002403813,0.01705474,0.0010026707,0.0009029506,0.0003612791],"domain_scores_gemma":[0.6909024,0.25971347,0.045390002,0.002569205,0.00053942576,0.0008855058],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02375586,0.0004946809,0.0063820677,0.0003548514,0.00013686184,0.00014850499,0.0007655091,0.0008686631,0.00008619604],"category_scores_gemma":[0.7733957,0.00042475,0.0006360341,0.00043740388,0.0007795555,0.00014872334,0.00028575904,0.001086023,0.000026222828],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019700874,0.00094929204,0.00003543244,0.0070795994,0.00025888078,0.0000069474495,0.00025195032,3.5823456e-7,9.819821e-7,0.099042624,0.01986966,0.8705342],"study_design_scores_gemma":[0.026989898,0.00019859207,0.000011254087,0.009344024,0.00071759394,0.000006371154,0.000016425769,0.000034697903,0.0000049296777,0.64569896,0.3166168,0.00036046843],"about_ca_topic_score_codex":0.000059753373,"about_ca_topic_score_gemma":0.000011568803,"teacher_disagreement_score":0.8701737,"about_ca_system_score_codex":0.00010208337,"about_ca_system_score_gemma":0.0026770313,"threshold_uncertainty_score":0.9998204},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W2758193932","doi":"10.1016/j.conctc.2017.09.010","title":"A two-stage design for phase II trials with time-to-event endpoint using restricted follow-up","year":2017,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Sample size determination; Research design; Log-rank test; Clinical endpoint; Event (particle physics); Type I and type II errors; Statistics; Clinical study design; Confidence interval; Protocol (science); Computer science; Sample (material); Clinical trial; Medicine; Mathematics; Survival analysis; Internal medicine; Pathology","score_opus":0.9432171982001953,"score_gpt":0.7028431125306549,"score_spread":0.24037408566954044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758193932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048885206,0.00030452714,0.9610737,0.009055109,0.0014803382,0.016997194,0.0026898552,0.00037895053,0.003131814],"genre_scores_gemma":[0.084237486,0.0001215383,0.90916544,0.0006265149,0.0010605201,0.0014870691,0.00007132574,0.00018163939,0.0030484584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93334764,0.050588842,0.013103966,0.0013465408,0.0008099521,0.0008030575],"domain_scores_gemma":[0.39055833,0.586105,0.010022525,0.011126813,0.0011198171,0.0010674945],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16544078,0.0007390194,0.0068421457,0.00026510493,0.002614915,0.0005254351,0.0048785727,0.0006158006,0.00053466257],"category_scores_gemma":[0.8604379,0.00056480156,0.002018866,0.00036937828,0.0012293302,0.0004161927,0.0019933153,0.0011125233,0.00010696468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17175208,0.03393651,0.0005466891,0.00066600245,0.013295577,0.00013314663,0.0011153237,0.00020552133,0.012449898,0.28223175,0.21653543,0.26713207],"study_design_scores_gemma":[0.14312565,0.012668031,0.00012795604,0.0017559944,0.0041798353,0.0000083590185,0.00021533929,0.024436297,0.0024902837,0.7083721,0.10035897,0.0022611772],"about_ca_topic_score_codex":0.00006012285,"about_ca_topic_score_gemma":0.000015400265,"teacher_disagreement_score":0.69499713,"about_ca_system_score_codex":0.0001365163,"about_ca_system_score_gemma":0.0015908794,"threshold_uncertainty_score":0.99968034},"labels":[],"label_agreement":null},{"id":"W2759661076","doi":"10.1016/j.cjca.2017.07.206","title":"TEMPORAL TRENDS IN USE OF COMPOSITE ENDPOINTS IN MAJOR CARDIOVASCULAR RANDOMIZED CLINICAL TRIALS","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Public Health","funders":"","keywords":"Medicine; Clinical endpoint; Clinical trial; Randomized controlled trial; Demographics; Population; Internal medicine; Surrogate endpoint; MEDLINE; Demography","score_opus":0.6915435491226017,"score_gpt":0.5796812520021392,"score_spread":0.11186229712046258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759661076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7763228,0.0023896473,0.18871465,0.0032052838,0.015656829,0.0026537364,0.00072483794,0.000018977265,0.010313264],"genre_scores_gemma":[0.8702706,0.0001243384,0.12841679,0.000052439696,0.0010494322,0.000009532436,0.000001545774,0.000027972084,0.00004734132],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96629095,0.027164744,0.00552733,0.0002828562,0.00028955177,0.00044455708],"domain_scores_gemma":[0.9106671,0.085121945,0.0024554348,0.00092254014,0.00026983712,0.0005631399],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.107335806,0.00022750543,0.008256106,0.00080365187,0.00006361279,0.00005783751,0.0007117475,0.0005135852,0.0000693686],"category_scores_gemma":[0.5060448,0.00017768003,0.0030324918,0.00014480021,0.0012026016,0.00014151783,0.000055661585,0.00089527766,0.000002688669],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07558714,0.00011477103,0.53442085,0.0002213676,0.01266637,0.0076353014,0.0004339272,0.0011617623,0.00010202375,0.031631056,0.014043234,0.3219822],"study_design_scores_gemma":[0.30443868,0.0004626916,0.15280972,0.00065183686,0.0024374274,0.00033912333,0.000058788894,0.00018644065,0.00012648021,0.5264059,0.011504614,0.00057832873],"about_ca_topic_score_codex":0.0027315146,"about_ca_topic_score_gemma":0.003391901,"teacher_disagreement_score":0.49477482,"about_ca_system_score_codex":0.00012382292,"about_ca_system_score_gemma":0.0006470008,"threshold_uncertainty_score":0.91918564},"labels":[],"label_agreement":null},{"id":"W2762646895","doi":"10.1016/j.msksp.2017.10.002","title":"Sample size estimation for cluster randomized controlled trials","year":2017,"lang":"en","type":"article","venue":"Musculoskeletal Science and Practice","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Health Research Council of New Zealand; Lottery Health Research","keywords":"Sample size determination; Cluster (spacecraft); Randomized controlled trial; Sample (material); External validity; Cluster randomised controlled trial; Clinical trial; Cluster size; Computer science; Medicine; Statistics; Mathematics; Surgery; Pathology","score_opus":0.4457909648543032,"score_gpt":0.6144321693979072,"score_spread":0.16864120454360404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762646895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004196603,0.000048721373,0.9574958,0.016993696,0.0014283238,0.006980468,0.000047234123,0.000059800215,0.012749344],"genre_scores_gemma":[0.06647193,0.00006926607,0.9317463,0.0006023128,0.0003512706,0.0005715668,3.8448437e-7,0.000014255187,0.00017270907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913359,0.0051380326,0.0016988666,0.0005243841,0.0009069361,0.00039585464],"domain_scores_gemma":[0.07263927,0.9229816,0.002575498,0.00073574664,0.00084846123,0.0002193826],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24015161,0.00020412957,0.0027906096,0.00006110375,0.0012658321,0.00093346264,0.0005187898,0.00011864636,0.00014756522],"category_scores_gemma":[0.99625015,0.00012159285,0.00055556884,0.00010486555,0.0017782251,0.0012606181,0.00018175982,0.00016784719,0.000010377023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.20815906,0.0002571254,0.0000074118952,0.00025077868,0.00039117926,0.0000020343605,0.00021177829,0.0000035896762,0.0008041152,0.5979211,0.0017686486,0.1902232],"study_design_scores_gemma":[0.17138073,0.00012651338,0.00003603551,0.000036545385,0.0011132807,0.000004662607,0.000052294876,0.010383797,0.00007732875,0.8154851,0.0011385637,0.000165148],"about_ca_topic_score_codex":0.00006106795,"about_ca_topic_score_gemma":0.000002994739,"teacher_disagreement_score":0.91869664,"about_ca_system_score_codex":0.00003816243,"about_ca_system_score_gemma":0.00019880944,"threshold_uncertainty_score":0.9735885},"labels":[],"label_agreement":null},{"id":"W2762760356","doi":"10.1093/pch/15.suppl_a.67ab","title":"Consort Extension for N-Of-1 Trials (Cent) Guidelines","year":2010,"lang":"en","type":"article","venue":"Paediatrics & Child Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Consolidated Standards of Reporting Trials; Extension (predicate logic); Medicine; Statistics; Clinical trial; Computer science; Mathematics; Internal medicine","score_opus":0.6588289650448088,"score_gpt":0.6180742725246293,"score_spread":0.04075469252017949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762760356","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025029678,0.002686715,0.90497357,0.03473277,0.018446714,0.009410318,0.002332736,0.0004684895,0.0019190051],"genre_scores_gemma":[0.0070974794,0.0012040809,0.9858512,0.0018275678,0.0038235493,0.00007064989,0.000011805504,0.000065230386,0.00004838394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992914,0.0011371165,0.0042779855,0.0005435039,0.0005599707,0.0005674062],"domain_scores_gemma":[0.868486,0.12701268,0.002271538,0.00085969904,0.0009387484,0.00043132642],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037247043,0.00025962509,0.0019519748,0.00016973451,0.0001999288,0.000021815626,0.00034449637,0.0003192831,0.00018399865],"category_scores_gemma":[0.60824674,0.0002029315,0.00048826082,0.00033779198,0.00012653586,0.000041615145,0.00009775913,0.0005743094,0.00001663122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004626053,0.00073068973,0.002302131,0.0016151511,0.000104971194,0.000002469021,0.00016071452,0.0000024537696,0.0003411756,0.6490222,0.17771488,0.16754057],"study_design_scores_gemma":[0.0028162978,0.00030134773,0.0010704121,0.00010481004,0.00019499758,0.0000070207366,0.000023173678,0.0002483327,0.0003506018,0.9746531,0.019964756,0.0002651536],"about_ca_topic_score_codex":0.000036937592,"about_ca_topic_score_gemma":0.000025178892,"teacher_disagreement_score":0.57099974,"about_ca_system_score_codex":0.00003407838,"about_ca_system_score_gemma":0.00044487926,"threshold_uncertainty_score":0.9913568},"labels":[],"label_agreement":null},{"id":"W2763787095","doi":"10.1371/journal.pone.0195145","title":"Conditional equivalence testing: An alternative remedy for publication bias","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Equivalence (formal languages); Publication bias; Computer science; Bayesian probability; Statistical hypothesis testing; Econometrics; Statistics; Mathematics; Artificial intelligence; Discrete mathematics; Confidence interval","score_opus":0.9344245942914531,"score_gpt":0.5979018871787765,"score_spread":0.3365227071126766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763787095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1546484,0.0000062668646,0.8287691,0.0021550935,0.00031192452,0.0020356858,0.00084669923,0.0003777341,0.0108491015],"genre_scores_gemma":[0.08265193,0.0000013075096,0.91481847,0.0003795515,0.0014554703,0.00020907995,0.00002233857,0.000026769076,0.00043506222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980395,0.00032564436,0.0005857398,0.00034941788,0.00047061517,0.0002291134],"domain_scores_gemma":[0.9416867,0.055482123,0.0004121311,0.00045577105,0.001798858,0.00016444795],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00263823,0.000113543174,0.00031615343,0.00005463554,0.000114091876,0.00005636009,0.00028927886,0.00008613367,0.00059618556],"category_scores_gemma":[0.42247343,0.00010446239,0.000040659623,0.0001750262,0.00027550952,0.00015902764,0.00005735879,0.00011726798,0.000109594934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016743422,0.0037721363,0.0010213971,0.00027330974,0.00026974536,0.0000013325206,0.00018334253,1.809801e-7,0.017004328,0.9673445,0.0039859405,0.0059763314],"study_design_scores_gemma":[0.0005479535,0.0007468926,0.0006120762,0.00012428711,0.00011868643,7.041497e-7,0.000010369943,0.0049363826,0.03657798,0.95612365,0.0000702041,0.00013083585],"about_ca_topic_score_codex":0.0000035370988,"about_ca_topic_score_gemma":0.0000020686402,"teacher_disagreement_score":0.4198352,"about_ca_system_score_codex":0.000043152973,"about_ca_system_score_gemma":0.000056413657,"threshold_uncertainty_score":0.65278137},"labels":[],"label_agreement":null},{"id":"W2765239123","doi":"10.1016/j.conctc.2017.11.001","title":"Bayesian adaptive clinical trials of combination treatments","year":2017,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McMaster University; Impact","funders":"","keywords":"Bayesian probability; Clinical trial; Computer science; Econometrics; Medicine; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.9662825611108533,"score_gpt":0.7437265522400163,"score_spread":0.22255600887083704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765239123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017068455,0.0044269417,0.68685997,0.041290775,0.017811125,0.026869738,0.0059386175,0.0011028446,0.19863153],"genre_scores_gemma":[0.610491,0.0018799314,0.38558918,0.0002550274,0.00074882666,0.00028097717,0.000048735757,0.00007824953,0.00062808336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8041691,0.16088851,0.031969506,0.0013349694,0.0010462848,0.0005916009],"domain_scores_gemma":[0.16806296,0.7905923,0.026029442,0.013249463,0.001238511,0.00082730927],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33767256,0.00059705466,0.00908716,0.00020047817,0.001009788,0.00023353999,0.005251553,0.001178441,0.00038037973],"category_scores_gemma":[0.9180294,0.0004749349,0.0039700624,0.00022983273,0.0037472758,0.00052035425,0.0017547946,0.0016396376,0.00009439989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036902395,0.011691192,0.04968432,0.00011463958,0.004714318,0.000017593426,0.0001342123,2.8008785e-7,0.00007912676,0.5327411,0.036424424,0.36070856],"study_design_scores_gemma":[0.016466958,0.0015924772,0.021823473,0.00055057154,0.001531638,0.0000018470051,0.00013346765,0.00139713,0.00017707725,0.95032907,0.005478201,0.00051807315],"about_ca_topic_score_codex":0.00009932877,"about_ca_topic_score_gemma":0.000026942325,"teacher_disagreement_score":0.6361062,"about_ca_system_score_codex":0.000073659365,"about_ca_system_score_gemma":0.0008769122,"threshold_uncertainty_score":0.9997702},"labels":[],"label_agreement":null},{"id":"W2766225997","doi":"10.1080/00031305.2017.1377111","title":"Bayesian Analysis on a Noncentral Fisher–Student’s Hypersphere","year":2017,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hypersphere; Mathematics; False discovery rate; Statistical hypothesis testing; Bayes factor; Null distribution; Null hypothesis; Bayesian probability; p-value; Bayes' theorem; Multiple comparisons problem; Weibull distribution; Statistics; Applied mathematics; Test statistic; Geometry","score_opus":0.3520839162328059,"score_gpt":0.5716076458469133,"score_spread":0.21952372961410738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766225997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11230932,0.00001411635,0.8242672,0.0055386354,0.00094538706,0.0009905735,0.0011082225,0.00022908559,0.054597463],"genre_scores_gemma":[0.6248642,0.000016024454,0.3728736,0.001239515,0.00033778758,0.0000352375,0.0000024916542,0.00004350048,0.0005876486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964729,0.0009752191,0.0007063585,0.00054160476,0.00069616415,0.000607752],"domain_scores_gemma":[0.9716646,0.024638547,0.0011916579,0.0021614318,0.00009644981,0.00024730162],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016405035,0.00031204204,0.0011577478,0.000069527465,0.0007773218,0.00032524692,0.0014829666,0.000051458806,0.0008453594],"category_scores_gemma":[0.03607605,0.00021114694,0.00031610872,0.00036760108,0.0015745985,0.00005662706,0.00020189078,0.00040889517,0.00013524578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008952403,0.0009719179,0.052848455,0.000056482735,0.004960492,0.0003205887,0.001410347,0.00006371406,0.000075912525,0.51336324,0.034447372,0.39058626],"study_design_scores_gemma":[0.0007595912,0.00047526992,0.42851713,0.00004352485,0.0025512583,0.0000027940093,0.00091353746,0.001830235,0.000040302697,0.56341034,0.00096885074,0.0004871661],"about_ca_topic_score_codex":0.0007169673,"about_ca_topic_score_gemma":0.00037788518,"teacher_disagreement_score":0.5125549,"about_ca_system_score_codex":0.00009523822,"about_ca_system_score_gemma":0.000053024505,"threshold_uncertainty_score":0.9720435},"labels":[],"label_agreement":null},{"id":"W2766988545","doi":"10.1016/j.jval.2017.08.1819","title":"Characteristics And Approvals Of Regulatory Submissions Based On Non-Randomized Studies In The United States And Europe","year":2017,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Medicine; Randomized controlled trial; Orphan drug; Placebo; Food and drug administration; Drug approval; Population; MEDLINE; European union; Alternative medicine; Family medicine; Intensive care medicine; Drug; Internal medicine; Pharmacology; Environmental health; Bioinformatics; Business; Law; Political science; Pathology","score_opus":0.6477175901327824,"score_gpt":0.576844853450072,"score_spread":0.07087273668271044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766988545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920495,0.00016493932,0.0016775986,0.003965791,0.00024269857,0.0015882318,0.000079636244,0.000013439938,0.0002181387],"genre_scores_gemma":[0.789669,0.004337886,0.20471284,0.0010365639,0.00008720693,0.000076662465,0.0000036051078,0.000034922086,0.000041316347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941435,0.0040622884,0.0011079177,0.00023649812,0.0002446167,0.00020519426],"domain_scores_gemma":[0.899725,0.09880676,0.0007224301,0.00057709916,0.00008911714,0.00007955506],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018890955,0.00013727794,0.0010724699,0.00013367689,0.00014533482,0.000026403175,0.00019909578,0.00006396703,0.000003840836],"category_scores_gemma":[0.19985071,0.00008291575,0.000034972967,0.00012656047,0.00085894566,0.000021797892,0.00007812886,0.00026411362,5.6750196e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.050690647,0.0038541828,0.05038675,0.02656889,0.00040124886,0.0002008757,0.040428184,0.0006580128,0.0001373736,0.79797226,0.003378313,0.025323244],"study_design_scores_gemma":[0.03886327,0.00043661078,0.04881717,0.0029028787,0.00006150279,0.0000023217722,0.00064811326,0.06686807,0.000049848262,0.8410133,0.00012827819,0.00020861912],"about_ca_topic_score_codex":0.00032961194,"about_ca_topic_score_gemma":0.0000046870273,"teacher_disagreement_score":0.20303525,"about_ca_system_score_codex":0.000023481649,"about_ca_system_score_gemma":0.00008041656,"threshold_uncertainty_score":0.8068893},"labels":[],"label_agreement":null},{"id":"W2768417485","doi":"10.1002/sim.7539","title":"Exponential decay for binary time‐varying covariates in Cox models","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Event (particle physics); Econometrics; Exponential growth; Binary data; Computer science; Mathematics; Binary number","score_opus":0.5055243770677599,"score_gpt":0.5754043878517637,"score_spread":0.06988001078400385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768417485","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024663734,0.000062160725,0.98943913,0.0008827561,0.0012839815,0.0010528426,0.00063026586,0.000041343388,0.00414113],"genre_scores_gemma":[0.052077007,0.000082066545,0.9465853,0.0001450033,0.00051154854,0.00013512354,0.000027458147,0.000059571328,0.00037695045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996647,0.0004286547,0.0014401322,0.0004906634,0.0004712413,0.0005222825],"domain_scores_gemma":[0.9414227,0.05695774,0.00051950803,0.0007948683,0.00015649393,0.00014871621],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064833816,0.00026539952,0.0011327165,0.00019322158,0.00019126086,0.000043773478,0.0006141466,0.00020529456,0.0005072263],"category_scores_gemma":[0.14759113,0.0002277655,0.000050284143,0.000102604696,0.0005819606,0.00011080702,0.00017955208,0.00039967362,0.000018678915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071804057,0.0002988916,0.00037739705,0.0004519904,0.000057419897,0.00021828385,0.00065024005,0.00011397613,0.0010620794,0.9669411,0.015160193,0.013950367],"study_design_scores_gemma":[0.00498547,0.00030908073,0.00061006565,0.000585428,0.000085539505,0.0000029014898,0.000043768905,0.07959841,0.00014503588,0.9133061,0.00010522819,0.00022293944],"about_ca_topic_score_codex":0.00015353077,"about_ca_topic_score_gemma":0.000056367644,"teacher_disagreement_score":0.14110774,"about_ca_system_score_codex":0.00009255147,"about_ca_system_score_gemma":0.00008651905,"threshold_uncertainty_score":0.92880076},"labels":[],"label_agreement":null},{"id":"W2769222633","doi":"10.6000/1927-5129.2017.13.96","title":"Impact of Logarithmic Transformation on the Restoration of Normality in Bioequivalence Data","year":2017,"lang":"en","type":"article","venue":"Journal of Basic & Applied Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Normality; Mathematics; Statistics; Skewness; Normal distribution; Estimator; Transformation (genetics); Bioequivalence; Data transformation; Normality test; Econometrics; Statistical hypothesis testing; Kurtosis; Computer science; Data mining; Medicine","score_opus":0.7586372073922317,"score_gpt":0.6109137437331346,"score_spread":0.14772346365909717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769222633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704927,0.000008316555,0.025080334,0.0007573261,0.00018012845,0.00024438874,0.00005286155,0.0000020587293,0.0031818622],"genre_scores_gemma":[0.9262034,0.000024354624,0.07369514,0.00001341812,0.000058458863,0.0000012019938,1.7907817e-7,0.0000024891815,0.0000013070952],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765944,0.0002724784,0.0011365887,0.0001234787,0.00068327633,0.00012470403],"domain_scores_gemma":[0.9888801,0.0083344,0.002016986,0.0006091516,0.00012043443,0.000038910355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017602954,0.00007885762,0.00038796774,0.00009898469,0.00013483132,0.000048747323,0.0015007063,0.000055446722,0.000043835906],"category_scores_gemma":[0.024054926,0.00004187354,0.000081285965,0.00016797835,0.0008363623,0.00037751207,0.0000758579,0.00022455747,0.0000011381862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016699508,0.0013623341,0.020208439,0.0003929494,0.00014874447,0.0000060446478,0.0026258044,0.0005763197,0.046656262,0.8076886,0.0012058298,0.1174587],"study_design_scores_gemma":[0.0008545427,0.00080946746,0.11193386,0.00026296847,0.00005460237,0.000004364626,0.00029219058,0.0019368896,0.010788581,0.872961,0.000008838395,0.00009270637],"about_ca_topic_score_codex":0.00003419693,"about_ca_topic_score_gemma":0.00001667355,"teacher_disagreement_score":0.11736599,"about_ca_system_score_codex":0.00003544571,"about_ca_system_score_gemma":0.00023468638,"threshold_uncertainty_score":0.98416585},"labels":[],"label_agreement":null},{"id":"W2770322578","doi":"10.1002/bimj.201700129","title":"On the necessity and design of studies comparing statistical methods","year":2017,"lang":"en","type":"letter","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":108,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Deutsche Forschungsgemeinschaft","keywords":"Biostatistics; Library science; Epidemiology; Medical statistics; Medicine; Computer science; Mathematics; Statistics","score_opus":0.9022525894811605,"score_gpt":0.6758531036730725,"score_spread":0.226399485808088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770322578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000050838247,0.0010369259,0.90914196,0.087561585,0.0014399459,0.00039981067,0.00007169287,0.000021218011,0.00027603962],"genre_scores_gemma":[0.0003464722,0.00048376797,0.9741894,0.022332806,0.002440681,0.00001332857,7.79843e-7,0.000055767217,0.00013696897],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98637635,0.009569925,0.0017744506,0.000487348,0.001253938,0.0005379871],"domain_scores_gemma":[0.56868535,0.4284523,0.0016664797,0.000652361,0.00037442477,0.00016906073],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.021139368,0.0004523844,0.0023832663,0.000736805,0.0005127874,0.00027395578,0.0011213376,0.00076505326,0.00017982093],"category_scores_gemma":[0.5858209,0.0002447036,0.00025915398,0.0005681716,0.0015202909,0.00005126548,0.00046399323,0.0042738067,0.000010294153],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013244842,0.00011047996,0.000035642992,0.00040168682,0.0008890102,0.0003763396,0.00003689432,4.0839097e-7,0.00002168912,0.01948901,0.94205564,0.036450766],"study_design_scores_gemma":[0.0005972907,0.00051561155,0.00020917084,0.0005469901,0.0005881491,0.00013332699,0.000019359302,0.00023136676,0.00012206625,0.98863,0.008109242,0.00029741446],"about_ca_topic_score_codex":0.0000028329277,"about_ca_topic_score_gemma":5.1898013e-8,"teacher_disagreement_score":0.969141,"about_ca_system_score_codex":0.0001275732,"about_ca_system_score_gemma":0.000113202725,"threshold_uncertainty_score":0.9980234},"labels":[],"label_agreement":null},{"id":"W2771785531","doi":"10.22237/jmasm/1509496260","title":"JMASM 50: A Web-based Shiny Application for Conducting a Two Dependent Samples Maximum Test (R)","year":2017,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Mathematics; Wilcoxon signed-rank test; Statistics; Test (biology); Statistical hypothesis testing; Student's t-test; Mann–Whitney U test; Statistical significance","score_opus":0.6270762867788159,"score_gpt":0.6083874458296579,"score_spread":0.018688840949158014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771785531","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006983065,0.00005989632,0.9943429,0.0006538594,0.0006670363,0.0013502716,0.00067048694,0.000065704684,0.0014915174],"genre_scores_gemma":[0.12936117,0.000008749633,0.86923087,0.00022225153,0.0008231202,0.00021654935,0.000004319867,0.00010975162,0.00002323599],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993629,0.0012081821,0.0028109697,0.0006852436,0.0009564043,0.0007102163],"domain_scores_gemma":[0.8216007,0.17314337,0.0030629695,0.001098712,0.0005819495,0.00051231636],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.020148616,0.0004855828,0.0018576141,0.00017031873,0.00060455216,0.00033277247,0.0012597113,0.00032697988,0.00016652144],"category_scores_gemma":[0.25536367,0.00040288057,0.0003606262,0.00008540356,0.0005488119,0.00014298839,0.00020697441,0.0009909923,0.000009692604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009142086,0.000561135,0.0001344142,0.00031600348,0.00016694458,0.0000159003,0.00006009145,0.00006540052,0.05007154,0.3290073,0.0004962805,0.61819077],"study_design_scores_gemma":[0.0061007007,0.00037213523,0.00023847922,0.00010320896,0.00059768034,0.000032672455,0.000037874863,0.04235063,0.009778425,0.93904316,0.0009301592,0.00041484265],"about_ca_topic_score_codex":0.000008333654,"about_ca_topic_score_gemma":0.000008691678,"teacher_disagreement_score":0.6177759,"about_ca_system_score_codex":0.00019561185,"about_ca_system_score_gemma":0.00041165572,"threshold_uncertainty_score":0.9998423},"labels":[],"label_agreement":null},{"id":"W2772025278","doi":"10.1038/nmeth.2858","title":"Comparing samples—part I","year":2014,"lang":"en","type":"article","venue":"Nature Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":89,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Computational biology; Biology; Computer science","score_opus":0.711703823304576,"score_gpt":0.664800381563338,"score_spread":0.04690344174123806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772025278","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011246284,0.00010098381,0.94971913,0.00035299404,0.0028652917,0.0002274611,0.000008701298,0.00023881916,0.045361962],"genre_scores_gemma":[0.008614029,0.000006027091,0.9885899,0.0009149082,0.0013171791,0.00002040956,0.0000013623383,0.00004875119,0.00048746914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926757,0.0052823634,0.00078131544,0.00048025112,0.0003827421,0.00039761284],"domain_scores_gemma":[0.8512007,0.14730029,0.00026555258,0.00088224775,0.00014385069,0.00020734544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018891772,0.00023227598,0.00092070637,0.00007489687,0.000102411104,0.0000487727,0.00045590042,0.0006274426,0.0005089358],"category_scores_gemma":[0.3682726,0.00018640274,0.00019942547,0.00028710612,0.00012980188,0.000043580592,0.00016903544,0.0014523157,0.000049871043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037482496,0.00006659837,0.00051251776,0.000079633704,0.0000473829,0.0000014737925,0.000032348096,0.0000012901287,0.0005276584,0.8251102,0.011445445,0.162138],"study_design_scores_gemma":[0.00046935395,0.000047628575,0.00080440927,0.000049779184,0.000075763346,0.000004297702,0.000007655126,0.00079481484,0.004604868,0.86243284,0.13050456,0.00020405733],"about_ca_topic_score_codex":0.0000032307241,"about_ca_topic_score_gemma":0.0000024623482,"teacher_disagreement_score":0.34938082,"about_ca_system_score_codex":0.000039352726,"about_ca_system_score_gemma":0.000021374266,"threshold_uncertainty_score":0.7601283},"labels":[],"label_agreement":null},{"id":"W2774950576","doi":"10.6000/1929-6029.2017.06.04.3","title":"Sample Size Calculation in Clinical Studies: Some Common Scenarios","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Sample size determination; Sample (material); Type I and type II errors; Statistical power; Computer science; Statistics; Power (physics); Power analysis; Econometrics; Mathematics; Algorithm","score_opus":0.8047432444648496,"score_gpt":0.7485851251915935,"score_spread":0.05615811927325609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774950576","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5663851,0.0006700146,0.3619408,0.044960473,0.021251915,0.0016776635,0.0009413788,0.000038285158,0.0021343974],"genre_scores_gemma":[0.48318785,0.0025473146,0.5119288,0.00032712898,0.0018872898,0.00001309896,0.000001704075,0.00003010045,0.000076732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9856359,0.003605027,0.0040196446,0.00035039513,0.0058611818,0.0005278572],"domain_scores_gemma":[0.469118,0.52513206,0.0015953374,0.00069760595,0.0028786424,0.00057834806],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06262598,0.0001709161,0.0010708731,0.00043210818,0.00014456802,0.00017431856,0.0024490745,0.00035029004,0.0006188227],"category_scores_gemma":[0.9245293,0.00013916144,0.00015180797,0.00015300978,0.0015916433,0.00024996954,0.00076048815,0.0031620597,0.000021590957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012939555,0.0015429776,0.09279962,0.00013843198,0.00037982315,0.005220878,0.00044100572,0.000017771052,0.00001147578,0.49537122,0.014147422,0.38863543],"study_design_scores_gemma":[0.0033695917,0.00030222646,0.06146066,0.0010844745,0.0000148014615,0.000029560193,0.00015702995,0.003698427,0.000016209278,0.9290847,0.0006643081,0.00011800725],"about_ca_topic_score_codex":0.00023686151,"about_ca_topic_score_gemma":0.0004634297,"teacher_disagreement_score":0.86190337,"about_ca_system_score_codex":0.00053097936,"about_ca_system_score_gemma":0.00077434524,"threshold_uncertainty_score":0.9991377},"labels":[],"label_agreement":null},{"id":"W2775460460","doi":"10.22237/jmasm/1509495120","title":"Power and Sample Size Estimation for Nonparametric Composite Endpoints: Practical Implementation using Data Simulations","year":2017,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Sample size determination; Nonparametric statistics; Mathematics; Statistics; Composite number; Estimation; Sample (material); Macro; Econometrics; Power (physics); Algorithm; Computer science; Engineering","score_opus":0.6839025047710354,"score_gpt":0.6877663432556742,"score_spread":0.003863838484638782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775460460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023714697,0.000017154754,0.9935019,0.00041633364,0.00041064137,0.00081693043,0.0023227395,0.000018418385,0.00012440245],"genre_scores_gemma":[0.12817602,0.0000084605,0.8714635,0.00009096379,0.00018933529,0.000009821694,0.000010284294,0.000048784885,0.000002823154],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99541676,0.0010855102,0.002000341,0.00049095484,0.0006190308,0.00038741578],"domain_scores_gemma":[0.6866343,0.30964997,0.0020795588,0.0009400121,0.0003863279,0.00030984034],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010867884,0.00027794534,0.0010740949,0.0001450732,0.0005314578,0.00039154862,0.0005829673,0.00019612265,0.0002651244],"category_scores_gemma":[0.44752857,0.00024143324,0.00009478368,0.00010319459,0.0003430495,0.00044819617,0.00039454657,0.0004950284,0.0000010204385],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001350141,0.0005158683,0.0002004041,0.00026135883,0.0004733424,0.000015513368,0.00019187594,0.00027300042,0.0125865275,0.3957189,0.0005941839,0.58781886],"study_design_scores_gemma":[0.0018590852,0.00017331901,0.0009436095,0.000030254756,0.0005522841,0.000031964977,0.000038444843,0.28452,0.0006972546,0.7109049,0.0000687586,0.00018008766],"about_ca_topic_score_codex":0.000008262808,"about_ca_topic_score_gemma":0.0000021781068,"teacher_disagreement_score":0.5876388,"about_ca_system_score_codex":0.000107110594,"about_ca_system_score_gemma":0.00018624756,"threshold_uncertainty_score":0.98453623},"labels":[],"label_agreement":null},{"id":"W2775554882","doi":"10.1016/j.ejca.2017.10.027","title":"C-statistic: A brief explanation of its construction, interpretation and limitations","year":2017,"lang":"en","type":"editorial","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":155,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistic; Interpretation (philosophy); Event (particle physics); Disease; Medicine; Psychology; Actuarial science; Computer science; Statistics; Mathematics; Pathology; Economics","score_opus":0.34385099275191666,"score_gpt":0.5225399485208768,"score_spread":0.17868895576896016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775554882","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010915892,0.001591935,0.26884577,0.00027342263,0.7194824,0.00027986596,0.00095265,0.00001575521,0.008449012],"genre_scores_gemma":[0.002094003,0.0064204894,0.6135161,0.000023090122,0.3771854,0.000006021001,0.000010434023,0.00009839632,0.0006460822],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954913,0.0015758252,0.0017878717,0.00020515228,0.0008075658,0.0001322832],"domain_scores_gemma":[0.95376647,0.03882505,0.004673421,0.00024731716,0.0023675396,0.000120222234],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043465523,0.00020731633,0.0008263261,0.00017268411,0.0000843442,0.00009482204,0.00035086487,0.00014416344,0.00009756738],"category_scores_gemma":[0.32507885,0.00018016328,0.00013964082,0.000059472455,0.00029011292,0.00017308899,0.00006224015,0.00070676336,0.0000036316787],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029878743,0.000034695404,0.000008299451,0.0004488083,0.0003011555,0.000037483052,0.00042671224,0.0000050996346,0.000043817457,0.005319001,0.7397542,0.25332198],"study_design_scores_gemma":[0.0037296123,0.0009237411,0.00052498013,0.005158449,0.0017984954,0.000034609864,0.0001599147,0.00015442586,0.00024000296,0.22727479,0.75952214,0.00047885193],"about_ca_topic_score_codex":0.0000029362973,"about_ca_topic_score_gemma":0.000012920415,"teacher_disagreement_score":0.3446703,"about_ca_system_score_codex":0.000068109235,"about_ca_system_score_gemma":0.00036745254,"threshold_uncertainty_score":0.7346845},"labels":[],"label_agreement":null},{"id":"W2776607725","doi":"10.1037/pha0000152","title":"On how patients with multiple sclerosis weigh side effect severity and treatment efficacy when making treatment decisions.","year":2017,"lang":"en","type":"article","venue":"Experimental and Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Greo","funders":"National Multiple Sclerosis Society","keywords":"Side effect (computer science); Medicine; PsycINFO; Multiple sclerosis; Intensive care medicine; MEDLINE; Psychiatry","score_opus":0.3917578389519786,"score_gpt":0.5597589495308026,"score_spread":0.16800111057882405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776607725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99456525,0.00013308052,0.00047096796,0.00065571134,0.0017295734,0.0016039119,0.00005003993,0.00005950299,0.0007319888],"genre_scores_gemma":[0.95241326,0.00016189265,0.046163525,0.00060586684,0.000240443,0.00020986368,0.000002894849,0.00004617272,0.00015608482],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965757,0.0010856775,0.0007388553,0.00096331176,0.00023480855,0.00040161904],"domain_scores_gemma":[0.95185983,0.046703443,0.00045390768,0.00062197313,0.000039449442,0.00032140085],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007613035,0.0004712435,0.0011786555,0.00005231191,0.0004299085,0.00011322009,0.00025516746,0.00027875177,0.0002496396],"category_scores_gemma":[0.0078458795,0.00029371274,0.00022127817,0.00002635866,0.0009154519,0.000092072645,0.0001837251,0.00025380144,0.000020627187],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031808507,0.015662342,0.19471684,0.000025791624,0.0017756545,0.00007147258,0.00028097045,2.1671644e-7,0.0009011438,0.0026412874,0.004401086,0.7477147],"study_design_scores_gemma":[0.14531268,0.039309748,0.735542,0.00044315853,0.0012114714,0.000006519335,0.000070803464,0.00031342288,0.00785775,0.065126605,0.00376819,0.0010376504],"about_ca_topic_score_codex":0.000019413283,"about_ca_topic_score_gemma":0.000010657455,"teacher_disagreement_score":0.74667704,"about_ca_system_score_codex":0.00023943807,"about_ca_system_score_gemma":0.000027819411,"threshold_uncertainty_score":0.9999515},"labels":[],"label_agreement":null},{"id":"W2776882820","doi":"10.1158/0008-5472.can-17-1345","title":"ConsensusDriver Improves upon Individual Algorithms for Predicting Driver Alterations in Different Cancer Types and Individual Patients","year":2017,"lang":"en","type":"article","venue":"Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Cancer; Algorithm; Computer science; Computational biology; Medicine; Biology; Internal medicine","score_opus":0.6910529857859166,"score_gpt":0.6218502542468978,"score_spread":0.06920273153901879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776882820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99406236,0.000118790995,0.0008097489,0.0008113506,0.0006809739,0.001569275,0.0017590709,0.00002292745,0.00016547424],"genre_scores_gemma":[0.94979036,0.00020169061,0.04740934,0.00005855181,0.000839252,0.0013371306,0.000013367156,0.000050469174,0.00029983607],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99716276,0.0005295271,0.0005229457,0.0005000939,0.00071894017,0.00056574534],"domain_scores_gemma":[0.98187625,0.016878735,0.0002165493,0.0004319797,0.0004174506,0.00017905056],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026361044,0.00017912778,0.00044836395,0.00014843694,0.0006169616,0.0003135639,0.00047647805,0.00017696587,0.00011583493],"category_scores_gemma":[0.03814259,0.00014210882,0.00005638622,0.000081271784,0.00050163403,0.00013548827,0.0004168479,0.00055492163,0.0000021713242],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001063167,0.0010646043,0.5071095,0.0010922786,0.0008778756,0.000018119828,0.0059015774,0.000008632028,0.003193449,0.027120642,0.012820605,0.43972954],"study_design_scores_gemma":[0.0067640957,0.000540737,0.5990061,0.0006652169,0.00018484704,5.7811695e-7,0.00023556696,0.0013028167,0.007583956,0.38260296,0.00067665876,0.00043646828],"about_ca_topic_score_codex":0.0004349605,"about_ca_topic_score_gemma":0.0006874936,"teacher_disagreement_score":0.43929306,"about_ca_system_score_codex":0.00014000772,"about_ca_system_score_gemma":0.00017494422,"threshold_uncertainty_score":0.96995956},"labels":[],"label_agreement":null},{"id":"W2782791289","doi":"10.1186/s12874-017-0456-8","title":"Comparison of nuisance parameters in pediatric versus adult randomized trials: a meta-epidemiologic empirical evaluation","year":2018,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"European Commission","keywords":"Medicine; Meta-analysis; Randomized controlled trial; Relative risk; Confidence interval; Sample size determination; Pediatrics; Rate ratio; Adverse effect; Internal medicine; Statistics","score_opus":0.9932412847400476,"score_gpt":0.8328314045220102,"score_spread":0.16040988021803737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782791289","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10519962,0.0013603038,0.88424057,0.0021142026,0.0020869963,0.0036398962,0.00001822067,0.0000621327,0.00127809],"genre_scores_gemma":[0.0785919,0.0006344561,0.91820806,0.00020267903,0.0010002693,0.0013011895,0.0000034109294,0.000034755445,0.000023252012],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.17814496,0.80271274,0.009695373,0.0015430994,0.0062574274,0.0016464023],"domain_scores_gemma":[0.0095328195,0.9846292,0.0017221255,0.0010674766,0.0023604305,0.0006879287],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7843372,0.00039322264,0.010927012,0.00079576176,0.000108873544,0.000018344082,0.0012506543,0.001298959,0.004288663],"category_scores_gemma":[0.9985229,0.00024604838,0.0013717175,0.0017552207,0.0049213204,0.000059076203,0.00049251015,0.0022188548,0.000084934174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5459636,0.0029788965,0.013321831,0.0015979018,0.0033966913,0.000035865232,0.0019773587,0.00005674143,0.00008113761,0.26747844,0.024957588,0.13815397],"study_design_scores_gemma":[0.08712043,0.0012550122,0.00045730767,0.0000722751,0.0024031908,0.000002388638,0.0002481988,0.034380138,0.00058167643,0.8732274,0.00004228523,0.00020969922],"about_ca_topic_score_codex":0.00019745981,"about_ca_topic_score_gemma":0.00057547906,"teacher_disagreement_score":0.60574895,"about_ca_system_score_codex":0.00019734808,"about_ca_system_score_gemma":0.0017998529,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W2789386439","doi":"10.1016/j.conctc.2018.03.002","title":"A novel approach for analyzing data on recurrent events with duration to estimate the combined cumulative rate of both variables over time","year":2018,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; AstraZeneca","keywords":"Estimator; Censoring (clinical trials); Statistics; Normality; Event (particle physics); Measure (data warehouse); Covariate; Computer science; Mathematics; Econometrics; Data mining","score_opus":0.8631519916147071,"score_gpt":0.6643119878506705,"score_spread":0.19884000376403665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789386439","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002262095,0.00006471072,0.982189,0.0041645337,0.00038380243,0.006567998,0.0021596728,0.00010253865,0.0021056207],"genre_scores_gemma":[0.12154941,0.000029642459,0.876624,0.00048630996,0.00036541687,0.0003950683,0.00032445625,0.000060643815,0.00016503647],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98100847,0.012324193,0.0052000196,0.000791167,0.00037601538,0.00030013762],"domain_scores_gemma":[0.59324783,0.3951507,0.0034701363,0.007093729,0.00078029226,0.00025728234],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07187845,0.00033973876,0.0020188198,0.00010989087,0.00042208654,0.000072512434,0.0030951418,0.00023610711,0.00004752306],"category_scores_gemma":[0.42497158,0.00021175192,0.00031880426,0.0005984556,0.00082497287,0.00021370978,0.0011560834,0.0005147874,0.000016457394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0427103,0.01859921,0.0038835227,0.00048289448,0.0061109276,0.0000011680322,0.0010694199,0.00015296174,0.0022326112,0.79884785,0.090588726,0.03532039],"study_design_scores_gemma":[0.020977413,0.007451802,0.0048113856,0.0015626559,0.001785551,0.0000017017561,0.00009225508,0.24378885,0.00037459008,0.71131057,0.0068644024,0.0009788444],"about_ca_topic_score_codex":0.000027375076,"about_ca_topic_score_gemma":0.000015285992,"teacher_disagreement_score":0.3877606,"about_ca_system_score_codex":0.000040231,"about_ca_system_score_gemma":0.00037547472,"threshold_uncertainty_score":0.95569646},"labels":[],"label_agreement":null},{"id":"W2789495180","doi":"10.1177/2472555218763608","title":"Statistical Behaviors: Personal and Computer-Aided Observations","year":2018,"lang":"en","type":"article","venue":"SLAS DISCOVERY","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Statistician; Statistical analysis; Plan (archaeology); Psychology; Radiation oncology; Medical education; Medicine; Statistics; Radiation therapy; Internal medicine; History; Pathology; Mathematics; Archaeology","score_opus":0.5167787290571915,"score_gpt":0.5332105817954129,"score_spread":0.016431852738221453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789495180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34582245,0.000009406671,0.65208465,0.00020164173,0.0006747999,0.0002219318,0.00039405958,0.00007182159,0.0005192055],"genre_scores_gemma":[0.18073316,0.000005897195,0.8175135,0.0003335484,0.0009368121,0.000021065487,0.00000777964,0.000028807872,0.0004193837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981486,0.00032296602,0.0005367898,0.0003888259,0.0003158886,0.0002869171],"domain_scores_gemma":[0.98070997,0.018655187,0.00011721409,0.000268147,0.000102446786,0.00014704339],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00085283734,0.00017317479,0.00040025698,0.000040155574,0.00014349582,0.00014550921,0.00014141259,0.00011576696,0.00038561883],"category_scores_gemma":[0.013332521,0.00014825053,0.00006607747,0.00012295933,0.0006633101,0.00020483306,0.00015716553,0.00019726071,0.000056556022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006705603,0.00024404624,0.0073948633,0.000058069527,0.00005117391,0.0000168114,0.00025951568,4.7221448e-8,0.00021775461,0.97477263,0.011267669,0.005650358],"study_design_scores_gemma":[0.0006797923,0.00040074476,0.066619106,0.00006715287,0.00012684034,0.000010158987,0.000063788655,0.0012306375,0.00018261612,0.929938,0.00045018893,0.00023094265],"about_ca_topic_score_codex":0.000019280811,"about_ca_topic_score_gemma":0.000016534736,"teacher_disagreement_score":0.16542888,"about_ca_system_score_codex":0.000032147127,"about_ca_system_score_gemma":0.00006211654,"threshold_uncertainty_score":0.9949786},"labels":[],"label_agreement":null},{"id":"W2790026935","doi":"10.1016/j.jclinepi.2018.02.001","title":"The win ratio approach did not alter study conclusions and may mitigate concerns regarding unequal composite end points in kidney transplant trials","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier de l’Université de Montréal; Ottawa Hospital; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Hazard ratio; Medicine; Confidence interval; Ramipril; Placebo; Kidney transplantation; Creatinine; Internal medicine; Randomized controlled trial; Relative risk; Urology; Statistical significance; Clinical trial; Transplantation; Surgery; Blood pressure; Pathology","score_opus":0.8016224349326246,"score_gpt":0.6587889254959833,"score_spread":0.1428335094366413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790026935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.749063,0.0001827412,0.21309972,0.028658675,0.0057102214,0.002043008,0.0002123128,0.000034577504,0.0009957532],"genre_scores_gemma":[0.71764183,0.00046532208,0.2745848,0.0042604883,0.002936215,0.0000182032,0.0000016086178,0.0000328439,0.000058671027],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88445234,0.09523673,0.018250007,0.0007184007,0.00057700975,0.00076550525],"domain_scores_gemma":[0.1980927,0.793338,0.006693359,0.0006167432,0.00041984924,0.00083935546],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2532452,0.00034941992,0.006837874,0.000116045776,0.00028224764,0.00004039225,0.000674943,0.00054026995,0.00009501003],"category_scores_gemma":[0.80239046,0.00019247792,0.0008268315,0.00017430465,0.0019846526,0.00010446851,0.00023753793,0.0019631332,0.000009460446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030635437,0.005134763,0.50146323,0.00028852446,0.004210117,0.00050335395,0.004082727,0.000050311308,0.0012530818,0.37646657,0.024444817,0.05146708],"study_design_scores_gemma":[0.022092963,0.006333483,0.065309346,0.0008167152,0.0012128684,0.0001528086,0.0006382684,0.0041003413,0.0003180442,0.89660984,0.0018886686,0.00052665634],"about_ca_topic_score_codex":0.000023658666,"about_ca_topic_score_gemma":0.000022360584,"teacher_disagreement_score":0.6981013,"about_ca_system_score_codex":0.00004804446,"about_ca_system_score_gemma":0.00027631645,"threshold_uncertainty_score":0.85289466},"labels":[],"label_agreement":null},{"id":"W2790250792","doi":"10.1371/journal.pone.0190615","title":"The development of a stochastic mathematical model of Alzheimer’s disease to help improve the design of clinical trials of potential treatments","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Clinical trial; Disease; Drug development; Neuroimaging; Medicine; Clinical study design; Alzheimer's disease; Alzheimer's Disease Neuroimaging Initiative; Intensive care medicine; Computer science; Bioinformatics; Drug; Pathology; Psychiatry; Biology","score_opus":0.8569185913835018,"score_gpt":0.5894300478054639,"score_spread":0.26748854357803786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790250792","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08678542,0.000046072593,0.90955335,0.00020078286,0.000111624664,0.0029003976,0.00031780312,0.00001400212,0.000070562055],"genre_scores_gemma":[0.3152213,0.000006592136,0.68442446,0.000015513542,0.00011743791,0.0001331978,7.2984665e-7,0.000027327987,0.000053428415],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9888242,0.0030605951,0.006263802,0.00034479774,0.0011989226,0.0003077133],"domain_scores_gemma":[0.8910471,0.10413809,0.0026493166,0.0011018991,0.0007853312,0.0002782588],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023920126,0.00023508201,0.0023036406,0.000057929166,0.00008273648,0.000008829246,0.0005906099,0.0001491831,0.000099636825],"category_scores_gemma":[0.2691423,0.00012357588,0.00041272843,0.00017186863,0.0008590083,0.000025842328,0.000262957,0.00016440418,0.000013261427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.051155463,0.09588465,0.00019471179,0.004987065,0.04529802,0.000007361996,0.008661794,0.001057676,0.357743,0.2734802,0.0012526159,0.16027746],"study_design_scores_gemma":[0.002267486,0.001166288,0.00011977181,0.00074207707,0.005372939,1.4732639e-7,0.000102076534,0.0694123,0.11892073,0.80173254,2.632098e-7,0.0001633944],"about_ca_topic_score_codex":0.0000016580373,"about_ca_topic_score_gemma":7.17529e-7,"teacher_disagreement_score":0.52825236,"about_ca_system_score_codex":0.000018581606,"about_ca_system_score_gemma":0.00047163622,"threshold_uncertainty_score":0.8290286},"labels":[],"label_agreement":null},{"id":"W2790860674","doi":"10.1007/s11606-018-4344-7","title":"Application and impact of run-in studies","year":2018,"lang":"en","type":"review","venue":"Journal of General Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; Royal College of Physicians and Surgeons of Canada; Engelberg Foundation; Laura and John Arnold Foundation; Brigham and Women's Hospital","keywords":"Medicine; MEDLINE; Intensive care medicine","score_opus":0.7451797080169629,"score_gpt":0.7055792509902872,"score_spread":0.039600457026675695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790860674","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025094717,0.98786086,0.010355533,0.000069791895,0.00090272777,0.00031140275,0.000016592538,0.0000033006609,0.00022882555],"genre_scores_gemma":[0.000029633047,0.89881134,0.097827725,0.000019037834,0.003063621,0.0000067559636,4.059607e-7,0.00002968385,0.00021181694],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947755,0.0007892026,0.003614047,0.00019662434,0.00045390136,0.00017075866],"domain_scores_gemma":[0.9756485,0.019585453,0.0038461257,0.00025762597,0.00050802913,0.00015422591],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058494136,0.0003104034,0.0045700474,0.00039199795,0.00001177204,0.0000057099523,0.00037180824,0.00021123199,0.00007842932],"category_scores_gemma":[0.055823613,0.00015857763,0.00051776634,0.00022018346,0.000451101,0.000040713418,0.00010841924,0.0006273618,0.0000022680147],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001534952,0.00011656596,0.00008206769,0.011127708,0.0016550812,0.00006271608,0.00015879623,2.0300439e-7,0.00001938626,0.0022797885,0.016222956,0.96812123],"study_design_scores_gemma":[0.002717497,0.006599414,0.00015543443,0.15537778,0.004679078,0.0012004068,0.00007333652,0.00006221869,0.000017377895,0.7113907,0.11730389,0.0004228663],"about_ca_topic_score_codex":0.000045228764,"about_ca_topic_score_gemma":0.000004187422,"teacher_disagreement_score":0.9676984,"about_ca_system_score_codex":0.00020210296,"about_ca_system_score_gemma":0.000120919205,"threshold_uncertainty_score":0.9521296},"labels":[],"label_agreement":null},{"id":"W2791409969","doi":"10.1136/bmj.k698","title":"Key design considerations for adaptive clinical trials: a primer for clinicians","year":2018,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Bill and Melinda Gates Foundation","keywords":"Clinical trial; Adaptive design; Computer science; Resource (disambiguation); Key (lock); Psychological intervention; Clinical study design; Research design; Risk analysis (engineering); Drug trial; Medical physics; Medicine; Management science; Intensive care medicine; Engineering; Psychiatry; Pathology; Computer security","score_opus":0.9552590505586375,"score_gpt":0.7305588347048191,"score_spread":0.22470021585381839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791409969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008287303,0.000016035801,0.9824475,0.004084447,0.0028332965,0.008480642,0.00046488454,0.0001264803,0.0014638606],"genre_scores_gemma":[0.0027491276,0.0000067341534,0.9857111,0.0019001786,0.0072241267,0.0016786607,0.0000021597018,0.00006744993,0.00066048553],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878659,0.0065807104,0.0042762975,0.000605088,0.00025045706,0.00042151476],"domain_scores_gemma":[0.2271218,0.7696115,0.0013611476,0.0006980884,0.0009799917,0.00022747248],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08004504,0.00023293578,0.0016770582,0.000055619083,0.00024763794,0.00005949972,0.0002038016,0.0004406294,0.00042427686],"category_scores_gemma":[0.8862401,0.00018598321,0.0007820483,0.00009719199,0.00050689426,0.000056203244,0.00005641663,0.00022831056,0.000099495715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022174667,0.00038030883,0.000020598833,0.000035928675,0.00037833716,0.0000017208284,0.00014869428,9.956279e-7,0.00003507764,0.4802012,0.49418795,0.022391716],"study_design_scores_gemma":[0.0042715496,0.0024594876,0.000035252244,0.00006953437,0.000614351,0.0000029738844,0.00007779279,0.004824508,0.0007724234,0.9715386,0.015080159,0.00025338662],"about_ca_topic_score_codex":0.000002557469,"about_ca_topic_score_gemma":0.000015598023,"teacher_disagreement_score":0.8061951,"about_ca_system_score_codex":0.000030571522,"about_ca_system_score_gemma":0.0004435697,"threshold_uncertainty_score":0.9472872},"labels":[],"label_agreement":null},{"id":"W2791886356","doi":"10.2147/clep.s156708","title":"Critical concepts in adaptive clinical trials","year":2018,"lang":"en","type":"review","venue":"Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of British Columbia","funders":"Bill and Melinda Gates Foundation","keywords":"Adaptive design; Sample size determination; Clinical trial; Bayesian probability; Clinical study design; Computer science; Randomization; Research design; Medicine; Machine learning; Data mining; Artificial intelligence; Statistics; Mathematics; Pathology","score_opus":0.9828560699097272,"score_gpt":0.8344826322595544,"score_spread":0.14837343765017275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791886356","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012665531,0.90530485,0.0692728,0.00075070467,0.017587302,0.003616765,0.0005528015,0.00023965181,0.002673855],"genre_scores_gemma":[7.351027e-7,0.5928393,0.39564463,0.001666866,0.009115222,0.00037010422,0.00001664041,0.00015904292,0.00018748597],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.443837,0.4803655,0.067969926,0.004755162,0.000581333,0.002491081],"domain_scores_gemma":[0.011919792,0.9713263,0.011296142,0.0031597912,0.0006010366,0.0016969534],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.5633891,0.0016739414,0.05982497,0.00038207436,0.00012318845,0.000033743647,0.0024515942,0.010827915,0.0025100058],"category_scores_gemma":[0.99587655,0.0011635678,0.011624728,0.0007886997,0.01010111,0.000103127706,0.0012415797,0.009490674,0.0029526805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023097526,0.0007964319,0.0001856826,0.0031071363,0.0005573602,0.00010015079,0.0000043144064,2.1317234e-8,6.713241e-10,0.26490897,0.053214606,0.67689437],"study_design_scores_gemma":[0.001061293,0.0011587217,0.000042366322,0.008489868,0.0020523625,0.00002182616,0.0000058217765,0.00004714408,7.1036417e-9,0.5312111,0.4552907,0.0006188042],"about_ca_topic_score_codex":0.00001455926,"about_ca_topic_score_gemma":0.000017916562,"teacher_disagreement_score":0.67627555,"about_ca_system_score_codex":0.00023914473,"about_ca_system_score_gemma":0.001591173,"threshold_uncertainty_score":0.99960077},"labels":[],"label_agreement":null},{"id":"W2792630427","doi":"10.14740/jocmr3349e","title":"The Impact of the Underlying Risk in Control Group and Effect Measures in Non-Inferiority Trials With Time-to-Event Data: A Simulation Study","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Medicine Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; McGill University Health Centre","funders":"","keywords":"Medicine; Event (particle physics); Event data; Data mining; Computer science","score_opus":0.8463705432990413,"score_gpt":0.7558805997036814,"score_spread":0.09048994359535989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792630427","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791065,0.00008610183,0.016131587,0.0013406342,0.00028122467,0.002962839,0.000015369318,0.000002948082,0.0000728046],"genre_scores_gemma":[0.99490464,0.00007965522,0.0039294856,0.000017445727,0.0010282708,0.000012886805,9.145069e-8,0.000018689461,0.000008842912],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9378663,0.052613232,0.005982957,0.0004050786,0.0026510605,0.00048137433],"domain_scores_gemma":[0.2798184,0.71559453,0.0021731136,0.0010812125,0.000998963,0.0003337821],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39800954,0.00017737538,0.0025118971,0.00024268283,0.00014708439,0.000040772182,0.00093703216,0.00015865953,0.000045744186],"category_scores_gemma":[0.84031296,0.0000646412,0.00019734722,0.0008385452,0.0011451313,0.000094792544,0.000305358,0.0021414808,0.0000027726803],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0318863,0.0017120047,0.7610212,0.00008046289,0.0008286264,0.00004074828,0.0005415425,0.00027256587,0.00015070075,0.00007505985,0.00075734337,0.20263343],"study_design_scores_gemma":[0.019703291,0.02889923,0.8768665,0.0012565039,0.0002726228,0.000004717872,0.0002480184,0.011832653,0.0000067181177,0.060802992,0.000026257876,0.00008044841],"about_ca_topic_score_codex":0.00028658824,"about_ca_topic_score_gemma":0.00033085878,"teacher_disagreement_score":0.66298133,"about_ca_system_score_codex":0.000107317894,"about_ca_system_score_gemma":0.0003454237,"threshold_uncertainty_score":0.9303788},"labels":[],"label_agreement":null},{"id":"W2794650963","doi":"10.1002/sim.7641","title":"Design of cancer trials based on progression‐free survival with intermittent assessment","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Censoring (clinical trials); Sample size determination; Medicine; Clinical trial; Randomized controlled trial; Clinical endpoint; Progression-free survival; Survival analysis; Confidence interval; Cancer; Clinical study design; Research design; Intensive care medicine; Oncology; Overall survival; Statistics; Internal medicine; Mathematics","score_opus":0.6283440379913406,"score_gpt":0.6537779914408499,"score_spread":0.025433953449509272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794650963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034239757,0.000020977888,0.9939245,0.00096184417,0.0012679755,0.0012816603,0.0003936835,0.000032907963,0.0017740545],"genre_scores_gemma":[0.031075828,0.000030640484,0.9677166,0.00028495808,0.00059127394,0.00017959955,0.000005803719,0.000046724086,0.000068571935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924922,0.0033799657,0.0019888184,0.00043285103,0.0013610541,0.0003451234],"domain_scores_gemma":[0.874663,0.12312911,0.00089382706,0.0007221411,0.000450597,0.00014131067],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018568445,0.0002810335,0.0017375668,0.0001936702,0.000047151225,0.000009700466,0.00043064976,0.00012432273,0.0018110315],"category_scores_gemma":[0.19240174,0.00016502301,0.000040265844,0.00034429476,0.0010722047,0.000017379638,0.00007312739,0.00038745793,0.0000032516098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009262231,0.0022803172,0.0105021,0.0013874935,0.0005322801,0.00028603786,0.000760358,0.00024483702,0.0012362801,0.6041833,0.06061654,0.30870822],"study_design_scores_gemma":[0.010341949,0.0076114913,0.004863686,0.003727078,0.00041911914,0.0000010446859,0.0001278015,0.021525554,0.0012115008,0.94973385,0.00014267622,0.00029421895],"about_ca_topic_score_codex":0.000045034805,"about_ca_topic_score_gemma":0.0000689359,"teacher_disagreement_score":0.34555057,"about_ca_system_score_codex":0.00013159642,"about_ca_system_score_gemma":0.00030386169,"threshold_uncertainty_score":0.99910146},"labels":[],"label_agreement":null},{"id":"W2799978916","doi":"10.1017/s0033291718001289","title":"Equivalence and non-inferiority testing in psychotherapy research","year":2018,"lang":"en","type":"letter","venue":"Psychological Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Equivalence (formal languages); Content (measure theory); Psychology; Psychotherapist; Information retrieval; Computer science; Mathematics; Discrete mathematics","score_opus":0.9178104425000236,"score_gpt":0.7194051522256781,"score_spread":0.1984052902743455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799978916","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011755886,0.00048028538,0.018113973,0.9251283,0.0037591008,0.002586379,0.000053921478,0.0002453805,0.037876807],"genre_scores_gemma":[0.0022536127,0.00088997855,0.6147395,0.35803378,0.022917517,0.0002552691,0.0000051767356,0.00012366379,0.0007815564],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9904964,0.0034918054,0.0017764291,0.0016201661,0.0014485623,0.0011666401],"domain_scores_gemma":[0.84907985,0.14874396,0.00036780405,0.0011646784,0.00041703432,0.00022664723],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.018952448,0.00053419714,0.0019040948,0.00040222864,0.00013176717,0.00004099877,0.0009613207,0.002010192,0.0018848642],"category_scores_gemma":[0.2121715,0.00035236153,0.00008339335,0.0011323722,0.003533221,0.000039792645,0.0001464573,0.0069389804,0.000107336076],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017743111,0.00019479298,0.0005799933,0.00043443477,0.000027827558,0.0006531769,0.00014081963,4.8462163e-9,0.00019704307,0.0014585281,0.9490938,0.04704214],"study_design_scores_gemma":[0.0019863434,0.002724087,0.0058710473,0.001979573,0.000033229262,0.00004369817,0.00001602991,0.000020421932,0.000004771738,0.9573196,0.02963056,0.00037063519],"about_ca_topic_score_codex":0.00003977977,"about_ca_topic_score_gemma":0.000004467031,"teacher_disagreement_score":0.9558611,"about_ca_system_score_codex":0.000076922835,"about_ca_system_score_gemma":0.000020673933,"threshold_uncertainty_score":0.99989283},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2801998539","doi":"10.1093/jnci/djy059","title":"Simulation Modeling of Cancer Clinical Trials: Application to Omitting Radiotherapy in Low-risk Breast Cancer","year":2018,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; Princess Margaret Cancer Centre; Hamilton Health Sciences; Queen's University","funders":"National Center for Advancing Translational Sciences; National Cancer Institute; National Institutes of Health; American Society of Preventive Oncology; Breast Cancer Research Foundation","keywords":"Medicine; Breast cancer; Hazard ratio; Lumpectomy; Confidence interval; Oncology; Radiation therapy; Internal medicine; Cancer; Clinical trial; Proportional hazards model; Clinical endpoint; Gynecology; Mastectomy","score_opus":0.674816908399467,"score_gpt":0.6724987019154679,"score_spread":0.0023182064839990524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801998539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3327286,0.00040270106,0.6549467,0.0037904433,0.0064522848,0.0010182193,0.000560821,0.000015257991,0.00008498884],"genre_scores_gemma":[0.8592183,0.00053010887,0.13012826,0.0007902939,0.009205797,0.000074156,3.6364042e-7,0.000030394896,0.00002232943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99293834,0.0016559938,0.003744913,0.00028046663,0.0011618768,0.00021839641],"domain_scores_gemma":[0.9752216,0.018626219,0.0033668054,0.00022909,0.0024138836,0.00014240602],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020698426,0.00019029365,0.0010671961,0.00021140452,0.00012008472,0.000028807015,0.0005722677,0.00020826163,0.00015749627],"category_scores_gemma":[0.08777583,0.00012875059,0.00041379244,0.00065420073,0.00020994816,0.00023978594,0.00007162857,0.00060429063,0.0000017615627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016396664,0.00021780693,0.016518472,0.000075457494,0.00033814955,5.044714e-7,0.00026954402,0.8708676,0.0005865876,0.003157478,0.00054338033,0.10578534],"study_design_scores_gemma":[0.0037550584,0.00010594803,0.012381638,0.0013479681,0.000297411,0.0000038579888,0.000021799557,0.8072314,0.00057451817,0.17295343,0.0010846688,0.0002422826],"about_ca_topic_score_codex":0.00049698225,"about_ca_topic_score_gemma":0.00067096244,"teacher_disagreement_score":0.5264897,"about_ca_system_score_codex":0.0007601902,"about_ca_system_score_gemma":0.0010220502,"threshold_uncertainty_score":0.9199082},"labels":[],"label_agreement":null},{"id":"W2804969681","doi":"10.1111/jth.14153","title":"Pharmacokinetics and the transition to extended half‐life factor concentrates: communication from the SSC of the ISTH","year":2018,"lang":"en","type":"review","venue":"Journal of Thrombosis and Haemostasis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Medicine; Pharmacokinetics; Population; Blood sampling; Bleed; Intensive care medicine; Pharmacology; Internal medicine; Surgery","score_opus":0.6288552473983134,"score_gpt":0.5719226758372812,"score_spread":0.056932571561032264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804969681","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087954814,0.9813723,0.005796111,0.008496611,0.00066659006,0.0016195757,0.0010845222,0.000007606546,0.00007714726],"genre_scores_gemma":[0.0011669289,0.9515714,0.04609339,0.0007472081,0.000365149,0.000013931069,0.0000022006166,0.00003507477,0.0000047227873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932124,0.0038149927,0.002067927,0.00020439338,0.0005223453,0.00017795964],"domain_scores_gemma":[0.9526443,0.04383556,0.0023320648,0.0006993659,0.0003451684,0.00014352283],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038969738,0.000318708,0.0023064818,0.0000363105,0.0002476184,0.00012052206,0.00091273914,0.00021739048,0.00018267718],"category_scores_gemma":[0.012398424,0.0001273883,0.0006296027,0.0002264863,0.0010279781,0.000057715748,0.00021031687,0.00069863565,0.000001764591],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004624441,0.00037112742,0.000015526455,0.0040509645,0.004284451,0.0000013849997,0.0052860356,6.298745e-7,0.000013305534,0.014374396,0.031070745,0.940069],"study_design_scores_gemma":[0.007492237,0.0006049291,0.00072948023,0.037765767,0.029592367,0.000053786625,0.0015247072,0.00009976789,0.00028514556,0.41247982,0.50854474,0.0008272353],"about_ca_topic_score_codex":0.000033524804,"about_ca_topic_score_gemma":0.0000076718225,"teacher_disagreement_score":0.93924177,"about_ca_system_score_codex":0.000043340136,"about_ca_system_score_gemma":0.00014476215,"threshold_uncertainty_score":0.99592054},"labels":[],"label_agreement":null},{"id":"W2805176315","doi":"10.1002/sim.7837","title":"A single‐index threshold Cox proportional hazard model for identifying a treatment‐sensitive subset based on multiple biomarkers","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Canadian Cancer Society","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Proportional hazards model; Estimator; Statistics; Hazard; Hazard ratio; Mathematics; Likelihood function; Computer science; Medicine; Oncology; Maximum likelihood; Biology; Confidence interval","score_opus":0.5433031768834886,"score_gpt":0.5514168099636382,"score_spread":0.008113633080149563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805176315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043620644,0.0000073204,0.9891508,0.0005954544,0.000737206,0.0016549845,0.0025265713,0.00007275459,0.0008927981],"genre_scores_gemma":[0.34630737,0.000004327092,0.6524093,0.00040886112,0.00041374538,0.000152759,0.00008555992,0.000054298158,0.00016378851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642414,0.0003198065,0.001301064,0.00065948465,0.0007679061,0.000527626],"domain_scores_gemma":[0.94326353,0.055162076,0.00042320188,0.00047970618,0.00046877048,0.00020269616],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028488995,0.0003682244,0.0009446572,0.0002669554,0.00015347262,0.00002539137,0.00018399568,0.00019252439,0.0001811615],"category_scores_gemma":[0.12200315,0.0002839303,0.000093913295,0.00028695262,0.001038013,0.00003780517,0.000034894554,0.00021276755,0.00001171482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026062548,0.007931798,0.016719278,0.0020862196,0.001565644,0.0009244887,0.005593231,0.0016505161,0.00834155,0.7379597,0.12180312,0.0693619],"study_design_scores_gemma":[0.0049046483,0.0013818479,0.000506392,0.00032074633,0.00013032573,0.000002262732,0.00009385498,0.522146,0.0005366532,0.46975777,0.000041373125,0.0001781438],"about_ca_topic_score_codex":0.00003367732,"about_ca_topic_score_gemma":0.0004233498,"teacher_disagreement_score":0.5204955,"about_ca_system_score_codex":0.00036068258,"about_ca_system_score_gemma":0.00019131797,"threshold_uncertainty_score":0.99996126},"labels":[],"label_agreement":null},{"id":"W2807052362","doi":"10.1007/s11606-018-4504-9","title":"Design and Interpretation of Noninferiority Trials","year":2018,"lang":"en","type":"letter","venue":"Journal of General Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta Hospital; University of Alberta","funders":"","keywords":"Medicine; Interpretation (philosophy); MEDLINE; Medical physics; Intensive care medicine","score_opus":0.6128194483842326,"score_gpt":0.591942085636786,"score_spread":0.02087736274744667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807052362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011668879,0.0004269216,0.87957084,0.111449346,0.006265448,0.00041967243,0.000025713967,0.000009994661,0.0006651889],"genre_scores_gemma":[0.0007044305,0.00045241995,0.89818585,0.062115878,0.036719497,0.000005254569,0.000001918684,0.00006968657,0.0017450665],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882247,0.0049766805,0.005189499,0.00027237317,0.0010821684,0.00025460217],"domain_scores_gemma":[0.9108209,0.08025218,0.0071594333,0.0003434577,0.0012587176,0.00016531242],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023439018,0.0003821381,0.004007055,0.0004034992,0.00002521279,0.000025839054,0.00054996775,0.0006989648,0.00078816805],"category_scores_gemma":[0.21561185,0.00023280866,0.00039810565,0.00011834832,0.0006896638,0.00008649974,0.00010705402,0.0020337112,0.0000033914785],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012414139,0.00003996019,0.000015614123,0.00045445474,0.0007711817,0.0003005806,0.00026640866,0.0000012342915,0.0016490306,0.00030704297,0.9794443,0.015508772],"study_design_scores_gemma":[0.0047278595,0.008881894,0.000061339095,0.008959438,0.0030320236,0.00088168826,0.000031660435,0.0019087491,0.0038879968,0.91676784,0.050448377,0.000411131],"about_ca_topic_score_codex":0.00003192472,"about_ca_topic_score_gemma":6.426966e-7,"teacher_disagreement_score":0.9289959,"about_ca_system_score_codex":0.00008998058,"about_ca_system_score_gemma":0.00013717116,"threshold_uncertainty_score":0.94936615},"labels":[],"label_agreement":null},{"id":"W2807133526","doi":"10.1161/circoutcomes.117.004419","title":"Examining the Influence of Component Outcomes on the Composite at the Design Stage","year":2018,"lang":"en","type":"article","venue":"Circulation Cardiovascular Quality and Outcomes","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre","funders":"","keywords":"Medicine; Component (thermodynamics); Heart failure; Clinical trial; Internal medicine; Quality of life (healthcare); Composite number; Ambulatory; Gerontology; Computer science; Nursing","score_opus":0.6531205185438971,"score_gpt":0.5131141734044478,"score_spread":0.14000634513944932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807133526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87471384,0.00012852503,0.12192051,0.0017600323,0.0002269161,0.00094364706,0.000035680627,0.000040912277,0.0002299054],"genre_scores_gemma":[0.98496574,0.000020066678,0.013375837,0.0014112485,0.00008502202,0.000043041444,0.0000012456566,0.000021523238,0.00007624901],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9909566,0.0064397315,0.0010201496,0.00035845477,0.0009908263,0.0002342384],"domain_scores_gemma":[0.90673554,0.09115032,0.000398918,0.0014592506,0.00019932084,0.000056642442],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019621443,0.00023858216,0.00091427995,0.000032675194,0.00063604215,0.00006489263,0.00041519522,0.00011294882,0.000062329476],"category_scores_gemma":[0.03383375,0.000104758044,0.0006083563,0.00018516937,0.0010762278,0.000055761146,0.00021828627,0.00025278193,0.000021747765],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002635248,0.00021719965,0.46329215,0.00036700847,0.0072047105,0.000006839478,0.004240512,0.010638852,0.0015259981,0.49904156,0.00032918045,0.01287246],"study_design_scores_gemma":[0.0005886496,0.000036825983,0.90864164,0.00004042211,0.0003363943,0.0000024323483,0.00023070547,0.00024617356,0.0006391379,0.08873788,0.00034373635,0.00015598083],"about_ca_topic_score_codex":0.00006289946,"about_ca_topic_score_gemma":0.0000054974043,"teacher_disagreement_score":0.4453495,"about_ca_system_score_codex":0.000053482017,"about_ca_system_score_gemma":0.000023208968,"threshold_uncertainty_score":0.9743047},"labels":[],"label_agreement":null},{"id":"W2807223243","doi":"10.1002/sim.7689","title":"Regulatory assessment of drug dissolution profiles comparability via maximum deviation","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Comparability; Bioequivalence; Statistics; Standard deviation; Mathematics; Dissolution testing; Benchmark (surveying); Similarity (geometry); Computer science; Econometrics; Medicine; Drug; Pharmacology; Pharmacokinetics","score_opus":0.3097714492522006,"score_gpt":0.5680756412596896,"score_spread":0.25830419200748894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807223243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036656212,0.00002311257,0.9589549,0.0003625201,0.0009605884,0.0006762319,0.00020662174,0.00004035415,0.0021195016],"genre_scores_gemma":[0.42221507,0.000008206198,0.5773846,0.00004024987,0.000263303,0.000021164702,0.000015195073,0.000014432539,0.000037807706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99582857,0.0011077579,0.00166422,0.00036744002,0.00075677485,0.0002752278],"domain_scores_gemma":[0.9744878,0.023756834,0.0006129361,0.0005659462,0.00046720155,0.00010927387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007470231,0.00018884259,0.00086888537,0.00012373172,0.00006097667,0.000004864201,0.00021791377,0.00010632037,0.0007681364],"category_scores_gemma":[0.054238692,0.000152889,0.000035058918,0.00030984124,0.0013094866,0.000041291158,0.00007440526,0.0002917557,0.0000079118845],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014894785,0.0004912255,0.03254878,0.000837889,0.00005619357,0.0000073934734,0.00067875086,0.000003679839,0.0011715889,0.92236614,0.0152961165,0.02639327],"study_design_scores_gemma":[0.0010364112,0.00030616228,0.15933853,0.00025926466,0.00007780042,0.0000011591281,0.00009419567,0.006646871,0.0004629167,0.8315724,0.00008503394,0.00011922584],"about_ca_topic_score_codex":0.000074980504,"about_ca_topic_score_gemma":0.000121273755,"teacher_disagreement_score":0.38555887,"about_ca_system_score_codex":0.00018611878,"about_ca_system_score_gemma":0.00009493681,"threshold_uncertainty_score":0.95372784},"labels":[],"label_agreement":null},{"id":"W2807568985","doi":"10.1186/s13063-018-2655-y","title":"Survey of professional views on sharing interim results by the Data Safety Monitoring Board (DSMB): what to share, with whom and why","year":2018,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"Canadian Institutes of Health Research","keywords":"Interim; Medicine; Interim analysis; Clinical trial; Data sharing; Event (particle physics); Safety monitoring; Family medicine; Alternative medicine; Bioinformatics; Internal medicine; Political science; Pathology; Law","score_opus":0.898219477676161,"score_gpt":0.6595940130821966,"score_spread":0.2386254645939644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807568985","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75818974,0.001658898,0.1462108,0.013497657,0.023311123,0.021932868,0.031099865,0.00042247228,0.0036765435],"genre_scores_gemma":[0.19425263,0.00044975782,0.79725736,0.0015077929,0.00424723,0.00024428713,0.00017884932,0.00021334324,0.0016487753],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99163187,0.0044826344,0.0022544963,0.00073686766,0.00059524184,0.000298876],"domain_scores_gemma":[0.8283507,0.16757484,0.0012240936,0.0022794243,0.00035883585,0.00021208047],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048799057,0.00024295751,0.001341716,0.00004950524,0.00017660984,0.00022036977,0.0010426833,0.00013964878,0.00014263394],"category_scores_gemma":[0.31059456,0.00013039597,0.00005215841,0.000248603,0.00028597453,0.00022034704,0.0009464789,0.00028117694,0.00002367267],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.087054364,0.0015019915,0.0064566294,0.0008041903,0.0013020097,0.0000127878575,0.005272857,0.0000027940212,0.005340919,0.008286895,0.43938547,0.44457906],"study_design_scores_gemma":[0.05670416,0.01582028,0.18279207,0.048391312,0.0021447958,0.000019798112,0.004166842,0.0011457913,0.11940387,0.47025964,0.09476601,0.004385439],"about_ca_topic_score_codex":0.00016111688,"about_ca_topic_score_gemma":0.00012634971,"teacher_disagreement_score":0.6510465,"about_ca_system_score_codex":0.000030723368,"about_ca_system_score_gemma":0.000065572065,"threshold_uncertainty_score":0.97946155},"labels":[],"label_agreement":null},{"id":"W287548508","doi":"10.1002/cjs.5550340203","title":"A class of sequential tests for two‐sample composite hypotheses","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Windsor; University of Alberta","funders":"","keywords":"Statistics; Mathematics; Binomial (polynomial); Statistical hypothesis testing; Test (biology); Sample size determination; Algorithm; Applied mathematics; Combinatorics; Biology","score_opus":0.46739090215719564,"score_gpt":0.4983513644980147,"score_spread":0.03096046234081906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W287548508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010201867,0.000067393004,0.97921056,0.00015408192,0.0008076874,0.0002831462,0.008768274,0.0000063206767,0.00050068035],"genre_scores_gemma":[0.13830112,0.000003003207,0.8610001,0.000072911855,0.0005020385,0.0000036138406,0.000007285327,0.000036145557,0.00007376831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974767,0.00025216583,0.0014781527,0.00013434116,0.00028873165,0.00036988914],"domain_scores_gemma":[0.94874084,0.04887752,0.0009282795,0.00020295057,0.000833344,0.0004170877],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015349472,0.00016371848,0.00072027015,0.00019788464,0.00009154925,0.00005000871,0.00030157872,0.00009713492,0.00021137283],"category_scores_gemma":[0.06002578,0.00015011673,0.00013304954,0.00014375041,0.00033341924,0.000048614966,0.000012483093,0.0002177386,0.0000024822384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013663738,0.000107032814,0.0026102352,0.00029357406,0.00016290364,0.00014554524,0.00008533093,0.00013426563,0.0014858958,0.9332988,0.05324007,0.008299665],"study_design_scores_gemma":[0.0013305703,0.00037189195,0.0012220123,0.00012875356,0.00024737758,0.00004323702,0.000023278842,0.00040640272,0.0012433791,0.99131143,0.0035148012,0.00015686445],"about_ca_topic_score_codex":0.0029174434,"about_ca_topic_score_gemma":0.011550305,"teacher_disagreement_score":0.12809926,"about_ca_system_score_codex":0.00013136401,"about_ca_system_score_gemma":0.0009755379,"threshold_uncertainty_score":0.947892},"labels":[],"label_agreement":null},{"id":"W2885084523","doi":"10.1097/phm.0000000000001016","title":"A Tale of Confusion From Overlapping Confidence Intervals","year":2018,"lang":"en","type":"letter","venue":"American Journal of Physical Medicine & Rehabilitation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Confusion; Medicine; Significant difference; Randomized controlled trial; Treatment effect; Statistics; Internal medicine; Mathematics; Psychology","score_opus":0.17506785275682984,"score_gpt":0.5043287647513413,"score_spread":0.3292609119945114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885084523","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37347332,0.00020408508,0.16041842,0.45833212,0.004531047,0.0016896181,0.00036337983,0.00008160599,0.0009063901],"genre_scores_gemma":[0.1706161,0.000012759724,0.7236653,0.07201081,0.033396978,0.000027695885,0.000020225247,0.00016847531,0.00008167864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9917694,0.0027476999,0.0029805764,0.00045662152,0.0017272576,0.0003184493],"domain_scores_gemma":[0.8037402,0.18914627,0.004975132,0.00054537377,0.0014522038,0.00014083216],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.003493292,0.0004187748,0.0033447454,0.00029235252,0.00003814194,0.000013718362,0.00059582025,0.00025207977,0.00039509154],"category_scores_gemma":[0.2188181,0.0002976795,0.00066371635,0.0004567377,0.0041232063,0.00012963965,0.00010224073,0.0018038522,0.000013318263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008216182,0.00066200574,0.00014058083,0.0013913263,0.0009231301,0.000108935244,0.010668972,0.0000022443373,0.008828848,0.0067259828,0.4846671,0.4850593],"study_design_scores_gemma":[0.0013163494,0.057447392,0.0004315563,0.008166345,0.00090439734,0.000011606022,0.0013990187,0.0001354832,0.00017478605,0.91661066,0.013078221,0.00032420974],"about_ca_topic_score_codex":0.00019700457,"about_ca_topic_score_gemma":0.0000014783992,"teacher_disagreement_score":0.90988463,"about_ca_system_score_codex":0.0001371955,"about_ca_system_score_gemma":0.00017546785,"threshold_uncertainty_score":0.99994755},"labels":[],"label_agreement":null},{"id":"W2885560771","doi":"10.14740/jocmr3536w","title":"Illustrating the Sense of a Network Meta-Analysis by Means of Dedicated Plots: A Way for Making It Conceptually Easier and More Immediately Understandable","year":2018,"lang":"en","type":"article","venue":"Journal of Clinical Medicine Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Sense (electronics); Biomedical engineering; Engineering; Electrical engineering","score_opus":0.9409437286820541,"score_gpt":0.7310702457995143,"score_spread":0.20987348288253982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885560771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06547457,0.005254659,0.85193264,0.07070528,0.0011286081,0.002864313,0.0002926048,0.000027238866,0.0023200952],"genre_scores_gemma":[0.6549753,0.00049283914,0.3409324,0.0007440423,0.0025952756,0.000018436867,0.0000013424666,0.00004960654,0.00019076094],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98426807,0.0059780986,0.006231135,0.00037269472,0.0025492804,0.0006007445],"domain_scores_gemma":[0.6532385,0.33896944,0.0031294362,0.00054656254,0.0037397884,0.00037632167],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10884704,0.00022633922,0.0041293073,0.00023927343,0.00017877911,0.000022761136,0.00059998035,0.00033973937,0.0006487355],"category_scores_gemma":[0.4751947,0.0001135737,0.0011496564,0.001422045,0.0058148475,0.00007149118,0.00018320871,0.0014400675,7.387976e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.022435792,0.0029561776,0.008182026,0.002795593,0.42522088,0.00019913782,0.013201719,0.00020544218,0.0013797323,0.09862816,0.39199135,0.032803994],"study_design_scores_gemma":[0.009657337,0.01392195,0.000623004,0.0010703133,0.12596945,0.000040432427,0.012378472,0.015314131,0.00065745995,0.8165743,0.0034311935,0.00036198684],"about_ca_topic_score_codex":0.000023534276,"about_ca_topic_score_gemma":0.000023586117,"teacher_disagreement_score":0.7179461,"about_ca_system_score_codex":0.000035955196,"about_ca_system_score_gemma":0.0003444781,"threshold_uncertainty_score":0.9968908},"labels":[],"label_agreement":null},{"id":"W2886011145","doi":"10.1111/rssc.12305","title":"Joint Modelling of a Binary and a Continuous Outcome Measured at Two Cycles to Determine the Optimal Dose","year":2018,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer","keywords":"Toxicity; Estimator; Probit model; Outcome (game theory); Probit; Maximum tolerated dose; Statistics; Computer science; Mathematics; Medicine; Internal medicine","score_opus":0.38681761127283804,"score_gpt":0.4428733709425216,"score_spread":0.05605575966968357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886011145","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06639923,0.000043413733,0.9296568,0.0008861337,0.0006120407,0.00072772114,0.0014182563,0.000024203875,0.00023220739],"genre_scores_gemma":[0.3050301,0.000014889641,0.6940102,0.0003184888,0.00035988537,0.00001560642,0.0000011852162,0.00005240382,0.00019722828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944313,0.000671196,0.0026498938,0.00040190207,0.0012410879,0.00060462713],"domain_scores_gemma":[0.97540617,0.021396188,0.0014734357,0.00058697694,0.0007170406,0.00042018908],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004528735,0.00044079623,0.0015381132,0.000039341397,0.00053776044,0.00010523191,0.0007014598,0.00018162889,0.00029689717],"category_scores_gemma":[0.019757014,0.00025427647,0.0003391379,0.00024139184,0.0020331845,0.00005452657,0.0007269535,0.00073906867,0.000010688568],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009293922,0.001198594,0.0010128516,0.0012115254,0.0022481428,0.00012688378,0.00799598,0.008174213,0.0088280635,0.8639535,0.07026721,0.025689166],"study_design_scores_gemma":[0.0041218847,0.0022623523,0.0048904107,0.00027573528,0.0015157805,0.00011865192,0.0011509277,0.06392844,0.0020641875,0.91792005,0.0010074069,0.0007441557],"about_ca_topic_score_codex":0.000030713465,"about_ca_topic_score_gemma":0.000019836372,"teacher_disagreement_score":0.23863089,"about_ca_system_score_codex":0.00017982294,"about_ca_system_score_gemma":0.00012636013,"threshold_uncertainty_score":0.99999094},"labels":[],"label_agreement":null},{"id":"W2886612504","doi":"10.1002/cjs.11460","title":"Response adaptive designs with asymptotic optimality","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Asymptotically optimal algorithm; Wald test; Statistic; Statistical inference; Upper and lower bounds; Statistics; Rate of convergence; Applied mathematics; Confidence interval; Inference; Mathematical optimization; Statistical hypothesis testing; Computer science; Key (lock)","score_opus":0.5732381775282754,"score_gpt":0.4962286941908855,"score_spread":0.07700948333738994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886612504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011682012,0.00002044993,0.9853962,0.0004285462,0.0005814659,0.00019004209,0.00073275884,0.000009892603,0.00095862214],"genre_scores_gemma":[0.1965868,0.00000216568,0.8026693,0.00023412074,0.00031025807,0.0000017433048,4.182667e-7,0.000035772515,0.00015943543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966146,0.0013299797,0.0009899924,0.00018913399,0.00040909075,0.0004672268],"domain_scores_gemma":[0.964671,0.031741984,0.00066813995,0.00032738474,0.0014356899,0.0011557643],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052122837,0.00020199474,0.0006087951,0.0002089951,0.00018182328,0.00007411134,0.00036559463,0.00012328406,0.0009730885],"category_scores_gemma":[0.09357974,0.00015809479,0.00006732333,0.00026790574,0.0010031435,0.0000834282,0.00001484497,0.00041054096,0.000041779356],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007843898,0.00015579363,0.0023625197,0.00009202619,0.000689922,0.0038213416,0.0017319805,0.000034064346,0.00014576293,0.85933983,0.10660351,0.017179321],"study_design_scores_gemma":[0.0014117528,0.0046886513,0.0057498845,0.0002471028,0.00031026755,0.00033889877,0.0002580106,0.00034669403,0.00037769997,0.9833592,0.0025874195,0.00032440887],"about_ca_topic_score_codex":0.00027308636,"about_ca_topic_score_gemma":0.0031133844,"teacher_disagreement_score":0.1849048,"about_ca_system_score_codex":0.00026963034,"about_ca_system_score_gemma":0.0028399175,"threshold_uncertainty_score":0.99994016},"labels":[],"label_agreement":null},{"id":"W2887772315","doi":"10.1155/2018/8134132","title":"Bayesian Equivalence Testing and Meta-Analysis in Two-Arm Trials with Binary Data","year":2018,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain Monte Carlo; Bayesian probability; Equivalence (formal languages); Posterior probability; Bayesian inference; Statistics; Computer science; Binary data; Inference; Markov chain; Mathematics; Binary number; Artificial intelligence","score_opus":0.879195414605161,"score_gpt":0.6877510291213192,"score_spread":0.1914443854838418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887772315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015748118,0.0003224581,0.9937778,0.002131734,0.00005325439,0.0006755608,0.000042094765,0.000041610165,0.0013806461],"genre_scores_gemma":[0.016745757,0.000010764283,0.9824411,0.0004873214,0.00018115102,0.00005600914,0.0000049982477,0.000025788839,0.000047065787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99089104,0.0049623735,0.002304692,0.00087243103,0.0006179175,0.00035154712],"domain_scores_gemma":[0.6979286,0.3005487,0.0004941861,0.00060833374,0.00020086917,0.00021933182],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04353956,0.00033592014,0.0037256556,0.0004414114,0.00008318687,0.000035821344,0.00040743244,0.00010091345,0.0009184678],"category_scores_gemma":[0.2932527,0.0001961434,0.00010604151,0.0014739571,0.0013242454,0.00012388702,0.00043640574,0.00037482564,0.0000026138407],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007725515,0.0014484047,0.0020450254,0.0021031285,0.027425114,0.00022960757,0.0018982245,0.00047544026,0.00027801964,0.866164,0.0003702983,0.09679014],"study_design_scores_gemma":[0.0012878578,0.00032754467,0.00069071515,0.00010128315,0.02742709,0.00002728938,0.000106116386,0.1649306,0.00001192394,0.8049001,0.000006770226,0.00018267556],"about_ca_topic_score_codex":0.000028636163,"about_ca_topic_score_gemma":0.000017967724,"teacher_disagreement_score":0.29558632,"about_ca_system_score_codex":0.000022434857,"about_ca_system_score_gemma":0.0000552577,"threshold_uncertainty_score":0.9999948},"labels":[],"label_agreement":null},{"id":"W2888107769","doi":"10.1097/phm.0000000000001023","title":"Hypothesis Testing in Superiority, Noninferiority, and Equivalence Clinical Trials","year":2018,"lang":"en","type":"review","venue":"American Journal of Physical Medicine & Rehabilitation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Null hypothesis; Statistical hypothesis testing; Alternative hypothesis; Medicine; Equivalence (formal languages); Null (SQL); Clinical trial; Econometrics; Statistics; Mathematics; Computer science; Data mining; Pathology","score_opus":0.7963871447940521,"score_gpt":0.6810308064840672,"score_spread":0.11535633830998493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888107769","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0303311,0.9502208,0.007242157,0.0017339647,0.0038497113,0.005803315,0.00014583777,0.00013061389,0.0005424961],"genre_scores_gemma":[0.0010728771,0.29470214,0.6962312,0.000074997646,0.0077359993,0.00005440624,7.388985e-7,0.00012101624,0.000006620668],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9659044,0.022696018,0.009022636,0.00075421995,0.0011559516,0.00046677655],"domain_scores_gemma":[0.3687892,0.62333435,0.006232137,0.00051496323,0.00071700505,0.000412344],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.064264156,0.0006514296,0.013346132,0.000551224,0.00006350672,0.00003826441,0.00063403696,0.00028586626,0.000039927425],"category_scores_gemma":[0.8893495,0.00041672794,0.001329427,0.0014223283,0.0044703633,0.00017038597,0.00020324854,0.0017851611,0.000011025861],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009823564,0.0003877401,0.00033945224,0.0047668894,0.00016568248,0.000019619632,0.0003723485,6.2465034e-8,0.0000017039492,0.0013857121,0.00008044197,0.9923821],"study_design_scores_gemma":[0.0022540854,0.08820358,0.001266274,0.0799628,0.005138248,0.00011682413,0.00068564736,0.000066169116,3.178786e-7,0.80328256,0.018268049,0.0007554236],"about_ca_topic_score_codex":0.00004652421,"about_ca_topic_score_gemma":0.000003845146,"teacher_disagreement_score":0.9916267,"about_ca_system_score_codex":0.00021470484,"about_ca_system_score_gemma":0.0005589769,"threshold_uncertainty_score":0.99982846},"labels":[],"label_agreement":null},{"id":"W2889432374","doi":"10.1111/bph.14485","title":"Preclinical efficacy in therapeutic area guidelines from the U.S. Food and Drug Administration and the European Medicines Agency: a cross‐sectional study","year":2018,"lang":"en","type":"article","venue":"British Journal of Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Food and drug administration; Medicine; Transparency (behavior); Regulatory science; Approved drug; Agency (philosophy); Pharmacology; Drug approval; Drug development; Drug; Medical physics; Computer science; Pathology","score_opus":0.4624428603682894,"score_gpt":0.5777931632969009,"score_spread":0.11535030292861148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889432374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9879555,0.0017772706,0.0023299283,0.0056023337,0.0015130929,0.00062519865,0.00002902428,0.000010767912,0.00015687844],"genre_scores_gemma":[0.98521316,0.000425557,0.00978442,0.0012759132,0.0032515866,0.000009690339,3.4221569e-7,0.000017827604,0.000021523269],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99142843,0.006084062,0.0017774845,0.00023553135,0.00030995355,0.00016456132],"domain_scores_gemma":[0.949844,0.048942152,0.00064092566,0.00009498525,0.00039834742,0.00007958481],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017291723,0.0001287955,0.000489815,0.000033705153,0.00018157926,0.000108044325,0.00033599968,0.00006427425,0.00020888771],"category_scores_gemma":[0.040187247,0.00007866252,0.000086089036,0.000101498066,0.0014320076,0.00006554751,0.000119066564,0.00059215166,0.0000017954994],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016913947,0.009817677,0.26719448,0.00009729716,0.0043092477,0.001959669,0.009208794,0.000010372427,0.0018479349,0.008887006,0.06525031,0.61450326],"study_design_scores_gemma":[0.01542146,0.0014136966,0.6202833,0.000104056475,0.00043348563,0.0006896638,0.00021107831,0.000116820454,0.000092033886,0.3608808,0.00024138897,0.00011224892],"about_ca_topic_score_codex":0.000030697796,"about_ca_topic_score_gemma":0.00019025618,"teacher_disagreement_score":0.614391,"about_ca_system_score_codex":0.00001619357,"about_ca_system_score_gemma":0.00009221527,"threshold_uncertainty_score":0.96789765},"labels":[],"label_agreement":null},{"id":"W2889900146","doi":"10.2217/cer-2018-0035","title":"Some issues for the evaluation of noninferiority trials","year":2018,"lang":"en","type":"article","venue":"Journal of Comparative Effectiveness Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"H2020 European Research Council","keywords":"Medicine; Confidence interval; Margin (machine learning); Adjuvant therapy; Placebo; Medical physics; Cancer; Internal medicine; Alternative medicine","score_opus":0.9613010515836794,"score_gpt":0.7999582645757043,"score_spread":0.1613427870079751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889900146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6369655,0.0023079114,0.35168877,0.0006761304,0.0021948684,0.0055947923,0.00006218144,0.000009866429,0.0004999484],"genre_scores_gemma":[0.913784,0.0000696138,0.08309387,0.0000054161455,0.002853018,0.00015396312,1.878253e-7,0.000015596854,0.000024308607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95042163,0.044645898,0.0017966288,0.00020562926,0.002614726,0.0003154732],"domain_scores_gemma":[0.4651242,0.5198521,0.0012510961,0.00037929122,0.013294192,0.00009913244],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28422365,0.0001452267,0.0017539529,0.00023102546,0.0002521859,0.000057792975,0.00055489683,0.000116571806,0.0001806135],"category_scores_gemma":[0.40860817,0.00007936214,0.00039930578,0.00045035663,0.0010739013,0.0001726127,0.00010033045,0.0005589482,0.00000883433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031061139,0.002489796,0.0014355235,0.0013229197,0.0042946874,0.0000055196906,0.0044987164,0.0003143568,0.058883928,0.77388406,0.014801952,0.107007384],"study_design_scores_gemma":[0.0031536804,0.0026162337,0.00962351,0.00032686646,0.0003226359,0.0000033469764,0.00026501282,0.0029278693,0.11356974,0.866661,0.00045659475,0.00007349693],"about_ca_topic_score_codex":0.000009569658,"about_ca_topic_score_gemma":0.0000039743913,"teacher_disagreement_score":0.48529744,"about_ca_system_score_codex":0.00018761348,"about_ca_system_score_gemma":0.000588053,"threshold_uncertainty_score":0.73704237},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2890320223","doi":"10.1001/jamainternmed.2018.3979","title":"A Randomized Clinical Trial of n-of-1 Trials—Tribulations of a Trial","year":2018,"lang":"en","type":"letter","venue":"JAMA Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Otorhinolaryngology; Family medicine; Neurology; Psychiatry","score_opus":0.7364424411634807,"score_gpt":0.6509974315149984,"score_spread":0.08544500964848223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890320223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010296726,0.00042610048,0.4345117,0.4327419,0.07666436,0.026905276,0.0022667586,0.0001550493,0.016032148],"genre_scores_gemma":[0.004158399,0.000700959,0.65133166,0.06702118,0.2705092,0.00089006114,0.0001609957,0.00039067745,0.0048368387],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9375215,0.03314968,0.025137074,0.0009080371,0.0027586273,0.00052508153],"domain_scores_gemma":[0.3238173,0.6561482,0.016695552,0.0015199211,0.0016314073,0.000187577],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.11969543,0.00065986253,0.017507637,0.00059526996,0.000026631193,0.000013870591,0.001331499,0.002661158,0.0039128335],"category_scores_gemma":[0.9295457,0.00041201993,0.003586582,0.00041235954,0.0042995457,0.00005256035,0.00027383817,0.003185347,0.000014838213],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5703548,0.00040074,0.0000017660857,0.0005535266,0.0015731711,0.000025286932,0.0000689842,3.2422648e-8,0.0000071202744,0.0028091602,0.42078513,0.0034202903],"study_design_scores_gemma":[0.6279492,0.007173399,0.0000010252974,0.0031770861,0.0037267155,0.000004695382,0.000008538133,0.000049172162,0.00010162077,0.3365363,0.021084743,0.00018756131],"about_ca_topic_score_codex":0.00019310613,"about_ca_topic_score_gemma":0.000003137123,"teacher_disagreement_score":0.8098503,"about_ca_system_score_codex":0.000054444678,"about_ca_system_score_gemma":0.00038954502,"threshold_uncertainty_score":0.99983317},"labels":[],"label_agreement":null},{"id":"W2891267158","doi":"10.1186/s13063-018-2877-z","title":"The Comparative Effectiveness of Innovative Treatments for Cancer (CEIT-Cancer) project: Rationale and design of the database and the collection of evidence available at approval of novel drugs","year":2018,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; McMaster University; University of Toronto","funders":"Krebsliga Schweiz; Laura and John Arnold Foundation","keywords":"Medicine; Comparative effectiveness research; Research design; Drug approval; Alternative medicine; Pharmacology; Drug; Pathology","score_opus":0.8860932698132773,"score_gpt":0.6364561263352206,"score_spread":0.24963714347805666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891267158","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48271373,0.0032501598,0.4438411,0.0005913661,0.0016605628,0.060835842,0.006490872,0.000022223243,0.00059413875],"genre_scores_gemma":[0.4490259,0.0017110993,0.5406934,0.000040800216,0.00035670344,0.006603011,0.0000055735018,0.000049854716,0.0015136754],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99384123,0.004304273,0.0012079461,0.00022492453,0.00031108965,0.0001105359],"domain_scores_gemma":[0.7643983,0.23282644,0.0016119181,0.00026529483,0.00088521733,0.000012850576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01987272,0.00013405221,0.001134971,0.000034645593,0.00019222414,0.000008566002,0.00017875986,0.00006184486,0.00002776246],"category_scores_gemma":[0.09005672,0.000055664455,0.000079804835,0.0004802592,0.0018184594,0.00006202308,0.00011544218,0.00006224685,1.5224033e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.19644412,0.0018223764,0.0028157532,0.005130662,0.0063952263,1.13405065e-7,0.016887665,0.00007896388,0.49353173,0.25764227,0.010944715,0.008306385],"study_design_scores_gemma":[0.015762974,0.0009406374,0.00092548964,0.0015545187,0.00093498046,6.876589e-7,0.0003097362,0.0026960978,0.8738962,0.1028027,0.000059716003,0.00011629672],"about_ca_topic_score_codex":0.00024614958,"about_ca_topic_score_gemma":0.000031719224,"teacher_disagreement_score":0.38036442,"about_ca_system_score_codex":0.000055672313,"about_ca_system_score_gemma":0.00034036025,"threshold_uncertainty_score":0.91760814},"labels":[],"label_agreement":null},{"id":"W2891278567","doi":"10.23889/ijpds.v3i4.1023","title":"A bayesian way to correct for measurement error in drug risk estimates from EHR data.","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Confounding; Medicine; Statistics; Bayesian probability; Medical prescription; Medical record; Econometrics; Data mining; Computer science; Mathematics; Internal medicine; Pharmacology","score_opus":0.7320061462199375,"score_gpt":0.6324739632224308,"score_spread":0.09953218299750677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891278567","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020094061,0.000010168621,0.9643582,0.0012141077,0.006755008,0.0007148955,0.0067813345,0.000026501928,0.000045700475],"genre_scores_gemma":[0.26689577,0.0000041436915,0.7316582,0.00016074535,0.0010772499,0.000020433585,0.0001499574,0.00001544281,0.00001803782],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961194,0.00016507535,0.0011180544,0.00073125685,0.001544661,0.00032156557],"domain_scores_gemma":[0.985591,0.010984146,0.00067391095,0.001134944,0.0013719854,0.00024404789],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01653013,0.00015196549,0.0003066277,0.0002824825,0.00031355425,0.00039597822,0.0040493994,0.000047588317,0.0001228846],"category_scores_gemma":[0.28499994,0.00012764345,0.00004965151,0.0002961412,0.00018025356,0.0012015858,0.00081625656,0.0001819575,0.000016537537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038179562,0.0013510081,0.0939034,0.000074930475,0.00054446916,0.00002256902,0.0014689829,0.00076154753,0.0036194136,0.059627432,0.19586194,0.63894635],"study_design_scores_gemma":[0.0011426313,0.00010864686,0.016473198,0.0002286664,0.000067782195,0.00000798947,0.000051142026,0.19083019,0.0004926678,0.78663737,0.0037571867,0.00020254505],"about_ca_topic_score_codex":0.00063900655,"about_ca_topic_score_gemma":0.0020023158,"teacher_disagreement_score":0.72700995,"about_ca_system_score_codex":0.00029364237,"about_ca_system_score_gemma":0.00017097585,"threshold_uncertainty_score":0.7524859},"labels":[],"label_agreement":null},{"id":"W2891886352","doi":"10.1080/00031305.2020.1717621","title":"Reconnecting <i>p</i> -Value and Posterior Probability Under One- and Two-Sided Tests","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Statistics; Mathematics; Posterior probability; Value (mathematics); p-value; Statistical hypothesis testing; Bayesian probability","score_opus":0.525964131273974,"score_gpt":0.5256489015127478,"score_spread":0.00031522976122622115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891886352","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7734604,0.000042390795,0.21181007,0.012095737,0.00012209339,0.0010207907,0.00028315416,0.0001787287,0.0009866225],"genre_scores_gemma":[0.40642878,0.000011722683,0.588656,0.0046828603,0.00015668444,0.000021652348,7.752411e-7,0.000033735614,0.000007794532],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966971,0.0014310017,0.00071323867,0.00053413125,0.00026358743,0.00036092842],"domain_scores_gemma":[0.92829806,0.070477836,0.00049276627,0.00037082922,0.00007747733,0.00028303277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018306004,0.00023727497,0.00081282714,0.000021394655,0.00018877692,0.00009310053,0.00020840556,0.000034581244,0.0000559943],"category_scores_gemma":[0.09677657,0.00017710737,0.00004361076,0.0002694933,0.0011877726,0.00004870069,0.00023626658,0.00034211576,0.000012547769],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009052863,0.00020533006,0.004813096,0.00046092263,0.00030443593,0.000036221398,0.0031422174,0.000010924638,0.0057120174,0.55249333,0.00092701154,0.4309892],"study_design_scores_gemma":[0.00066201,0.00053969526,0.021443632,0.00007034932,0.0001912291,0.000016683794,0.0007379218,0.00097093615,0.00024069945,0.9748377,0.000026995707,0.00026214076],"about_ca_topic_score_codex":0.00021951395,"about_ca_topic_score_gemma":0.000060850696,"teacher_disagreement_score":0.43072706,"about_ca_system_score_codex":0.000031218864,"about_ca_system_score_gemma":0.000051305866,"threshold_uncertainty_score":0.9108317},"labels":[],"label_agreement":null},{"id":"W2894616212","doi":"10.7748/nr.2018.e1582","title":"A review of the non-equivalent control group post-test-only design","year":2018,"lang":"en","type":"review","venue":"Nurse Researcher","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Winnipeg Regional Health Authority","funders":"","keywords":"Test (biology); Group (periodic table); Psychology; Computer science; Mathematics; Biology; Chemistry","score_opus":0.7595054080589233,"score_gpt":0.6540582156320327,"score_spread":0.1054471924268906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894616212","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.568673e-8,0.97089535,0.01706068,0.0003863683,0.00050385634,0.007776143,0.0005913147,0.000039749535,0.002746471],"genre_scores_gemma":[1.2130332e-7,0.8606896,0.13628528,0.00035163152,0.00061766873,0.0004990934,0.000004404693,0.00015151202,0.001400733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98104465,0.012948298,0.002707785,0.00079126,0.0016802684,0.00082774885],"domain_scores_gemma":[0.7583759,0.23459546,0.001876028,0.0033534814,0.0013553913,0.00044373382],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027688863,0.00062150485,0.004643931,0.00013229778,0.000104099105,0.000044496166,0.0022410671,0.0007111448,0.0024484105],"category_scores_gemma":[0.4627985,0.0003326131,0.0018096353,0.0008395997,0.0011135335,0.000043919874,0.00033561388,0.0016833282,0.000483877],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035431527,0.00043711852,9.2524516e-7,0.252095,0.00035807997,0.000011332598,0.000012435719,2.431344e-9,9.928979e-7,0.0037067041,0.091899656,0.6514423],"study_design_scores_gemma":[0.0005612463,0.0005214631,0.0000035548487,0.32509497,0.0020660516,0.000024995637,0.000004472029,0.000006262939,0.0000019138265,0.06165869,0.60973406,0.0003223045],"about_ca_topic_score_codex":0.000011617652,"about_ca_topic_score_gemma":0.0000017813027,"teacher_disagreement_score":0.65112,"about_ca_system_score_codex":0.0002548181,"about_ca_system_score_gemma":0.0013945982,"threshold_uncertainty_score":0.9999126},"labels":[],"label_agreement":null},{"id":"W2894881243","doi":"10.1016/j.chest.2018.07.021","title":"Outcome Switching in Triple Therapy in Influenza A(H3N2) Infection","year":2018,"lang":"en","type":"letter","venue":"CHEST Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clarithromycin; Medicine; Oseltamivir; Internal medicine; Randomized controlled trial; Gastroenterology; Coronavirus disease 2019 (COVID-19)","score_opus":0.7068518704538621,"score_gpt":0.5937109442398392,"score_spread":0.11314092621402294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894881243","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37447318,0.00076929055,0.18818927,0.38237,0.03958587,0.005122622,0.00011044683,0.00049313554,0.008886193],"genre_scores_gemma":[0.0017385861,0.0005630316,0.5690744,0.39262992,0.03491955,0.00008695445,0.0000043161936,0.0003402429,0.0006430214],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934507,0.0019577814,0.002855021,0.00043777746,0.00064877147,0.000649955],"domain_scores_gemma":[0.9770417,0.021011364,0.0011835856,0.00049445,0.0001514736,0.00011738295],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.009431339,0.0004512205,0.0014700241,0.0006386821,0.000092561364,0.00020046071,0.00048452546,0.0014926501,0.0006813298],"category_scores_gemma":[0.07286219,0.00036594248,0.00034651638,0.00042541735,0.000104352555,0.00016417468,0.00008853425,0.0080801435,0.00008492606],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045365974,0.00061119226,0.16610916,0.0012773004,0.00028684444,0.0023863032,0.0012142023,0.000005043657,0.0001277077,0.00072390365,0.7704641,0.05634056],"study_design_scores_gemma":[0.003543894,0.00024938834,0.014244301,0.0007039034,0.00004262084,0.00012916642,0.000010222646,0.000031817377,0.000060821243,0.7714545,0.20904288,0.00048648432],"about_ca_topic_score_codex":0.000052054365,"about_ca_topic_score_gemma":0.000038511822,"teacher_disagreement_score":0.7707306,"about_ca_system_score_codex":0.0004725144,"about_ca_system_score_gemma":0.0001680427,"threshold_uncertainty_score":0.99987924},"labels":[],"label_agreement":null},{"id":"W2894992918","doi":"10.5041/rmmj.10351","title":"Detection and Diagnostic Overall Accuracy Measures of Medical Tests","year":2018,"lang":"en","type":"article","venue":"Rambam Maimonides Medical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medical diagnosis; Diagnostic accuracy; Bayes' theorem; Population; Medicine; Test (biology); Accuracy and precision; Statistics; Contrast (vision); Diagnostic test; Sensitivity (control systems); Computer science; Machine learning; Artificial intelligence; Bayesian probability; Pathology; Pediatrics; Mathematics; Radiology; Environmental health","score_opus":0.3770743818396729,"score_gpt":0.5377760369627361,"score_spread":0.16070165512306323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894992918","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.534174,0.0005188892,0.45526248,0.005060764,0.00317953,0.00044482932,0.0000143585,0.00012192196,0.001223211],"genre_scores_gemma":[0.8807547,0.0011559518,0.11440749,0.00067997485,0.0029252488,0.000010484599,2.097979e-7,0.000041280415,0.000024642737],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922522,0.0014138469,0.0017362165,0.00033821736,0.003758786,0.00050077523],"domain_scores_gemma":[0.8116107,0.18439491,0.0009299102,0.00048454208,0.0006202396,0.0019597064],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013807283,0.00025514397,0.0008474745,0.00013621156,0.00020568325,0.00009166194,0.00064307183,0.0006215332,0.0036743865],"category_scores_gemma":[0.7756471,0.00018484716,0.00018195498,0.00020946543,0.0013521218,0.00013528335,0.00027066685,0.0013682211,0.000030688458],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003069829,0.0005334633,0.005422232,0.00021211673,0.00026787873,0.00045421612,0.00022710323,1.8264886e-7,0.00076672377,0.021587307,0.0067790467,0.96344274],"study_design_scores_gemma":[0.0019641093,0.000892281,0.029072577,0.001288376,0.00020338953,0.0014812535,0.000067288485,0.0010176,0.0024597088,0.95942384,0.0018447945,0.00028477496],"about_ca_topic_score_codex":0.000025060514,"about_ca_topic_score_gemma":0.00006517678,"teacher_disagreement_score":0.96315795,"about_ca_system_score_codex":0.00006216358,"about_ca_system_score_gemma":0.00040752225,"threshold_uncertainty_score":0.9972364},"labels":[],"label_agreement":null},{"id":"W2896211924","doi":"10.1136/annrheumdis-2018-eular.2705","title":"OP0309 Characterisation of clinical benefits in subjects classified as acr20 non-responders at week 104 of apremilast treatment: subanalysis of 3 long-term, phase iii trials","year":2018,"lang":"en","type":"article","venue":"Annals of the Rheumatic Diseases","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital","funders":"Janssen Research and Development; KU Leuven","keywords":"Apremilast; Medicine; Internal medicine; Clinical trial; Term (time); Intensive care medicine; Psoriatic arthritis; Rheumatoid arthritis","score_opus":0.7321362683283751,"score_gpt":0.6138100759340432,"score_spread":0.11832619239433184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896211924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961371,0.00016851621,0.00073545333,0.00025044204,0.00034511278,0.0012264189,0.0009544694,0.000014867422,0.00016765375],"genre_scores_gemma":[0.9945351,0.00077307614,0.004321585,0.000051874635,0.00009059146,0.000049018527,0.000020218715,0.000038461236,0.00012010479],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9882475,0.00372019,0.0063779904,0.00045435064,0.0008538429,0.00034613442],"domain_scores_gemma":[0.9217926,0.06988231,0.0061472612,0.001340446,0.00060513255,0.00023221874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007929154,0.00036133357,0.003980946,0.00027862968,0.000056634257,0.000013580127,0.0006800134,0.00024348006,0.00071736425],"category_scores_gemma":[0.16203582,0.00024096805,0.0015156891,0.00063051865,0.0010157744,0.00012645888,0.00021451295,0.00011344812,0.000009981271],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08165924,0.04710106,0.15808308,0.008454823,0.013126543,0.000021389245,0.0055202716,0.00007266776,0.009625717,0.011505623,0.0020680453,0.6627615],"study_design_scores_gemma":[0.029893318,0.006202159,0.5719866,0.00699468,0.0055447947,0.0000028901645,0.00045366542,0.0015285767,0.21921836,0.15751089,0.000005718551,0.0006583418],"about_ca_topic_score_codex":0.00011544586,"about_ca_topic_score_gemma":0.00006902083,"teacher_disagreement_score":0.6621032,"about_ca_system_score_codex":0.00004104292,"about_ca_system_score_gemma":0.0002911754,"threshold_uncertainty_score":0.98263913},"labels":[],"label_agreement":null},{"id":"W2896537297","doi":"10.1016/j.ejps.2018.10.019","title":"Summary report of second EUFEPS/AAPS conference on global harmonization in bioequivalence","year":2018,"lang":"en","type":"article","venue":"European Journal of Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Harmonization; Biopharmaceutics; Political science; Standardization; Medicine; Pharmacology; Business; Bioavailability; Chemistry; Law","score_opus":0.6869290671599527,"score_gpt":0.5986708203144571,"score_spread":0.08825824684549566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896537297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64241546,0.00021650828,0.1304685,0.003661657,0.0038706893,0.00048338977,0.000080470076,0.000048110232,0.2187552],"genre_scores_gemma":[0.78833795,0.00006588125,0.21088144,0.00025474696,0.00037241713,3.2267263e-7,1.2146693e-7,0.000008933002,0.00007818763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99461067,0.0021995634,0.0017154707,0.00029917795,0.00086117827,0.00031395743],"domain_scores_gemma":[0.9930808,0.005068793,0.0009772386,0.00019097464,0.0004319105,0.00025031663],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016324097,0.00015217475,0.00046200337,0.00011121202,0.00007857342,0.000054592536,0.00076915906,0.00003803018,0.001038042],"category_scores_gemma":[0.035378546,0.00010954056,0.00010667725,0.00072082994,0.0017694539,0.00018374178,0.00014283574,0.0003306976,0.0000301311],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023409268,0.002950714,0.03956862,0.0006162062,0.00022707107,0.00670394,0.0009808921,0.000042295862,0.04891427,0.6274975,0.026080228,0.24407731],"study_design_scores_gemma":[0.0040228143,0.005464328,0.031157661,0.001876467,0.00020003997,0.0009633107,0.00030699655,0.002401826,0.05383223,0.89110595,0.007999789,0.00066860643],"about_ca_topic_score_codex":0.0000011427126,"about_ca_topic_score_gemma":0.0000019602437,"teacher_disagreement_score":0.26360843,"about_ca_system_score_codex":0.000052739517,"about_ca_system_score_gemma":0.00016774834,"threshold_uncertainty_score":0.9998751},"labels":[],"label_agreement":null},{"id":"W2897367577","doi":"10.1002/pst.1906","title":"Applications of Bayesian statistical methodology to clinical trial design: A case study of a phase 2 trial with an interim futility assessment in patients with knee osteoarthritis","year":2018,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Xenon Pharmaceuticals (Canada)","funders":"Eli Lilly and Company","keywords":"Interim; Interim analysis; Medicine; Placebo; Clinical trial; WOMAC; Osteoarthritis; Sample size determination; Celecoxib; Randomized controlled trial; Bayesian probability; Clinical study design; Physical therapy; Medical physics; Computer science; Surgery; Internal medicine; Alternative medicine; Statistics; Artificial intelligence","score_opus":0.7394911056247505,"score_gpt":0.6836660418249617,"score_spread":0.0558250637997888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897367577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35637304,0.000001373465,0.63335556,0.000015286221,0.00031294706,0.008425682,0.0014528402,0.000033288416,0.000029962537],"genre_scores_gemma":[0.45817116,7.205667e-7,0.5408816,0.000048910617,0.00021775062,0.0006188423,0.000013770868,0.00004516936,0.000002073183],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9815742,0.011307181,0.0041288794,0.0011555211,0.0011275773,0.00070664653],"domain_scores_gemma":[0.9232951,0.07293544,0.0008981401,0.0010169494,0.0010154449,0.0008389584],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00996171,0.00050641305,0.0023477846,0.0002437182,0.000121205594,0.00004252936,0.0004716846,0.00025841274,0.00064519455],"category_scores_gemma":[0.031128282,0.000398866,0.00008660834,0.0007855755,0.0014712992,0.00010016027,0.0002423826,0.0009429301,0.00000531176],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6675031,0.043721933,0.0030861008,0.00015252351,0.00032700782,0.00036603343,0.00059301686,0.000002832663,0.0000045134498,0.014455259,0.00006969189,0.269718],"study_design_scores_gemma":[0.604518,0.31144148,0.0010646691,0.000077714954,0.0012819454,0.0000333108,0.0009280349,0.0025859924,0.00006802182,0.0773544,0.00007786984,0.0005685773],"about_ca_topic_score_codex":0.00013503637,"about_ca_topic_score_gemma":0.00039885557,"teacher_disagreement_score":0.26914942,"about_ca_system_score_codex":0.000120999845,"about_ca_system_score_gemma":0.00045339737,"threshold_uncertainty_score":0.99984634},"labels":[],"label_agreement":null},{"id":"W2897801176","doi":"10.1111/2041-210x.13159","title":"I can see clearly now: Reinterpreting statistical significance","year":2019,"lang":"en","type":"article","venue":"Methods in Ecology and Evolution","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"CLARITY; Null hypothesis; Statistical hypothesis testing; Meaning (existential); Alternative hypothesis; Psychology; Context (archaeology); Cognitive psychology; Computer science; Econometrics; Statistics; Mathematics; Geography; Biology","score_opus":0.2100571163939553,"score_gpt":0.537255500117731,"score_spread":0.32719838372377574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897801176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15634464,0.000029719045,0.83824027,0.0004927855,0.0011614109,0.0005146993,0.000027137243,0.000062872496,0.0031264555],"genre_scores_gemma":[0.30607027,0.000011585274,0.6933671,0.000112718684,0.000064381784,0.000032473337,7.5921565e-7,0.000016310461,0.0003243427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99357176,0.0046062316,0.00077772804,0.0005023089,0.00012824984,0.0004137064],"domain_scores_gemma":[0.93223315,0.06713937,0.00019036277,0.0002833738,0.000058104953,0.000095620155],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0096421875,0.00016543476,0.00062731846,0.000104085906,0.000066527115,0.000017288934,0.00015100122,0.0003427796,0.0005021446],"category_scores_gemma":[0.073959626,0.00015688127,0.000047394697,0.0001793517,0.00027243065,0.00005361922,0.00011666758,0.00056523434,0.000068348905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037951436,0.0001741202,0.23372592,0.0002100623,0.00004964561,0.000014986057,0.0003046921,0.000026837504,0.0033213533,0.72797066,0.0006818308,0.03314038],"study_design_scores_gemma":[0.0005472021,0.0002356306,0.19074272,0.000044460474,0.000029855184,0.0000060798284,0.000093900264,0.0049862494,0.00017873826,0.8028807,0.00010299803,0.00015145855],"about_ca_topic_score_codex":0.000037856433,"about_ca_topic_score_gemma":0.00012504606,"teacher_disagreement_score":0.14972563,"about_ca_system_score_codex":0.00017637697,"about_ca_system_score_gemma":0.000066003035,"threshold_uncertainty_score":0.9338408},"labels":[],"label_agreement":null},{"id":"W2898353673","doi":"10.1080/10543406.2018.1535503","title":"Randomized dose-escalation designs for drug combination cancer trials with immunotherapy","year":2018,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"H2020 Marie Skłodowska-Curie Actions; Institute of Cancer Research; National Institutes of Health; Institut National Du Cancer; European Commission; National Institute for Health and Care Research","keywords":"Medicine; Randomization; Clinical trial; Randomized controlled trial; Therapeutic index; Oncology; Drug; Internal medicine; Pharmacology","score_opus":0.6868558580038793,"score_gpt":0.63370480115248,"score_spread":0.053151056851399314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898353673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068002017,0.00021503819,0.98773116,0.0011985812,0.0016320746,0.0018511525,0.00043628766,0.00002990203,0.00010559312],"genre_scores_gemma":[0.075630285,0.00047910959,0.9217537,0.00042195717,0.0014115134,0.00008618228,0.0000035613723,0.00006398167,0.00014973029],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918258,0.0035509376,0.0031657186,0.00024747118,0.00082329655,0.00038675233],"domain_scores_gemma":[0.8572172,0.13810223,0.0023644972,0.00019072817,0.0018631511,0.00026220822],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023595557,0.00030148416,0.002305676,0.0001609512,0.00016858496,0.000106528896,0.0003003773,0.0001653419,0.00084750185],"category_scores_gemma":[0.09988462,0.00018947494,0.00037442803,0.00026332008,0.00081821607,0.00012982292,0.000025599658,0.0004120902,0.000007525808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.38523892,0.001317808,0.00010827326,0.0003411917,0.00206087,0.000025363937,0.00045697403,0.000012023476,0.0048316843,0.47095236,0.017068071,0.11758647],"study_design_scores_gemma":[0.19578357,0.0009474882,0.00008133385,0.00017837649,0.0014470697,0.000016732616,0.000031533928,0.0065596257,0.011143711,0.7821314,0.0014223286,0.0002568412],"about_ca_topic_score_codex":0.000004922473,"about_ca_topic_score_gemma":0.000003146026,"teacher_disagreement_score":0.31117904,"about_ca_system_score_codex":0.00014927372,"about_ca_system_score_gemma":0.00025226054,"threshold_uncertainty_score":0.9279551},"labels":[],"label_agreement":null},{"id":"W2898416500","doi":"10.6000/1929-6029.2018.07.04.2","title":"On Comparing Survival Curves with Right-Censored Data According to the Events Occur at the Beginning, in the Middle and at the End of Study Period","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Period (music); Wilcoxon signed-rank test; Statistics; Event (particle physics); Log-rank test; Type I and type II errors; Test (biology); Mathematics; Survival analysis; Psychology; Econometrics; Demography; Biology; Mann–Whitney U test; Sociology","score_opus":0.7100981351492474,"score_gpt":0.6440371806920502,"score_spread":0.06606095445719717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898416500","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9381959,0.00018115304,0.032220997,0.02562399,0.0010204851,0.0012413099,0.00047728285,0.0000035794612,0.0010353364],"genre_scores_gemma":[0.9831931,0.00017501194,0.015618108,0.00041687256,0.0004715042,0.000019195137,0.000004550828,0.000017804023,0.00008383508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98715645,0.0048717,0.0012328248,0.00028786485,0.0061094407,0.00034169824],"domain_scores_gemma":[0.8489166,0.14883526,0.00044638143,0.00072390586,0.0009372405,0.0001406277],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0475233,0.00014067683,0.00044484372,0.0001548279,0.00025559275,0.00008445324,0.003424852,0.00005772489,0.00053965364],"category_scores_gemma":[0.22729956,0.000054747565,0.000032836775,0.00036191804,0.0015010731,0.000055129658,0.0016177489,0.0014263733,0.000009930994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01599811,0.0062295706,0.34476689,0.00047250834,0.002019264,0.003445875,0.03624464,0.00013081277,0.000072455376,0.35946465,0.14534435,0.08581088],"study_design_scores_gemma":[0.012014621,0.0059543704,0.19915923,0.008258907,0.0002648689,0.0006660271,0.029815516,0.013163521,0.00013651614,0.7236487,0.006389074,0.0005286476],"about_ca_topic_score_codex":0.00017425201,"about_ca_topic_score_gemma":0.0036782164,"teacher_disagreement_score":0.36418405,"about_ca_system_score_codex":0.00017715352,"about_ca_system_score_gemma":0.0002395282,"threshold_uncertainty_score":0.9807752},"labels":[],"label_agreement":null},{"id":"W2898430617","doi":"10.1093/annonc/mdy284.058","title":"Quality of docetaxel toxicity reporting for castration resistant prostate cancer (CRPC): A systematic review","year":2018,"lang":"en","type":"review","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Docetaxel; Prostate cancer; Clinical trial; Consolidated Standards of Reporting Trials; Internal medicine; Oncology; Checklist; Cancer","score_opus":0.9294521394121379,"score_gpt":0.7524040361756805,"score_spread":0.17704810323645737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898430617","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000088188335,0.98564106,0.0022054582,0.00023524399,0.00045774016,0.009546307,0.001262606,0.000028875082,0.00061386306],"genre_scores_gemma":[0.0000026030102,0.840685,0.15697743,0.00017222842,0.00020040017,0.0017274176,0.000014085475,0.00005205151,0.00016878026],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9747441,0.0064072646,0.01720291,0.0006664955,0.0005375202,0.00044170587],"domain_scores_gemma":[0.87238914,0.08252063,0.041739464,0.0011783583,0.002036394,0.0001360114],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047701005,0.00046054687,0.01394998,0.00011289225,0.000055718938,0.000010137457,0.00048434682,0.0006656877,0.0000767812],"category_scores_gemma":[0.5473251,0.0003258432,0.0016580813,0.0003624921,0.0003312112,0.00004777331,0.00012659673,0.00034929856,0.0000040331192],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008520078,0.0002524134,2.9407232e-7,0.90982693,0.0006294278,0.000005484686,0.00003886837,1.738955e-8,0.000005208652,0.007512796,0.0038956825,0.07774765],"study_design_scores_gemma":[0.00037498694,0.0015627691,9.0978057e-7,0.77208555,0.0053217863,0.000016874445,0.00001840699,0.0000016292163,0.00005836924,0.17397995,0.04621646,0.0003622978],"about_ca_topic_score_codex":0.000038436316,"about_ca_topic_score_gemma":0.00007778632,"teacher_disagreement_score":0.49962407,"about_ca_system_score_codex":0.00012383296,"about_ca_system_score_gemma":0.0013257167,"threshold_uncertainty_score":0.99991935},"labels":[],"label_agreement":null},{"id":"W2898563665","doi":"10.6000/1929-6029.2018.07.04.1","title":"A Simulation Based Evaluation of Sample Size Methods for Biomarker Studies","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Biomarker; Sample size determination; Statistical power; Type I and type II errors; Statistics; Nominal level; Sample (material); Computer science; Medicine; Oncology; Mathematics; Biology; Confidence interval; Chemistry","score_opus":0.8960419701603737,"score_gpt":0.809772509734291,"score_spread":0.08626946042608263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898563665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038884224,0.00010334571,0.99245536,0.0011483559,0.0015804792,0.00046546504,0.00022616072,0.0000042337397,0.00012815176],"genre_scores_gemma":[0.20620358,0.000056723693,0.79304785,0.00008207293,0.0005545832,0.000027243483,0.0000018862754,0.000017221617,0.000008844811],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9849137,0.00596432,0.0023288426,0.00023723804,0.0062424047,0.0003134894],"domain_scores_gemma":[0.13493542,0.8386326,0.00088421634,0.00023932451,0.025087686,0.00022078726],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11897033,0.00012073536,0.00061609305,0.0005196202,0.00005399477,0.000029881212,0.00075221906,0.0001787124,0.001618795],"category_scores_gemma":[0.9681892,0.000095441785,0.000116422496,0.0003970764,0.0010323357,0.00007148965,0.0001447078,0.000526383,0.0000024687538],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019527246,0.00064238906,0.000451426,0.00018946083,0.000525315,0.000022799291,0.00039404526,0.00036345873,0.0002743959,0.08257243,0.002704898,0.9099067],"study_design_scores_gemma":[0.0023452598,0.00040440747,0.00042521718,0.00038423968,0.000056081968,0.0000016489832,0.000116299,0.33149555,0.0005644287,0.6637038,0.00044852635,0.000054513],"about_ca_topic_score_codex":0.000016218939,"about_ca_topic_score_gemma":0.000025309871,"teacher_disagreement_score":0.90985215,"about_ca_system_score_codex":0.0004030914,"about_ca_system_score_gemma":0.0011497351,"threshold_uncertainty_score":0.99929386},"labels":[],"label_agreement":null},{"id":"W2898700495","doi":"10.1097/pr9.0000000000000697","title":"Designing and conducting proof-of-concept chronic pain analgesic clinical trials","year":2018,"lang":"en","type":"article","venue":"PAIN Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Clinical trial; Proof of concept; Tolerability; Medicine; Chronic pain; Population; Analgesic; Intensive care medicine; Psychological intervention; Intervention (counseling); Physical therapy; Alternative medicine; Computer science; Psychiatry; Internal medicine; Pathology","score_opus":0.8029388543816742,"score_gpt":0.6223564239088796,"score_spread":0.18058243047279465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898700495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025537742,0.00042869223,0.97059804,0.00019027515,0.0012067729,0.0012801698,0.0000061344153,0.000112142596,0.0006400216],"genre_scores_gemma":[0.30823404,0.000007739226,0.6896016,0.00017592407,0.0018038838,0.00004164858,0.0000012024586,0.000042618096,0.00009136615],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95814335,0.03359596,0.006292293,0.00090057944,0.0005467495,0.0005210674],"domain_scores_gemma":[0.6095404,0.38511527,0.0037416378,0.0009190656,0.00038044102,0.00030321022],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3011457,0.00025654497,0.0018775518,0.000078670244,0.00012729371,0.00004350392,0.00014334987,0.0003229172,0.00044199004],"category_scores_gemma":[0.84633845,0.00020507944,0.00030562442,0.00024271106,0.0008910429,0.0000669988,0.00012011834,0.00039329674,0.0000019833892],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009744146,0.00025079676,0.0077664168,0.00044524227,0.00034304423,0.0002542146,0.00034289615,0.000001430596,0.0017321917,0.0037809988,0.0072192308,0.9777661],"study_design_scores_gemma":[0.000934544,0.0016216806,0.00020488443,0.0006763488,0.00035049062,0.00006737468,0.00019818488,0.0018751095,0.04029955,0.95228523,0.001075927,0.00041067484],"about_ca_topic_score_codex":0.000011403467,"about_ca_topic_score_gemma":0.0000045813867,"teacher_disagreement_score":0.9773554,"about_ca_system_score_codex":0.000048398928,"about_ca_system_score_gemma":0.00024925286,"threshold_uncertainty_score":0.8362897},"labels":[],"label_agreement":null},{"id":"W2899206436","doi":"10.1002/cpt.1270","title":"Opportunities and Challenges Related to the Implementation of Model‐Based Bioequivalence Criteria","year":2018,"lang":"en","type":"article","venue":"Clinical Pharmacology & Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"American Association of Pharmaceutical Scientists","keywords":"Bioequivalence; Strengths and weaknesses; Computer science; Management science; Econometrics; Mathematics; Medicine; Economics; Pharmacology; Psychology; Pharmacokinetics","score_opus":0.8623221871967739,"score_gpt":0.6812235939164175,"score_spread":0.18109859328035638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899206436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73725927,0.0015522325,0.09338955,0.15849067,0.00497155,0.0025049727,0.00033848287,0.00024424685,0.0012490463],"genre_scores_gemma":[0.5433017,0.009646515,0.4035391,0.04254316,0.00067901146,0.00009860737,0.0000021660796,0.0000716198,0.00011813549],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956954,0.0019867183,0.0014149074,0.00037639018,0.00021053418,0.0003160517],"domain_scores_gemma":[0.97467625,0.024033599,0.00038548958,0.00037478542,0.00036079623,0.00016905837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00558632,0.00019276231,0.0005676269,0.000059584425,0.00014408576,0.00001356611,0.00039979062,0.00021969064,0.00061802735],"category_scores_gemma":[0.0015025005,0.00013703557,0.00012092881,0.00013082898,0.0021994987,0.000046556488,0.00017626892,0.0002925085,0.000014435047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025259757,0.0019396289,0.0015125347,0.00078931276,0.0024602024,0.000022615872,0.00739701,0.00001806608,0.014594632,0.10056018,0.028242696,0.83993715],"study_design_scores_gemma":[0.0041050706,0.003604465,0.0033065868,0.00007978888,0.0020587698,0.000005632411,0.0014953489,0.015943285,0.010726522,0.9463523,0.011885997,0.0004362408],"about_ca_topic_score_codex":0.0000019273828,"about_ca_topic_score_gemma":0.000006457978,"teacher_disagreement_score":0.8457921,"about_ca_system_score_codex":0.000019473335,"about_ca_system_score_gemma":0.00012043352,"threshold_uncertainty_score":0.8104145},"labels":[],"label_agreement":null},{"id":"W2899645235","doi":"10.18433/jpps30021","title":"Revisiting FDA’s 1995 Guidance on Bioequivalence Establishment of Topical Dermatologic Corticosteroids: New Research Based Recommendations","year":2018,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"NONMEM; Population; Bioequivalence; Medicine; Statistics; Parametric statistics; Mathematics; Econometrics; Pharmacology; Pharmacokinetics","score_opus":0.8337749841132915,"score_gpt":0.6882336763124286,"score_spread":0.14554130780086294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899645235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52598536,0.0017713284,0.2796722,0.16529459,0.007273691,0.0020832447,0.00009870752,0.00015339865,0.017667469],"genre_scores_gemma":[0.59633607,0.00023540515,0.40077367,0.001452258,0.0011390417,0.0000049113205,1.6924649e-7,0.0000127546655,0.000045699424],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9919419,0.0027276075,0.0022498285,0.0004314273,0.0019431171,0.0007061088],"domain_scores_gemma":[0.9597656,0.03746432,0.0009598453,0.00028820298,0.00088716374,0.00063486694],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016486788,0.0002220725,0.0007026324,0.00031490924,0.00038224205,0.00013392912,0.0013036961,0.00007859221,0.0020545828],"category_scores_gemma":[0.06620103,0.00015798242,0.00023130602,0.0011820018,0.0025618298,0.0003284492,0.00023627553,0.0009415261,0.000035618596],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021247002,0.00227964,0.024993263,0.0006526005,0.00019078614,0.00018863296,0.00062678475,0.00003654093,0.06740577,0.12215757,0.060372777,0.71897095],"study_design_scores_gemma":[0.0061079836,0.0031981212,0.0013216911,0.0020376472,0.00037659734,0.00015883184,0.0004318577,0.014520673,0.4911642,0.38547343,0.09461905,0.00058991654],"about_ca_topic_score_codex":0.000014398459,"about_ca_topic_score_gemma":0.000001344484,"teacher_disagreement_score":0.71838105,"about_ca_system_score_codex":0.00015750837,"about_ca_system_score_gemma":0.0006162478,"threshold_uncertainty_score":0.9988577},"labels":[],"label_agreement":null},{"id":"W2900570413","doi":"10.1161/circulationaha.117.026229","title":"Composite End Points in Clinical Research","year":2017,"lang":"en","type":"review","venue":"Circulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre","funders":"","keywords":"Medicine; Clinical trial; Event (particle physics); Intensive care medicine; Internal medicine","score_opus":0.9668561325273701,"score_gpt":0.7787165620159249,"score_spread":0.18813957051144525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900570413","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000037650185,0.98346907,0.0054032337,0.000056639557,0.0016972839,0.0024911698,0.00007407144,0.00006634302,0.006704537],"genre_scores_gemma":[0.00006357869,0.8740342,0.124634646,0.000010361782,0.00097655674,0.00010048731,0.000023237904,0.00007628104,0.00008063426],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98437643,0.010356562,0.0032498126,0.0007912235,0.00078268046,0.00044326723],"domain_scores_gemma":[0.86436343,0.13273743,0.0010759243,0.0014688377,0.00020079668,0.00015359293],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037108693,0.0002960312,0.003173616,0.00034769363,0.00015785459,0.00013015406,0.0007448466,0.0010913544,0.00023564299],"category_scores_gemma":[0.26419073,0.0002545044,0.0006512513,0.0002987039,0.00040725112,0.000074405514,0.0002664542,0.002008235,0.0005579255],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007253768,0.00013220338,0.00047389214,0.005691406,0.000053481905,0.000027975588,0.000010510518,5.597561e-8,3.2658846e-8,0.022920439,0.0003201283,0.9703626],"study_design_scores_gemma":[0.00035139627,0.000019789579,0.002329904,0.012014765,0.00022527413,0.0000046575105,0.0000014143127,0.00003680255,5.514562e-8,0.68953466,0.2952524,0.00022886417],"about_ca_topic_score_codex":0.00001014352,"about_ca_topic_score_gemma":0.000008679367,"teacher_disagreement_score":0.9701338,"about_ca_system_score_codex":0.00023987054,"about_ca_system_score_gemma":0.0003033782,"threshold_uncertainty_score":0.9999907},"labels":[],"label_agreement":null},{"id":"W2900742318","doi":"10.1136/bmj.k3532","title":"The reporting of studies conducted using observational routinely collected health data statement for pharmacoepidemiology (RECORD-PE)","year":2018,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":620,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; SickKids Foundation; University of Toronto; University of Ottawa; Jewish General Hospital; Children's Hospital of Eastern Ontario; Institute for Clinical Evaluative Sciences; McGill University; Ottawa Hospital","funders":"Medical Research Council; Fonds de Recherche du Québec - Santé; Wellcome Trust; Crohn's and Colitis Canada; Canadian Institutes of Health Research; National Institute for Health and Care Research; International Society for Pharmacoepidemiology; Canadian Association of Gastroenterology","keywords":"Pharmacoepidemiology; Observational study; Statement (logic); Medicine; Data science; Computer science; Pharmacovigilance; Data mining; Family medicine; Information retrieval; Pharmacology; Internal medicine; Adverse effect","score_opus":0.9784678425915878,"score_gpt":0.7711311390194552,"score_spread":0.20733670357213263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900742318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1448984,0.0005456258,0.8196272,0.023367317,0.0047997325,0.0053645596,0.0011105262,0.00013045617,0.00015613427],"genre_scores_gemma":[0.0046844496,0.00006490527,0.9933572,0.0007654496,0.0008420834,0.000074386444,0.000020325471,0.000022888345,0.00016831324],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9905534,0.0019137028,0.0065166964,0.00039114678,0.00025931635,0.00036577537],"domain_scores_gemma":[0.7079672,0.27139777,0.016617987,0.0015413023,0.0023298631,0.00014588959],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04327711,0.00013805475,0.0010189193,0.000027614471,0.0003499571,0.0000109293815,0.0003736808,0.00005820431,0.00004189062],"category_scores_gemma":[0.7134925,0.000091254995,0.00007244172,0.00022834947,0.0003848274,0.000051066236,0.0003231829,0.000121281744,0.0000012610831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011021291,0.0002892035,0.00937507,0.0012012477,0.0018233139,0.0000041345515,0.000611317,0.0000135652035,0.0029231051,0.075717255,0.8888193,0.018120367],"study_design_scores_gemma":[0.0017573597,0.00049938646,0.003023941,0.00033174467,0.00022047022,0.000009238645,0.0006147874,0.03451212,0.0010198328,0.94677836,0.011007253,0.00022551804],"about_ca_topic_score_codex":0.00005241434,"about_ca_topic_score_gemma":0.00007059676,"teacher_disagreement_score":0.877812,"about_ca_system_score_codex":0.000095858835,"about_ca_system_score_gemma":0.0004971356,"threshold_uncertainty_score":0.98514754},"labels":[],"label_agreement":null},{"id":"W2900745997","doi":"10.6000/1929-6029.2018.07.04.4","title":"Combining Survival and Toxicity Effect Sizes from Clinical Trials: NCCTG 89-20-52 (Alliance)","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Toxicity; Medicine; Clinical trial; Radiation therapy; Internal medicine; Overall survival; Survival analysis; Quality of life (healthcare); Survival rate; Randomized controlled trial; Oncology","score_opus":0.7744812795514252,"score_gpt":0.7272900553013018,"score_spread":0.047191224250123454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900745997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29606494,0.00037725546,0.677895,0.006346168,0.013857777,0.00077687134,0.0010390285,0.000033359414,0.0036095926],"genre_scores_gemma":[0.35089356,0.00193171,0.6389315,0.00031509117,0.007745903,0.000014014235,0.000008286171,0.000053940665,0.00010602799],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9629902,0.023153879,0.005422561,0.00054939376,0.0072532766,0.0006306616],"domain_scores_gemma":[0.32261315,0.67191297,0.0012566763,0.00034632612,0.0029626032,0.0009082877],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18102574,0.00024336339,0.0018899856,0.00031119448,0.000105408515,0.00019383471,0.001538358,0.0004913206,0.002815686],"category_scores_gemma":[0.8864252,0.00018126307,0.00021824079,0.0003023782,0.0023602315,0.00012629232,0.0006011665,0.0032036426,0.000045708515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068933517,0.0013751544,0.027475407,0.000117858675,0.0011561002,0.0027829257,0.0004097064,8.3571825e-7,0.00044575054,0.22283658,0.029519984,0.70698637],"study_design_scores_gemma":[0.006576152,0.001871862,0.006186177,0.0011419615,0.00006872632,0.000034814388,0.00013492667,0.0030191801,0.00051266205,0.9781622,0.0021039147,0.00018738056],"about_ca_topic_score_codex":0.000082427854,"about_ca_topic_score_gemma":0.00013930151,"teacher_disagreement_score":0.7553257,"about_ca_system_score_codex":0.00020452078,"about_ca_system_score_gemma":0.00070109096,"threshold_uncertainty_score":0.99909604},"labels":[],"label_agreement":null},{"id":"W2901178661","doi":"10.1093/annonc/mdy430.011","title":"Phase I investigator’s perceptions to ‘supersized seamless trials in oncology'","year":2018,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Family medicine; Clinical trial; Likert scale; Popularity; Oncology; Internal medicine; Psychology; Social psychology","score_opus":0.8991731111111113,"score_gpt":0.7310220453656908,"score_spread":0.1681510657454205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901178661","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91749716,0.0000289328,0.021126356,0.035771646,0.001736595,0.0017647566,0.00022230888,0.0000967762,0.021755466],"genre_scores_gemma":[0.22047329,0.00007846088,0.7681552,0.009869044,0.0009945919,0.00017805584,0.0000032241664,0.000041477026,0.00020662282],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878585,0.0080579575,0.0027498011,0.0004950521,0.00029506668,0.0005436762],"domain_scores_gemma":[0.83997583,0.15651922,0.0010013895,0.00083192985,0.00081344834,0.0008581763],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027525147,0.00023112014,0.0026696182,0.0003418145,0.00007018451,0.000011620189,0.00047937094,0.00057514914,0.002160515],"category_scores_gemma":[0.50224286,0.00020120668,0.00032078865,0.00057195575,0.00090736564,0.000068548805,0.0001954333,0.00038043625,0.00025759646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004787917,0.010170706,0.00043066547,0.00015371651,0.00036271694,0.00010252499,0.006969703,0.0000021539909,0.039861683,0.15992634,0.3515755,0.42565638],"study_design_scores_gemma":[0.009947704,0.016531736,0.00029507335,0.000119646116,0.00013960642,0.000011123272,0.0009112434,0.00005961882,0.011898946,0.8792889,0.08049397,0.00030244308],"about_ca_topic_score_codex":0.000047349913,"about_ca_topic_score_gemma":0.00015650822,"teacher_disagreement_score":0.7470289,"about_ca_system_score_codex":0.00012228078,"about_ca_system_score_gemma":0.00080345024,"threshold_uncertainty_score":0.99875164},"labels":[],"label_agreement":null},{"id":"W2901222219","doi":"10.5539/ijsp.v8n1p25","title":"An Exact Method for Power Calculation for a Three-arm Clinical Endpoint Bioequivalence Study","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Equivalence (formal languages); Bioequivalence; Sample size determination; Test (biology); Statistics; Exact test; Applied mathematics; Discrete mathematics; Medicine","score_opus":0.5024841564433383,"score_gpt":0.6257449473578522,"score_spread":0.12326079091451392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901222219","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056152,0.000008593802,0.9391385,0.00034031383,0.0018067755,0.001229753,0.0012825634,0.0000119720935,0.000029578543],"genre_scores_gemma":[0.23060839,0.000005194847,0.7684407,0.00008070708,0.0008084034,0.000028647019,0.0000036419947,0.000017202832,0.000007087883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99602383,0.0007688027,0.0020845272,0.0003726291,0.0005554152,0.00019480278],"domain_scores_gemma":[0.9519542,0.043348752,0.0010686913,0.00026278436,0.0031689373,0.00019666288],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016526498,0.0001729571,0.0006229357,0.00007864741,0.00009087259,0.00010594721,0.00041643257,0.000119100725,0.00013166582],"category_scores_gemma":[0.08950305,0.0001341493,0.00017535948,0.000055871486,0.00029684324,0.00013788542,0.00006987522,0.00021719941,8.7059266e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0075159622,0.0052996394,0.02637744,0.00016489447,0.000902511,0.00001636805,0.00069566607,0.0000115121775,0.0001519286,0.63275033,0.001872961,0.3242408],"study_design_scores_gemma":[0.002500675,0.006686784,0.028315483,0.00003563401,0.00020754858,0.000012588511,0.000044336062,0.011582566,0.00006809644,0.9498745,0.00052849186,0.00014330253],"about_ca_topic_score_codex":0.000012324956,"about_ca_topic_score_gemma":0.000059748567,"teacher_disagreement_score":0.3240975,"about_ca_system_score_codex":0.00007344877,"about_ca_system_score_gemma":0.00014483236,"threshold_uncertainty_score":0.91816646},"labels":[],"label_agreement":null},{"id":"W2902854630","doi":"10.1080/02664763.2018.1552668","title":"Testing homogeneity in a heteroscedastic contaminated normal mixture","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneity (statistics); Heteroscedasticity; Statistics; Mixture model; Inference; Mathematics; Normal distribution; Test statistic; Type I and type II errors; Statistical hypothesis testing; Computer science; Artificial intelligence","score_opus":0.32812212445169364,"score_gpt":0.49402816850563375,"score_spread":0.1659060440539401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902854630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12694773,0.000012053079,0.8681828,0.000036851256,0.00085550995,0.000308778,0.00023990915,0.000027416047,0.0033889867],"genre_scores_gemma":[0.36866558,0.0000027311808,0.63072246,0.00010534753,0.00045711346,0.000003510764,7.1668484e-7,0.000027313126,0.000015227073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966173,0.00028548908,0.0018994478,0.00022259864,0.0005606222,0.000414513],"domain_scores_gemma":[0.96371144,0.033916548,0.0011783842,0.00026008455,0.0007187843,0.00021476569],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033072028,0.00023948238,0.00090007926,0.00017632966,0.00008121806,0.000049047765,0.00035708284,0.00019517493,0.00017621212],"category_scores_gemma":[0.069230266,0.0002020256,0.00007131761,0.00043608606,0.00032953784,0.00005296305,0.00008951318,0.0006993002,0.000023956143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00510833,0.0027211981,0.009717839,0.0011696838,0.00063921546,0.0018036494,0.0025375164,0.00010120057,0.0491621,0.64544594,0.025898658,0.2556947],"study_design_scores_gemma":[0.002702474,0.0010125788,0.011116995,0.00020213198,0.00018047709,0.00009369913,0.0001042301,0.0014751409,0.0036218825,0.9789909,0.00020125737,0.00029824805],"about_ca_topic_score_codex":0.0000049349765,"about_ca_topic_score_gemma":0.000022688318,"teacher_disagreement_score":0.33354497,"about_ca_system_score_codex":0.00011182096,"about_ca_system_score_gemma":0.00016015022,"threshold_uncertainty_score":0.93861},"labels":[],"label_agreement":null},{"id":"W2903905844","doi":"10.1016/j.jclinepi.2018.11.028","title":"Noninferiority drug trials fail to report adequate methodological detail: an assessment of noninferiority trials from 2010 to 2015","year":2018,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Drug trial; Clinical trial; Medical physics; Intensive care medicine; Endpoint Determination; MEDLINE; Internal medicine","score_opus":0.9581161805867473,"score_gpt":0.7801152593479854,"score_spread":0.17800092123876188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903905844","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013978213,0.0001257527,0.619411,0.33317724,0.029400364,0.0024401753,0.0011752227,0.00007162786,0.00022045111],"genre_scores_gemma":[0.0002170696,0.00028121794,0.7838761,0.16158998,0.05318554,0.00009215786,0.000045291607,0.00015812056,0.0005544756],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3141035,0.56448334,0.111438416,0.0038656555,0.003479094,0.002629946],"domain_scores_gemma":[0.035899777,0.88773316,0.06550334,0.003952611,0.00426593,0.0026451715],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.769501,0.0016688054,0.0640103,0.00074561883,0.00015647887,0.0000944403,0.0036980705,0.0082901325,0.0051410766],"category_scores_gemma":[0.9888797,0.0011051446,0.009330846,0.0006111462,0.0015699334,0.0002585867,0.0012727783,0.014308487,0.00015727834],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003929153,0.00082842127,0.011466362,0.00021341429,0.003327456,0.0019920748,0.00009103993,0.000015684915,0.000053187647,0.0023515741,0.9597966,0.015935024],"study_design_scores_gemma":[0.0041196053,0.007581129,0.02824425,0.0008947496,0.004890888,0.00022143444,0.00004593688,0.00007331302,0.000072098905,0.77278966,0.17993306,0.0011338709],"about_ca_topic_score_codex":0.0004102716,"about_ca_topic_score_gemma":0.000057497888,"teacher_disagreement_score":0.77986354,"about_ca_system_score_codex":0.0003312218,"about_ca_system_score_gemma":0.0027246675,"threshold_uncertainty_score":0.9996059},"labels":[],"label_agreement":null},{"id":"W2905463162","doi":"10.1001/jamaoncol.2018.5877","title":"Assessment of Frequency and Reporting of Changes in Cancer Trial Design After Initiation of Patient Accrual","year":2018,"lang":"en","type":"letter","venue":"JAMA Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre","funders":"Vetenskapsrådet; National Natural Science Foundation of China","keywords":"Medicine; Accrual; Clinical trial; Research design; Clinical study design; Oncology; Drug trial; Internal medicine; Statistics; Accounting","score_opus":0.665240267925091,"score_gpt":0.6166713619402905,"score_spread":0.04856890598480046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905463162","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7580357,0.00043122808,0.06208118,0.15052435,0.010227724,0.011623716,0.0015178975,0.000060799342,0.0054974067],"genre_scores_gemma":[0.03180657,0.000114389724,0.9494696,0.015372397,0.002481508,0.00068400556,0.000009361879,0.0000461256,0.000016030584],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912366,0.003156659,0.004551787,0.00037923126,0.0004305436,0.0002451585],"domain_scores_gemma":[0.94331837,0.046183422,0.009697133,0.00034125333,0.0004291068,0.00003070449],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0070863534,0.00020796513,0.0021730817,0.00022183612,0.000009795385,0.000005087312,0.0001462221,0.0013596485,0.00042699516],"category_scores_gemma":[0.108159445,0.00017519835,0.00011198264,0.00014592282,0.00033426264,0.00003341585,0.00012851348,0.0008049577,2.4465058e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.052616835,0.0063202768,0.02961885,0.02656145,0.0027158153,0.0026895471,0.008801878,0.000010745222,0.006869098,0.012670404,0.42034745,0.43077764],"study_design_scores_gemma":[0.029999496,0.021433398,0.010477248,0.0026796784,0.0010094288,0.00001752275,0.00014570296,0.00010863872,0.005943565,0.92240703,0.005146874,0.0006314178],"about_ca_topic_score_codex":0.00012627235,"about_ca_topic_score_gemma":0.00010516895,"teacher_disagreement_score":0.90973663,"about_ca_system_score_codex":0.00021205882,"about_ca_system_score_gemma":0.00058327534,"threshold_uncertainty_score":0.9999368},"labels":[],"label_agreement":null},{"id":"W2905514961","doi":"10.1002/bimj.201800181","title":"Maximum likelihood estimation of generalized linear models for adaptive designs: Applications and asymptotics","year":2018,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Estimator; Categorical variable; Asymptotic distribution; Generalized linear model; Mathematics; Statistics; Econometrics; Inference; Statistical inference; Generalized estimating equation; Normality; Clinical trial; Computer science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.5521678229803676,"score_gpt":0.5339061822595332,"score_spread":0.01826164072083436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905514961","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014509157,0.00014879186,0.99709594,0.00015626018,0.00019396502,0.0006679227,0.000103964376,0.000028405719,0.00015382818],"genre_scores_gemma":[0.04706647,0.00008595605,0.9519774,0.00006576518,0.0007132319,0.000046347086,0.0000013640285,0.000028282713,0.000015219838],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976686,0.00031472568,0.0010798309,0.00024067143,0.00041043866,0.00028573204],"domain_scores_gemma":[0.97828496,0.019878633,0.0005677771,0.00022380619,0.00076051534,0.00028430455],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002858661,0.00015754199,0.0005460094,0.0005296704,0.000162587,0.000045077708,0.00022344054,0.0002009661,0.0000434304],"category_scores_gemma":[0.029457305,0.00012519654,0.00015000527,0.0011855677,0.00030117462,0.0001014163,0.00006910015,0.0001892867,0.0000058163555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070248434,0.0008149617,0.000037747894,0.00016043962,0.00033162517,0.000002400168,0.00012291451,0.00009653634,0.0013678058,0.3397339,0.0023321204,0.65429705],"study_design_scores_gemma":[0.001302416,0.00082158827,0.00003403983,0.00003528816,0.00016651089,0.000020956279,0.000015716323,0.1423816,0.0020629675,0.85287035,0.00016469399,0.00012389834],"about_ca_topic_score_codex":0.0000015300398,"about_ca_topic_score_gemma":1.7493713e-7,"teacher_disagreement_score":0.65417314,"about_ca_system_score_codex":0.000058583286,"about_ca_system_score_gemma":0.00008759161,"threshold_uncertainty_score":0.978718},"labels":[],"label_agreement":null},{"id":"W2906016239","doi":"10.1016/j.jval.2018.09.2375","title":"PRM258 - METHODOLOGICAL APPROACHES FOR CONDUCTING MATCHING-ADJUSTED INDIRECT COMPARISONS INVOLVING MULTIPLE RANDOMIZED CONTROLLED TRIALS","year":2018,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; Dalhousie University","funders":"","keywords":"Randomized controlled trial; Pooling; Matching (statistics); Meta-analysis; Computer science; Medicine; Consistency (knowledge bases); Set (abstract data type); Statistics; Data mining; Medical physics; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.9602785610421709,"score_gpt":0.637073148182864,"score_spread":0.32320541285930693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906016239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051112387,0.0007679479,0.92617804,0.0019011381,0.0022348622,0.016993444,0.00010330939,0.00026897131,0.0004398817],"genre_scores_gemma":[0.13890944,0.00006217057,0.858018,0.00035431125,0.0010393375,0.0014825317,0.000006298918,0.000063155596,0.00006478659],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8996482,0.089370295,0.008393215,0.00094985194,0.0005964967,0.0010419447],"domain_scores_gemma":[0.18020232,0.814815,0.0038594392,0.0005740819,0.00023111944,0.00031803234],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29497093,0.00047273556,0.013326435,0.0003116831,0.00035175704,0.00009309476,0.0004279436,0.00045095402,0.00013909016],"category_scores_gemma":[0.88810116,0.0003113955,0.0012097446,0.00042229658,0.0005898776,0.00008257153,0.00014141745,0.00072658045,0.000010514469],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.30936214,0.0014749471,0.00063995976,0.0027308792,0.0017175163,0.0000064410647,0.0058173807,0.00077151106,0.00035921184,0.661528,0.0029325048,0.012659518],"study_design_scores_gemma":[0.23298495,0.00031398507,0.000026561922,0.00044727928,0.00026836083,0.0000033632123,0.0006809579,0.09455508,0.00033671828,0.67006785,0.000051977335,0.00026293722],"about_ca_topic_score_codex":0.0005478221,"about_ca_topic_score_gemma":0.00005779686,"teacher_disagreement_score":0.72544473,"about_ca_system_score_codex":0.00020971085,"about_ca_system_score_gemma":0.0003676375,"threshold_uncertainty_score":0.99993384},"labels":[],"label_agreement":null},{"id":"W2906331464","doi":"10.17863/cam.35497","title":"The CONSORT extension for Stepped-Wedge Cluster Randomised Trials: baseline assessment of reporting quality -and assessment of inter-rater reliability using a crowd-sourcing systematic review","year":2019,"lang":"en","type":"article","venue":"Apollo (University of Cambridge)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"National Institute for Health and Care Research","keywords":"Consolidated Standards of Reporting Trials; Inter-rater reliability; Reliability (semiconductor); Baseline (sea); Cluster (spacecraft); Medicine; Systematic review; Quality assessment; Cluster randomised controlled trial; Clinical trial; Physical therapy; MEDLINE; Psychology; Statistics; Randomized controlled trial; Computer science; Mathematics; Surgery; External quality assessment; Internal medicine; Political science; Pathology","score_opus":0.49481794821079994,"score_gpt":0.5602087962658171,"score_spread":0.06539084805501716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906331464","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33660847,0.0005021962,0.65266734,0.0005475455,0.0003463451,0.008867282,0.00013494995,0.000023085931,0.000302776],"genre_scores_gemma":[0.4372569,0.0003618205,0.56193125,0.00009034273,0.00002996202,0.000011058048,0.000004345685,0.000025987305,0.0002883548],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9846213,0.008166331,0.005809785,0.0005111979,0.00061641895,0.00027499752],"domain_scores_gemma":[0.8039088,0.17663713,0.016118908,0.0016733103,0.0015091894,0.0001526713],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.102588825,0.00024108517,0.004107138,0.000079582045,0.00014942198,0.000018281526,0.0003108837,0.00014629759,0.000037188925],"category_scores_gemma":[0.1996527,0.00017736852,0.0008068004,0.00018071262,0.00033683187,0.000110867666,0.00028402422,0.00024888656,4.680132e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067620883,0.0009983468,0.013151953,0.92436266,0.0022574165,0.000011560469,0.0004975724,0.00005004126,0.014343339,0.034482583,0.0011794501,0.0019030176],"study_design_scores_gemma":[0.15156035,0.0024266944,0.031483006,0.44436848,0.034208946,0.00007663076,0.012738543,0.26686373,0.003984496,0.04934897,0.00024803588,0.0026921134],"about_ca_topic_score_codex":0.00015026164,"about_ca_topic_score_gemma":0.000009305686,"teacher_disagreement_score":0.47999415,"about_ca_system_score_codex":0.00012767912,"about_ca_system_score_gemma":0.00026871372,"threshold_uncertainty_score":0.92407364},"labels":[],"label_agreement":null},{"id":"W2907138006","doi":"10.5539/ijsp.v8n1p120","title":"Sequential Testing in Reliability and Validity Studies With Repeated Measurements per Subject","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sequential probability ratio test; Statistics; Sample size determination; Reliability (semiconductor); Mathematics; Statistical hypothesis testing; Statistical power; Sequential analysis; Null hypothesis; Z-test; Test statistic; Statistic; Power (physics)","score_opus":0.6675577160278215,"score_gpt":0.5476726252864234,"score_spread":0.11988509074139819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907138006","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9129127,0.000040233277,0.085608445,0.00031622848,0.000567899,0.0002491893,0.00013242375,0.000009846367,0.00016299268],"genre_scores_gemma":[0.46200606,0.000023295794,0.53778356,0.000026461468,0.00014713292,0.0000024907858,3.6851824e-7,0.0000062557283,0.0000043434],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997069,0.00076021056,0.0011061853,0.0002658861,0.0006483279,0.00015037664],"domain_scores_gemma":[0.9783051,0.017544549,0.00062083214,0.00015631477,0.0032709548,0.00010227617],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008522601,0.0001440902,0.00047149914,0.00007063383,0.000058417954,0.00005899569,0.00015979634,0.000060405928,0.000039500985],"category_scores_gemma":[0.1392602,0.0001008405,0.000028438515,0.000090782,0.0006861126,0.000106079584,0.00011084386,0.0002638424,5.697979e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036471295,0.000933548,0.9106283,0.00059191097,0.0007824137,0.00015230919,0.0017343867,0.000018948649,0.0008578539,0.028924115,0.0005347147,0.051194374],"study_design_scores_gemma":[0.0012372212,0.0007960604,0.07375091,0.00022821037,0.00008121251,0.000071316186,0.000052719737,0.0002593012,0.00034294935,0.9230357,0.000030376159,0.00011405537],"about_ca_topic_score_codex":0.0000368913,"about_ca_topic_score_gemma":0.000090187976,"teacher_disagreement_score":0.8941116,"about_ca_system_score_codex":0.00014613969,"about_ca_system_score_gemma":0.00011882213,"threshold_uncertainty_score":0.8679902},"labels":[],"label_agreement":null},{"id":"W2911723635","doi":"10.1002/9781118445112.stat06351","title":"Multiple Comparison Procedures","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Manitoba","funders":"","keywords":"Pairwise comparison; Variance (accounting); Statistics; Normality; Analysis of variance; Homogeneity (statistics); Multiple comparisons problem; Mathematics; Simple (philosophy); Computer science; Econometrics","score_opus":0.481149776638878,"score_gpt":0.5500234040775236,"score_spread":0.06887362743864561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911723635","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009825079,0.00046108174,0.8757686,0.000091095826,0.0014543623,0.0014998701,0.06057211,0.0009888856,0.05915416],"genre_scores_gemma":[0.00017343395,0.0009402405,0.8437506,0.00023534415,0.0013064413,0.000109240485,0.0017272912,0.001318317,0.15043907],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99233395,0.0011754774,0.0025369148,0.0014619835,0.0013968815,0.0010947903],"domain_scores_gemma":[0.9607516,0.034337085,0.002203898,0.001689509,0.00040741276,0.0006105069],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013159369,0.0012046366,0.0030665349,0.000409723,0.00013270117,0.00012885213,0.0011911354,0.0011935438,0.008691362],"category_scores_gemma":[0.11774858,0.0010470422,0.00017866438,0.00034508936,0.00089013716,0.000036931724,0.00036436738,0.0016338446,0.00085554906],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009741777,0.00080475636,0.00022278757,0.0015889365,0.00024087827,0.000028041242,0.000038048092,0.0000020510465,0.000011654311,0.16330503,0.8101692,0.023491167],"study_design_scores_gemma":[0.0015756064,0.00041702506,0.000075056894,0.0018631776,0.0004431038,0.0000056362173,0.000049338072,0.0016926632,0.000015593674,0.5803229,0.41234234,0.001197556],"about_ca_topic_score_codex":0.00015847247,"about_ca_topic_score_gemma":0.002256174,"teacher_disagreement_score":0.41701788,"about_ca_system_score_codex":0.0001383092,"about_ca_system_score_gemma":0.0004644006,"threshold_uncertainty_score":0.9999224},"labels":[],"label_agreement":null},{"id":"W2911938742","doi":"10.1002/cjs.11482","title":"A consistent estimator for logistic mixed effect models","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; Huntington Society of Canada; Hewlett-Packard Development Company; National Science Foundation","keywords":"Estimator; Covariate; Random effects model; Econometrics; Normality; Logistic regression; Statistics; Mixed model; Independence (probability theory); Mathematics; Computer science; Medicine","score_opus":0.5403284648349026,"score_gpt":0.5035855842461586,"score_spread":0.036742880588743976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911938742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058706882,0.00007345704,0.9871348,0.00019609691,0.0027065247,0.00078705023,0.0023788211,0.000009368413,0.00084316544],"genre_scores_gemma":[0.14843863,0.000003942569,0.8509027,0.00013791201,0.00019402403,0.000011137371,0.000004444606,0.000050540748,0.00025671988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967832,0.0005313893,0.0015927947,0.00022612362,0.00036778089,0.0004987054],"domain_scores_gemma":[0.93042344,0.06664996,0.0008642892,0.00036840275,0.0007730544,0.0009208621],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004332595,0.00024273955,0.0011600738,0.0001934408,0.00009838667,0.0000931933,0.0003878522,0.00016618306,0.00047777942],"category_scores_gemma":[0.12533511,0.00019759218,0.00023874581,0.000120810684,0.00022604933,0.000070241724,0.00001646616,0.00035066195,0.00004771188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018594218,0.000034862223,0.00074019324,0.00056809356,0.00022700158,0.00021038136,0.00007267835,0.00034542423,0.000031240677,0.9244488,0.06300465,0.010130724],"study_design_scores_gemma":[0.0019515806,0.0011248194,0.00021330871,0.0001990819,0.00035298066,0.00009606293,0.000039374358,0.011518016,0.0000837595,0.98257726,0.0016145287,0.00022921964],"about_ca_topic_score_codex":0.00012872904,"about_ca_topic_score_gemma":0.0006228825,"teacher_disagreement_score":0.14256795,"about_ca_system_score_codex":0.00022215805,"about_ca_system_score_gemma":0.0013141235,"threshold_uncertainty_score":0.8820326},"labels":[],"label_agreement":null},{"id":"W2911987067","doi":"10.1016/j.jacc.2004.02.021","title":"Composite confusion","year":2004,"lang":"en","type":"letter","venue":"Journal of the American College of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Medicine; Confusion; Composite number; Composite material; Psychoanalysis","score_opus":0.2246274955680671,"score_gpt":0.4723853100082871,"score_spread":0.24775781444022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911987067","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011994687,0.00029308593,0.048531838,0.92043716,0.010391912,0.0010705215,0.0018685558,0.00003143724,0.0053808326],"genre_scores_gemma":[0.009749107,0.00034933467,0.6645974,0.3058831,0.018286645,0.000009131587,0.0000019765791,0.00016680919,0.000956484],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925589,0.003896167,0.002173535,0.00023483095,0.0007875885,0.00034900816],"domain_scores_gemma":[0.95640635,0.036264997,0.005854689,0.00077962864,0.00061767234,0.000076644086],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028316244,0.00032757304,0.0039543468,0.00019065358,0.00006308967,0.000006397011,0.0013495459,0.00048405718,0.000036670815],"category_scores_gemma":[0.02682927,0.00019789557,0.001579366,0.0003589515,0.0017386354,0.000022312597,0.0002998848,0.0027762456,0.000004611061],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031945584,0.000023520102,0.00015340473,0.00015151035,0.00095817127,0.0012293512,0.000007486107,0.000041503885,0.0003934639,0.002316795,0.99390006,0.0005053036],"study_design_scores_gemma":[0.0012319818,0.001081137,0.0004749583,0.00051707914,0.0012336113,0.0024925347,0.000030323316,0.0000024744188,0.0003513927,0.71320343,0.2791116,0.00026949748],"about_ca_topic_score_codex":0.000005150708,"about_ca_topic_score_gemma":3.3606884e-7,"teacher_disagreement_score":0.71478844,"about_ca_system_score_codex":0.00018915438,"about_ca_system_score_gemma":0.00049946964,"threshold_uncertainty_score":0.9995244},"labels":[],"label_agreement":null},{"id":"W2912994842","doi":"10.1080/03610918.2018.1530783","title":"A more powerful familywise error control procedure for evaluating mean equivalence","year":2019,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Bonferroni correction; Type I and type II errors; Equivalence (formal languages); Multiple comparisons problem; Mathematics; Statistics; Monte Carlo method; Computer science; Discrete mathematics","score_opus":0.681679522865821,"score_gpt":0.6534516722237909,"score_spread":0.02822785064203015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912994842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039481275,0.00009200995,0.9566797,0.00043727545,0.00018147755,0.0023571895,0.00038209392,0.00008133668,0.00030766783],"genre_scores_gemma":[0.507743,0.000010573669,0.49187776,0.00015729552,0.00001672938,0.00007428476,0.00004862604,0.000022094766,0.00004963868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970947,0.0007597942,0.0011428426,0.00039879658,0.00035122296,0.0002526294],"domain_scores_gemma":[0.9375991,0.060521662,0.00048672772,0.00071515056,0.000592982,0.00008435524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025851368,0.00021182516,0.00048830966,0.00015817705,0.00017427909,0.00008403594,0.00037522265,0.00014240571,0.000040386538],"category_scores_gemma":[0.025670702,0.0002206722,0.00005524904,0.00029542213,0.00019012525,0.0001383612,0.00014218102,0.0002718443,0.000016234479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006392458,0.0007163197,0.007649258,0.0010779146,0.00011829888,0.0000013886472,0.004439569,0.22409756,0.00030243522,0.6370065,0.00054111844,0.12341039],"study_design_scores_gemma":[0.0018117484,0.00013021672,0.0034751752,0.00009856958,0.00005185442,6.8671915e-7,0.0002621664,0.5784459,0.0000025448694,0.4155327,0.000045475554,0.00014292069],"about_ca_topic_score_codex":0.000007845967,"about_ca_topic_score_gemma":0.000016609325,"teacher_disagreement_score":0.46826172,"about_ca_system_score_codex":0.00009525077,"about_ca_system_score_gemma":0.00010391655,"threshold_uncertainty_score":0.9825365},"labels":[],"label_agreement":null},{"id":"W2914598381","doi":"10.3899/jrheum.181054","title":"Adaptive Trial Designs in Rheumatology: Report from the OMERACT Special Interest Group","year":2019,"lang":"en","type":"review","venue":"The Journal of Rheumatology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"Sanofi; Pfizer; Celltrion; Eli Lilly and Company","keywords":"Medicine; Rheumatology; Internal medicine; Physical therapy; Family medicine","score_opus":0.7486996449454308,"score_gpt":0.5732690370821051,"score_spread":0.17543060786332576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914598381","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017819827,0.95086056,0.020376433,0.00067126827,0.021785304,0.0038773736,0.0001555468,0.000034131837,0.00045740866],"genre_scores_gemma":[0.00012566187,0.9589471,0.040087312,0.000039517192,0.00058348547,0.000039056475,0.000006051611,0.00011908129,0.00005273859],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9717244,0.01837914,0.00812912,0.00049820315,0.0006238696,0.0006452878],"domain_scores_gemma":[0.68281233,0.30696613,0.008704624,0.0012035404,0.00018650055,0.00012687461],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.020401735,0.00075267133,0.00896297,0.00028217316,0.0001154306,0.000053782915,0.0026344534,0.001148303,0.0008087485],"category_scores_gemma":[0.15958092,0.0003602424,0.0014601711,0.00044465196,0.0007851371,0.00010147441,0.00048325243,0.004092991,0.00019834399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0493519,0.0015333828,0.0005235945,0.00654686,0.0067510325,0.0015039351,0.0012198315,0.000001439444,2.8110702e-7,0.1130958,0.08499703,0.7344749],"study_design_scores_gemma":[0.015596681,0.0014424815,0.00001407938,0.026066937,0.0043390365,0.026036907,0.0003431484,0.000008349038,2.4236243e-7,0.70728475,0.21821223,0.0006551413],"about_ca_topic_score_codex":0.00021873691,"about_ca_topic_score_gemma":0.00023317759,"teacher_disagreement_score":0.7338198,"about_ca_system_score_codex":0.00024763466,"about_ca_system_score_gemma":0.000983627,"threshold_uncertainty_score":0.99988496},"labels":[],"label_agreement":null},{"id":"W2915084183","doi":"10.1007/s10928-019-09623-w","title":"Bioequivalence for highly variable drugs: regulatory agreements, disagreements, and harmonization","year":2019,"lang":"en","type":"review","venue":"Journal of Pharmacokinetics and Pharmacodynamics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Global Brain Health Institute","keywords":"Bioequivalence; Regulatory science; Regulatory agency; Harmonization; Econometrics; Variable (mathematics); Limit (mathematics); Food and drug administration; Computer science; Agency (philosophy); Constant (computer programming); Statistics; Risk analysis (engineering); Mathematics; Medicine; Economics; Pharmacology","score_opus":0.4121485277850134,"score_gpt":0.5570332166696518,"score_spread":0.1448846888846384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2915084183","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052361906,0.8912506,0.1022934,0.00006926347,0.0032289198,0.001851804,0.0011131562,0.00002120821,0.00011928553],"genre_scores_gemma":[0.000010856841,0.7537117,0.24485457,0.00011157081,0.0008420778,0.00002470684,0.000018465646,0.00010794752,0.00031813266],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99472946,0.0006937912,0.0029102077,0.00052724045,0.00067499955,0.00046432047],"domain_scores_gemma":[0.98142016,0.014033499,0.0033032082,0.0003228652,0.0005324776,0.0003877985],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004257162,0.0006701177,0.0028399762,0.00032115603,0.00012123849,0.00014665931,0.0005674385,0.00035645935,0.0001116587],"category_scores_gemma":[0.0032155076,0.0005356945,0.00045776472,0.00032829534,0.00020655243,0.00018320262,0.00028531038,0.00082123803,0.0000028005888],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001483664,0.00028342436,0.0000069662397,0.050333075,0.0015210155,0.000011850472,0.00006634227,0.000009060316,0.000106026826,0.015149645,0.006473004,0.9258912],"study_design_scores_gemma":[0.0038874627,0.0004096086,0.0000013129809,0.007768695,0.015631543,0.00008570213,0.000020755891,0.005142202,0.00003259144,0.079651676,0.8866069,0.0007615933],"about_ca_topic_score_codex":9.555881e-7,"about_ca_topic_score_gemma":7.170507e-8,"teacher_disagreement_score":0.92512965,"about_ca_system_score_codex":0.00014834641,"about_ca_system_score_gemma":0.0002733652,"threshold_uncertainty_score":0.9997095},"labels":[],"label_agreement":null},{"id":"W2916449784","doi":"10.1002/sim.8119","title":"Optimising the two‐stage randomised trial design when some participants are indifferent in their treatment preferences","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preference; Randomized controlled trial; Treatment and control groups; Treatment effect; Medicine; Clinical trial; Research design; Psychology; Statistics; Mathematics; Surgery; Internal medicine","score_opus":0.6713702372673928,"score_gpt":0.5579903408757302,"score_spread":0.11337989639166257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916449784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3946572,0.000324048,0.588015,0.001333184,0.003240737,0.010894246,0.0005169307,0.00008957733,0.00092903926],"genre_scores_gemma":[0.39545372,0.0003525242,0.60183066,0.0003224704,0.00068300613,0.00064897956,0.000014922848,0.00007177679,0.00062195025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99225336,0.0037246507,0.0019547672,0.000562911,0.0007295002,0.00077479123],"domain_scores_gemma":[0.88099235,0.11749399,0.0006136296,0.0006572688,0.00007773177,0.00016500843],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009697568,0.00041301336,0.0017402796,0.00019580353,0.00007461514,0.000044056953,0.00047311242,0.0001574896,0.0012867323],"category_scores_gemma":[0.07111423,0.00021653021,0.00007460401,0.000240649,0.00038276313,0.000056292774,0.00009754873,0.00051977776,0.000026234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.31983846,0.0052274936,0.01199132,0.0011561998,0.0012254782,0.0005756513,0.038485654,0.001865853,0.00063362607,0.47314194,0.0060146274,0.13984369],"study_design_scores_gemma":[0.17984588,0.0015509615,0.00098395,0.00051618944,0.00013956652,8.3114514e-7,0.0011393154,0.0057437285,0.00019336095,0.80962133,0.000043082026,0.00022179735],"about_ca_topic_score_codex":0.00013972916,"about_ca_topic_score_gemma":0.00018073336,"teacher_disagreement_score":0.3364794,"about_ca_system_score_codex":0.00025741843,"about_ca_system_score_gemma":0.0001536184,"threshold_uncertainty_score":0.9996262},"labels":[],"label_agreement":null},{"id":"W2917596343","doi":"10.1002/9781118445112.stat06572","title":"Multiple Comparison Tests: Nonparametric and Resampling Approaches","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Resampling; Statistics; Sampling distribution; Test statistic; Mathematics; Nonparametric statistics; Estimator; Statistic; Quantile; Heteroscedasticity; Statistical hypothesis testing; Econometrics; Ancillary statistic; Studentized range; Empirical distribution function; Standard error","score_opus":0.6709925666418755,"score_gpt":0.5358238571198032,"score_spread":0.13516870952207227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2917596343","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046389683,0.0011063239,0.93639404,0.00006624069,0.0007490134,0.001372269,0.034529947,0.0005777427,0.02515801],"genre_scores_gemma":[0.0004552698,0.0013990019,0.96160656,0.0001058108,0.00085272966,0.00008916952,0.0012020858,0.0010352833,0.033254106],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927681,0.0011710385,0.002366054,0.0015878311,0.0011228602,0.0009841342],"domain_scores_gemma":[0.92681247,0.06893485,0.0019408012,0.0014752938,0.00024224864,0.0005943538],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020491518,0.0011104597,0.0029855475,0.000693914,0.00015783659,0.00018771175,0.0008094616,0.0011134235,0.0014201299],"category_scores_gemma":[0.120036915,0.0009832869,0.00011898465,0.00060348643,0.0008291845,0.000043844004,0.00046781896,0.0017356788,0.0001648688],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017454942,0.0013288835,0.0014439229,0.002583865,0.00046383022,0.00003772277,0.000092588416,0.000008939273,0.000010018855,0.23917061,0.56623465,0.1884504],"study_design_scores_gemma":[0.0024359422,0.00064629246,0.00035778113,0.001975066,0.0007429392,0.0000114832665,0.00014284378,0.015482716,0.000009406444,0.7356166,0.24083471,0.0017442054],"about_ca_topic_score_codex":0.00022105691,"about_ca_topic_score_gemma":0.0008659832,"teacher_disagreement_score":0.49644598,"about_ca_system_score_codex":0.0001296355,"about_ca_system_score_gemma":0.00019088406,"threshold_uncertainty_score":0.9994927},"labels":[],"label_agreement":null},{"id":"W2918325349","doi":"10.1001/jamainternmed.2018.7166","title":"A Case for n-of-1 Trials","year":2019,"lang":"en","type":"letter","venue":"JAMA Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Medicine; Otorhinolaryngology; Family medicine; Neurology; Psychiatry","score_opus":0.7629614864493258,"score_gpt":0.6262843226129909,"score_spread":0.13667716383633488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918325349","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010630222,0.00019179609,0.33222547,0.6444683,0.012410237,0.0031435261,0.0014105422,0.000071668466,0.005972148],"genre_scores_gemma":[0.000085470805,0.000036867532,0.5090968,0.42941943,0.049048387,0.00022421326,0.000029746227,0.00016842913,0.01189068],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915403,0.0022560111,0.0043115267,0.00061724486,0.00082387537,0.00045100946],"domain_scores_gemma":[0.60839474,0.38805604,0.0023337957,0.0007247582,0.00041728566,0.00007335649],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018048117,0.00049942423,0.0049347887,0.00027432127,0.000025350539,0.000024165614,0.00070029986,0.0015247086,0.0024470196],"category_scores_gemma":[0.7403538,0.00031817958,0.0008139797,0.00012438011,0.0003709211,0.000039676248,0.00013855452,0.0022888656,0.00004755699],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004890595,0.000037638285,0.0000045484603,0.003399126,0.00059569004,0.0039360095,0.000090127796,3.3299642e-8,0.000036459027,0.0037634985,0.97004724,0.017600577],"study_design_scores_gemma":[0.004499115,0.0012768874,5.647383e-7,0.003541764,0.0012233267,0.0011800114,0.00002272329,0.00005646503,0.00019103772,0.52611166,0.4616487,0.0002477474],"about_ca_topic_score_codex":0.00013576775,"about_ca_topic_score_gemma":0.0000024520748,"teacher_disagreement_score":0.7223057,"about_ca_system_score_codex":0.00008235587,"about_ca_system_score_gemma":0.000090129455,"threshold_uncertainty_score":0.99992704},"labels":[],"label_agreement":null},{"id":"W2919124814","doi":"10.22237/jmasm/1571659200","title":"Comparing Means under Heteroscedasticity and Nonnormality: Further Exploring Robust Means Modeling","year":2020,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University","funders":"","keywords":"Heteroscedasticity; Mathematics; Statistics; Type I and type II errors; Normality; Homogeneity (statistics); Monte Carlo method; Econometrics; Variance (accounting); Analysis of variance","score_opus":0.8046739812709921,"score_gpt":0.5436600857329671,"score_spread":0.261013895538025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919124814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007095882,0.00007608975,0.9901718,0.00063830276,0.0003647508,0.00033283787,0.000055703593,0.000077923716,0.0011866991],"genre_scores_gemma":[0.30486107,0.000036203342,0.6941498,0.00043294538,0.00042852768,0.000014514594,5.90042e-7,0.00007420607,0.0000021645685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931508,0.0020354446,0.0026202875,0.000607043,0.0009458113,0.00064066396],"domain_scores_gemma":[0.95915294,0.038454685,0.00079302787,0.00034588674,0.0002943376,0.00095910375],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007873126,0.00047819066,0.0020375114,0.00011525032,0.00015851336,0.00015222709,0.00047039823,0.00022864502,0.00014678382],"category_scores_gemma":[0.032763362,0.00040281602,0.00021092949,0.00023690258,0.00029386466,0.000198313,0.00032333023,0.0014367822,0.000005867812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028176284,0.0004982976,0.0001638538,0.000933925,0.00085859286,0.000100964855,0.00422802,0.09552221,0.009014553,0.70509726,0.00014919639,0.1806155],"study_design_scores_gemma":[0.0010855208,0.00015099237,0.00006923015,0.00006729179,0.0003145036,0.000021287693,0.0003550246,0.45455414,0.00034583217,0.54276866,0.0000136685585,0.00025388188],"about_ca_topic_score_codex":0.0000037244847,"about_ca_topic_score_gemma":0.0000017147901,"teacher_disagreement_score":0.35903192,"about_ca_system_score_codex":0.000103839746,"about_ca_system_score_gemma":0.00008598451,"threshold_uncertainty_score":0.99984235},"labels":[],"label_agreement":null},{"id":"W2920935249","doi":"10.12688/gatesopenres.12912.2","title":"Highly Efficient Clinical Trials Simulator (HECT): Software application for planning and simulating platform adaptive trials","year":2019,"lang":"en","type":"preprint","venue":"Gates Open Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Bill and Melinda Gates Foundation","keywords":"Computer science; Simulation; Software; Clinical trial; Medicine; Operating system","score_opus":0.9393052779707239,"score_gpt":0.7455081536449564,"score_spread":0.19379712432576757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920935249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034686044,0.00063357234,0.90818,0.0005426233,0.0019984304,0.05054962,0.0024216115,0.00021692831,0.0007711703],"genre_scores_gemma":[0.20233104,0.0000714068,0.7906469,0.00008664739,0.0021502085,0.0039194264,0.00011350295,0.00023379044,0.00044706097],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95401514,0.028331228,0.010564148,0.0031870943,0.0022888384,0.0016135405],"domain_scores_gemma":[0.19418655,0.79752547,0.003741298,0.002115417,0.0018087227,0.00062252366],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.37731305,0.0007534219,0.0073984917,0.0004135333,0.0005846099,0.0011539574,0.0024429923,0.0019247384,0.00014158292],"category_scores_gemma":[0.85672724,0.0005898844,0.0010227471,0.00040157893,0.0005864328,0.000123657,0.006949831,0.0035749436,0.00008456289],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.043019235,0.0032101516,0.004820884,0.010757247,0.0057812985,0.00005151975,0.002335797,0.098980024,0.00039244763,0.2578878,0.0206577,0.5521059],"study_design_scores_gemma":[0.0061566276,0.00081765704,0.00019208681,0.0016263709,0.00042076784,0.0000010203304,0.0003352303,0.2278309,0.00042937437,0.76059747,0.0009655058,0.00062700326],"about_ca_topic_score_codex":0.00010934306,"about_ca_topic_score_gemma":0.000004589316,"teacher_disagreement_score":0.76919425,"about_ca_system_score_codex":0.00030884118,"about_ca_system_score_gemma":0.001096248,"threshold_uncertainty_score":0.99988294},"labels":[],"label_agreement":null},{"id":"W2920997529","doi":"10.17160/josha.6.3.546","title":"Can a Selection-Centric, Strengths-Based Approach to Cancer Treatment Help Treat or Prevent Cancer and Metastatic Disease?","year":2019,"lang":"en","type":"article","venue":"Journal of Science Humanities and Arts - JOSHA","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Selection (genetic algorithm); Cancer; Disease; Medicine; Cancer treatment; Intensive care medicine; Oncology; Computer science; Internal medicine; Artificial intelligence","score_opus":0.42538058447408583,"score_gpt":0.4992189614617724,"score_spread":0.07383837698768658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920997529","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99250877,0.00087691564,0.0021509856,0.0017703982,0.0006568063,0.0010764885,0.0002502735,0.00001990817,0.00068944105],"genre_scores_gemma":[0.7908789,0.0014072009,0.19720891,0.0012593687,0.0006993825,0.00017296702,8.0502156e-7,0.000048748803,0.008323719],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981278,0.00012188535,0.0005888957,0.00029238305,0.0005487935,0.00032023314],"domain_scores_gemma":[0.9962076,0.0027215579,0.0003708167,0.00013351951,0.00022598382,0.00034051668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010127111,0.0001921678,0.00054258166,0.00020992993,0.00028543617,0.00021457359,0.00016875385,0.000020245676,0.0004882032],"category_scores_gemma":[0.0022551238,0.00011476621,0.00007927131,0.0002501763,0.00043321282,0.00017636444,0.000043973454,0.00011638519,9.236787e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008651251,0.01587096,0.05202618,0.0065739187,0.0022851585,0.0004084352,0.032529723,0.006728551,0.0040955846,0.3118248,0.022600455,0.53640497],"study_design_scores_gemma":[0.04144908,0.029344233,0.044537656,0.009295115,0.01022239,0.00057080295,0.03324356,0.06045224,0.015935903,0.68458724,0.06461943,0.005742351],"about_ca_topic_score_codex":0.00012123585,"about_ca_topic_score_gemma":0.00013357263,"teacher_disagreement_score":0.5306626,"about_ca_system_score_codex":0.00026837885,"about_ca_system_score_gemma":0.0006128657,"threshold_uncertainty_score":0.5345482},"labels":[],"label_agreement":null},{"id":"W2921183574","doi":"10.1016/j.jclinepi.2019.03.003","title":"Most noninferiority trials were not designed to preserve active comparator treatment effects","year":2019,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Comparator; Engineering","score_opus":0.9516926757785006,"score_gpt":0.7644278044881085,"score_spread":0.18726487129039204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921183574","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011250056,0.8537277,0.11439557,0.0016231324,0.019346867,0.009272217,0.0008729246,0.00007326404,0.00057583966],"genre_scores_gemma":[0.000003013509,0.6192602,0.37481663,0.0009040768,0.004527462,0.00011944697,0.00000581765,0.000101059384,0.00026232016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7500936,0.20698747,0.03950533,0.0014200395,0.0007833335,0.0012102373],"domain_scores_gemma":[0.07867682,0.88532895,0.031762358,0.0016602501,0.00093774387,0.0016339018],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.21090518,0.0013734186,0.07314091,0.00037893924,0.00009455302,0.00004043663,0.0017710759,0.0035048896,0.00043055578],"category_scores_gemma":[0.9652413,0.0007908327,0.009964184,0.00048596965,0.000463265,0.000113468624,0.00043329873,0.0038031356,0.0005201738],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026140588,0.00121412,0.000078893514,0.008550378,0.0049070143,0.00014876026,0.000016832126,0.000004108358,4.931192e-7,0.010967643,0.018169846,0.95332783],"study_design_scores_gemma":[0.0052382406,0.012049998,0.00021016314,0.015409753,0.014219281,0.0001336823,0.000005797919,0.000016787506,0.000008564004,0.17103177,0.78087294,0.00080302905],"about_ca_topic_score_codex":0.000017099648,"about_ca_topic_score_gemma":0.00000553269,"teacher_disagreement_score":0.95252484,"about_ca_system_score_codex":0.0005552073,"about_ca_system_score_gemma":0.0029700687,"threshold_uncertainty_score":0.99995077},"labels":[],"label_agreement":null},{"id":"W2924458846","doi":"10.1002/sim.8142","title":"Randomised trials with provision for early stopping for benefit (or harm): The impact on the estimated treatment effect","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Ottawa; McMaster University; Ottawa Hospital; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Early stopping; Interim; Interim analysis; Type I and type II errors; Estimation; Harm; Sample size determination; Econometrics; Meta-analysis; Statistics; Stopping time; Treatment effect; Computer science; Clinical trial; Medicine; Mathematics; Psychology; Economics; Artificial intelligence","score_opus":0.5239753487763673,"score_gpt":0.6123429647629159,"score_spread":0.08836761598654863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924458846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104293816,0.00005579348,0.8605178,0.0021000204,0.0008412556,0.029951897,0.0018559393,0.000069479924,0.00031399433],"genre_scores_gemma":[0.16415986,0.00006055969,0.82911456,0.00037381414,0.0007362719,0.0043274057,0.000059598104,0.00014966412,0.0010182781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954565,0.0016107457,0.0014967213,0.00045337918,0.00050970865,0.00047293378],"domain_scores_gemma":[0.6042905,0.39451775,0.00050535786,0.00046843616,0.00014157806,0.0000764106],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019736053,0.00043779294,0.0021589962,0.000093363255,0.00016018665,0.00004813239,0.0003243683,0.00012756645,0.00040650688],"category_scores_gemma":[0.28169402,0.00013401412,0.00019053412,0.00022095417,0.00024775264,0.000025446432,0.00002492065,0.0002545266,0.000009611809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3574391,0.00091685285,0.0012609009,0.0015155596,0.0021990621,0.00004223558,0.0027573362,0.0006303307,0.0009611249,0.39896175,0.023014093,0.21030168],"study_design_scores_gemma":[0.11479622,0.032249596,0.0013914283,0.0016608526,0.0011984989,0.000004341015,0.00017563716,0.025180845,0.00094485807,0.8218828,0.00019521198,0.00031974493],"about_ca_topic_score_codex":0.00007772278,"about_ca_topic_score_gemma":0.000016681932,"teacher_disagreement_score":0.42292103,"about_ca_system_score_codex":0.00019781891,"about_ca_system_score_gemma":0.00011971475,"threshold_uncertainty_score":0.7243566},"labels":[],"label_agreement":null},{"id":"W2936140401","doi":"10.33892/aph.2019.89.17-21","title":"Bioequivalence metrics for absorption rates: linearity, specificity, sensitivity","year":2019,"lang":"en","type":"article","venue":"Acta Pharmaceutica Hungarica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sensitivity (control systems); Cmax; Absorption (acoustics); Kinetic energy; Metric (unit); Bioequivalence; Mathematics; Biological system; Chemistry; Equivalence (formal languages); Statistics; Materials science; Analytical Chemistry (journal); Chromatography; Pharmacokinetics; Physics; Pharmacology; Medicine; Pure mathematics; Biology","score_opus":0.6183178078171082,"score_gpt":0.5859712756704464,"score_spread":0.03234653214666183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936140401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13734792,0.00021944272,0.80544955,0.009886462,0.00983488,0.00974797,0.0012818873,0.001292988,0.024938924],"genre_scores_gemma":[0.5633478,0.00016678951,0.4338544,0.00077254826,0.0005972426,0.000056977227,0.000008941026,0.00007994546,0.0011153356],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955212,0.0010807404,0.0010723388,0.000853914,0.0007094863,0.0007623303],"domain_scores_gemma":[0.9160737,0.08199014,0.0004230873,0.000794741,0.00039807524,0.0003202551],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0071295993,0.000382761,0.00094400503,0.00021241466,0.00016295277,0.00013491511,0.00045368323,0.00033041445,0.0010941974],"category_scores_gemma":[0.055622157,0.00036266499,0.00034454063,0.00077651587,0.00021015285,0.00019713253,0.00034419695,0.0007172183,0.0004102994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035584874,0.005417884,0.011931743,0.004284729,0.0014212872,0.000095106625,0.0005058439,0.000031048843,0.3638462,0.3560436,0.11615541,0.13670866],"study_design_scores_gemma":[0.0053053307,0.0007068372,0.0017702313,0.00015945919,0.0009909387,0.000034085293,0.00009019536,0.059748117,0.101832926,0.71521115,0.112730816,0.0014199407],"about_ca_topic_score_codex":0.000009107863,"about_ca_topic_score_gemma":0.000002225533,"teacher_disagreement_score":0.42599988,"about_ca_system_score_codex":0.00014726182,"about_ca_system_score_gemma":0.00009253038,"threshold_uncertainty_score":0.9998825},"labels":[],"label_agreement":null},{"id":"W2936620722","doi":"10.1007/s43441-019-00065-7","title":"Defining Efficacy Estimands in Clinical Trials: Examples Illustrating ICH E9(R1) Guidelines","year":2020,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Pharmacy; Management science; Clinical trial; Computer science; Psychology; Outcomes research; Process (computing); Medicine; Alternative medicine; Family medicine; Economics","score_opus":0.883004335025943,"score_gpt":0.6623581172211382,"score_spread":0.22064621780480476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936620722","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67518055,0.00015638192,0.31513825,0.0053075715,0.0013772525,0.0011441025,0.00001732591,0.00034785428,0.0013307191],"genre_scores_gemma":[0.52379364,0.0000069776843,0.4727025,0.002974403,0.0004507601,0.000018083996,0.0000017451024,0.000027763761,0.000024110534],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98842144,0.0025768501,0.0061243325,0.0010173598,0.0012534414,0.000606556],"domain_scores_gemma":[0.8744225,0.117448576,0.003646325,0.0015394114,0.0025071097,0.0004360844],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09158845,0.00032096912,0.0013407799,0.00034874337,0.00028595616,0.00018177558,0.0009035463,0.00025313997,0.00018752995],"category_scores_gemma":[0.47467566,0.00026595805,0.00015729497,0.0049011386,0.0013900362,0.0003459556,0.00019513439,0.0006795314,0.000041994103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024341303,0.00011783658,0.0037924238,0.000045011686,0.000030359652,0.0000044692592,0.0003808949,0.0000928613,0.004517297,0.690535,0.0003226091,0.2999178],"study_design_scores_gemma":[0.0044370336,0.0007497654,0.041463688,0.00035928196,0.00011853465,0.000008070488,0.0004837202,0.055363297,0.0032578935,0.8915561,0.001416911,0.0007857222],"about_ca_topic_score_codex":0.0000071469008,"about_ca_topic_score_gemma":0.0000028523082,"teacher_disagreement_score":0.3830872,"about_ca_system_score_codex":0.00008845174,"about_ca_system_score_gemma":0.00077068934,"threshold_uncertainty_score":0.99997926},"labels":[],"label_agreement":null},{"id":"W2938672498","doi":"10.1016/j.respe.2019.03.016","title":"Dose-response relationship in the context of a maintenance randomized control trial: reanalysis of the PRODIGE 9 trial","year":2019,"lang":"fr","type":"article","venue":"Revue d Épidémiologie et de Santé Publique","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Medicine; Context (archaeology); Randomized controlled trial; Internal medicine; Population; Bevacizumab; Observational study; Chemotherapy","score_opus":0.2524337344973533,"score_gpt":0.48984378021909114,"score_spread":0.23741004572173785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938672498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8783943,0.0014680405,0.03629524,0.048319746,0.005069296,0.026526533,0.00075652084,0.00005978404,0.0031105627],"genre_scores_gemma":[0.9636594,0.00047273372,0.031116096,0.0015950843,0.00047231792,0.0010102874,0.000004482001,0.000054312124,0.001615302],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.84873015,0.14253019,0.006249842,0.00085385627,0.0006988815,0.000937093],"domain_scores_gemma":[0.45558754,0.5382214,0.003486428,0.0020849952,0.00052362005,0.000095986565],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16775022,0.0004939321,0.004623661,0.00026056395,0.00007064231,0.00007142896,0.0017544676,0.0010409526,0.00028654307],"category_scores_gemma":[0.85314703,0.00027670522,0.0020485274,0.0013358674,0.00152993,0.00017560746,0.00021067879,0.0017995293,0.000021390793],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6361891,0.0007111576,0.0018446939,0.0003992113,0.00035771265,0.00000832596,0.0010437815,0.00007548237,0.000060608574,0.3576472,0.0005411691,0.0011215291],"study_design_scores_gemma":[0.6017683,0.00095930556,0.003534387,0.0008294567,0.0007657468,0.000008009451,0.0005149515,0.0014314972,0.00007987648,0.38951957,0.0003678326,0.00022103492],"about_ca_topic_score_codex":0.00021670747,"about_ca_topic_score_gemma":0.000059097565,"teacher_disagreement_score":0.6853968,"about_ca_system_score_codex":0.0003311031,"about_ca_system_score_gemma":0.00180444,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W2941126996","doi":"","title":"Statistical process control to optimize quality assurance in radiotherapy: applied to Intensity-Modulated Radiation Therapy (IMRT)","year":2007,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Multileaf collimator; Statistical process control; Quality assurance; Computer science; Radiation therapy; Control chart; Medical physics; Reliability engineering; Medicine; Process (computing); Radiation treatment planning; Surgery; Engineering","score_opus":0.1612715146024829,"score_gpt":0.45595044136440427,"score_spread":0.29467892676192137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941126996","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07254278,0.00015748854,0.912485,0.006788245,0.00041491288,0.0032408852,0.00034370256,0.00028485578,0.003742139],"genre_scores_gemma":[0.3269809,0.00016766637,0.67101514,0.0009920794,0.000066673325,0.00033609025,0.000073512456,0.00009143706,0.0002764923],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9818512,0.012549156,0.0023314017,0.0015268022,0.0010112254,0.00073017273],"domain_scores_gemma":[0.9210766,0.072111025,0.0009878769,0.0025464974,0.0027026765,0.00057534425],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037218746,0.00061622594,0.0018021697,0.0004149871,0.0001684319,0.00031319863,0.0014584258,0.0006962954,0.0002935674],"category_scores_gemma":[0.110732906,0.00062809524,0.00021507901,0.00090255734,0.00024608357,0.00006458535,0.0004387859,0.0013095799,0.000046713823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005084919,0.005768456,0.0065618646,0.0015011483,0.0008935453,0.00004266885,0.02859216,0.005258778,0.009075103,0.37879166,0.004308592,0.55412114],"study_design_scores_gemma":[0.012056021,0.000011791507,0.074252926,0.0036477814,0.0001521095,0.0000071946047,0.00021359087,0.02834747,0.034646183,0.8407096,0.0032534525,0.0027018364],"about_ca_topic_score_codex":0.0004911985,"about_ca_topic_score_gemma":0.00039298242,"teacher_disagreement_score":0.55141926,"about_ca_system_score_codex":0.000499717,"about_ca_system_score_gemma":0.0004145667,"threshold_uncertainty_score":0.99961704},"labels":[],"label_agreement":null},{"id":"W2942218366","doi":"10.1177/1740774519829053","title":"Sample size calculation for stepped-wedge cluster-randomized trials with more than two levels of clustering","year":2019,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"ZonMw","keywords":"Cluster analysis; Sample size determination; Statistics; Cluster (spacecraft); Wedge (geometry); Mathematics; Randomized controlled trial; Sample (material); Cluster randomised controlled trial; Medicine; Computer science; Internal medicine; Chemistry; Chromatography","score_opus":0.7961628239582689,"score_gpt":0.6575450384263186,"score_spread":0.13861778553195025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942218366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069036014,0.000047846537,0.9056845,0.0008748192,0.003540207,0.018584335,0.001675444,0.00015739235,0.00039948316],"genre_scores_gemma":[0.1875438,0.000031563908,0.8088716,0.00037589416,0.0019397703,0.0005541903,0.000010972083,0.00012979808,0.0005423639],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9360504,0.043960575,0.016871953,0.0013009629,0.0010500839,0.0007660052],"domain_scores_gemma":[0.0898484,0.90051496,0.0071257157,0.0014084423,0.0007200377,0.0003824332],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27991474,0.0006144029,0.014316923,0.0001346077,0.0000983343,0.000099441844,0.0006483322,0.00072827755,0.0010366531],"category_scores_gemma":[0.9522637,0.000393892,0.0034482903,0.0003474115,0.0006836685,0.00015805992,0.00024818545,0.0005632319,0.000039912273],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.794524,0.0020747373,0.0032673853,0.002789938,0.006107678,0.000008352713,0.00045833964,0.0005722763,0.0015569357,0.10214324,0.0036820988,0.08281501],"study_design_scores_gemma":[0.37248763,0.0009939679,0.00059941557,0.00064362003,0.0024693438,0.0000024751494,0.00006970008,0.0073424634,0.00089125603,0.61372817,0.00024044373,0.0005315015],"about_ca_topic_score_codex":0.000036954625,"about_ca_topic_score_gemma":0.000021974956,"teacher_disagreement_score":0.8565544,"about_ca_system_score_codex":0.00006390024,"about_ca_system_score_gemma":0.0002828812,"threshold_uncertainty_score":0.99987656},"labels":[],"label_agreement":null},{"id":"W2942609530","doi":"10.1002/cjs.11498","title":"Analysis of generalized semiparametric mixed varying‐coefficients models for longitudinal data","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Dental and Craniofacial Research; National Institute of Allergy and Infectious Diseases; ACT Government; National Institute of Mental Health; University of North Carolina at Charlotte; National Institutes of Health; National Science Foundation","keywords":"Semiparametric regression; Semiparametric model; Mixed model; Longitudinal data; Mathematics; Econometrics; Applied mathematics; Statistics; Computer science; Nonparametric statistics; Data mining","score_opus":0.6662317291683647,"score_gpt":0.5065623197730502,"score_spread":0.1596694093953145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942609530","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02102844,0.0001326672,0.9619747,0.00004963456,0.0010998367,0.0003610473,0.015196539,0.00000453274,0.00015264444],"genre_scores_gemma":[0.2194541,0.000020596384,0.7801847,0.00004673991,0.00009177509,0.0000020452428,0.00006799908,0.0000314525,0.00010059705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964778,0.00033981373,0.001881802,0.00033329873,0.0005256944,0.00044161335],"domain_scores_gemma":[0.967136,0.028802741,0.001356653,0.0009235154,0.0011220251,0.000659045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00403814,0.00020451934,0.0014643933,0.0011402192,0.00006749717,0.000058050835,0.001042238,0.00015051443,0.0004614101],"category_scores_gemma":[0.06348455,0.0001849565,0.0002451685,0.0013936409,0.0001580606,0.00012607433,0.000063465974,0.00026252997,0.000004473347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007357645,0.00051017274,0.03134015,0.0011510481,0.012772105,0.00023690882,0.00047801217,0.05578844,0.000116782336,0.78480625,0.073486574,0.038577802],"study_design_scores_gemma":[0.0020269288,0.00034644746,0.0017343271,0.000100549405,0.0056846887,0.00001286434,0.00003337176,0.33824912,0.000060944363,0.650987,0.00048560338,0.00027813963],"about_ca_topic_score_codex":0.0005700317,"about_ca_topic_score_gemma":0.0013313742,"teacher_disagreement_score":0.2824607,"about_ca_system_score_codex":0.00013703654,"about_ca_system_score_gemma":0.0010531936,"threshold_uncertainty_score":0.9444041},"labels":[],"label_agreement":null},{"id":"W2942616731","doi":"10.1007/978-3-030-05120-4_27","title":"Simple Statistical Tests and P Values","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Simon Fraser University; Impact; University of British Columbia","funders":"","keywords":"Simple (philosophy); Statistical hypothesis testing; Computer science; Statistical analysis; Statistical theory; Statistical model; Test (biology); Statistical software; Statistics; Data science; Artificial intelligence; Mathematics; Epistemology","score_opus":0.5592909698985852,"score_gpt":0.5684563556988214,"score_spread":0.009165385800236181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942616731","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007075756,0.000058781454,0.14118606,0.00008481405,0.00040255114,0.000621069,0.0006871415,0.00014388243,0.8568086],"genre_scores_gemma":[0.000040800387,0.00006227998,0.5731589,0.00020946914,0.00025663857,0.0000039096562,0.0000081816825,0.000086210064,0.42617357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99745536,0.00014837184,0.0009932315,0.00063145114,0.00048069574,0.00029089293],"domain_scores_gemma":[0.8822531,0.11660464,0.00024638302,0.000589907,0.000103939026,0.00020202713],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0014743169,0.00041176396,0.0012906663,0.00006618723,0.00004363204,0.000057296795,0.00020295291,0.000610792,0.012973125],"category_scores_gemma":[0.052971717,0.0003228284,0.000117823845,0.000013101827,0.00035284218,0.000026600943,0.00025972413,0.0005643841,0.0008155839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022281682,0.000018534049,0.00001640218,0.00024256822,0.00008639804,0.000021183969,0.000006517941,2.2592294e-8,0.000002292789,0.9366328,0.048519906,0.014431067],"study_design_scores_gemma":[0.00039071232,0.00018926951,0.00007043516,0.000118234035,0.00024894436,0.000007506688,0.0000029169864,0.000055600456,0.000007412781,0.9620353,0.036485173,0.00038849164],"about_ca_topic_score_codex":0.000004253037,"about_ca_topic_score_gemma":0.0000047289077,"teacher_disagreement_score":0.4319729,"about_ca_system_score_codex":0.000035664565,"about_ca_system_score_gemma":0.000090993715,"threshold_uncertainty_score":0.9999624},"labels":[],"label_agreement":null},{"id":"W2943323131","doi":"10.48550/arxiv.1905.01402","title":"Test for homogeneity with unordered paired observations","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Homogeneity (statistics); Limiting; Statistics; Mathematics; Type I and type II errors; Combinatorics; Statistical hypothesis testing; Sample size determination; Computer science","score_opus":0.7386664602803285,"score_gpt":0.3908272818987555,"score_spread":0.34783917838157297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943323131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1258936,0.000010124229,0.8686802,0.0001742706,0.0005883136,0.0021125455,0.0011472994,0.00025207447,0.0011416014],"genre_scores_gemma":[0.51755095,0.000033338903,0.47859558,0.00009098273,0.00015870709,0.000013732855,0.00003684351,0.00007289058,0.0034469794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974393,0.00037354117,0.0005291014,0.0011216825,0.00012588808,0.00041046803],"domain_scores_gemma":[0.95377445,0.043398906,0.00061844685,0.0015086515,0.0005151838,0.00018435024],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011753873,0.00041646013,0.0009673091,0.000115118295,0.00015252005,0.000052713516,0.0008140758,0.00046571644,0.000110373185],"category_scores_gemma":[0.028742196,0.0004042424,0.0003510669,0.0003846515,0.0002293747,0.00007701864,0.0005666455,0.0005794471,0.00003874609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008761711,0.0013368686,0.044652488,0.0021418163,0.001009907,0.00012988836,0.00010995898,0.019312924,0.00007578363,0.92360735,0.006085178,0.0006616738],"study_design_scores_gemma":[0.0019928974,0.00026461616,0.0029398473,0.00025216382,0.0007787276,0.0000013909588,0.00006225582,0.030255813,0.000108767264,0.9623491,0.00042593788,0.0005684955],"about_ca_topic_score_codex":0.000044940214,"about_ca_topic_score_gemma":0.000085420565,"teacher_disagreement_score":0.39165735,"about_ca_system_score_codex":0.00017783241,"about_ca_system_score_gemma":0.00035762947,"threshold_uncertainty_score":0.9998409},"labels":[],"label_agreement":null},{"id":"W2944062769","doi":"10.1177/1740774519846504","title":"There is still a place for significance testing in clinical trials","year":2019,"lang":"en","type":"editorial","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ottawa Hospital","funders":"National Cancer Institute","keywords":"Significance testing; Clinical trial; Medicine; Internal medicine; Statistics; Mathematics","score_opus":0.9151790812600603,"score_gpt":0.7300723107311436,"score_spread":0.18510677052891666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944062769","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030218283,0.00069929386,0.026891708,0.0009978131,0.93856263,0.018694056,0.012018053,0.00041031756,0.0014239498],"genre_scores_gemma":[0.000036258087,0.0010117239,0.36220568,0.00058785937,0.63062143,0.0012211989,0.00008185792,0.00044926285,0.003784754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.6679681,0.22938861,0.08673692,0.007976452,0.004654516,0.0032753828],"domain_scores_gemma":[0.006068225,0.96217567,0.024181213,0.0041206824,0.0022901774,0.0011640359],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.68818456,0.0020396719,0.03304171,0.00040365555,0.00015819985,0.0004659157,0.003356641,0.013000886,0.0012633954],"category_scores_gemma":[0.9974046,0.0015780805,0.008887789,0.0010027381,0.0011924506,0.00018888111,0.0008084252,0.009354039,0.00064935716],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007538366,0.0015905849,0.00034266495,0.0015735923,0.001217398,0.000040815787,0.000039862905,0.000004420274,0.0000074326235,0.0016606089,0.9069658,0.07901844],"study_design_scores_gemma":[0.02128758,0.0022399493,0.000057329067,0.0026842135,0.0024224422,7.278854e-7,0.00004011208,0.0005329362,0.00002061427,0.41347882,0.55584174,0.0013935402],"about_ca_topic_score_codex":0.000059252405,"about_ca_topic_score_gemma":0.000031166674,"teacher_disagreement_score":0.7327871,"about_ca_system_score_codex":0.00038199057,"about_ca_system_score_gemma":0.0051424047,"threshold_uncertainty_score":0.9996496},"labels":[],"label_agreement":null},{"id":"W2944291700","doi":"10.1016/b978-0-12-813539-6.00021-3","title":"A Risk-Based Paradigm of Biomarkers in Clinical Trials","year":2019,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"","keywords":"Clinical trial; Risk analysis (engineering); Context (archaeology); Intensive care medicine; Medicine; Drug development; Computer science; Drug; Pharmacology; Pathology; Geography","score_opus":0.5402041268873206,"score_gpt":0.5601394975680688,"score_spread":0.019935370680748243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944291700","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000083961626,0.00037265295,0.0022451119,0.000085116146,0.002167447,0.003682493,0.00089602644,0.000077542,0.99038965],"genre_scores_gemma":[0.00026421325,0.0002738488,0.4873865,0.00032863452,0.0008787091,0.000091959104,0.000012245902,0.00032815023,0.51043576],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98157454,0.006760828,0.009240466,0.001076123,0.000861974,0.0004860474],"domain_scores_gemma":[0.76450074,0.22899015,0.0046566147,0.0015123106,0.00012016539,0.00022000527],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06027727,0.0007268374,0.0064132013,0.00037943813,0.00003159086,0.000027226475,0.0007390279,0.0017864801,0.0010769741],"category_scores_gemma":[0.23720373,0.00059614575,0.0021651925,0.000043083375,0.00072097697,0.000019201952,0.00017746055,0.0017301692,0.00021924473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006816714,0.000101833626,0.0001620095,0.0005617755,0.00084042794,0.000031639076,0.000018280432,4.203528e-7,0.0000024591714,0.12596379,0.00044355332,0.87119216],"study_design_scores_gemma":[0.0035889696,0.00034557816,0.0000830143,0.0018672294,0.0011101505,0.000001279321,0.0000021193239,0.00005895088,0.00003548816,0.86346346,0.12890689,0.00053689705],"about_ca_topic_score_codex":0.0000014985492,"about_ca_topic_score_gemma":0.000018428686,"teacher_disagreement_score":0.87065524,"about_ca_system_score_codex":0.000106119805,"about_ca_system_score_gemma":0.00071119546,"threshold_uncertainty_score":0.9998362},"labels":[],"label_agreement":null},{"id":"W2945053476","doi":"10.1200/edbk_238831","title":"Value-Added Decisions in Oncology","year":2019,"lang":"en","type":"review","venue":"American Society of Clinical Oncology Educational Book","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Null hypothesis; Value (mathematics); Outcome (game theory); Statement (logic); Actuarial science; p-value; Medicine; Set (abstract data type); Agency (philosophy); Test (biology); Food and drug administration; Economics; Statistics; Econometrics; Mathematics; Computer science; Risk analysis (engineering); Political science; Microeconomics","score_opus":0.826436994075985,"score_gpt":0.7366554256937266,"score_spread":0.08978156838225848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945053476","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001575747,0.9434726,0.0031941684,0.0121263955,0.0051547526,0.0035891652,0.00033722047,0.00006966596,0.03204028],"genre_scores_gemma":[5.132872e-7,0.5503589,0.44135118,0.0030818488,0.0009430776,0.00024631276,0.000025806781,0.00006557585,0.003926795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9788057,0.008875071,0.009498091,0.0013699374,0.00075981003,0.0006913946],"domain_scores_gemma":[0.51330245,0.47981054,0.0052989656,0.0009237414,0.00032151604,0.0003427808],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.015610208,0.00068522705,0.013247892,0.00017327965,0.00007246017,0.000011941824,0.0014100169,0.0020559358,0.0020589943],"category_scores_gemma":[0.23663856,0.00056656223,0.004540707,0.0008990051,0.0039815363,0.00007665923,0.00048186295,0.0031786265,0.0005069986],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057899535,0.0026476495,0.000051490068,0.0011758001,0.000572918,0.0000030110277,0.00008942306,5.90905e-7,5.5197965e-8,0.040891547,0.10286575,0.85164386],"study_design_scores_gemma":[0.00091908214,0.0012521219,0.00013642781,0.002210006,0.0013286133,0.000011658806,0.00013237458,0.00001251431,6.309482e-8,0.20347898,0.7901252,0.00039294135],"about_ca_topic_score_codex":0.000055164,"about_ca_topic_score_gemma":0.000008889376,"teacher_disagreement_score":0.85125095,"about_ca_system_score_codex":0.0011061501,"about_ca_system_score_gemma":0.019096065,"threshold_uncertainty_score":0.9996786},"labels":[],"label_agreement":null},{"id":"W2946565097","doi":"10.1002/sim.8194","title":"To add or not to add a new treatment arm to a multiarm study: A decision‐theoretic framework","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Computer science; Medicine","score_opus":0.4236848403530717,"score_gpt":0.6166050279663471,"score_spread":0.1929201876132754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946565097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033307776,0.000013700716,0.95472115,0.0021040696,0.0021527954,0.0063413046,0.0006337072,0.00009647727,0.0006290244],"genre_scores_gemma":[0.047696985,0.000016948741,0.94425577,0.004505618,0.00078068225,0.00031537763,0.000004783242,0.000116755815,0.002307088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99372256,0.00077187055,0.0021225496,0.0011514005,0.0014106992,0.0008209266],"domain_scores_gemma":[0.8612483,0.13563636,0.00021679426,0.0014284104,0.00023843274,0.0012316823],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004049385,0.0005806576,0.0020760985,0.00047325005,0.00006637943,0.00004389648,0.0007096394,0.00022996463,0.010892377],"category_scores_gemma":[0.39021152,0.0003916332,0.0000754164,0.0012711139,0.00012144474,0.000023959854,0.00032964122,0.00052827207,0.0014876922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009840446,0.00287344,0.0012699275,0.00019849003,0.00027533757,0.00072722294,0.021452654,0.00012687546,0.000097388,0.49247324,0.09580829,0.3748567],"study_design_scores_gemma":[0.0066314046,0.018038059,0.0027396688,0.0017141544,0.00030086038,0.0000066963853,0.0019678304,0.00025419498,0.0000674001,0.96392506,0.0038124563,0.0005421871],"about_ca_topic_score_codex":0.0002949155,"about_ca_topic_score_gemma":0.00079945213,"teacher_disagreement_score":0.47145185,"about_ca_system_score_codex":0.00046446722,"about_ca_system_score_gemma":0.00026368373,"threshold_uncertainty_score":0.99985355},"labels":[],"label_agreement":null},{"id":"W2947049706","doi":"10.1016/j.cmpb.2019.05.029","title":"Goftte: A R package for assessing goodness-of-fit in proportional (sub) distributions hazards regression models","year":2019,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Institut National Du Cancer","keywords":"Goodness of fit; Statistics; Computer science; Regression analysis; Censoring (clinical trials); Monte Carlo method; Mathematics","score_opus":0.555451432145992,"score_gpt":0.5929846527981623,"score_spread":0.03753322065217024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947049706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08497006,0.00020843379,0.91214657,0.00038012106,0.0007365298,0.0014234065,0.000044881148,0.00003827295,0.00005173487],"genre_scores_gemma":[0.05956969,0.000036073474,0.9399309,0.00004393603,0.00021070198,0.0001371063,0.00003201528,0.00002383938,0.000015718728],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99658614,0.0009553736,0.00130436,0.0005038501,0.0002947915,0.00035548356],"domain_scores_gemma":[0.9852204,0.013722584,0.0004011258,0.00037547894,0.00015764157,0.00012278343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008964463,0.00022821422,0.0010113303,0.00020317658,0.000041400588,0.000040203515,0.00020246099,0.000236033,0.000018537208],"category_scores_gemma":[0.0039802245,0.00016146293,0.00010764176,0.0006196916,0.00031351324,0.00012086765,0.00017093054,0.00030093038,4.8187354e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011193023,0.0005344765,0.0047878055,0.00087285927,0.000030174437,0.0000070892365,0.0001768235,0.0000023476082,0.0018441913,0.047599513,0.00011972471,0.94391304],"study_design_scores_gemma":[0.0026621507,0.00053142884,0.0033288577,0.001769421,0.00005017697,0.000009843224,0.00007305646,0.05822542,0.0010780678,0.9317698,0.00028716348,0.00021463449],"about_ca_topic_score_codex":0.0000076046886,"about_ca_topic_score_gemma":0.0000014432534,"teacher_disagreement_score":0.9436984,"about_ca_system_score_codex":0.0000548352,"about_ca_system_score_gemma":0.00007882811,"threshold_uncertainty_score":0.65842676},"labels":[],"label_agreement":null},{"id":"W2947191914","doi":"","title":"Can we disregard the whole model? Omnibus non-inferiority testing for $R^{2}$ in multivariable linear regression and $\\hat{\\eta}^{2}$ in ANOVA","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Statistics; Outcome (game theory); Null hypothesis; Statistical hypothesis testing; Type I and type II errors; Multiple comparisons problem; Analysis of variance; Linear regression; Bayesian probability; Linear model; Statistical power; Variance (accounting); Econometrics; Regression analysis; Mathematics; Computer science","score_opus":0.598334970752778,"score_gpt":0.4084113986404532,"score_spread":0.18992357211232475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947191914","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5169795,0.00004587656,0.47739446,0.0004893321,0.00066924345,0.0030544368,0.00042392017,0.000096643606,0.0008465969],"genre_scores_gemma":[0.74302983,0.000077693294,0.25590497,0.000049372593,0.00011044036,0.000012895695,0.0000081665585,0.000055265908,0.0007513315],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996613,0.0006478376,0.00080639165,0.0012224595,0.00014617227,0.00056411204],"domain_scores_gemma":[0.9695847,0.028260307,0.00060583744,0.0011748442,0.00021705915,0.00015725923],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031200375,0.0004783773,0.0012071938,0.00022036213,0.00013118346,0.00006253649,0.0007597365,0.0006190885,0.000011730757],"category_scores_gemma":[0.027642498,0.00038948373,0.00017955682,0.0005264295,0.00024606258,0.00010662399,0.0013671987,0.0014304206,0.000005994932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002432645,0.0016217522,0.15275212,0.00706644,0.0003652916,0.00046235204,0.002258161,0.6690401,0.00092135987,0.15574548,0.0007307463,0.0066035483],"study_design_scores_gemma":[0.0014575279,0.00005253516,0.0010038401,0.0008907241,0.00008864369,8.117851e-7,0.00010082366,0.4963043,0.000062860054,0.49973032,0.00002465901,0.00028294325],"about_ca_topic_score_codex":0.00040523885,"about_ca_topic_score_gemma":0.00031349252,"teacher_disagreement_score":0.34398484,"about_ca_system_score_codex":0.00029007456,"about_ca_system_score_gemma":0.00033044524,"threshold_uncertainty_score":0.9998557},"labels":[],"label_agreement":null},{"id":"W2947409284","doi":"10.1016/j.jclinepi.2019.05.033","title":"Single pivotal trials with few corroborating characteristics were used for FDA approval of cancer therapies","year":2019,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; Impact","funders":"Krebsliga Schweiz","keywords":"Medicine; Drug approval; Clinical trial; Cancer drugs; Cancer; Internal medicine; Pharmacology; Drug","score_opus":0.8519589956572093,"score_gpt":0.6813135385636881,"score_spread":0.1706454570935212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947409284","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76751775,0.0002917583,0.22380358,0.0025576488,0.0044385535,0.001103148,0.00017880871,0.000019945632,0.000088845714],"genre_scores_gemma":[0.27214974,0.00020938738,0.724468,0.0006044033,0.0023920878,0.000023477516,0.0000019914974,0.000054584518,0.000096311785],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96624684,0.017443236,0.014946008,0.00044167056,0.00041288038,0.00050935586],"domain_scores_gemma":[0.35321945,0.62931705,0.016031655,0.00040548373,0.0007844105,0.00024197996],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12730555,0.0003288401,0.010630224,0.00009291695,0.000044395598,0.000014932627,0.0004921229,0.0006530146,0.00035956132],"category_scores_gemma":[0.772912,0.0001899184,0.0014301356,0.00013906707,0.0005353748,0.00009547267,0.000069986,0.0010763174,0.000004911905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026748482,0.0022060312,0.63289833,0.0019204313,0.0040768976,0.000027321936,0.00035387295,0.00009659032,0.003773542,0.10069436,0.004199758,0.2230044],"study_design_scores_gemma":[0.020372462,0.02599934,0.030691624,0.0019444581,0.0021810126,0.000057097535,0.00034273224,0.0016875382,0.0012832176,0.9111769,0.0035892026,0.0006743689],"about_ca_topic_score_codex":0.000009538372,"about_ca_topic_score_gemma":0.0000070698675,"teacher_disagreement_score":0.81048256,"about_ca_system_score_codex":0.00004214549,"about_ca_system_score_gemma":0.00038283702,"threshold_uncertainty_score":0.8986226},"labels":[],"label_agreement":null},{"id":"W2947538236","doi":"10.1002/jrsm.1362","title":"Estimating hazard ratios from published Kaplan‐Meier survival curves: A methods validation study","year":2019,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; Public Health Ontario; University of Toronto; Sunnybrook Health Science Centre","funders":"Canadian Centre for Applied Research in Cancer Control","keywords":"Intraclass correlation; Inter-rater reliability; Hazard ratio; Statistics; Reliability (semiconductor); Medicine; Standard error; Gold standard (test); Mathematics; Confidence interval; Reproducibility; Physics","score_opus":0.7748885543966163,"score_gpt":0.7029467070522295,"score_spread":0.0719418473443868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947538236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026071317,0.00015589633,0.9575539,0.0011225785,0.0023095019,0.0043414724,0.00012934742,0.0003397504,0.007976192],"genre_scores_gemma":[0.0039468757,0.00003267494,0.9931335,0.00008260553,0.0008219396,0.00096928567,0.000010680472,0.0001786573,0.00082382065],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82870734,0.16054447,0.003183572,0.0022321856,0.0037014398,0.0016310016],"domain_scores_gemma":[0.26763305,0.72635424,0.0007851159,0.0031927086,0.0014104035,0.0006244665],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23504312,0.0005908317,0.0025959515,0.00058985554,0.0004047987,0.0006724669,0.001762715,0.00048083038,0.009094314],"category_scores_gemma":[0.82062197,0.0004926352,0.000418119,0.0017709226,0.0003356333,0.00060210755,0.00095226686,0.0019522681,0.00041123637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001046052,0.0042052595,0.013486969,0.002670925,0.0025562996,0.00006955235,0.0020340667,0.000074934534,0.030993896,0.023777064,0.014865037,0.9042199],"study_design_scores_gemma":[0.0014784621,0.00051047595,0.0027489504,0.001156267,0.0004753343,0.000003266934,0.0013872813,0.018356984,0.04324121,0.9289679,0.0008357418,0.00083813246],"about_ca_topic_score_codex":0.0002512846,"about_ca_topic_score_gemma":0.0000128867305,"teacher_disagreement_score":0.9051908,"about_ca_system_score_codex":0.00030464627,"about_ca_system_score_gemma":0.00041448345,"threshold_uncertainty_score":0.9997525},"labels":[],"label_agreement":null},{"id":"W2947771303","doi":"10.1016/j.drudis.2019.05.018","title":"Unbiased data analytic strategies to improve biomarker discovery in precision medicine","year":2019,"lang":"en","type":"review","venue":"Drug Discovery Today","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick; Toronto General Hospital","funders":"Diabetes Canada","keywords":"Overfitting; Biomarker discovery; Precision medicine; Computer science; Data science; Analytics; Preprocessor; Data pre-processing; Biomarker; Data mining; Machine learning; Artificial intelligence; Medicine; Proteomics; Biology","score_opus":0.6483316119005409,"score_gpt":0.6010919350572403,"score_spread":0.04723967684330055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947771303","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038182803,0.90947914,0.06493787,0.00041354934,0.0057254396,0.0068545495,0.007759282,0.00013587852,0.0046560825],"genre_scores_gemma":[0.000038464495,0.9475742,0.04324143,0.000172424,0.00093607116,0.00022961923,0.00068700034,0.0002784828,0.0068423087],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98791844,0.0031253472,0.004233039,0.0025259585,0.0012841066,0.0009131009],"domain_scores_gemma":[0.8974781,0.09557781,0.0013057411,0.0052716206,0.00008568092,0.00028106393],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010129146,0.0012215412,0.0070960475,0.0007313387,0.0000623958,0.00056570885,0.003262289,0.0006651526,0.00034482687],"category_scores_gemma":[0.094253324,0.00080372056,0.00063891953,0.0015381181,0.00032289998,0.0014934412,0.0021629906,0.0011432654,0.0003268934],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024272775,0.00053596473,0.000008292137,0.03441432,0.0007277221,0.00012535646,0.00015042849,0.0000060963225,0.0000070207975,0.028517576,0.04586248,0.88940203],"study_design_scores_gemma":[0.0019745503,0.0003057736,0.00003334109,0.07284269,0.0045530796,0.000010327236,0.0003758349,0.00025100828,0.0000036802974,0.3404574,0.5772409,0.0019514445],"about_ca_topic_score_codex":0.00029647193,"about_ca_topic_score_gemma":0.00015887772,"teacher_disagreement_score":0.8874506,"about_ca_system_score_codex":0.00038004806,"about_ca_system_score_gemma":0.0010738634,"threshold_uncertainty_score":0.9994414},"labels":[],"label_agreement":null},{"id":"W2949510378","doi":"10.1016/j.conctc.2019.100396","title":"Effects of biomarker diagnostic accuracy on biomarker-guided phase 2 trials","year":2019,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of British Columbia","funders":"Mitacs","keywords":"Biomarker; Type I and type II errors; Sample size determination; Statistical power; Clinical trial; Medicine; Computer science; Oncology; Statistics; Internal medicine; Biology; Mathematics; Genetics","score_opus":0.9019626976464337,"score_gpt":0.6980636363815192,"score_spread":0.20389906126491442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949510378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44762683,0.02114003,0.20636798,0.042512428,0.03678497,0.110203914,0.0071370658,0.0031776365,0.12504913],"genre_scores_gemma":[0.8156245,0.0025953907,0.17879778,0.001105758,0.00045295362,0.00075637863,0.00008360492,0.00015095902,0.00043268251],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8820769,0.097703084,0.017587662,0.0011169874,0.0009421405,0.0005732181],"domain_scores_gemma":[0.06152452,0.92189854,0.008458338,0.0068986793,0.0006291487,0.0005907464],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1580463,0.00070998695,0.008002804,0.00037971133,0.00021553537,0.00010871502,0.0033765915,0.0009213801,0.0008419028],"category_scores_gemma":[0.96398556,0.0005470698,0.0029337362,0.00091488915,0.001194363,0.00027139537,0.001097105,0.0012400654,0.0005807482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010708512,0.030443273,0.0042431904,0.001972534,0.006296869,0.00005669597,0.00021210346,0.0000012845944,0.015658524,0.2995203,0.21656616,0.41432053],"study_design_scores_gemma":[0.062209677,0.0031775623,0.0051060654,0.0030914522,0.00213847,0.0000052425617,0.00008920361,0.0010045569,0.0074841836,0.8747753,0.03961472,0.0013035994],"about_ca_topic_score_codex":0.000028815315,"about_ca_topic_score_gemma":0.0000018554431,"teacher_disagreement_score":0.8241955,"about_ca_system_score_codex":0.00007130011,"about_ca_system_score_gemma":0.00065554294,"threshold_uncertainty_score":0.9996981},"labels":[],"label_agreement":null},{"id":"W2950108952","doi":"10.1186/s13063-019-3471-8","title":"The randomization-induced risk of a trial failing to attain its target power: assessment and mitigation","year":2019,"lang":"en","type":"letter","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Randomization; Medicine; Restricted randomization; Power (physics); Randomized controlled trial; Statistical power; Mendelian randomization; Clinical trial; Risk analysis (engineering); Computer science; Statistics; Actuarial science; Mathematics; Surgery; Economics; Internal medicine","score_opus":0.5402051692395645,"score_gpt":0.5942785201324021,"score_spread":0.0540733508928376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950108952","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022338001,0.00044632072,0.4220578,0.46086594,0.024020694,0.063878946,0.0038633037,0.000299209,0.002229769],"genre_scores_gemma":[0.0023711352,0.00034133453,0.92718446,0.052529614,0.014220561,0.001413346,0.000081690494,0.00027797327,0.0015798574],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9711878,0.021543033,0.004892602,0.0007329723,0.0011685527,0.00047504777],"domain_scores_gemma":[0.57012975,0.42537713,0.0032706265,0.0007790772,0.0003733302,0.00007008034],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062855795,0.00048235504,0.0038569504,0.00016816451,0.00018966229,0.00019590136,0.00050623267,0.0010981283,0.00029574026],"category_scores_gemma":[0.63081807,0.00030987212,0.0006296324,0.00025623076,0.0000948701,0.00006131974,0.00017013967,0.0013773297,0.00003633337],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.043477036,0.00014785505,0.000026518832,0.000692113,0.0019192401,0.000013982862,0.00028668766,0.000030533454,0.00079158077,0.011609396,0.9350753,0.0059297658],"study_design_scores_gemma":[0.16860026,0.0013355172,0.000021387918,0.00062690326,0.0022597557,0.00000174247,0.00006035116,0.000397295,0.0018541833,0.7659225,0.058138788,0.0007813328],"about_ca_topic_score_codex":0.000009981,"about_ca_topic_score_gemma":0.000001306913,"teacher_disagreement_score":0.8769365,"about_ca_system_score_codex":0.00010889457,"about_ca_system_score_gemma":0.00036298292,"threshold_uncertainty_score":0.9999353},"labels":[],"label_agreement":null},{"id":"W2951146013","doi":"","title":"Hälsoekonomiska modeller vid diabetes: ett hjälpmedel för klinisk forskning och behandlingsval","year":2012,"lang":"sv","type":"article","venue":"Lund University Publications (Lund University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics","funders":"","keywords":"MODELLER; Medicine; Chemistry","score_opus":0.3312367472960832,"score_gpt":0.4095630151343983,"score_spread":0.07832626783831509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951146013","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02793477,0.00017826873,0.1978276,0.0036798648,0.0015971338,0.0016022895,0.0010536034,0.0006566592,0.7654698],"genre_scores_gemma":[0.015279466,0.00051072513,0.28167206,0.00044101066,0.0011451872,0.0000031616444,0.00015453399,0.0001845674,0.70060927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9926977,0.0018906235,0.001132379,0.0014233411,0.00083294255,0.0020229984],"domain_scores_gemma":[0.97626466,0.017548583,0.0012554788,0.0021013124,0.0010681588,0.0017618281],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003028774,0.0008989203,0.0014924175,0.0018612475,0.0023033419,0.00032871324,0.0023633833,0.0010898156,0.0020402272],"category_scores_gemma":[0.00792893,0.001161422,0.0008447218,0.0033060967,0.0009003632,0.0025218357,0.0014023292,0.0015490318,0.00057106727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023643124,0.001632528,0.003587133,0.00021480379,0.00093599694,0.000020418582,0.0012299317,0.00009570835,0.00006455516,0.9784852,0.012341794,0.0011554491],"study_design_scores_gemma":[0.0039377473,0.00020641685,0.00070324267,0.00020165423,0.0027799,0.000006523158,0.0043389006,0.0054794885,0.000074906675,0.016087934,0.9648198,0.0013634934],"about_ca_topic_score_codex":0.00016133083,"about_ca_topic_score_gemma":0.00005389208,"teacher_disagreement_score":0.96239734,"about_ca_system_score_codex":0.0015464096,"about_ca_system_score_gemma":0.000907393,"threshold_uncertainty_score":0.9990836},"labels":[],"label_agreement":null},{"id":"W2953717045","doi":"","title":"Utilisation de la maîtrise statistique des processus (MSP) pour optimiser les contrôles qualité en radiothérapie conformationnelle par modulation d'intensité (RCMI)","year":2007,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre d'expertise et de recherche en infrastructures urbaines","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.1315740636206651,"score_gpt":0.40552556346888435,"score_spread":0.27395149984821926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953717045","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08006468,0.0010420076,0.8915001,0.0049180365,0.0003742406,0.0017863737,0.0005659975,0.0003789018,0.019369638],"genre_scores_gemma":[0.29389432,0.0017108488,0.6988484,0.00013859382,0.00013628704,0.0001637191,0.00034305564,0.0001322185,0.0046325475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95158046,0.04156711,0.0033452462,0.0013383524,0.0011261889,0.0010426601],"domain_scores_gemma":[0.8316253,0.1555103,0.0027756488,0.0024191611,0.006988928,0.0006806454],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.055360705,0.00097641227,0.001609169,0.00039484623,0.00092929334,0.00081815326,0.0015082359,0.0016863196,0.0013842797],"category_scores_gemma":[0.19695994,0.001034382,0.00052117935,0.000623533,0.0018790027,0.00039602257,0.0008767385,0.001881168,0.00011439258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029810236,0.0016735303,0.0036273715,0.0025140436,0.0004801562,0.000026685262,0.030003117,0.0020518175,0.0016210927,0.71483344,0.0014859656,0.24138469],"study_design_scores_gemma":[0.0031063636,0.000004408824,0.020463778,0.004785733,0.00048531318,0.000055331584,0.0019099829,0.23522021,0.026051564,0.7027323,0.0040238197,0.0011611813],"about_ca_topic_score_codex":0.0020327177,"about_ca_topic_score_gemma":0.0005844584,"teacher_disagreement_score":0.24022351,"about_ca_system_score_codex":0.0008502516,"about_ca_system_score_gemma":0.0009532507,"threshold_uncertainty_score":0.9996097},"labels":[],"label_agreement":null},{"id":"W2954690927","doi":"10.5539/ijsp.v7n6p81","title":"Evaluation of Performance of Adaptive Designs Based on Treatment Effect Intervals","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health","keywords":"Sample size determination; Flexibility (engineering); Early stopping; Adaptive design; Interim; Selection (genetic algorithm); Computer science; Interim analysis; Treatment effect; Statistics; Sample (material); Mathematics; Clinical trial; Machine learning; Medicine","score_opus":0.5405882645561305,"score_gpt":0.5548984099407206,"score_spread":0.014310145384590078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954690927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55243987,0.000013266051,0.44572562,0.00006215647,0.0005327901,0.00038267145,0.00038315327,0.0000027589515,0.00045771204],"genre_scores_gemma":[0.613688,0.000010374569,0.38619468,0.000008621845,0.00008585787,0.0000046680802,6.945777e-7,0.000004755882,0.0000023405353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99635994,0.0012337723,0.0010741041,0.00013304301,0.0011169219,0.00008219883],"domain_scores_gemma":[0.9742745,0.020961681,0.0009965356,0.00014739457,0.0035610015,0.000058859492],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010450134,0.0001243633,0.0004903392,0.000092733506,0.000019827969,0.000010862051,0.00017180642,0.00005527385,0.00021460657],"category_scores_gemma":[0.043460965,0.000080851445,0.00009385343,0.000055612338,0.00032499988,0.000044465196,0.00002522572,0.00009557676,9.567905e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008630441,0.001955399,0.012545068,0.0003104686,0.0010784199,0.0000068871655,0.000551666,0.0004738409,0.00094521383,0.07491629,0.00022114927,0.89836514],"study_design_scores_gemma":[0.0030071905,0.015199433,0.011556425,0.0004286836,0.0005150487,0.000006028065,0.000009972213,0.07294576,0.020771291,0.8754503,0.000019166002,0.000090676636],"about_ca_topic_score_codex":0.000006894862,"about_ca_topic_score_gemma":0.000005023604,"teacher_disagreement_score":0.8982745,"about_ca_system_score_codex":0.00019429176,"about_ca_system_score_gemma":0.00020652851,"threshold_uncertainty_score":0.9645964},"labels":[],"label_agreement":null},{"id":"W2955509706","doi":"10.1016/j.conctc.2019.100406","title":"Reporting of master protocols towards a standardized approach: A systematic review","year":2019,"lang":"en","type":"review","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of British Columbia","funders":"Mitacs","keywords":"Protocol (science); Computer science; Systematic review; Medical physics; MEDLINE; Medicine; Alternative medicine; Pathology","score_opus":0.9837234204527768,"score_gpt":0.7622965049051657,"score_spread":0.22142691554761118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955509706","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.735093e-9,0.8060885,0.020516144,0.00023850972,0.00045561872,0.15979733,0.0012201976,0.0002051133,0.0114785945],"genre_scores_gemma":[3.6129208e-7,0.6281739,0.32623076,0.00019364643,0.00022081155,0.044402335,0.0001162929,0.00018212781,0.0004798006],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.7233555,0.16090387,0.11135807,0.0018497177,0.0018216748,0.0007112171],"domain_scores_gemma":[0.21729326,0.6133485,0.14490494,0.022003908,0.0018018832,0.0006475142],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","open_science","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.35923332,0.0013606272,0.060184844,0.0003366563,0.00018077079,0.00014701347,0.006407079,0.0018022972,0.00024171817],"category_scores_gemma":[0.93194175,0.00089980505,0.011822578,0.0012539068,0.0011248126,0.00019360926,0.0026649449,0.0033171838,0.00015761598],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007157787,0.000988743,0.0000015337171,0.8570907,0.002501099,0.000005696617,0.000017142078,7.3322886e-9,4.6269346e-8,0.008709647,0.0066577345,0.12395608],"study_design_scores_gemma":[0.001606462,0.00026225997,1.7611187e-7,0.71205,0.014833351,0.00002148122,0.000020406851,0.000013414044,2.2592994e-7,0.030677825,0.23983864,0.00067574147],"about_ca_topic_score_codex":0.0000068920513,"about_ca_topic_score_gemma":5.602381e-7,"teacher_disagreement_score":0.5727084,"about_ca_system_score_codex":0.000171706,"about_ca_system_score_gemma":0.0047873645,"threshold_uncertainty_score":0.99991447},"labels":[],"label_agreement":null},{"id":"W2955606726","doi":"10.1016/j.conctc.2019.100402","title":"An alternative trial-level measure for evaluating failure-time surrogate endpoints based on prediction error","year":2019,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer; Ligue Contre le Cancer","keywords":"Statistics; Correlation; Surrogate endpoint; Standard error; Clinical trial; Measure (data warehouse); Mathematics; Medicine; Computer science; Data mining; Internal medicine","score_opus":0.9352083243389143,"score_gpt":0.6897237555682655,"score_spread":0.24548456877064884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955606726","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06638074,0.00032518245,0.7910889,0.022133358,0.012095865,0.06686768,0.015572551,0.0020836608,0.023452105],"genre_scores_gemma":[0.41775304,0.00001745866,0.57829124,0.00078746374,0.0009189315,0.0013734228,0.00028119047,0.00013201294,0.00044525764],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9381815,0.05057046,0.00824679,0.0012973198,0.0011635041,0.00054043427],"domain_scores_gemma":[0.55174524,0.43811974,0.0033348943,0.00529629,0.0010408463,0.00046301],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14792128,0.0005999134,0.0035136042,0.00024759423,0.00044455932,0.00018664723,0.0027572594,0.0007892741,0.0006218462],"category_scores_gemma":[0.60640657,0.00051014207,0.0015491691,0.00043095573,0.00054476864,0.00040837243,0.0003277162,0.0013693393,0.00034444823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.42055836,0.04190158,0.0054126675,0.0009985949,0.005859329,0.000014510838,0.0010114379,0.0008157504,0.009067998,0.2418953,0.078606084,0.19385839],"study_design_scores_gemma":[0.15473977,0.011836863,0.0004318289,0.0009882904,0.0007731433,0.0000010805904,0.00016501799,0.23778017,0.0005792241,0.587988,0.0038091454,0.00090741814],"about_ca_topic_score_codex":0.000013683225,"about_ca_topic_score_gemma":0.000011581911,"teacher_disagreement_score":0.45848528,"about_ca_system_score_codex":0.00013996894,"about_ca_system_score_gemma":0.00096629566,"threshold_uncertainty_score":0.999735},"labels":[],"label_agreement":null},{"id":"W2956065293","doi":"10.1002/sim.8497","title":"Estimation of treatment effects following a sequential trial of multiple treatments","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Frequentist inference; Interim; Interim analysis; Confidence interval; Statistics; Replicate; Econometrics; Computer science; Nominal level; Bayesian probability; Mathematics; Randomized controlled trial; Medicine; Bayesian inference","score_opus":0.4719794924011268,"score_gpt":0.5884031063488133,"score_spread":0.11642361394768652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956065293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05835096,0.000099347235,0.93060327,0.00013712098,0.00419805,0.004435637,0.0017198955,0.000050726852,0.00040499872],"genre_scores_gemma":[0.29542854,0.00010052257,0.7037044,0.000014606369,0.0003173178,0.00021752623,0.00013425988,0.000051488034,0.00003130703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940061,0.0014040577,0.0028322558,0.0006352446,0.0008250015,0.0002973501],"domain_scores_gemma":[0.92687887,0.070711724,0.0014663661,0.00067782175,0.000108243636,0.00015695962],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019993049,0.0004995877,0.0031624136,0.00022945054,0.000025238785,0.0000070952096,0.00031432527,0.00040617937,0.00008016587],"category_scores_gemma":[0.1952213,0.00039449192,0.00027539852,0.00023181624,0.00033172875,0.000018560146,0.00023813368,0.0004694774,0.0000031771717],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07873887,0.009448243,0.0015206366,0.030397652,0.010122814,0.0016104353,0.012011952,0.0024828934,0.0045110537,0.2695782,0.0045183874,0.5750589],"study_design_scores_gemma":[0.076310724,0.0054439497,0.00017550892,0.0022991789,0.0022433074,7.190315e-7,0.00004348997,0.021746496,0.002094751,0.8893996,0.0000065420977,0.00023574289],"about_ca_topic_score_codex":0.0004615256,"about_ca_topic_score_gemma":0.000033618562,"teacher_disagreement_score":0.61982137,"about_ca_system_score_codex":0.00041404233,"about_ca_system_score_gemma":0.0003322934,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W2956873218","doi":"10.1016/s1470-2045(19)30338-9","title":"The fragility of phase 3 trials supporting FDA-approved anticancer medicines: a retrospective analysis","year":2019,"lang":"en","type":"article","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; Thunder Bay Regional Health Sciences Centre; NOSM University","funders":"","keywords":"Medicine; Fragility; Statistical significance; Confidence interval; Clinical trial; Randomized controlled trial; Sample size determination; Internal medicine; Statistics","score_opus":0.5921369313792776,"score_gpt":0.6538412243340906,"score_spread":0.061704292954813056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956873218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81976503,0.00022492342,0.117596924,0.027809277,0.0030116134,0.004015514,0.00043536138,0.00016785089,0.026973533],"genre_scores_gemma":[0.8908183,0.00014803812,0.10644417,0.0009137549,0.0012400616,0.00010349573,0.000003040534,0.000024942994,0.00030418704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891735,0.0071529504,0.0022806316,0.000407328,0.0004883953,0.0004972038],"domain_scores_gemma":[0.7651045,0.23076786,0.0022865057,0.0014119773,0.0003466518,0.00008255004],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06059473,0.00018809318,0.0033816986,0.000056998353,0.000121083795,0.000017525113,0.00072724454,0.00020576065,0.001152381],"category_scores_gemma":[0.32081234,0.00008717444,0.0004791774,0.00072523236,0.00073040323,0.000028413728,0.00016066946,0.00054752093,0.000021757465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010997554,0.0021158163,0.06531785,0.00056233193,0.013640428,0.000030424304,0.003882408,0.000019821011,0.01003998,0.7591866,0.02642429,0.10778248],"study_design_scores_gemma":[0.0062549007,0.0009452164,0.007274076,0.000028611606,0.0028981762,0.0000022786496,0.00059540954,0.0015911041,0.0009897358,0.9749924,0.004287995,0.0001400957],"about_ca_topic_score_codex":0.000037275808,"about_ca_topic_score_gemma":0.0000762558,"teacher_disagreement_score":0.2602176,"about_ca_system_score_codex":0.00013747791,"about_ca_system_score_gemma":0.00018205373,"threshold_uncertainty_score":0.9997607},"labels":[],"label_agreement":null},{"id":"W2960228950","doi":"10.1093/bioinformatics/btz335","title":"Enhancing the drug discovery process: Bayesian inference for the analysis and comparison of dose–response experiments","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Genome Canada","keywords":"Computer science; Bayesian probability; Inference; Data mining; Bayesian inference; Machine learning; Artificial intelligence","score_opus":0.23821785965506612,"score_gpt":0.530511155671486,"score_spread":0.29229329601641985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960228950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2729477,0.00005399253,0.72547257,0.00016692707,0.0001596648,0.0009859573,0.00006508622,0.000018358503,0.00012976809],"genre_scores_gemma":[0.68087393,0.000008994127,0.31885716,0.00007055839,0.00002244002,0.00004999522,0.0000012477162,0.000009020377,0.00010664133],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783677,0.00025043968,0.001219956,0.00012564319,0.00035963653,0.00020754561],"domain_scores_gemma":[0.91756946,0.08111648,0.00063190644,0.00052868464,0.00010775291,0.00004571296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038171557,0.00015718941,0.00061672134,0.00007174382,0.00012221393,0.00010483103,0.00038588548,0.00007033898,0.00003828939],"category_scores_gemma":[0.028626295,0.00007938072,0.00015792038,0.00036260035,0.00018337878,0.00018568886,0.00012071445,0.00014316721,0.000005000818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015263485,0.002926471,0.14471175,0.0171131,0.015242774,0.0000019661911,0.3265348,0.0018771534,0.009862334,0.3044024,0.0044370196,0.15762672],"study_design_scores_gemma":[0.0035770782,0.0006411716,0.015306821,0.0005110642,0.0036146177,0.00000176336,0.05017954,0.5059682,0.09106355,0.32794568,0.0003775382,0.0008129804],"about_ca_topic_score_codex":0.000006441531,"about_ca_topic_score_gemma":0.000010999955,"teacher_disagreement_score":0.504091,"about_ca_system_score_codex":0.000018874776,"about_ca_system_score_gemma":0.00007142623,"threshold_uncertainty_score":0.979556},"labels":[],"label_agreement":null},{"id":"W2962928908","doi":"10.1177/0962280217708662","title":"Prediction and tolerance intervals for dynamic treatment regimes.","year":2017,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Tolerance interval; Computer science; Interval (graph theory); Confidence interval; Econometrics; Statistics; Data mining; Mathematics","score_opus":0.5842375872824908,"score_gpt":0.5244207354744689,"score_spread":0.059816851808021876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962928908","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26626137,0.0004570386,0.6789991,0.008265579,0.0068216375,0.014917349,0.0014154246,0.00050286535,0.02235964],"genre_scores_gemma":[0.4887029,0.00012868462,0.49963674,0.0000743598,0.00036566114,0.006012735,0.0000017753608,0.000033579356,0.0050435746],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990279,0.00009269166,0.00033233588,0.00024693264,0.00008720345,0.00021292694],"domain_scores_gemma":[0.9918793,0.007262809,0.00023073172,0.0004900239,0.00003977786,0.000097389886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012374828,0.00010306642,0.00032941098,0.000017781971,0.00015058991,0.00008581706,0.00014147768,0.000079409874,0.000007959551],"category_scores_gemma":[0.041023057,0.00007931686,0.00007615054,0.000011106867,0.00012117442,0.00006992571,0.000045461537,0.00004614358,0.0000017235058],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015070538,0.000101932965,0.0009192299,0.000088321256,0.000076527656,0.0000017307021,0.000045477173,1.8120052e-7,0.0000067587043,0.020859139,0.0010250559,0.9767249],"study_design_scores_gemma":[0.0017591411,0.000106585794,0.10512317,0.00002723926,0.00011213955,0.000002369834,0.000005239077,0.00090472604,0.0002858247,0.88923883,0.0023439939,0.0000907643],"about_ca_topic_score_codex":0.00000502782,"about_ca_topic_score_gemma":0.0000059986573,"teacher_disagreement_score":0.9766342,"about_ca_system_score_codex":0.000063541134,"about_ca_system_score_gemma":0.000007217498,"threshold_uncertainty_score":0.9670548},"labels":[],"label_agreement":null},{"id":"W2962996894","doi":"10.1186/s40488-019-0099-x","title":"Meta analysis of binary data with excessive zeros in two-arm trials","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Distributions and Applications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Bayesian probability; Markov chain Monte Carlo; Statistics; Frequentist inference; Dirichlet process; Dirichlet distribution; Mathematics; Odds; Econometrics; Markov chain; Bayesian inference; Computer science; Logistic regression","score_opus":0.5840704927796984,"score_gpt":0.5903778023597469,"score_spread":0.006307309580048548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962996894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008930243,0.00027016015,0.97144,0.00034234134,0.000027896956,0.0006253026,0.018210871,0.000006743277,0.00014644054],"genre_scores_gemma":[0.4563638,0.0001090556,0.54320943,0.00002206466,0.000050542014,0.000054216744,0.00015749267,0.000011048669,0.0000223721],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962326,0.00072476605,0.0021375264,0.00030721314,0.00040607026,0.0001917964],"domain_scores_gemma":[0.9475893,0.04984431,0.0013128815,0.0006766739,0.0003974205,0.00017943556],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005082514,0.00016378665,0.002219948,0.00024304069,0.000057029207,0.0000371241,0.0004174338,0.00006752953,0.0009337636],"category_scores_gemma":[0.013266588,0.00010635888,0.00025078483,0.0011719493,0.00030596525,0.00012469984,0.00013793775,0.000316375,0.0000041106473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019932161,0.0010753067,0.001446684,0.000094299205,0.01790373,0.000010386811,0.000021705975,0.00007742817,0.0002936824,0.9758391,0.0005501095,0.0024882422],"study_design_scores_gemma":[0.0022040892,0.00041305833,0.018800527,0.000049550494,0.12183772,0.000016619559,0.00021708921,0.0026638543,0.0000899355,0.85282445,0.000639777,0.00024332319],"about_ca_topic_score_codex":0.000021415437,"about_ca_topic_score_gemma":0.000011887493,"teacher_disagreement_score":0.44743356,"about_ca_system_score_codex":0.00003343692,"about_ca_system_score_gemma":0.00012717757,"threshold_uncertainty_score":0.9999795},"labels":[],"label_agreement":null},{"id":"W2963018021","doi":"10.1016/j.eururo.2019.07.013","title":"Re: Scientists Rise up Against Statistical Significance","year":2019,"lang":"en","type":"letter","venue":"European Urology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine","score_opus":0.3932360839177287,"score_gpt":0.49253349210319597,"score_spread":0.09929740818546728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963018021","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013223475,0.00018381282,0.33312854,0.3997219,0.02601019,0.0024088137,0.0033828653,0.0007883676,0.23424329],"genre_scores_gemma":[0.00033753418,0.00004229684,0.3340459,0.63576424,0.00898049,0.00003015929,0.00013082317,0.00044075237,0.020227818],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9819237,0.012231279,0.0019171941,0.0017969887,0.00089358713,0.0012372767],"domain_scores_gemma":[0.8958558,0.10099368,0.00086763053,0.0019000284,0.0002050883,0.00017779345],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006754387,0.0007268542,0.0017515906,0.00022054296,0.00013798337,0.0001284957,0.0015970251,0.00094574934,0.0025639697],"category_scores_gemma":[0.14154164,0.00066375104,0.00030156737,0.00027278508,0.0012804965,0.00004573666,0.00063425326,0.0046031233,0.009470441],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008014771,0.000059140562,0.000024525487,0.0003031227,0.00010877028,0.0034365107,0.000040125993,0.0000015131387,0.000018390592,0.008436389,0.98243356,0.0050578183],"study_design_scores_gemma":[0.00083960884,0.00028096227,0.00012105609,0.000046284942,0.00022786978,0.000016757187,0.0000034230827,0.00007934285,0.000007847356,0.17119525,0.8265862,0.00059542037],"about_ca_topic_score_codex":0.0000028591724,"about_ca_topic_score_gemma":0.0000015237837,"teacher_disagreement_score":0.23604235,"about_ca_system_score_codex":0.00007213112,"about_ca_system_score_gemma":0.00017307106,"threshold_uncertainty_score":0.9995814},"labels":[],"label_agreement":null},{"id":"W2963325162","doi":"10.1002/sim.8327","title":"Information content of stepped‐wedge designs when treatment effect heterogeneity and/or implementation periods are present","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; National Medical Research Council; Medical Research Council","keywords":"Computer science; Sequence (biology); Cluster (spacecraft); Wedge (geometry); Econometrics; Treatment effect; Statistics; Data mining; Mathematics; Medicine; Biology","score_opus":0.510180498051622,"score_gpt":0.5711178178960157,"score_spread":0.060937319844393656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963325162","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49992362,0.00010992698,0.4926609,0.00040696556,0.00079237676,0.004398579,0.0012539317,0.000042664273,0.0004110158],"genre_scores_gemma":[0.33573055,0.000236001,0.6631841,0.00015550834,0.00016400695,0.00022055213,0.000082164675,0.00003299996,0.00019410254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99689966,0.00082165556,0.0013509212,0.00020258452,0.00047060996,0.00025458637],"domain_scores_gemma":[0.97561896,0.023164615,0.00059984694,0.00033603716,0.00016276455,0.00011775295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023928105,0.00023799301,0.0009859882,0.00013816834,0.000033118504,0.000014814202,0.00011895742,0.00009658124,0.00069016195],"category_scores_gemma":[0.01552112,0.00014942737,0.000039978408,0.00011198695,0.00019947748,0.000093941155,0.00006125105,0.00013305584,0.000013234249],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053284634,0.00081428717,0.30568448,0.006555818,0.0008381978,0.000063874526,0.013267054,0.000021133665,0.0029635837,0.14775859,0.012010028,0.50469446],"study_design_scores_gemma":[0.053805836,0.026387058,0.25286207,0.0019811816,0.0013301319,0.000032371598,0.00951462,0.005212924,0.013801913,0.6320377,0.0020152922,0.0010188773],"about_ca_topic_score_codex":0.00025797667,"about_ca_topic_score_gemma":0.00017552232,"teacher_disagreement_score":0.5036756,"about_ca_system_score_codex":0.00015888292,"about_ca_system_score_gemma":0.000053415053,"threshold_uncertainty_score":0.99277157},"labels":[],"label_agreement":null},{"id":"W2963426032","doi":"10.1080/01621459.2018.1527700","title":"FarmTest: Factor-Adjusted Robust Multiple Testing With Approximate False Discovery Control","year":2018,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences","keywords":"False discovery rate; Multiple comparisons problem; Estimator; Computer science; Robust statistics; Covariance; Normality; Inference; Statistical hypothesis testing; Mathematics; Statistics; Data mining; Econometrics; Artificial intelligence","score_opus":0.2885035623946631,"score_gpt":0.44852181038620226,"score_spread":0.16001824799153913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963426032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16372335,0.000004993369,0.83393496,0.0008422009,0.0004787159,0.00033724846,0.00046011707,0.000037334117,0.00018107714],"genre_scores_gemma":[0.5211197,0.0000019978063,0.4779426,0.00029777296,0.0005240399,0.0000049064693,4.5486172e-7,0.00003102289,0.0000775369],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948978,0.0017351699,0.001415823,0.00025921958,0.0012102431,0.00048178685],"domain_scores_gemma":[0.89652896,0.09751185,0.0042958762,0.00031908945,0.0011577352,0.00018646341],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030725303,0.00026148435,0.0011066847,0.00007398003,0.00021447049,0.00015683234,0.000451622,0.00008911125,0.000046486402],"category_scores_gemma":[0.30191973,0.00015093367,0.0001705546,0.0006256381,0.00057705736,0.00021024467,0.000083042854,0.0006541316,0.000011260383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004531723,0.0017542888,0.8556944,0.00021636712,0.002337326,0.00010327835,0.0005952912,0.0003159852,0.005432007,0.03922273,0.011641115,0.07815549],"study_design_scores_gemma":[0.00629412,0.0034132185,0.54534626,0.0004202878,0.001363642,0.000082657025,0.00038873797,0.015443841,0.0009033973,0.42544082,0.00022008066,0.00068295613],"about_ca_topic_score_codex":0.00005367878,"about_ca_topic_score_gemma":0.000029168996,"teacher_disagreement_score":0.3862181,"about_ca_system_score_codex":0.00049913616,"about_ca_system_score_gemma":0.00018030823,"threshold_uncertainty_score":0.7039605},"labels":[],"label_agreement":null},{"id":"W2963448461","doi":"10.1016/j.clinthera.2019.07.004","title":"Should Clinical Trials Be Terminated Early?","year":2019,"lang":"en","type":"article","venue":"Clinical Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Interim; Medicine; Clinical trial; Sample size determination; Adverse effect; Early stopping; Intensive care medicine; Internal medicine; Law; Statistics","score_opus":0.9506823842536484,"score_gpt":0.7409873142813458,"score_spread":0.20969506997230258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963448461","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84267116,0.0003619806,0.07936868,0.009901908,0.030800104,0.0069070496,0.00043206388,0.0015056494,0.028051393],"genre_scores_gemma":[0.24180593,0.001341014,0.7195566,0.023020424,0.0053817215,0.00009701111,0.000012380942,0.00038774317,0.008397133],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96615845,0.020564515,0.010011037,0.0013646063,0.0010117276,0.00088964764],"domain_scores_gemma":[0.58504224,0.4097453,0.0020622844,0.0021544455,0.00038806302,0.00060765643],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.097772725,0.00061377883,0.0046441825,0.000106662796,0.00010824575,0.0001427288,0.0012756083,0.001869364,0.0028813411],"category_scores_gemma":[0.2801905,0.00045837718,0.0023066725,0.00045915268,0.0009239437,0.00012717223,0.0003813094,0.0026541771,0.0010997886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028589962,0.0045223106,0.12955922,0.0002255195,0.0027813157,0.000078788624,0.00015274227,0.0000015221248,0.00025313522,0.17745571,0.015666753,0.666444],"study_design_scores_gemma":[0.007517703,0.0022584621,0.015243738,0.00016719064,0.0011782529,0.000007080418,0.000060030285,0.0010850719,0.0002454813,0.89726263,0.07410011,0.0008742362],"about_ca_topic_score_codex":0.0000036670342,"about_ca_topic_score_gemma":0.0000015767736,"teacher_disagreement_score":0.7198069,"about_ca_system_score_codex":0.000050215724,"about_ca_system_score_gemma":0.00022528546,"threshold_uncertainty_score":0.9997868},"labels":[],"label_agreement":null},{"id":"W2969575993","doi":"10.4236/ojs.2019.94035","title":"On the Index of Repeatability: Estimation and Sample Size Requirements","year":2019,"lang":"en","type":"article","venue":"Open Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Repeatability; Statistics; Sample size determination; Variance (accounting); Estimator; Mathematics; Sample (material); Index (typography); Computer science","score_opus":0.49683111304261746,"score_gpt":0.56086270556895,"score_spread":0.06403159252633256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969575993","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11682185,0.000009439055,0.8789332,0.0005750791,0.0005150411,0.00085675303,0.0006022412,0.0000039534593,0.0016824685],"genre_scores_gemma":[0.25142416,0.000016332377,0.74833864,0.000109988476,0.000025403535,0.000002013067,3.5843826e-7,0.000012434193,0.000070698334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973169,0.0006363127,0.0012567989,0.00013832386,0.0005241361,0.00012752575],"domain_scores_gemma":[0.8141844,0.18384254,0.0011885762,0.00036899777,0.00033862283,0.00007683611],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0066094156,0.00011216438,0.0005715847,0.000031370793,0.000047463996,0.00007433669,0.0004416027,0.00005818702,0.0011010962],"category_scores_gemma":[0.34339163,0.00007005629,0.000043623168,0.000099356475,0.00014773187,0.000109863766,0.00017515215,0.0002649238,0.0000064605915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079438504,0.0003199572,0.0059968005,0.0002665153,0.00018503105,0.000010258113,0.00028392737,0.0000416016,0.00016963668,0.9298846,0.004946855,0.057100393],"study_design_scores_gemma":[0.001010978,0.0006334858,0.0037221538,0.00023144929,0.0000819679,0.0000075694907,0.000104714745,0.0015276353,0.0002672003,0.9922714,0.00006721112,0.00007419734],"about_ca_topic_score_codex":0.000014399218,"about_ca_topic_score_gemma":0.0000018226708,"teacher_disagreement_score":0.33678222,"about_ca_system_score_codex":0.00003559451,"about_ca_system_score_gemma":0.00008987527,"threshold_uncertainty_score":0.999812},"labels":[],"label_agreement":null},{"id":"W2970155428","doi":"10.1164/ajrccm-conference.2019.199.1_meetingabstracts.a6001","title":"Increasing Number of Treatment Decisions Undermines Balance Between Study Arms in Randomized Trials: A Simulation Study","year":2019,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Balance (ability); Randomized controlled trial; Computer science; Physical medicine and rehabilitation; Medicine; Internal medicine","score_opus":0.7484706481977657,"score_gpt":0.6578024464268771,"score_spread":0.09066820177088852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970155428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9348376,0.000005202825,0.055829428,0.000026808102,0.00019622767,0.008196434,0.000020348507,0.0000460951,0.0008418503],"genre_scores_gemma":[0.7394533,0.0000041138137,0.26019856,0.0000059197205,0.00007900014,0.000117585885,8.835718e-7,0.000021546586,0.00011904652],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9767798,0.017935116,0.004003368,0.0005045994,0.0005295303,0.00024755127],"domain_scores_gemma":[0.4861115,0.51259893,0.0006391046,0.00048243697,0.00010593408,0.00006208373],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03572161,0.00025843724,0.0045295428,0.00013148287,0.000027359796,0.000029167506,0.00018675347,0.00011312593,0.0006555854],"category_scores_gemma":[0.4404706,0.00015838188,0.0003546661,0.00036249243,0.000060587074,0.000067927984,0.00008577481,0.00012237701,0.000047343405],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028775828,0.006181592,0.94874626,0.000023833585,0.0007696576,0.0000063085618,0.0017951817,0.00031609015,0.000020206338,0.00248456,0.0000054614197,0.010874998],"study_design_scores_gemma":[0.33484325,0.0010416106,0.031585094,0.0001371731,0.0010953313,8.2694555e-7,0.0029491535,0.0055748643,0.000032092143,0.6224985,0.0000022402858,0.00023989065],"about_ca_topic_score_codex":0.00039658244,"about_ca_topic_score_gemma":0.00005956478,"teacher_disagreement_score":0.91716117,"about_ca_system_score_codex":0.00012791173,"about_ca_system_score_gemma":0.00006709105,"threshold_uncertainty_score":0.9929275},"labels":[],"label_agreement":null},{"id":"W2971381351","doi":"10.1002/sim.8320","title":"Discussion of Schuemie et al: “A plea to stop using the case‐control design in retrospective database studies”","year":2019,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Medicine; Pharmacoepidemiology; Epidemiology; Family medicine; Plea; Biostatistics; Pharmacoeconomics; Library science; Medical prescription; Internal medicine; Political science","score_opus":0.5841074927165224,"score_gpt":0.605698572106588,"score_spread":0.02159107939006555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971381351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003376124,0.00016904966,0.72509426,0.2662786,0.0015938681,0.002474582,0.004271844,0.000018759376,0.00006526132],"genre_scores_gemma":[0.00029806356,0.00016334496,0.75574076,0.24255194,0.00084509165,0.00008659769,0.00003701317,0.00011884908,0.00015831567],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98795265,0.0063865497,0.0027452507,0.0009594022,0.0012725592,0.0006835726],"domain_scores_gemma":[0.81638724,0.18085349,0.00096880423,0.0013021504,0.0004067295,0.00008161791],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.018986924,0.000610779,0.0030399894,0.00047082294,0.00006798173,0.000015951076,0.0006405137,0.00045346978,0.00022149216],"category_scores_gemma":[0.40099514,0.00032388984,0.000080518126,0.00073654787,0.00076973834,0.000050624494,0.00033117944,0.0037961416,0.000008797886],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025402574,0.00008044598,0.00011735412,0.0008213679,0.00023519366,0.006250531,0.0012655957,0.000096845186,0.000097977674,0.015631462,0.97395825,0.0011909525],"study_design_scores_gemma":[0.0056892633,0.0011002964,0.00012922399,0.007416442,0.0009708605,0.00014581706,0.001770587,0.0050763395,0.000027345248,0.9671036,0.009856165,0.0007140861],"about_ca_topic_score_codex":0.00029404662,"about_ca_topic_score_gemma":0.000162874,"teacher_disagreement_score":0.9641021,"about_ca_system_score_codex":0.0005988748,"about_ca_system_score_gemma":0.00025391133,"threshold_uncertainty_score":0.9999213},"labels":[],"label_agreement":null},{"id":"W2972625246","doi":"10.1016/j.conctc.2019.100446","title":"Minimizing control group allocation in randomized trials using dynamic borrowing of external control data – An application to second line therapy for non-small cell lung cancer","year":2019,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McMaster University; Impact","funders":"","keywords":"Lung cancer; Control (management); Randomized controlled trial; Medicine; Oncology; Computer science; Internal medicine; Artificial intelligence","score_opus":0.7204909650107075,"score_gpt":0.6257871096498172,"score_spread":0.09470385536089032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972625246","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06792465,0.0030315972,0.89810175,0.0012840423,0.000971803,0.026168145,0.0023313458,0.00007588025,0.00011076447],"genre_scores_gemma":[0.57437295,0.00057680963,0.4220518,0.00065794203,0.0003215243,0.0017625355,0.00015173384,0.000078776124,0.000025972846],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93415457,0.048087757,0.015406579,0.0013491503,0.00048797313,0.00051397015],"domain_scores_gemma":[0.37867945,0.6054683,0.007856352,0.006818052,0.0007755285,0.00040232236],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2202521,0.0005292207,0.008962495,0.00034110158,0.00016496128,0.00011439141,0.0035227812,0.0006197066,0.00011011993],"category_scores_gemma":[0.29898685,0.00044998692,0.0012898868,0.00047673946,0.0003588021,0.00047888662,0.0004670961,0.0007873457,0.0000054091447],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.46097744,0.015539084,0.018224455,0.0025695432,0.005023416,0.00000406832,0.0016748664,0.0015115339,0.29842705,0.02961797,0.0013842224,0.1650464],"study_design_scores_gemma":[0.29120648,0.00056599,0.00047231017,0.00091586396,0.0011497899,5.521882e-7,0.00015585804,0.6458765,0.00062813255,0.058111776,0.00032811036,0.00058857765],"about_ca_topic_score_codex":0.00019881764,"about_ca_topic_score_gemma":0.00015701973,"teacher_disagreement_score":0.644365,"about_ca_system_score_codex":0.00012624284,"about_ca_system_score_gemma":0.00077678484,"threshold_uncertainty_score":0.9997952},"labels":[],"label_agreement":null},{"id":"W2973201797","doi":"10.1016/j.ijrobp.2019.06.1145","title":"Don't Be Fazed by Phase II: The Use of Randomized Phase II Trials in Radiation Oncology","year":2019,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Cancer Care Ontario","funders":"","keywords":"Medicine; Clinical trial; Randomized controlled trial; Sample size determination; Psychological intervention; Accrual; Oncology; Internal medicine; Radiation therapy; Medical physics; Statistics","score_opus":0.3396307544010067,"score_gpt":0.5579521155839701,"score_spread":0.21832136118296336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973201797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77834713,0.00045103993,0.19267234,0.014713539,0.009425641,0.0028676742,0.0010577581,0.00005179097,0.00041308466],"genre_scores_gemma":[0.7958704,0.0023696583,0.19369578,0.0037110243,0.0036637108,0.00015806066,0.00017641485,0.000098200064,0.00025674305],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9799281,0.012648733,0.00594825,0.00041288036,0.0006769691,0.0003850856],"domain_scores_gemma":[0.8496977,0.14102483,0.0077882363,0.00035139083,0.0009965092,0.000141351],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.026383149,0.00037279577,0.003828534,0.00032859435,0.00011426133,0.00004572544,0.00095046265,0.00067096646,0.00066001876],"category_scores_gemma":[0.17067844,0.0002596192,0.0010520454,0.0003508619,0.00062975555,0.00043861382,0.0002010522,0.0010358434,0.000013014388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10298778,0.012057892,0.0017989946,0.000040565952,0.003741438,0.000032552347,0.0024258636,0.00066679606,0.022188436,0.24714276,0.03225464,0.57466227],"study_design_scores_gemma":[0.4055314,0.006999308,0.00003737183,0.00009940323,0.00075784227,0.000037708513,0.000110169494,0.009248861,0.0056718467,0.47148648,0.09967851,0.0003410989],"about_ca_topic_score_codex":0.00003534594,"about_ca_topic_score_gemma":0.000005180552,"teacher_disagreement_score":0.57432115,"about_ca_system_score_codex":0.0007725093,"about_ca_system_score_gemma":0.0007778844,"threshold_uncertainty_score":0.9999856},"labels":[],"label_agreement":null},{"id":"W2973459418","doi":"10.1186/s13063-019-3664-1","title":"Systematic review of basket trials, umbrella trials, and platform trials: a landscape analysis of master protocols","year":2019,"lang":"en","type":"review","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":435,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Stantec (Canada); HIV Legal Network; McMaster University Medical Centre; University of British Columbia; Impact","funders":"","keywords":"Medicine; Clinical trial; Interquartile range; MEDLINE; Randomization; Protocol (science); Randomized controlled trial; Sample size determination; Research design; Alternative medicine; Internal medicine; Pathology; Statistics","score_opus":0.9347214944396993,"score_gpt":0.7018322329760908,"score_spread":0.23288926146360855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973459418","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.3312877e-7,0.784909,0.0043888604,0.000032494747,0.0008303617,0.2024719,0.0067759496,0.00006978607,0.00052139355],"genre_scores_gemma":[1.2942897e-7,0.89887345,0.063651785,0.000074294825,0.00088982895,0.03560239,0.00015581399,0.00021768776,0.0005345948],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.58420604,0.28902388,0.11873249,0.0027727317,0.0039502387,0.0013146286],"domain_scores_gemma":[0.17701657,0.74085426,0.076996736,0.0038598543,0.0008545723,0.00041800027],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.63581926,0.0020054665,0.18997714,0.002001922,0.000071234754,0.00018648418,0.0017712414,0.0021526474,0.0044175945],"category_scores_gemma":[0.9527566,0.0011171905,0.022264974,0.0032165705,0.00029491817,0.00014701387,0.0004938445,0.0010629419,0.00008141722],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008139888,0.0003252006,4.8658245e-7,0.8757757,0.038873527,0.0000058414003,0.000034282075,1.4246298e-7,0.0000019957656,0.005702276,0.0039748424,0.07449174],"study_design_scores_gemma":[0.004550603,0.00039935973,1.433441e-7,0.6123487,0.34063593,0.000007977419,0.000019982479,0.000014526266,0.000009980212,0.017338354,0.023970265,0.00070419005],"about_ca_topic_score_codex":0.000012536791,"about_ca_topic_score_gemma":0.0000026859068,"teacher_disagreement_score":0.4518304,"about_ca_system_score_codex":0.00014036166,"about_ca_system_score_gemma":0.0011831104,"threshold_uncertainty_score":0.9992688},"labels":[],"label_agreement":null},{"id":"W2974839292","doi":"10.1136/bmj.l5221","title":"Design characteristics, risk of bias, and reporting of randomised controlled trials supporting approvals of cancer drugs by European Medicines Agency, 2014-16: cross sectional analysis","year":2019,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":244,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Medical Research Council; Economic and Social Research Council; U.S. Department of the Treasury; National Institute for Health and Care Research; Bill and Melinda Gates Foundation; Harvard University; National Institutes of Health; National Science Foundation","keywords":"Medicine; Clinical trial; Randomized controlled trial; Reporting bias; Research design; Clinical endpoint; Publication bias; MEDLINE; Family medicine; Meta-analysis; Internal medicine; Statistics","score_opus":0.4469013499055617,"score_gpt":0.5635049915159488,"score_spread":0.11660364161038711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974839292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8103694,0.00023863757,0.18450333,0.000056859717,0.00049334613,0.0031267898,0.0005046466,0.000023849769,0.0006831415],"genre_scores_gemma":[0.8246808,0.00020069466,0.17425919,0.00002292837,0.00031435702,0.00007849102,0.000012476423,0.00003724221,0.00039383778],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9723406,0.011123768,0.015030037,0.00046997578,0.0007687268,0.00026689234],"domain_scores_gemma":[0.79089457,0.16438042,0.043200485,0.00055650563,0.000851522,0.00011650574],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16630846,0.00023784366,0.0059397924,0.00017630396,0.000043190317,0.000020237765,0.00018652492,0.00013628058,0.00097319874],"category_scores_gemma":[0.68727046,0.00016069545,0.0009832832,0.00028043718,0.00026298684,0.000041422074,0.00007482371,0.00018467617,0.0000016760165],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027121015,0.00045451193,0.88763595,0.0019625581,0.01576965,0.000008532779,0.0010558015,0.0001426707,0.042897124,0.00046169004,0.005372381,0.017118128],"study_design_scores_gemma":[0.2687288,0.0011455744,0.4423322,0.001504433,0.041817173,0.000011264689,0.00063375366,0.015548165,0.09109859,0.13568956,0.000064988766,0.00142549],"about_ca_topic_score_codex":0.00015394995,"about_ca_topic_score_gemma":0.0000019708702,"teacher_disagreement_score":0.52096194,"about_ca_system_score_codex":0.00002159463,"about_ca_system_score_gemma":0.00012660003,"threshold_uncertainty_score":0.99994004},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2977285302","doi":"10.1093/annonc/mdz265.005","title":"Complementary medicine (CM) use in phase III clinical trials (P3T) conducted by the Canadian Cancer Trials Group (CCTG)","year":2019,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Internal medicine; Lung cancer; Adverse effect; Homeopathy; Clinical trial; Colorectal cancer; Cancer; Quality of life (healthcare); Logistic regression; Incidence (geometry); Propensity score matching; Breast cancer; Oncology; Family medicine; Alternative medicine; Pathology","score_opus":0.9419416788129851,"score_gpt":0.7454897348363904,"score_spread":0.1964519439765947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977285302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.824148,0.0016221135,0.002731537,0.13259618,0.012843597,0.013084602,0.0067305346,0.00010693942,0.0061365077],"genre_scores_gemma":[0.8300911,0.0039359764,0.10797618,0.05131874,0.004127699,0.00071509293,0.00028820548,0.00020012265,0.0013468848],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95531285,0.033709824,0.008916499,0.0006833937,0.00057581684,0.00080160255],"domain_scores_gemma":[0.6355664,0.35996,0.0028466734,0.00078414736,0.00038393537,0.000458831],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13041009,0.00035056495,0.0059784707,0.00023599181,0.00009609174,0.000024254787,0.0007517586,0.00064731785,0.010125872],"category_scores_gemma":[0.40329087,0.00021785201,0.00050759927,0.00043158565,0.0009876117,0.000111201356,0.00013227508,0.0009147903,0.00003541491],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049649463,0.0016547685,0.0033494532,0.00009653765,0.001148069,0.000052179537,0.00036198038,0.000001535465,0.0019201204,0.06151243,0.7563832,0.16855481],"study_design_scores_gemma":[0.06378316,0.00861218,0.001512782,0.00036888302,0.0008875496,0.000009018732,0.0005633029,0.00022256393,0.000965703,0.56862307,0.35391265,0.0005391129],"about_ca_topic_score_codex":0.1356924,"about_ca_topic_score_gemma":0.26377937,"teacher_disagreement_score":0.50711066,"about_ca_system_score_codex":0.00017694596,"about_ca_system_score_gemma":0.001006797,"threshold_uncertainty_score":0.990779},"labels":[],"label_agreement":null},{"id":"W2977939617","doi":"10.1093/annonc/mdz265.002","title":"Implementation of PRO-CTCAE in phase I clinical trials identifies under reporting of adverse events","year":2019,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Adverse effect; Clinical trial; Common Terminology Criteria for Adverse Events; Internal medicine; Tolerability; Physical therapy","score_opus":0.9240178606030828,"score_gpt":0.7853572982876386,"score_spread":0.1386605623154442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977939617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99264944,0.00002497699,0.004088794,0.00044306,0.0007861365,0.0011722636,0.00006728279,0.000009264954,0.0007587695],"genre_scores_gemma":[0.8896763,0.000088131375,0.109923564,0.00011770517,0.000083932064,0.000024976325,0.0000037851207,0.000016041797,0.00006558344],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98050755,0.005375193,0.013146839,0.0003341799,0.0003799536,0.00025630606],"domain_scores_gemma":[0.904759,0.07980958,0.0143969,0.00045968825,0.0005025024,0.00007236146],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06678187,0.00012837868,0.0027007365,0.00015787843,0.000009594802,9.579468e-7,0.00020408061,0.00027878315,0.0007745995],"category_scores_gemma":[0.2716271,0.00010933193,0.00044902027,0.00021279082,0.00017884633,0.00007757605,0.00011452434,0.00021402998,0.000008008489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006142809,0.0115060825,0.32194176,0.002834512,0.0016574659,0.00005366541,0.0017161928,0.000036148605,0.037967872,0.107963815,0.004193136,0.50398654],"study_design_scores_gemma":[0.009428199,0.0039844303,0.03780693,0.00024222933,0.0001865883,0.0000029292673,0.001809025,0.000038093796,0.05416928,0.89201826,0.00017456072,0.00013950156],"about_ca_topic_score_codex":0.00006278848,"about_ca_topic_score_gemma":0.00005526912,"teacher_disagreement_score":0.7840544,"about_ca_system_score_codex":0.0000210489,"about_ca_system_score_gemma":0.00031008807,"threshold_uncertainty_score":0.9609445},"labels":[],"label_agreement":null},{"id":"W2977977580","doi":"10.1177/1740774519873883","title":"Benefit, burden, and impact for a cohort of post-approval cancer combination trials","year":2019,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Clinical trial; Food and drug administration; Adverse effect; Hazard ratio; Drug; Randomized controlled trial; MEDLINE; Internal medicine; Cancer; Intensive care medicine; Confidence interval; Pharmacology","score_opus":0.7600792878732857,"score_gpt":0.6883477543706762,"score_spread":0.07173153350260952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977977580","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95390666,0.00043909578,0.022822816,0.0019069219,0.005081264,0.012346389,0.0028010043,0.00011255423,0.0005833245],"genre_scores_gemma":[0.4797835,0.0011771729,0.5103491,0.0004742509,0.005627474,0.00096034823,0.000045070807,0.0001837942,0.0013992818],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97733814,0.010588145,0.010008041,0.0009312272,0.0006484084,0.00048604538],"domain_scores_gemma":[0.4140667,0.5798822,0.0040696627,0.0007681173,0.00088803103,0.00032529267],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17454949,0.00036853945,0.006879879,0.00012600613,0.00005719968,0.00006428243,0.00036659135,0.0007119567,0.001258289],"category_scores_gemma":[0.8095685,0.00025319456,0.0018617087,0.00021874419,0.0003102241,0.00010387196,0.00014371883,0.00039822285,0.000021773367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018318001,0.0016190062,0.046140086,0.001828055,0.0050550513,0.000003654001,0.000170999,0.000020545058,0.006816822,0.315064,0.008978894,0.5959849],"study_design_scores_gemma":[0.017065391,0.0026491778,0.0149208335,0.00031919006,0.001724545,0.0000017921366,0.00004684107,0.00074279396,0.0011213316,0.9601831,0.0008514661,0.0003735607],"about_ca_topic_score_codex":0.00006898391,"about_ca_topic_score_gemma":0.000004251448,"teacher_disagreement_score":0.6451191,"about_ca_system_score_codex":0.00005720821,"about_ca_system_score_gemma":0.00026817847,"threshold_uncertainty_score":0.999992},"labels":[],"label_agreement":null},{"id":"W2978462138","doi":"10.11919/j.issn.1002-0829.217070","title":"The Differences and Similarities Between Two-Sample <i>T</i>-Test and Paired <i>T</i>-Test.","year":2017,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Test (biology); Statistics; Student's t-test; Confusion; Mathematics; Sample (material); Medicine; Psychology; Statistical significance; Biology; Physics","score_opus":0.590758071255841,"score_gpt":0.4869642464323993,"score_spread":0.10379382482344174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978462138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92188156,0.0014411531,0.022943342,0.027879698,0.0023524286,0.0064824126,0.0025421497,0.00065109134,0.013826155],"genre_scores_gemma":[0.9269372,0.00034523752,0.07087681,0.00015682093,0.00058460864,0.00060983544,8.045552e-7,0.000031866562,0.0004568237],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99792016,0.0003214978,0.00057330995,0.000374224,0.00030046495,0.0005103622],"domain_scores_gemma":[0.7629502,0.23569481,0.0003420665,0.000708318,0.00006397441,0.00024064061],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037528179,0.00021738446,0.00057442405,0.000021608574,0.0011040857,0.0007120917,0.0005123286,0.00011721067,0.000009343811],"category_scores_gemma":[0.35950658,0.0001395965,0.00006272197,0.000034415476,0.0012565274,0.00012361576,0.0004219114,0.00026025157,0.0000015032725],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023776063,0.00006310478,0.58356696,0.00009433328,0.00006916635,0.0000047434314,0.000087767476,6.6882064e-9,0.0000045903803,0.032436494,0.0012242658,0.3824248],"study_design_scores_gemma":[0.00049651,0.000028076893,0.45170933,0.000014449396,0.00007297385,0.0000012346886,0.000029925355,0.000014791118,0.00006422575,0.54665446,0.00079711754,0.000116865995],"about_ca_topic_score_codex":0.00006416924,"about_ca_topic_score_gemma":0.00006609749,"teacher_disagreement_score":0.514218,"about_ca_system_score_codex":0.000012982558,"about_ca_system_score_gemma":0.000015344156,"threshold_uncertainty_score":0.8491846},"labels":[],"label_agreement":null},{"id":"W2979269615","doi":"10.1016/s1470-2045(19)30583-2","title":"A critique of the fragility index","year":2019,"lang":"en","type":"letter","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Fragility; Clinical trial; Oncology; Food and drug administration; Alternative medicine; Clinical Oncology; Internal medicine; Pharmacology; Cancer; Pathology","score_opus":0.6148560317831308,"score_gpt":0.6006552477939483,"score_spread":0.014200783989182453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979269615","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003977251,0.000042157277,0.008388404,0.95539504,0.0037320459,0.0011905093,0.00037929075,0.000054253935,0.030420583],"genre_scores_gemma":[0.0010377213,0.000044563043,0.08900053,0.8955948,0.011252907,0.0001092191,0.000003256689,0.00006466117,0.0028923412],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895657,0.008127145,0.001026491,0.00037444953,0.00043606592,0.00047016746],"domain_scores_gemma":[0.83799034,0.15906188,0.0007995872,0.0019747573,0.00015438825,0.00001906498],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0075797588,0.00026176666,0.0020703329,0.000027509055,0.000057887173,0.000011235771,0.0018764359,0.0016908356,0.00067763956],"category_scores_gemma":[0.10159788,0.00012780126,0.00034780678,0.00015173647,0.0008782987,0.000012825063,0.00052005635,0.004472336,0.00006628814],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008612447,0.00005137842,0.00020246409,0.000580056,0.00011241091,0.00001789564,0.00007429919,3.5145663e-7,0.000008655669,0.02566626,0.9717716,0.0014284778],"study_design_scores_gemma":[0.00044108744,0.0000797752,0.00033901224,0.000070958,0.00010735989,0.000008421639,0.000005245925,0.000011487001,0.000029991226,0.54920286,0.44961867,0.000085160886],"about_ca_topic_score_codex":0.000040659677,"about_ca_topic_score_gemma":0.000017325021,"teacher_disagreement_score":0.52353656,"about_ca_system_score_codex":0.0001264686,"about_ca_system_score_gemma":0.0003253767,"threshold_uncertainty_score":0.9996052},"labels":[],"label_agreement":null},{"id":"W2980148093","doi":"10.1097/jcp.0000000000000901","title":"Statistics Commentary Series","year":2018,"lang":"en","type":"editorial","venue":"Journal of Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Library science; Series (stratigraphy); Psychology; Psychiatry; Computer science","score_opus":0.46466132566315216,"score_gpt":0.6780955305289073,"score_spread":0.2134342048657551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980148093","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015150385,0.00017106715,0.022497825,0.003185204,0.9709643,0.0004307728,0.0017653841,0.0000419803,0.0007919639],"genre_scores_gemma":[0.000002789879,0.0020310478,0.43208218,0.0019827154,0.5630977,0.0000070149213,0.000011019695,0.00009811473,0.00068739435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9779601,0.007450194,0.011275849,0.00070728536,0.0019135342,0.0006930465],"domain_scores_gemma":[0.64079976,0.34589526,0.009036216,0.00068627397,0.0028245233,0.0007579606],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.027794354,0.000688944,0.0051953644,0.0002660289,0.00011938323,0.00006636307,0.0018510638,0.0030996343,0.0050289994],"category_scores_gemma":[0.40285075,0.0005517972,0.0012447069,0.00024310063,0.001754978,0.00016434432,0.0003216182,0.0071230154,0.00017412506],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009351706,0.0012128212,0.00004639081,0.00031118238,0.0016857011,0.00046426605,0.000018818613,1.6128239e-7,0.00000672916,0.000605216,0.97773683,0.0085601695],"study_design_scores_gemma":[0.0059683705,0.00314709,0.000015979542,0.00016745282,0.0013065573,0.000021843209,0.000008415069,0.0000031901543,0.000008331787,0.41178238,0.57728463,0.0002857601],"about_ca_topic_score_codex":0.0000022484007,"about_ca_topic_score_gemma":0.000008699786,"teacher_disagreement_score":0.4111772,"about_ca_system_score_codex":0.00013127035,"about_ca_system_score_gemma":0.0010079512,"threshold_uncertainty_score":0.99969333},"labels":[],"label_agreement":null},{"id":"W2982138023","doi":"10.1016/j.jtho.2019.08.317","title":"MS04.04 Optimal Clinical Trial Design for Adjuvant Systemic Therapy","year":2019,"lang":"en","type":"article","venue":"Journal of Thoracic Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Oncology; Clinical trial; Generalizability theory; Systemic therapy; Adjuvant therapy; Stage (stratigraphy); Intensive care medicine; Internal medicine; Adjuvant; Cancer; Breast cancer","score_opus":0.7109457035851906,"score_gpt":0.6913900502921834,"score_spread":0.019555653293007236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982138023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32367072,0.00034075775,0.6583616,0.0009690877,0.013419775,0.0027797746,0.000022519955,0.00003452216,0.00040125198],"genre_scores_gemma":[0.06755219,0.00026136043,0.92747045,0.00038764626,0.003800024,0.00004664115,4.0376455e-7,0.00006010054,0.0004212217],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883025,0.006218388,0.0041750274,0.0003563031,0.0004975712,0.00045016338],"domain_scores_gemma":[0.8423397,0.15322219,0.003073044,0.0004533015,0.0006389811,0.00027276116],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036374565,0.00026458295,0.0026631744,0.0001504742,0.00005690283,0.00003769159,0.00071543024,0.00072680926,0.00041034128],"category_scores_gemma":[0.088077165,0.00018318385,0.0009431501,0.00014791847,0.00017714607,0.000110635905,0.0000766373,0.00094734214,0.00007290903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.4516419,0.002407171,0.00015171841,0.00026981375,0.00089662283,0.00013841975,0.0001674627,0.00011401498,0.00091300986,0.0073223305,0.020118017,0.51585954],"study_design_scores_gemma":[0.11633316,0.089776345,0.00013999222,0.000602471,0.001119569,0.0009854775,0.00037318424,0.0016579559,0.0015601233,0.7608708,0.025952963,0.0006279251],"about_ca_topic_score_codex":5.088803e-7,"about_ca_topic_score_gemma":2.2131583e-7,"teacher_disagreement_score":0.7535485,"about_ca_system_score_codex":0.00021150615,"about_ca_system_score_gemma":0.0008448011,"threshold_uncertainty_score":0.99225515},"labels":[],"label_agreement":null},{"id":"W2985494620","doi":"10.1093/eurpub/ckz185.258","title":"Cloud-computing and precision medicine: Big data offers big opportunities","year":2019,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Precision medicine; Big data; Data science; Personalization; Cloud computing; Computer science; Personalized medicine; Transparency (behavior); Analytics; Agile software development; Data sharing; World Wide Web; Data mining; Computer security; Medicine; Bioinformatics","score_opus":0.8866205473081783,"score_gpt":0.5732655753815961,"score_spread":0.31335497192658224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985494620","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08772222,0.0007409652,0.851685,0.035917222,0.01048459,0.00048112593,0.0000685076,0.00006894546,0.012831459],"genre_scores_gemma":[0.35285866,0.0019543879,0.6292778,0.004164367,0.010864096,2.5862727e-7,0.0000067609553,0.00014786774,0.0007257542],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9795631,0.015709005,0.0028703324,0.0003903035,0.00093002466,0.00053721137],"domain_scores_gemma":[0.96987545,0.026316164,0.0018325603,0.0008406503,0.0003140536,0.00082112063],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.105127975,0.00018295583,0.00089474197,0.0002381183,0.00010299968,0.00008947644,0.000930048,0.000039587892,0.00015513599],"category_scores_gemma":[0.10690258,0.00012707831,0.000060050686,0.0001978967,0.00020914755,0.00015461931,0.0005201316,0.0006292585,0.000020491265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021111251,0.00006337726,0.00026826595,0.00020474385,0.00005403044,0.00005660425,0.00059299555,2.8781017e-7,0.00001160291,0.00805351,0.02016085,0.9705126],"study_design_scores_gemma":[0.014852465,0.012542051,0.023320904,0.006044891,0.0002372029,0.0013618502,0.009619955,0.0017548769,0.0000193128,0.30849946,0.62055945,0.001187569],"about_ca_topic_score_codex":0.0000053116364,"about_ca_topic_score_gemma":9.567649e-7,"teacher_disagreement_score":0.96932507,"about_ca_system_score_codex":0.00005772496,"about_ca_system_score_gemma":0.0004929804,"threshold_uncertainty_score":0.9214591},"labels":[],"label_agreement":null},{"id":"W2986737925","doi":"10.1007/s10985-019-09490-0","title":"Multiple event times in the presence of informative censoring: modeling and analysis by copulas","year":2019,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"Institute of Cancer Research; Canadian Statistical Sciences Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Censoring (clinical trials); Estimator; Computer science; Econometrics; Bivariate analysis; Statistics; Joint probability distribution; Marginal distribution; Mathematics; Data mining; Random variable","score_opus":0.3095969661835676,"score_gpt":0.5054492151954478,"score_spread":0.19585224901188025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986737925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2546281,0.00016939228,0.7386125,0.00029742718,0.000051427483,0.00072581053,0.00476952,0.00003075936,0.00071509],"genre_scores_gemma":[0.7624782,0.00006332621,0.23691675,0.000057026602,0.000016838409,0.000011400101,0.00034321725,0.000008780668,0.00010450426],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965697,0.00091981806,0.0012433458,0.00045010436,0.00058398885,0.00023305314],"domain_scores_gemma":[0.9697417,0.027845254,0.0004324082,0.0018124385,0.000097349206,0.000070844],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050547975,0.00017464915,0.0011002753,0.00035140765,0.000040424016,0.00005480092,0.0010125038,0.0000987193,0.00036880965],"category_scores_gemma":[0.031233056,0.0001194239,0.00021865727,0.0023557513,0.00009244269,0.00025687265,0.00048564124,0.00022446067,0.00001788392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006904383,0.0017972431,0.78552663,0.0009086098,0.045716535,0.000013750454,0.008691446,0.113795355,0.00033684706,0.023875207,0.00886547,0.009782483],"study_design_scores_gemma":[0.00039337095,0.000029807767,0.0021318465,0.000023954839,0.005828886,2.1788033e-7,0.0005618946,0.9733454,0.00005018616,0.01740938,0.00007901544,0.0001460353],"about_ca_topic_score_codex":0.00036426942,"about_ca_topic_score_gemma":0.0000667005,"teacher_disagreement_score":0.85955006,"about_ca_system_score_codex":0.0000151288095,"about_ca_system_score_gemma":0.000017405886,"threshold_uncertainty_score":0.9769273},"labels":[],"label_agreement":null},{"id":"W2991902418","doi":"10.1177/0022034519891953","title":"CONSORT Extension for Within-Person Randomized Clinical Trials","year":2019,"lang":"en","type":"article","venue":"Journal of Dental Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of British Columbia","funders":"","keywords":"Randomized controlled trial; Extension (predicate logic); Consolidated Standards of Reporting Trials; Medicine; Psychology; Computer science; Internal medicine","score_opus":0.9347632881258013,"score_gpt":0.7651473257390851,"score_spread":0.16961596238671628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991902418","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8808075,0.0004634918,0.09931745,0.0012366751,0.008426348,0.0066248314,0.000054153024,0.000027926451,0.0030415899],"genre_scores_gemma":[0.2644305,0.00028483837,0.731114,0.00015190354,0.0019199784,0.00003954927,7.0237314e-7,0.0000599598,0.0019986138],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9545199,0.036279045,0.0058606057,0.00039136573,0.0024110083,0.0005380592],"domain_scores_gemma":[0.27902174,0.7161021,0.0021979955,0.00045675936,0.0017719758,0.00044943226],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42918032,0.00016764773,0.0034356283,0.00029495943,0.000092558796,0.000101812075,0.00053095527,0.00030921792,0.00074418494],"category_scores_gemma":[0.8630507,0.00010324687,0.0016293237,0.00023600408,0.0005486945,0.00011969723,0.000110103196,0.0014659301,0.00011476317],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6728137,0.0021148974,0.0031944378,0.0006804424,0.0019773222,0.00025046905,0.00028536914,0.0000039352517,0.009494054,0.18314119,0.059524823,0.06651938],"study_design_scores_gemma":[0.18299861,0.001837394,0.0001536,0.00048794903,0.00030379818,0.00010788756,0.0006844684,0.00094175315,0.0023755732,0.8094138,0.00053864863,0.00015652075],"about_ca_topic_score_codex":0.0000029516725,"about_ca_topic_score_gemma":9.864424e-7,"teacher_disagreement_score":0.67982304,"about_ca_system_score_codex":0.00009090054,"about_ca_system_score_gemma":0.000356455,"threshold_uncertainty_score":0.8148303},"labels":[],"label_agreement":null},{"id":"W2994409524","doi":"10.1080/00031305.2020.1816214","title":"Null Hypothesis Significance Testing Interpreted and Calibrated by Estimating Probabilities of Sign Errors: A Bayes-Frequentist Continuum","year":2020,"lang":"en","type":"article","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Bayes factor; Frequentist inference; Posterior probability; Bayesian probability; Statistics; Bayes' theorem; Mathematics; p-value; Statistical hypothesis testing; Sign (mathematics); Null hypothesis; Prior probability; Alternative hypothesis; Statistical power; Econometrics; Bayesian inference; Mathematical analysis","score_opus":0.36817545539381347,"score_gpt":0.4518311482418546,"score_spread":0.08365569284804114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994409524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101112366,0.00004973148,0.8932944,0.0014407071,0.00012611861,0.0011297263,0.0017492702,0.00024568284,0.0008519814],"genre_scores_gemma":[0.36735445,0.000002462898,0.63184106,0.000588876,0.00008349469,0.000052248415,0.0000021434128,0.000052149426,0.000023105935],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955253,0.0017139498,0.0013625029,0.00055243407,0.00039435015,0.0004514423],"domain_scores_gemma":[0.89258564,0.10512488,0.001406964,0.0004294578,0.00021362324,0.00023946099],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001482716,0.00034229807,0.0012527165,0.000037716098,0.00014023644,0.000082385224,0.00047645922,0.00005224674,0.000099498815],"category_scores_gemma":[0.20389616,0.00026000422,0.000076842276,0.0006448548,0.0023034369,0.00007323117,0.0001581667,0.0003551701,0.0000072229486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023908925,0.00073154893,0.008218993,0.003684911,0.001319089,0.00013081699,0.013750354,0.00007439631,0.10367113,0.07198223,0.059734292,0.73431134],"study_design_scores_gemma":[0.0010550021,0.001891505,0.0024005356,0.00055986404,0.0005195353,0.000011357612,0.002924074,0.05728111,0.005282698,0.9271859,0.00009929095,0.00078913633],"about_ca_topic_score_codex":0.00057786965,"about_ca_topic_score_gemma":0.000024743302,"teacher_disagreement_score":0.8552037,"about_ca_system_score_codex":0.000039681567,"about_ca_system_score_gemma":0.00009418105,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W2995118312","doi":"10.1002/pds.4932","title":"Trial designs using real‐world data: The changing landscape of the regulatory approval process","year":2019,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":257,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; McGill University Health Centre","funders":"Pfizer","keywords":"Observational study; Leverage (statistics); Risk analysis (engineering); Medicine; Randomized controlled trial; Clinical study design; Real world data; Data collection; Clinical trial; Process (computing); Management science; Computer science; Data science; Machine learning; Engineering","score_opus":0.8271081619909781,"score_gpt":0.6490336892071032,"score_spread":0.1780744727838749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995118312","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010639933,0.9730147,0.01342046,0.00052039,0.004624754,0.006329291,0.0009747786,0.00008096349,0.00092827063],"genre_scores_gemma":[0.000053745145,0.95587534,0.041321803,0.00027486397,0.0019943733,0.00009647069,0.00002929938,0.00008595422,0.0002681572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9758838,0.01934376,0.002908647,0.00094365596,0.0003081794,0.00061198877],"domain_scores_gemma":[0.7746774,0.22053477,0.002889476,0.0017113219,0.00008273217,0.00010432265],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04863141,0.0005508542,0.004579778,0.00014485359,0.00031984926,0.0000127909,0.0017512786,0.00033988818,0.000071707946],"category_scores_gemma":[0.06647392,0.00026692945,0.0005586774,0.0006651687,0.00090402097,0.00007716483,0.0011336979,0.001449366,0.000005415372],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052015935,0.0002738477,0.00018829967,0.04624811,0.0020169406,0.0000057812513,0.00037066947,0.000023297405,9.300897e-7,0.067540444,0.009485191,0.8686449],"study_design_scores_gemma":[0.019337514,0.00013394954,0.00004306429,0.016918533,0.026697371,0.000086415996,0.00023687175,0.0067381714,0.000011685876,0.33676487,0.5912829,0.0017486282],"about_ca_topic_score_codex":0.000021866805,"about_ca_topic_score_gemma":0.00000770715,"teacher_disagreement_score":0.8668963,"about_ca_system_score_codex":0.00004848551,"about_ca_system_score_gemma":0.0004466284,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W2995883695","doi":"10.1016/j.jval.2019.09.633","title":"PCN440 NETWORK META-ANALYSIS USING FRACTIONAL POLYNOMIALS: HEURISTIC FOR MODEL SELECTION INCORPORATING BEYOND-TRIAL EXTRAPOLATIONS (A MELANOMA EXAMPLE)","year":2019,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Precision Nanosystems (Canada)","funders":"","keywords":"Model selection; Gompertz function; Weibull distribution; Mathematics; Extrapolation; Deviance (statistics); Boolean model; Statistics; Parametric statistics; Computer science; Econometrics","score_opus":0.796887340975208,"score_gpt":0.5686788188507079,"score_spread":0.22820852212450005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995883695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025040237,0.00016507276,0.9705486,0.0003468684,0.0007985971,0.0027113694,0.00017048592,0.00007923296,0.00013951921],"genre_scores_gemma":[0.18008895,0.0000055929386,0.8185264,0.00025294855,0.00077918376,0.00017430088,0.000018117229,0.0000516964,0.000102836864],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928708,0.002621392,0.0026367009,0.0007267203,0.00054265856,0.0006016947],"domain_scores_gemma":[0.9351819,0.062471528,0.0014833529,0.0004734016,0.00019467625,0.00019511816],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013479733,0.00029824837,0.0021682987,0.0003703621,0.00031257753,0.00006923362,0.0002046387,0.0002667065,0.00032875995],"category_scores_gemma":[0.018472837,0.0002800056,0.00090385316,0.0013351553,0.00005284374,0.00015657955,0.000055305438,0.0004681278,0.00000919105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00131249,0.00021712952,0.000625669,0.00017592873,0.006222566,4.5055614e-7,0.00010729817,0.73127824,0.00003215671,0.25957587,0.00025100555,0.00020121386],"study_design_scores_gemma":[0.002162504,0.00015175626,0.000029540144,0.000009410071,0.0067602815,0.0000011137046,0.000013678329,0.505093,0.000005102262,0.48562273,0.000014121689,0.00013674222],"about_ca_topic_score_codex":0.0016635134,"about_ca_topic_score_gemma":0.0001430109,"teacher_disagreement_score":0.22618523,"about_ca_system_score_codex":0.00041329037,"about_ca_system_score_gemma":0.00068941887,"threshold_uncertainty_score":0.9999652},"labels":[],"label_agreement":null},{"id":"W2996565064","doi":"10.1093/ije/dyaa026","title":"Design, analysis and reporting of multi-arm trials and strategies to address multiple testing","year":2020,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Impact; St. Michael's Hospital","funders":"Cancer Research UK; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Bonferroni correction; Type I and type II errors; Protocol (science); Multiple comparisons problem; Medicine; Clinical trial; False discovery rate; Test strategy; Test (biology); Statistical hypothesis testing; Medical physics; Statistics; Computer science; Pathology; Alternative medicine; Mathematics","score_opus":0.9335887181904791,"score_gpt":0.681603008594827,"score_spread":0.25198570959565203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996565064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07376298,0.00016510079,0.9230076,0.0025675222,0.000258306,0.00016588948,0.000028339948,0.000008948243,0.00003530725],"genre_scores_gemma":[0.33418965,0.00003548285,0.6651073,0.00041611653,0.00023947268,0.000002550431,3.47176e-7,0.0000068780128,0.0000022030779],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883238,0.0039995043,0.007017696,0.00025227937,0.00023761136,0.00016907997],"domain_scores_gemma":[0.46150222,0.52193743,0.014535917,0.00016673411,0.0014920327,0.00036569807],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040295385,0.00013062602,0.002327705,0.00021379605,0.000023143766,0.000019944142,0.00025501553,0.000112224785,0.00004975503],"category_scores_gemma":[0.9307252,0.00009546208,0.00022246107,0.000217949,0.00014742324,0.00008108491,0.00013893911,0.00025790714,4.625984e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040227296,0.0005626501,0.66251355,0.0003254823,0.014740023,0.0004948235,0.0025819587,0.012839584,0.04433015,0.042893413,0.0012117842,0.21348383],"study_design_scores_gemma":[0.003623105,0.0013484817,0.084261924,0.00036030737,0.002149202,0.00020563879,0.0006648726,0.050529953,0.0039675417,0.8524271,0.00013203887,0.0003298402],"about_ca_topic_score_codex":0.0000346228,"about_ca_topic_score_gemma":0.000005333657,"teacher_disagreement_score":0.89042985,"about_ca_system_score_codex":0.000018803557,"about_ca_system_score_gemma":0.00007200352,"threshold_uncertainty_score":0.9882179},"labels":[],"label_agreement":null},{"id":"W2997307408","doi":"10.5287/ora-mprrex7vx","title":"Improving the specification of the target difference in the sample size calculation of a randomised trial of treatments for osteoarthritis","year":2019,"lang":"en","type":"dissertation","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Oxford; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; GlaxoSmithKline; Novartis Pharmaceuticals Corporation; Oxford Health NHS Foundation Trust; Pfizer; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Minimal clinically important difference; WOMAC; Osteoarthritis; Sample size determination; Medicine; Physical therapy; Clinical trial; Randomized controlled trial; Sample (material); Physical medicine and rehabilitation; Statistics; Mathematics; Surgery; Alternative medicine; Internal medicine","score_opus":0.18576529498478467,"score_gpt":0.41062694915442005,"score_spread":0.22486165416963538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997307408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8770662,0.00002804356,0.10181397,0.00024858068,0.00034749543,0.011685879,0.0033438802,0.000012283386,0.0054536727],"genre_scores_gemma":[0.7374211,0.000585316,0.25837576,0.000006009865,0.000083779196,0.0000091303455,0.00029467145,0.000049968672,0.0031742398],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99454385,0.0027979447,0.00069848157,0.0004188032,0.0011696528,0.0003712723],"domain_scores_gemma":[0.90799516,0.08877497,0.0015344673,0.0009144145,0.0007184531,0.000062520565],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051128734,0.00023115052,0.0010047441,0.0003615247,0.0003226736,0.000011107435,0.0017817985,0.0002724825,0.000056644763],"category_scores_gemma":[0.026815461,0.00017110766,0.000656995,0.00077976746,0.0008993098,0.00010050697,0.00026680957,0.00063847366,2.5945292e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.66976434,0.0034332636,0.0058264183,0.004993551,0.0014971929,0.000015890773,0.03580727,0.0000568636,0.014211997,0.15939632,0.00058816164,0.10440874],"study_design_scores_gemma":[0.25261736,0.0058901804,0.08500171,0.0017436725,0.001698649,0.0000014543022,0.08157025,0.0026433014,0.0042873607,0.5624362,0.001439812,0.0006700195],"about_ca_topic_score_codex":0.0009152455,"about_ca_topic_score_gemma":0.0008899521,"teacher_disagreement_score":0.41714698,"about_ca_system_score_codex":0.00014127846,"about_ca_system_score_gemma":0.00047807605,"threshold_uncertainty_score":0.9813821},"labels":[],"label_agreement":null},{"id":"W2998980882","doi":"10.1002/9780470061596.risk0903","title":"BioequivalenceArticle originally published in <i>Encyclopedia of Biostatistics, 2nd Edition</i> (2005, John Wiley &amp; Sons, Ltd).","year":2008,"lang":"en","type":"other","venue":"Encyclopedia of Quantitative Risk Analysis and Assessment","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Biostatistics; Nonparametric statistics; Bioavailability; Econometrics; Mathematics; Medicine; Pharmacology; Internal medicine","score_opus":0.13658594738820118,"score_gpt":0.47599661248058345,"score_spread":0.33941066509238227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998980882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044702096,0.0041123033,0.6466949,0.0006237919,0.0014197086,0.0019738998,0.011936205,0.00015213466,0.32861686],"genre_scores_gemma":[0.00039925348,0.12800156,0.85120004,0.000020464386,0.0002927581,0.00006233962,0.00012210276,0.0001820932,0.019719392],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99246573,0.0019777813,0.0027550356,0.0010253885,0.0011778165,0.0005982299],"domain_scores_gemma":[0.97864974,0.016586514,0.0031988095,0.00089206384,0.00038001832,0.00029284548],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003962123,0.00064073014,0.0030808046,0.0014506094,0.00008291703,0.000046233225,0.0004606628,0.00043208827,0.0040355464],"category_scores_gemma":[0.02178611,0.0005475626,0.0005114124,0.0017824114,0.00079302676,0.00015319383,0.0001880806,0.0007723176,0.000015905556],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019892007,0.0026211124,0.15143903,0.0014940808,0.0070028417,0.000076375596,0.0008136206,0.000029310631,0.00004189886,0.12731089,0.6911799,0.01779204],"study_design_scores_gemma":[0.0044222833,0.0010387865,0.06708661,0.0021190061,0.013147904,0.0000041017834,0.0011627119,0.001154525,0.00007035721,0.44296855,0.46446422,0.0023609556],"about_ca_topic_score_codex":0.0019053996,"about_ca_topic_score_gemma":0.002924274,"teacher_disagreement_score":0.31565768,"about_ca_system_score_codex":0.000094168296,"about_ca_system_score_gemma":0.00047044497,"threshold_uncertainty_score":0.99969757},"labels":[],"label_agreement":null},{"id":"W2998989154","doi":"10.1093/aje/161.supplement_1.s69c","title":"276: Simulations for the Comparison and Validation of Imputation Methods for Missing Diagnoses of Lifetime Disorders","year":2005,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Imputation (statistics); Medical diagnosis; Missing data; Medicine; Statistics; Mathematics; Pathology","score_opus":0.5058828539316633,"score_gpt":0.6538506653892575,"score_spread":0.1479678114575942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998989154","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026055448,0.0004169954,0.9680406,0.0049221395,0.00014641594,0.00037258794,0.000035076937,0.0000037305776,0.000007031423],"genre_scores_gemma":[0.2686744,0.00010354341,0.7309287,0.00012976161,0.00014262296,0.000008087486,0.0000010664346,0.0000103357315,0.0000014787256],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99464995,0.002864842,0.0021313953,0.00012241284,0.00007080282,0.00016057586],"domain_scores_gemma":[0.54841053,0.44861883,0.0025783638,0.000107064334,0.00023718202,0.000048025093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013472996,0.00009813154,0.0011821012,0.00008270605,0.000060132443,0.0000031915822,0.00013959632,0.00006131693,0.000013705497],"category_scores_gemma":[0.42451483,0.00006485999,0.00020978619,0.00012015297,0.00061232003,0.00005169421,0.000020753701,0.000123809,6.3114065e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036541888,0.00014153778,0.009490934,0.00007637356,0.00023263536,2.0543505e-8,0.0003360714,0.012014432,0.00061065255,0.020250034,0.0004609257,0.95602095],"study_design_scores_gemma":[0.00078860065,0.0013012936,0.0030625924,0.000059227194,0.00043622512,0.000002976012,0.00024868408,0.07625823,0.0019957542,0.91482764,0.00094557396,0.00007318039],"about_ca_topic_score_codex":0.0000139360845,"about_ca_topic_score_gemma":0.0000028860254,"teacher_disagreement_score":0.95594776,"about_ca_system_score_codex":0.000018917399,"about_ca_system_score_gemma":0.000045293407,"threshold_uncertainty_score":0.5803327},"labels":[],"label_agreement":null},{"id":"W3000286044","doi":"10.6004/jnccn.2019.7345","title":"Response Rates and Durations of Response for Biomarker-Based Cancer Drugs in Nonrandomized Versus Randomized Trials","year":2020,"lang":"en","type":"review","venue":"Journal of the National Comprehensive Cancer Network","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Medicine; Randomized controlled trial; Relative risk; Meta-analysis; Pharmacogenomics; Confidence interval; Biomarker; Internal medicine; Oncology; Pharmacology","score_opus":0.7160078237002326,"score_gpt":0.6306847045581461,"score_spread":0.08532311914208657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000286044","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012971925,0.9796828,0.0051948274,0.0044187387,0.0039123986,0.005399151,0.0012441025,0.000009133162,0.000009152033],"genre_scores_gemma":[0.00008111091,0.88547343,0.11148656,0.00038292122,0.0014981751,0.00095186045,0.000003981115,0.00008004174,0.00004193989],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9443724,0.047378197,0.006486718,0.00037919192,0.0010787749,0.000304698],"domain_scores_gemma":[0.46958283,0.52229625,0.006110841,0.00015298139,0.0017551931,0.00010191517],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041515503,0.0004987288,0.0099802315,0.00033515727,0.00012855513,0.000052910487,0.0005874547,0.00038793017,0.00010091147],"category_scores_gemma":[0.53112775,0.00029503976,0.0029292572,0.0009042855,0.00046730487,0.00006258168,0.00011546426,0.0007308991,4.6798056e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.94611603,0.00008794915,5.9176847e-7,0.0022441242,0.0027601132,0.0000030880447,0.00006946252,0.0005849783,0.000018732411,0.0012208213,0.012639614,0.034254476],"study_design_scores_gemma":[0.4669787,0.00037765305,0.000018131726,0.028319547,0.009396908,0.000010072996,0.00003291634,0.0016744967,0.000026025738,0.14080341,0.35182875,0.0005334007],"about_ca_topic_score_codex":0.0000058090427,"about_ca_topic_score_gemma":0.0000053346766,"teacher_disagreement_score":0.48961228,"about_ca_system_score_codex":0.00055982743,"about_ca_system_score_gemma":0.0036015688,"threshold_uncertainty_score":0.9999502},"labels":[],"label_agreement":null},{"id":"W3003781265","doi":"10.1002/sim.8487","title":"Correction to Walter SD, Turner RM, Macaskill P. Optimising the two‐stage randomised trial design when some participants are indifferent in their treatment preferences (2019). Statistics in Medicine 38, 2317‐2331","year":2020,"lang":"en","type":"erratum","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton Health Sciences; Impact","funders":"","keywords":"Citation; Order (exchange); Medicine; Library science; Psychology; Computer science","score_opus":0.5087324334082165,"score_gpt":0.5251660379332699,"score_spread":0.01643360452505338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003781265","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005822903,0.0011994843,0.90247536,0.0041658077,0.07096446,0.014412598,0.004790065,0.00014065484,0.0012692995],"genre_scores_gemma":[0.005094033,0.009010294,0.92457944,0.003304039,0.017850488,0.004219089,0.0019214067,0.0007928237,0.03322841],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97994316,0.008411633,0.0059917276,0.0018049952,0.0020692202,0.0017792725],"domain_scores_gemma":[0.8695962,0.12617068,0.002069935,0.0011918672,0.0003151775,0.00065614964],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.011351417,0.0015972807,0.0060578627,0.00092512264,0.00018018087,0.00010137026,0.0011374891,0.00082813436,0.0020205365],"category_scores_gemma":[0.22201848,0.000946366,0.00015929138,0.0008780904,0.001009893,0.0000890776,0.00031786354,0.0037231275,0.00003881999],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.054629523,0.0010123705,0.0001444936,0.0008112873,0.00047092506,0.0009094471,0.0144327525,0.00044904152,0.000015545807,0.0062733702,0.89672136,0.024129909],"study_design_scores_gemma":[0.20008029,0.007049061,0.00070685043,0.00921127,0.0012763845,0.000009584943,0.0028395085,0.021555327,0.000039149938,0.7499898,0.005859518,0.0013832273],"about_ca_topic_score_codex":0.0015782648,"about_ca_topic_score_gemma":0.0035568033,"teacher_disagreement_score":0.8908618,"about_ca_system_score_codex":0.0013824956,"about_ca_system_score_gemma":0.00080955523,"threshold_uncertainty_score":0.9996775},"labels":[],"label_agreement":null},{"id":"W3004002562","doi":"10.1002/sim.8465","title":"Bayesian hierarchical meta‐analytic methods for modeling surrogate relationships that vary across treatment classes using aggregate data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research","keywords":"Surrogate endpoint; Bayesian probability; Computer science; Surrogate model; Surrogate data; Bayesian inference; Meta-analysis; Class (philosophy); Econometrics; Statistics; Data mining; Artificial intelligence; Machine learning; Mathematics; Medicine; Internal medicine","score_opus":0.8988886626769544,"score_gpt":0.6656536011715628,"score_spread":0.23323506150539164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004002562","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032446868,0.0006120487,0.991186,0.0030498402,0.00048003002,0.0012402026,0.0028835374,0.00009363835,0.00013023136],"genre_scores_gemma":[0.01582179,0.00031193256,0.9824257,0.00043591257,0.0005712519,0.000083078274,0.00020258616,0.00010546935,0.00004227394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99193186,0.0035981862,0.0020382237,0.0011247402,0.00057620124,0.00073076907],"domain_scores_gemma":[0.8525165,0.14519617,0.0005010422,0.0011370787,0.00018408945,0.00046513224],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012459028,0.00049600255,0.0022963448,0.00012195722,0.0002737233,0.00005232618,0.00074002304,0.0002567014,0.0002142447],"category_scores_gemma":[0.2451172,0.00036826683,0.00015707737,0.0005248212,0.00048358543,0.00013822709,0.00032907363,0.00078363606,0.0000042718907],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021023683,0.0009072746,0.0010150166,0.0029466192,0.00997664,0.0005211566,0.007840617,0.008763543,0.0005553112,0.8215508,0.0034020569,0.14041863],"study_design_scores_gemma":[0.0015254432,0.00022354102,0.00000794793,0.000099504105,0.002820168,0.0000051000993,0.00025825086,0.50265574,0.000038548056,0.49199712,0.00018682476,0.00018183187],"about_ca_topic_score_codex":0.00010377444,"about_ca_topic_score_gemma":0.00010617853,"teacher_disagreement_score":0.4938922,"about_ca_system_score_codex":0.00017175305,"about_ca_system_score_gemma":0.00019765517,"threshold_uncertainty_score":0.9998769},"labels":[],"label_agreement":null},{"id":"W3004570628","doi":"10.1038/s41467-019-13929-1","title":"Combined burden and functional impact tests for cancer driver discovery using DriverPower","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prostate Cancer Canada; Genome Canada; Institute of Cancer Research; Princess Margaret Cancer Centre; Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; University of Calgary; Vector Institute; Canada's Michael Smith Genome Sciences Centre; University Health Network; McGill University and Génome Québec Innovation Centre; Toronto General Hospital; University of Toronto; BC Cancer Agency; SickKids Foundation; University of Ottawa; McGill University; Simon Fraser University; Ontario Institute for Cancer Research","funders":"National Cancer Institute; National Institute of Environmental Health Sciences; Government of Ontario; Francis Crick Institute","keywords":"Cancer; Computer science; Computational biology; Medicine; Bioinformatics; Biology; Internal medicine","score_opus":0.5251382102481553,"score_gpt":0.5807650512924323,"score_spread":0.05562684104427695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004570628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21585867,0.007866619,0.6379217,0.12220293,0.00240494,0.0058508287,0.005329485,0.0006394347,0.0019254157],"genre_scores_gemma":[0.49015948,0.00014616582,0.5086881,0.0005805071,0.00028548637,0.000055510813,0.000016396385,0.000025595356,0.000042753145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987151,0.00028721566,0.00038660725,0.00024733163,0.00018610335,0.00017766382],"domain_scores_gemma":[0.9717773,0.026851896,0.00018940789,0.00077340705,0.00026166433,0.0001463191],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00045192166,0.00015887148,0.0003678744,0.00003504677,0.00024601657,0.00007062227,0.0004459661,0.00027229148,0.000104573606],"category_scores_gemma":[0.031514708,0.00013161005,0.00014337111,0.00021302451,0.0002444956,0.00015265442,0.0003821611,0.00069611904,0.0000027656836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007869686,0.0003888776,0.01634781,0.0002529978,0.000979345,0.0000023810308,0.0010866908,0.00014373894,0.012922225,0.89832616,0.059941627,0.008821165],"study_design_scores_gemma":[0.0033264277,0.00029173854,0.027596088,0.0001804183,0.000675933,0.0000039871643,0.00013584412,0.033040725,0.0002762858,0.91717654,0.01671039,0.0005856131],"about_ca_topic_score_codex":0.000018684143,"about_ca_topic_score_gemma":0.000023751842,"teacher_disagreement_score":0.2743008,"about_ca_system_score_codex":0.00007565783,"about_ca_system_score_gemma":0.00012782375,"threshold_uncertainty_score":0.97664326},"labels":[],"label_agreement":null},{"id":"W3005076266","doi":"10.1177/0962280220902179","title":"Modeling of cumulative effects of time-varying drug exposures on within-subject changes in a continuous outcome","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Institute of Population and Public Health; Canadian Institutes of Health Research","keywords":"Random effects model; Statistics; Outcome (game theory); Econometrics; Mixed model; Medicine; Regression analysis; Correlation; Mathematics; Computer science; Meta-analysis; Internal medicine","score_opus":0.6354828221668393,"score_gpt":0.6687579758259045,"score_spread":0.03327515365906519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005076266","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045620136,0.00011222799,0.9482494,0.001879692,0.00028622866,0.0017264532,0.00010314666,0.000050102295,0.001972592],"genre_scores_gemma":[0.23061162,0.000044349046,0.76882774,0.00022664317,0.00012658094,0.00007857206,0.0000018211138,0.000056714438,0.000025960164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.963566,0.027029414,0.0033565287,0.0010039345,0.003980282,0.0010638224],"domain_scores_gemma":[0.5245866,0.4735356,0.00029754027,0.0004978898,0.0003916358,0.00069074775],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0520197,0.00035280033,0.002524083,0.0005181199,0.000053507778,0.000020318379,0.0008869296,0.00045179308,0.00084782095],"category_scores_gemma":[0.8565768,0.00028366462,0.00013650855,0.0014787865,0.0012632454,0.000043963275,0.0005627278,0.0029570288,0.00001536766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071812966,0.0030651747,0.0049073733,0.012625349,0.00033400833,0.0019681724,0.011472153,0.0011319652,0.007287607,0.5840921,0.00076523056,0.3651696],"study_design_scores_gemma":[0.0025299627,0.0013099803,0.00026366083,0.0015989162,0.0000346505,0.0000014570419,0.00026339933,0.28658205,0.009184215,0.6979885,0.0000059093645,0.00023727045],"about_ca_topic_score_codex":0.00020884235,"about_ca_topic_score_gemma":0.000034197517,"teacher_disagreement_score":0.8045571,"about_ca_system_score_codex":0.00012287412,"about_ca_system_score_gemma":0.0003205657,"threshold_uncertainty_score":0.99996156},"labels":[],"label_agreement":null},{"id":"W3006396558","doi":"10.1002/sim.8495","title":"A hierarchical testing approach for detecting safety signals in clinical trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Clinical trial; Data mining; Safety monitoring; Curse of dimensionality; Class (philosophy); Artificial intelligence; Medicine; Bioinformatics","score_opus":0.8299342855077583,"score_gpt":0.649968645019091,"score_spread":0.17996564048866726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006396558","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008180633,0.00005646465,0.9924365,0.0016461937,0.00048670688,0.0022574181,0.0004674259,0.000085256346,0.0017459437],"genre_scores_gemma":[0.023281367,0.000032113483,0.9729939,0.0013777714,0.0020358453,0.00016709657,0.000019744853,0.000072890376,0.000019276467],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9817003,0.008138868,0.007718976,0.0009863504,0.0007312799,0.0007242247],"domain_scores_gemma":[0.45262548,0.5453329,0.0010276175,0.00036147644,0.00022207802,0.0004304409],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07828288,0.00035671765,0.0033436269,0.00017468893,0.00007973493,0.000021939144,0.00045895218,0.00036139417,0.00019079213],"category_scores_gemma":[0.9464482,0.00028159335,0.00015739076,0.0008786796,0.0005528857,0.000036750538,0.00014930606,0.0015402362,0.000004855847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044992846,0.00087101065,0.0087572485,0.0026317849,0.00021078957,0.00023355879,0.001925873,0.00031488482,0.00068875327,0.30412826,0.010274447,0.6654641],"study_design_scores_gemma":[0.00796526,0.0012219066,0.0011654252,0.00040346675,0.00016369838,0.000004026003,0.000331703,0.13982262,0.00003100501,0.84839904,0.00019844307,0.00029339915],"about_ca_topic_score_codex":0.000024118312,"about_ca_topic_score_gemma":0.000013190388,"teacher_disagreement_score":0.8681654,"about_ca_system_score_codex":0.00008662988,"about_ca_system_score_gemma":0.0001788388,"threshold_uncertainty_score":0.99996364},"labels":[],"label_agreement":null},{"id":"W3006624376","doi":"10.1002/pst.2005","title":"START: single‐to‐double arm transition design for phase II clinical trials","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Randomization; Frequentist inference; Computer science; Restricted randomization; Null hypothesis; Clinical study design; Clinical trial; Randomized controlled trial; Statistics; Research design; Gold standard (test); Medical physics; Medicine; Mathematics; Surgery; Bayesian probability; Internal medicine; Bayesian inference","score_opus":0.9480752190546133,"score_gpt":0.7157514049968547,"score_spread":0.2323238140577586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006624376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006861018,0.00003976919,0.9785313,0.008933083,0.001326423,0.0052348347,0.0046710027,0.00031645293,0.0002610309],"genre_scores_gemma":[0.018480292,0.000050914467,0.9701976,0.008428275,0.0022385926,0.00035480232,0.000046286197,0.00013857699,0.00006465007],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98763174,0.004905534,0.004552674,0.0010892561,0.00085347175,0.0009673483],"domain_scores_gemma":[0.8068024,0.18984646,0.00058543996,0.00039675413,0.0004611614,0.0019078255],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022166694,0.00053534016,0.002443877,0.000073716285,0.0003072273,0.00012866288,0.0005190884,0.00036500368,0.00196165],"category_scores_gemma":[0.31978798,0.00047962638,0.0005242293,0.0004232185,0.00033745304,0.00010088261,0.00015520267,0.00081562385,0.00018563497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030961014,0.009319725,0.0000041287626,0.00089705206,0.00076125475,0.00009895299,0.0010151421,0.0001553969,0.005775302,0.3656887,0.20588115,0.3794422],"study_design_scores_gemma":[0.03184917,0.012177281,0.0000017642188,0.00007601994,0.0019993351,0.0000043515142,0.000054765133,0.08089796,0.019392082,0.79698354,0.055740785,0.00082293275],"about_ca_topic_score_codex":0.0000014938358,"about_ca_topic_score_gemma":5.685975e-7,"teacher_disagreement_score":0.43129486,"about_ca_system_score_codex":0.00009776677,"about_ca_system_score_gemma":0.00017838762,"threshold_uncertainty_score":0.9997655},"labels":[],"label_agreement":null},{"id":"W3006857637","doi":"10.1016/j.jvir.2019.12.565","title":"Abstract No. 504 Ex vivo evaluation of the effect of multiple electrode radiofrequency needle tip convergence on size of ablation zone","year":2020,"lang":"en","type":"article","venue":"Journal of Vascular and Interventional Radiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston General Hospital","funders":"","keywords":"Ablation; Ablation zone; Radiofrequency ablation; Medicine; Electrode; Volume (thermodynamics); Biomedical engineering; Ex vivo; Nuclear medicine; In vivo; Physics","score_opus":0.21251658887105954,"score_gpt":0.46494785758222956,"score_spread":0.25243126871117005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006857637","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9686541,0.00083030114,0.029260045,0.00017521871,0.0004967264,0.0003645121,0.000034845252,0.000002724722,0.00018155902],"genre_scores_gemma":[0.9798715,0.000105702595,0.019801922,0.00002355753,0.00017789881,0.000003416103,8.209879e-7,0.000009200068,0.000005994127],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99587166,0.0018471661,0.0014494486,0.00013167488,0.000597107,0.00010293622],"domain_scores_gemma":[0.9825497,0.015176132,0.0014910605,0.00015450282,0.0005685451,0.00006000489],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0068706153,0.00011459183,0.00074102596,0.00005042467,0.000020615738,0.0000030313256,0.00020378895,0.00012077661,0.00071193976],"category_scores_gemma":[0.093146466,0.00007424554,0.00068464153,0.00011336204,0.00018557913,0.000057829664,0.000027671938,0.0002604798,0.0000016436169],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010420173,0.0021529002,0.055677626,0.0062357127,0.0072157965,0.000013463795,0.00082068105,0.0035490082,0.82235837,0.048123807,0.0055241436,0.0379083],"study_design_scores_gemma":[0.019522222,0.022593545,0.22162165,0.0021938854,0.002758653,0.00012875193,0.00006600969,0.017848575,0.34093338,0.37171003,0.00023361652,0.00038965445],"about_ca_topic_score_codex":0.000008185943,"about_ca_topic_score_gemma":8.042442e-7,"teacher_disagreement_score":0.481425,"about_ca_system_score_codex":0.00003869926,"about_ca_system_score_gemma":0.00006558884,"threshold_uncertainty_score":0.91449237},"labels":[],"label_agreement":null},{"id":"W3008310671","doi":"10.1093/ije/dyz237","title":"A tutorial on sample size calculation for multiple-period cluster randomized parallel, cross-over and stepped-wedge trials using the Shiny CRT Calculator","year":2019,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":250,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Collaboration for Leadership in Applied Health Research and Care - Greater Manchester; National Institute for Health and Care Research; NHS Blood and Transplant","keywords":"Sample size determination; Calculator; Cluster analysis; Cluster (spacecraft); Computer science; Cluster randomised controlled trial; Statistics; Sample (material); Statistical power; Randomized controlled trial; Data mining; Mathematics; Medicine","score_opus":0.5529050393700715,"score_gpt":0.614777663946381,"score_spread":0.06187262457630949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008310671","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3437035,0.00009355142,0.6413427,0.0027034276,0.0100155,0.0018819638,0.00021584716,0.00001225635,0.000031218075],"genre_scores_gemma":[0.26007184,0.000039599297,0.73304594,0.001956423,0.00472414,0.000046379708,0.00000390544,0.000037472928,0.00007432119],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985866,0.008813848,0.004175599,0.0003463528,0.00047166058,0.0003265013],"domain_scores_gemma":[0.34307897,0.6529865,0.0028881445,0.00024639687,0.00067392434,0.00012603702],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054949798,0.00025859103,0.002603902,0.00011037092,0.00008621045,0.000074938514,0.00046784047,0.0003440981,0.00036861512],"category_scores_gemma":[0.85575116,0.00014760194,0.00092109287,0.000052202515,0.00039055452,0.00014269866,0.00011012545,0.00045257685,0.0000052303544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.52720374,0.0004352576,0.026994672,0.00012318273,0.0041951123,0.000017083541,0.0005179259,0.0068062805,0.0013880971,0.42048132,0.006031785,0.0058055264],"study_design_scores_gemma":[0.1477391,0.00027705115,0.0018409841,0.00014163749,0.00032028928,0.0000617969,0.00001845603,0.04570004,0.000049020626,0.8019127,0.0017517089,0.00018718728],"about_ca_topic_score_codex":0.000050233124,"about_ca_topic_score_gemma":0.0000045359216,"teacher_disagreement_score":0.80080134,"about_ca_system_score_codex":0.00015910364,"about_ca_system_score_gemma":0.0001166683,"threshold_uncertainty_score":0.9731281},"labels":[],"label_agreement":null},{"id":"W3008358016","doi":"10.1136/bmjopen-2019-034306","title":"Patient burden and clinical advances associated with postapproval monotherapy cancer drug trials: a retrospective cohort study","year":2020,"lang":"en","type":"article","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Retrospective cohort study; Cohort study; Clinical trial; Drug; Cancer drugs; Epidemiology; MEDLINE; Intensive care medicine; Internal medicine; Pharmacology","score_opus":0.6232461939357197,"score_gpt":0.6445325353801237,"score_spread":0.021286341444404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008358016","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9224866,0.00015309794,0.0046088547,0.0058396887,0.00071743573,0.06258958,0.0005529385,0.00018723436,0.0028645538],"genre_scores_gemma":[0.49466893,0.00037456912,0.49054253,0.0025857845,0.002280144,0.008792941,0.000009035999,0.00023402691,0.0005120345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9897411,0.006268532,0.0020797912,0.0008673638,0.0007556515,0.00028758243],"domain_scores_gemma":[0.95501924,0.04238475,0.001485936,0.0004923436,0.00031847405,0.00029925947],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019209048,0.0002875224,0.0024843407,0.000023097004,0.00011400192,0.00019011502,0.00046509085,0.00012622224,0.00035145014],"category_scores_gemma":[0.19852212,0.00019275396,0.00013859749,0.0002826693,0.00019219994,0.0001698796,0.0004205295,0.00043523635,0.000006880152],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010908991,0.0011600866,0.8978586,0.00006325359,0.0029826134,0.00008734273,0.0046759173,0.000005859255,0.000006684722,0.0022270742,0.0042449,0.075778626],"study_design_scores_gemma":[0.03753883,0.014996494,0.5648503,0.00091889454,0.0025951813,0.0000039353254,0.0071766498,0.0014082026,0.00010188221,0.36705214,0.0016709157,0.0016865876],"about_ca_topic_score_codex":0.0002353072,"about_ca_topic_score_gemma":0.00022383363,"teacher_disagreement_score":0.4859337,"about_ca_system_score_codex":0.00009911003,"about_ca_system_score_gemma":0.00020185659,"threshold_uncertainty_score":0.8082291},"labels":[],"label_agreement":null},{"id":"W3008510792","doi":"10.1186/s12874-020-0899-1","title":"A systematic survey of randomised trials that stopped early for reasons of futility","year":2020,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interim; Interim analysis; Early stopping; Sample size determination; Clinical trial; Medicine; Data monitoring committee; Protocol (science); Sample (material); Psychological intervention; Set (abstract data type); Generalizability theory; Research design; Medical physics; Statistics; Alternative medicine; Computer science; Internal medicine; Psychiatry","score_opus":0.9898736424568401,"score_gpt":0.7985629352472344,"score_spread":0.19131070720960563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008510792","genre_codex":"methods","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042077127,0.48061273,0.50444615,0.000050661274,0.00063789665,0.012810434,0.0013331894,0.00003351225,0.000071223825],"genre_scores_gemma":[0.0000026025687,0.49905446,0.49832517,0.000007992963,0.00024721038,0.0021848218,0.000022870983,0.00008837407,0.00006648602],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16426763,0.8089391,0.01682447,0.0018856257,0.0064518135,0.0016313405],"domain_scores_gemma":[0.022849,0.9651564,0.0062523573,0.0021829766,0.0022606724,0.0012986277],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.7454215,0.000763649,0.03770428,0.00065952743,0.00010038654,0.000028134817,0.0029657986,0.0029048487,0.0010884089],"category_scores_gemma":[0.99814045,0.00048128306,0.0039168797,0.0016045338,0.0025770094,0.00003285494,0.0009457489,0.002756268,0.000023464512],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070809443,0.00031198032,0.000008964465,0.7011159,0.0019031769,0.000015947833,0.000075352815,8.87175e-9,0.0000011810475,0.020889958,0.0012001379,0.26739645],"study_design_scores_gemma":[0.027919473,0.002439901,0.000044840177,0.27225223,0.00991961,0.000029103352,0.00015812895,0.00014229381,0.000051101524,0.673228,0.0129198395,0.0008954736],"about_ca_topic_score_codex":0.00032835625,"about_ca_topic_score_gemma":0.00019333092,"teacher_disagreement_score":0.6523381,"about_ca_system_score_codex":0.0001687452,"about_ca_system_score_gemma":0.008487181,"threshold_uncertainty_score":0.9998247},"labels":[],"label_agreement":null},{"id":"W3008867523","doi":"10.1136/fmch-2019-000262","title":"Variable selection strategies and its importance in clinical prediction modelling","year":2020,"lang":"en","type":"article","venue":"Family Medicine and Community Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":995,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Akaike information criterion; Feature selection; Selection (genetic algorithm); Bayesian information criterion; Variable (mathematics); Statistic; Computer science; Model selection; Bayesian probability; Statistics; Machine learning; Mathematics; Artificial intelligence","score_opus":0.7929098891837675,"score_gpt":0.5963941095425003,"score_spread":0.1965157796412672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008867523","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56166005,0.0012488103,0.43022215,0.0042769816,0.00022400539,0.00057096634,0.000023273436,0.00011786257,0.0016559095],"genre_scores_gemma":[0.6571102,0.0027536522,0.33446673,0.005197659,0.00042264463,0.00001534603,0.00000586435,0.00001957995,0.000008304338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99488217,0.0033112315,0.0011994393,0.00021051643,0.00018401345,0.00021260638],"domain_scores_gemma":[0.9792271,0.019989492,0.00024904512,0.0001785775,0.00007177663,0.0002839926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010053014,0.00012745266,0.00067671435,0.000041620435,0.00023455403,0.00001742101,0.00010644515,0.0001357157,0.000015949312],"category_scores_gemma":[0.01944612,0.00010725082,0.000018808501,0.00027343738,0.00012374778,0.00012390703,0.00007031023,0.0014981419,7.512419e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091650593,0.001075353,0.04875666,0.004643594,0.00012029287,0.000009048196,0.012407998,0.00041038796,0.00014343011,0.8972015,0.008274673,0.026040584],"study_design_scores_gemma":[0.0019210397,0.0022646175,0.011195764,0.00045152043,0.000035626003,0.0000040723444,0.007193748,0.111558475,0.0000014917179,0.8648952,0.00036554644,0.000112888956],"about_ca_topic_score_codex":0.0009129336,"about_ca_topic_score_gemma":0.00011832747,"teacher_disagreement_score":0.11114808,"about_ca_system_score_codex":0.000029661178,"about_ca_system_score_gemma":0.00019206661,"threshold_uncertainty_score":0.9888135},"labels":[],"label_agreement":null},{"id":"W3008923208","doi":"10.1002/sim.8507","title":"A bootstrap semiparametric homogeneity test for the distributions of multigroup proportional data, with applications to analysis of quality of life outcomes in clinical trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Canadian Cancer Society","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Statistics; Mathematics; Homogeneity (statistics); Nonparametric statistics; Type I and type II errors; Statistical hypothesis testing; Parametric statistics; Likelihood-ratio test; Wald test; Test statistic; Null hypothesis; Empirical likelihood; Econometrics; Confidence interval","score_opus":0.8162034951521221,"score_gpt":0.6841353634128662,"score_spread":0.1320681317392559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008923208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073818727,0.000059511094,0.9434448,0.0022050354,0.00005509027,0.002448392,0.044384535,0.000008240609,0.000012536539],"genre_scores_gemma":[0.30048904,0.000053385713,0.69875234,0.0001389727,0.000078179255,0.00021554988,0.00025777624,0.000011122808,0.0000035998266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902402,0.0017146043,0.006576452,0.00048626374,0.00077666494,0.00020581191],"domain_scores_gemma":[0.5117924,0.48377645,0.002503215,0.0010629056,0.0006379201,0.00022707655],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031074725,0.00017629849,0.003190238,0.00026588776,0.000030896048,0.0000036285774,0.0006431569,0.00011929604,0.00010096854],"category_scores_gemma":[0.775755,0.000105331295,0.00016814495,0.0028402922,0.00086390367,0.00002183645,0.0001382451,0.00030346416,4.0282364e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011173222,0.0023477306,0.6918463,0.0010112406,0.002050693,0.0000016079376,0.00024617638,0.00028918678,0.00014607434,0.2875761,0.0022454287,0.0111221],"study_design_scores_gemma":[0.004940282,0.0011002945,0.80686927,0.00011819403,0.0040588393,1.4125801e-7,0.00042537315,0.015829599,0.00006758717,0.16630661,0.00009317839,0.00019064387],"about_ca_topic_score_codex":0.00024709626,"about_ca_topic_score_gemma":0.00047291772,"teacher_disagreement_score":0.7446803,"about_ca_system_score_codex":0.000028559967,"about_ca_system_score_gemma":0.0002611533,"threshold_uncertainty_score":0.9977125},"labels":[],"label_agreement":null},{"id":"W3009777504","doi":"10.1016/s1470-2045(20)30092-9","title":"Statistical significance and clinical evidence – Authors' reply","year":2020,"lang":"en","type":"letter","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Observational study; Medicine; Confounding; Bonferroni correction; Clinical trial; Randomized controlled trial; Publication bias; Alternative medicine; Medical physics; Family medicine; Meta-analysis; Internal medicine; Statistics; Pathology","score_opus":0.8081831323988989,"score_gpt":0.6434700718790197,"score_spread":0.16471306051987922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009777504","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029305822,0.00020472678,0.08240694,0.9103821,0.0030271746,0.0010976491,0.00044474498,0.00023106558,0.002176282],"genre_scores_gemma":[0.00003926976,0.00068846205,0.44243127,0.535697,0.0203881,0.0000917971,0.00000744462,0.000070313865,0.000586352],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97845197,0.016075168,0.0024757038,0.0013732457,0.0007040291,0.0009198725],"domain_scores_gemma":[0.6407304,0.3569089,0.0008750665,0.0011574704,0.00012535091,0.00020281553],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.014154453,0.00052073674,0.0035642171,0.000040637293,0.00016815116,0.00008946879,0.0014262146,0.0015525691,0.000688881],"category_scores_gemma":[0.40939498,0.0003432887,0.00025037734,0.00020094837,0.0024227314,0.000046505094,0.0006518733,0.008254902,0.0002810246],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041945712,0.000051064355,0.00014303211,0.00048781844,0.00020729765,0.001357533,0.00006462126,4.00234e-8,0.0000035224923,0.025245564,0.95535666,0.016663373],"study_design_scores_gemma":[0.00052242243,0.00068335526,0.00020805736,0.00014382796,0.00043792994,0.00003672298,0.0000074180043,0.00007587728,0.0000017303495,0.48720786,0.5104384,0.00023640298],"about_ca_topic_score_codex":0.000025329786,"about_ca_topic_score_gemma":0.00000804082,"teacher_disagreement_score":0.46196228,"about_ca_system_score_codex":0.00014579942,"about_ca_system_score_gemma":0.00050465594,"threshold_uncertainty_score":0.9999019},"labels":[],"label_agreement":null},{"id":"W3010442290","doi":"10.1002/sim.8519","title":"Sample size and power calculations for open cohort longitudinal cluster randomized trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Health and Medical Research Council; Medical Research Council Canada","keywords":"Sample size determination; Statistics; Cohort; Sample (material); Sampling (signal processing); Cluster sampling; Cluster (spacecraft); Statistical power; Autocorrelation; Econometrics; Mathematics; Psychology; Demography; Computer science; Population","score_opus":0.6232407975323997,"score_gpt":0.6131850654261651,"score_spread":0.01005573210623456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010442290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032676634,0.00006682595,0.98229223,0.008457235,0.00051314896,0.0056926985,0.001840281,0.000031710133,0.0007790916],"genre_scores_gemma":[0.010792845,0.00007436935,0.9855385,0.0025195312,0.00043893338,0.0004617998,0.000026678697,0.000044383985,0.00010299146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930314,0.0029233736,0.0027191543,0.0005578466,0.00044147082,0.00032677766],"domain_scores_gemma":[0.33087653,0.6677544,0.00057331665,0.0002860741,0.00023587245,0.0002738225],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02782529,0.0002572004,0.0034913574,0.00005576249,0.00009159881,0.000055211043,0.0003372523,0.00014491452,0.0018694499],"category_scores_gemma":[0.9372823,0.00018176758,0.00010410559,0.0002148895,0.00063845527,0.000052836636,0.00022068324,0.00028805636,0.0000044512594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027980588,0.00007402827,0.0011579087,0.0002854194,0.000341569,0.000018044482,0.0006465451,0.00000720816,0.000018695368,0.9004258,0.066535555,0.0025086533],"study_design_scores_gemma":[0.12014097,0.00029555606,0.0009792091,0.00012738701,0.0006954227,0.0000018627427,0.000084503255,0.0061684875,0.000006671675,0.8705961,0.00072176725,0.00018206889],"about_ca_topic_score_codex":0.00012867109,"about_ca_topic_score_gemma":0.00003078949,"teacher_disagreement_score":0.909457,"about_ca_system_score_codex":0.00005015614,"about_ca_system_score_gemma":0.00009283315,"threshold_uncertainty_score":0.999043},"labels":[],"label_agreement":null},{"id":"W3011439370","doi":"10.1183/13993003.00138-2020","title":"Avoiding immortal time bias in observational studies","year":2020,"lang":"en","type":"letter","venue":"European Respiratory Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Observational study; Psychology; Statistics; Mathematics","score_opus":0.8975412588780904,"score_gpt":0.5763419801818803,"score_spread":0.3211992786962101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011439370","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013272279,0.006300527,0.009772746,0.9168384,0.013464712,0.0022234619,0.0007062513,0.0007650577,0.036656573],"genre_scores_gemma":[0.00009686561,0.00010311152,0.1650319,0.79834926,0.034640666,0.000010088407,0.000008599651,0.00037285622,0.0013866486],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9732625,0.02108017,0.003068076,0.00067913,0.0012802868,0.00062986993],"domain_scores_gemma":[0.9334682,0.06396336,0.0015827749,0.00043482403,0.0003422861,0.00020853378],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017709099,0.0005762036,0.0015789667,0.00029633284,0.00035062025,0.00021471232,0.00092072267,0.00030681555,0.0008482545],"category_scores_gemma":[0.29706463,0.00048291511,0.0004738095,0.00035257352,0.00027317635,0.0001402544,0.00038166757,0.010757575,0.00096149935],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039876395,0.000034103596,0.00015881468,0.00019509066,0.00028426858,0.020753905,0.00018427004,0.0000038536346,0.00006503064,0.00039361027,0.97552603,0.0023611342],"study_design_scores_gemma":[0.0013841775,0.0002889565,0.0005578876,0.0013834013,0.00022809966,0.00022818056,0.000075221324,0.000047572463,0.000028793724,0.22282742,0.77213025,0.00082003704],"about_ca_topic_score_codex":1.6771607e-7,"about_ca_topic_score_gemma":2.3685386e-7,"teacher_disagreement_score":0.27935553,"about_ca_system_score_codex":0.00024299996,"about_ca_system_score_gemma":0.00022142834,"threshold_uncertainty_score":0.99981636},"labels":[],"label_agreement":null},{"id":"W3011730613","doi":"","title":"A different perspective of “cross-world independence assumption” and the utility of natural effects versus controlled effects.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Independence (probability theory); Perspective (graphical); Natural (archaeology); Mediation; Positive economics; Natural experiment; Econometrics; Economics; Political science; Computer science; Mathematics; Geography; Statistics; Artificial intelligence; Law","score_opus":0.3898224111680776,"score_gpt":0.414987509378773,"score_spread":0.025165098210695402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011730613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.874501,0.00038550774,0.11421886,0.00019179136,0.002336025,0.0045887358,0.00015054794,0.00011060426,0.0035169593],"genre_scores_gemma":[0.9926822,0.00009736919,0.006918873,0.000023009108,0.000086535394,0.000008894225,0.0000015763184,0.000024607416,0.00015692516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99469674,0.0030684723,0.0007475189,0.0009249231,0.00029787637,0.0002644713],"domain_scores_gemma":[0.8685075,0.12883767,0.0011474781,0.0008476297,0.00051331526,0.00014637307],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020627659,0.00042922515,0.0023414511,0.00012880808,0.00008740213,0.000036096888,0.0007447041,0.00032150437,0.000061982435],"category_scores_gemma":[0.08568579,0.00030819603,0.00069274736,0.0003117721,0.0017536061,0.000061109255,0.0013214378,0.001468168,0.0000031891382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029190412,0.00030502112,0.0025225438,0.0024163267,0.0016822474,0.00007767712,0.00033530613,0.00006136046,0.00007538692,0.9630356,0.000042304553,0.0002558534],"study_design_scores_gemma":[0.02756386,0.00020092611,0.0124540245,0.00036772076,0.0016364226,5.729561e-7,0.000088149,0.029148327,0.000985349,0.9272988,7.7155534e-7,0.00025506533],"about_ca_topic_score_codex":0.0001223436,"about_ca_topic_score_gemma":0.000054002358,"teacher_disagreement_score":0.1261892,"about_ca_system_score_codex":0.00013818659,"about_ca_system_score_gemma":0.000107074666,"threshold_uncertainty_score":0.999937},"labels":[],"label_agreement":null},{"id":"W3012873319","doi":"10.1245/s10434-020-08394-w","title":"ASO Author Reflections: Completion Axillary Dissection Can Be Avoided but Inconsistent Trial Design Complicates Choosing Between Alternative Strategies","year":2020,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; St. Michael's Hospital","funders":"","keywords":"Medicine; Surgical oncology; Axillary Dissection; General surgery; Dissection (medical); Surgery; Medical physics; Internal medicine; Breast cancer; Mastectomy; Cancer","score_opus":0.893633462227729,"score_gpt":0.6404908187308922,"score_spread":0.2531426434968368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012873319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12221025,0.00014965743,0.67899525,0.18507981,0.0016744386,0.0037595853,0.0004589613,0.00047105987,0.0072009657],"genre_scores_gemma":[0.7204078,0.00050055486,0.27603287,0.0010036818,0.0017664791,0.0001526988,0.000034587665,0.000057278874,0.000044081684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99240553,0.004263536,0.0018611915,0.0005772942,0.00047390946,0.00041855185],"domain_scores_gemma":[0.93955445,0.05842991,0.00092498405,0.0002630179,0.000476501,0.0003511013],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0037083053,0.0002965848,0.0016224004,0.00010993591,0.00020190477,0.000056343863,0.0003058366,0.0004111625,0.00016164908],"category_scores_gemma":[0.0126979,0.0002590683,0.00034419115,0.00040752086,0.00054607005,0.000119207994,0.0001498453,0.000632329,0.000010906285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12083921,0.004453294,0.00041376665,0.00089189404,0.0031991126,0.0006084934,0.0034096304,0.0007648601,0.010437367,0.72646517,0.024787772,0.103729434],"study_design_scores_gemma":[0.013827099,0.008524513,0.00028751724,0.00010995203,0.00030109775,0.000036529716,0.00086312136,0.0009580791,0.008930449,0.94175094,0.023969619,0.00044107749],"about_ca_topic_score_codex":0.000109003544,"about_ca_topic_score_gemma":0.000015859554,"teacher_disagreement_score":0.5981975,"about_ca_system_score_codex":0.00009553616,"about_ca_system_score_gemma":0.00026125016,"threshold_uncertainty_score":0.9999862},"labels":[],"label_agreement":null},{"id":"W3013810674","doi":"10.1155/2020/7398324","title":"Correlation Coefficients for a Study with Repeated Measures","year":2020,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; National Institute of General Medical Sciences; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; Elan; Northern California Institute for Research and Education; Alzheimer's Association; Fujirebio US; Pfizer; Biogen; BioClinica; Zhejiang Gongshang University; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Merck; Alzheimer's Drug Discovery Foundation; IXICO; Takeda Pharmaceutical Company; AbbVie; Foundation for the National Institutes of Health; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Pearson product-moment correlation coefficient; Correlation; Statistics; Correlation coefficient; Mathematics; Partial correlation; Correlation ratio; Mean squared error; Distance correlation; Fisher transformation; Interclass correlation; Intraclass correlation; Psychometrics; Geometry","score_opus":0.6271278416503825,"score_gpt":0.6103846208891412,"score_spread":0.01674322076124124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013810674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052225357,0.00003128104,0.9897815,0.002557261,0.00009046381,0.001776841,0.000009343157,0.00007801359,0.00045278706],"genre_scores_gemma":[0.045024566,0.0000017256247,0.9540095,0.000618641,0.00013709495,0.00014287037,0.0000028457184,0.000028713874,0.000034043627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965657,0.0011679354,0.0010728788,0.00046384538,0.00051784236,0.00021180876],"domain_scores_gemma":[0.92854387,0.070639126,0.0002159422,0.00014480473,0.00024568196,0.00021056368],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006106722,0.00021226087,0.00091792963,0.000085490414,0.00007556059,0.000017139662,0.00014019947,0.00008867319,0.000090449445],"category_scores_gemma":[0.1260211,0.00013666425,0.000041056366,0.0003992074,0.0002836871,0.00003884561,0.00005828535,0.00024221926,0.0000030054566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028114805,0.0021678912,0.0028160647,0.0018266086,0.0003488216,0.000049701095,0.008949299,0.0026647686,0.00018143673,0.80748355,0.0014223009,0.16927806],"study_design_scores_gemma":[0.0037109077,0.0016671176,0.00069486035,0.00019714094,0.00013884291,0.000008317028,0.0008316207,0.15911415,0.000012795732,0.83339167,0.00009061482,0.00014195906],"about_ca_topic_score_codex":0.0000013780217,"about_ca_topic_score_gemma":5.3161875e-7,"teacher_disagreement_score":0.16913609,"about_ca_system_score_codex":0.000021743914,"about_ca_system_score_gemma":0.00003284326,"threshold_uncertainty_score":0.8813408},"labels":[],"label_agreement":null},{"id":"W3014840511","doi":"10.1111/biom.13247","title":"Discussion on “Predictively consistent prior effective sample sizes,” by Beat Neuenschwander, Sebastian Weber, Heinz Schmidli, and Anthony O'Hagan","year":2020,"lang":"en","type":"letter","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Multivariate statistics; Prior probability; Binary number; Dirichlet distribution; Mathematics; Statistics; Applied mathematics; Mathematical analysis","score_opus":0.28294551863920875,"score_gpt":0.45626916965863934,"score_spread":0.1733236510194306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014840511","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008040217,0.0019979302,0.26980534,0.67098576,0.008507956,0.00989799,0.03503719,0.0012735545,0.0016902563],"genre_scores_gemma":[0.0014947159,0.00085389544,0.71400934,0.2736802,0.006689266,0.00039889774,0.00072135695,0.0006524203,0.0014998771],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99110746,0.0024265,0.0016848121,0.0019749256,0.0018311098,0.00097516266],"domain_scores_gemma":[0.85506475,0.14221926,0.0009598061,0.0009182428,0.00028399576,0.00055396126],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0019653887,0.0011415384,0.002612801,0.0012712062,0.0003680532,0.00027940792,0.00066588377,0.0019609574,0.00024566991],"category_scores_gemma":[0.24413502,0.0007735371,0.00051406026,0.003260778,0.0008179226,0.000090694855,0.00060458074,0.0033519752,0.000077160956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029618587,0.00029650662,0.00013022215,0.0011350296,0.00048012324,0.00036475228,0.0000858711,9.7697274e-8,0.00022694483,0.0005101298,0.92658323,0.06989091],"study_design_scores_gemma":[0.005470307,0.00416957,0.0007676046,0.0013408451,0.0017923379,0.000038579303,0.00007929499,0.00024462875,0.0014987928,0.2156957,0.7666428,0.0022595557],"about_ca_topic_score_codex":0.00003757442,"about_ca_topic_score_gemma":0.0000016162636,"teacher_disagreement_score":0.44420403,"about_ca_system_score_codex":0.00036582522,"about_ca_system_score_gemma":0.00015620892,"threshold_uncertainty_score":0.99947155},"labels":[],"label_agreement":null},{"id":"W3015122744","doi":"10.1002/sim.8595","title":"Graphical approaches for the control of generalized error rates","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"False discovery rate; Multiple comparisons problem; Graphical model; Context (archaeology); Word error rate; Control (management); Statistical hypothesis testing","score_opus":0.6677080684007569,"score_gpt":0.5681343876762122,"score_spread":0.09957368072454476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015122744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002651588,0.0002264724,0.984962,0.012194999,0.00033286578,0.0011194004,0.00071468926,0.000022712022,0.00016172456],"genre_scores_gemma":[0.1551751,0.000060207083,0.84273595,0.0013259342,0.0005057311,0.0001361439,0.000008165896,0.000030326637,0.000022433838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723,0.0005966699,0.0012306295,0.00028617264,0.00040220452,0.00025431803],"domain_scores_gemma":[0.87514436,0.12403581,0.00030055578,0.00026449797,0.00013474168,0.00012000525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036815363,0.000176648,0.0009880277,0.000045066816,0.00004702329,0.00000589287,0.00034002413,0.00010813701,0.00025286718],"category_scores_gemma":[0.23973274,0.00010232095,0.000073171825,0.00027578883,0.00081856805,0.00001258582,0.000038381655,0.00030022464,0.0000017071109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005578937,0.00006979813,0.0003882257,0.0003559461,0.00011393683,0.0000061357478,0.00045049173,0.000025323216,0.0001645947,0.97513425,0.014535346,0.008198043],"study_design_scores_gemma":[0.0049969126,0.00048445302,0.00053893885,0.00006230995,0.00028033223,8.031401e-7,0.00025567345,0.06738761,0.00009565438,0.9251791,0.0006123212,0.000105839004],"about_ca_topic_score_codex":0.000014512845,"about_ca_topic_score_gemma":0.000010495848,"teacher_disagreement_score":0.2360512,"about_ca_system_score_codex":0.000012022579,"about_ca_system_score_gemma":0.000042408086,"threshold_uncertainty_score":0.7666713},"labels":[],"label_agreement":null},{"id":"W3015442555","doi":"10.1038/s41409-020-0871-z","title":"Precision medicine: Statistical methods for estimating adaptive treatment strategies","year":2020,"lang":"en","type":"editorial","venue":"Bone Marrow Transplantation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Precision medicine; Marketing buzz; Computer science; Replicate; Point (geometry); Statistics; Medicine; Operations research; Mathematics; Pathology","score_opus":0.35063200344842793,"score_gpt":0.5732529388532968,"score_spread":0.22262093540486882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015442555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015954264,0.000100758836,0.7090464,0.00017039396,0.28389016,0.0018077904,0.004111268,0.00018951934,0.0006821203],"genre_scores_gemma":[0.000012300555,0.00022203408,0.73293203,0.000019450257,0.26482344,0.00060075714,0.0011302365,0.00013824466,0.00012149757],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99230975,0.0025201603,0.0023496074,0.0012273127,0.0010430382,0.00055012247],"domain_scores_gemma":[0.77725506,0.2208679,0.0008273182,0.00038840878,0.00039732587,0.00026398484],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0044510616,0.00083174865,0.002378787,0.00015822942,0.00020464638,0.0001224575,0.0003387996,0.0012013365,0.00028948637],"category_scores_gemma":[0.1032694,0.0006627096,0.000321339,0.00021563831,0.00030258304,0.00015049553,0.000027110838,0.00075095944,0.00002103502],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057878057,0.00025487944,3.71235e-7,0.004252338,0.0005680993,0.000106867104,0.0016383263,0.00004940831,0.0005742807,0.06396601,0.56103396,0.36176765],"study_design_scores_gemma":[0.0050547766,0.0035607256,0.000003975217,0.0011602064,0.0033564812,0.0000073896745,0.00019562624,0.013146778,0.00030962672,0.9283273,0.04415594,0.0007211488],"about_ca_topic_score_codex":0.000088386645,"about_ca_topic_score_gemma":0.000024626761,"teacher_disagreement_score":0.8643613,"about_ca_system_score_codex":0.00029233747,"about_ca_system_score_gemma":0.00061694963,"threshold_uncertainty_score":0.9995824},"labels":[],"label_agreement":null},{"id":"W3015662163","doi":"10.1111/biom.13277","title":"A powerful procedure that controls the false discovery rate with directional information","year":2020,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"False discovery rate; Multiple comparisons problem; Computer science; Statistical hypothesis testing; Data mining; Control (management); Value (mathematics); Statistics; Computational biology; Machine learning; Artificial intelligence; Mathematics; Biology; Gene; Genetics","score_opus":0.3902658894803887,"score_gpt":0.46597937872472,"score_spread":0.0757134892443313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015662163","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025673242,0.00013998956,0.95836,0.010230237,0.000684667,0.0015550228,0.0004762547,0.00024179235,0.0026387905],"genre_scores_gemma":[0.57800514,0.0000846176,0.41272566,0.007774999,0.0007594168,0.0001171141,0.000018161632,0.00005491314,0.00045998825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998173,0.0003107236,0.0005095459,0.00019465113,0.0005876894,0.00022440532],"domain_scores_gemma":[0.9701871,0.028883075,0.00036698286,0.00023861493,0.00018780389,0.00013642172],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018145991,0.0001695297,0.00036764576,0.00020132778,0.000096075695,0.00024517786,0.00027037496,0.00011343603,0.000074508775],"category_scores_gemma":[0.13121147,0.00009193143,0.000092724826,0.0027855805,0.00014252577,0.00042513668,0.000079320904,0.00024132553,0.00009209076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0073496574,0.0012997768,0.023234395,0.0023328583,0.0017982188,0.00006158236,0.0037615981,0.00008051663,0.0023522442,0.67206806,0.17882888,0.10683219],"study_design_scores_gemma":[0.011272416,0.0027164712,0.03202861,0.00024224419,0.00085392065,0.000047958845,0.0016239051,0.0039685965,0.007876395,0.7914894,0.14629398,0.001586096],"about_ca_topic_score_codex":0.0000037327236,"about_ca_topic_score_gemma":9.1903223e-7,"teacher_disagreement_score":0.55233186,"about_ca_system_score_codex":0.00004115747,"about_ca_system_score_gemma":0.0000968636,"threshold_uncertainty_score":0.8761067},"labels":[],"label_agreement":null},{"id":"W3015891597","doi":"10.1038/s41571-020-0368-0","title":"Informative censoring — a neglected cause of bias in oncology trials","year":2020,"lang":"en","type":"review","venue":"Nature Reviews Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":96,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Censoring (clinical trials); Medicine; Clinical trial; Oncology; Internal medicine; Randomized controlled trial; Dropout (neural networks); Clinical endpoint; Disease; Pathology","score_opus":0.9448741470251816,"score_gpt":0.7660528400446187,"score_spread":0.17882130698056287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015891597","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010000907,0.9788648,0.0009221703,0.0005368806,0.0045920936,0.009225198,0.00035055875,0.0001061552,0.0054011843],"genre_scores_gemma":[2.6565928e-7,0.6959756,0.3008322,0.00082886335,0.001593243,0.0005754088,0.000028962655,0.000108317494,0.00005715495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81599087,0.135065,0.044636954,0.0020258445,0.0009894653,0.0012918811],"domain_scores_gemma":[0.21700656,0.75380206,0.025999,0.0017849146,0.00057816046,0.000829318],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.08276943,0.0014290422,0.05556507,0.00061674166,0.00005413397,0.000025640733,0.0019146254,0.012242589,0.00058640726],"category_scores_gemma":[0.9203298,0.0009274833,0.0064742076,0.0026744837,0.0008306735,0.000120832694,0.0008807246,0.01565328,0.00039012288],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029501767,0.00093032344,0.000005272225,0.027207227,0.00092335965,0.0002667699,0.0000828792,3.6313914e-8,9.2394835e-8,0.014050207,0.0107505545,0.9454883],"study_design_scores_gemma":[0.0026990864,0.002368226,0.000006447934,0.025311878,0.0059405896,0.000060316826,0.000014703966,0.0000051508214,4.943585e-7,0.046851825,0.9160787,0.0006625688],"about_ca_topic_score_codex":0.0000068864833,"about_ca_topic_score_gemma":0.000050467395,"teacher_disagreement_score":0.9448257,"about_ca_system_score_codex":0.001147315,"about_ca_system_score_gemma":0.004429026,"threshold_uncertainty_score":0.999846},"labels":[],"label_agreement":null},{"id":"W3016729763","doi":"10.1177/1740774520914306","title":"Bayesian methods for pilot studies","year":2020,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Public Health Ontario; St. Joseph’s Healthcare Hamilton; Impact; SickKids Foundation; University of Toronto","funders":"","keywords":"Randomized controlled trial; Frequentist inference; Prior probability; Bayesian probability; Statistics; Confidence interval; Computer science; Medicine; Bayesian inference; Mathematics; Surgery","score_opus":0.9799706100301048,"score_gpt":0.8082921533921043,"score_spread":0.17167845663800052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016729763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013814804,0.0005541355,0.9774049,0.013676389,0.004042573,0.0029290307,0.00013390598,0.00032922596,0.00079167425],"genre_scores_gemma":[0.001378086,0.00038115145,0.9847374,0.006399333,0.006455073,0.00035300126,0.0000018278356,0.00009001651,0.0002041031],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95441085,0.03441836,0.008943794,0.0012342125,0.00037270252,0.0006201089],"domain_scores_gemma":[0.08603406,0.9098885,0.0019450191,0.00081811316,0.0004954629,0.0008188281],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15724134,0.0003914534,0.0053955372,0.000043377997,0.000138841,0.00006423632,0.0006458739,0.0003762908,0.0004762738],"category_scores_gemma":[0.97591877,0.00028200352,0.0015136823,0.00032140652,0.0005368112,0.000068062225,0.00028416057,0.00061867124,0.00009540177],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037380874,0.00066375715,0.00010850411,0.00065775536,0.0018395752,0.000008786499,0.00017108516,0.00000124101,0.00047419075,0.25678837,0.12964164,0.60590696],"study_design_scores_gemma":[0.0055381786,0.0026419251,0.00002095592,0.00007939034,0.0008838752,7.3607697e-7,0.00010211727,0.00083273876,0.0009609651,0.95730877,0.031291924,0.00033840828],"about_ca_topic_score_codex":5.6495156e-7,"about_ca_topic_score_gemma":4.089328e-7,"teacher_disagreement_score":0.87547016,"about_ca_system_score_codex":0.000029846642,"about_ca_system_score_gemma":0.00012699072,"threshold_uncertainty_score":0.9999632},"labels":[],"label_agreement":null},{"id":"W3017239231","doi":"10.1016/j.jclinepi.2020.02.011","title":"The fragility of trial results involves more than statistical significance alone","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Fragility; Statistical significance; Clinical significance; Stability (learning theory); Statistical analysis; Clinical trial; Statistical power; Statistical hypothesis testing; Statistics; Medicine; Econometrics; Computer science; Mathematics; Internal medicine; Machine learning","score_opus":0.8646482945307179,"score_gpt":0.6803537811364027,"score_spread":0.18429451339431524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017239231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15814145,0.0004941341,0.71452814,0.11720365,0.0068348367,0.0013938451,0.00056605024,0.000055667428,0.000782237],"genre_scores_gemma":[0.23566878,0.0007361001,0.7557409,0.0033739489,0.004397907,0.000009801883,0.000001837134,0.000033371583,0.000037385747],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9323344,0.040917367,0.02436908,0.00072799873,0.0009114893,0.00073965936],"domain_scores_gemma":[0.15088326,0.8364107,0.010406098,0.0007206054,0.0007407544,0.00083859154],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.131073,0.00029196803,0.005850076,0.00003682973,0.000102859995,0.000012816871,0.0011324366,0.0006524595,0.000089469904],"category_scores_gemma":[0.971268,0.00016435566,0.0012453578,0.00024330313,0.0026708068,0.000068543486,0.00022018667,0.002437795,0.0000135629525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.37375233,0.0017054487,0.0140426755,0.0003392298,0.0012357647,0.00013703543,0.00031207397,0.000057767986,0.000050939834,0.43480128,0.10883254,0.06473291],"study_design_scores_gemma":[0.026102135,0.0052987295,0.016949775,0.00008482905,0.00026440163,0.000008247474,0.00010633471,0.0009078471,0.000048671496,0.94508946,0.0049752663,0.00016431183],"about_ca_topic_score_codex":0.000015267084,"about_ca_topic_score_gemma":0.00000610764,"teacher_disagreement_score":0.840195,"about_ca_system_score_codex":0.000027086746,"about_ca_system_score_gemma":0.00047209222,"threshold_uncertainty_score":0.9998636},"labels":[],"label_agreement":null},{"id":"W3018449087","doi":"10.1097/jcp.0000000000001200","title":"Statistics Commentary Series. Commentary No. 39: Moderation and Mediation","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Moderation; Mediation; Library science; Psychology; Psychiatry; Sociology; Computer science; Social science; Social psychology","score_opus":0.4755503541402956,"score_gpt":0.6156846107866031,"score_spread":0.14013425664630746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018449087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.096062265,0.00027793396,0.5056043,0.37691262,0.018773329,0.0011392318,0.0005154861,0.00008019827,0.0006345941],"genre_scores_gemma":[0.019118622,0.0015962617,0.84328824,0.1288909,0.0070321234,0.0000070724045,0.0000071461805,0.000040195024,0.000019437939],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99287266,0.0024461083,0.0037052657,0.00028890313,0.00044495933,0.00024211948],"domain_scores_gemma":[0.9511899,0.045757234,0.0018218606,0.00014682957,0.00047832128,0.0006059079],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005178827,0.00021271057,0.0012601191,0.000056349185,0.00008174935,0.00003132289,0.00029041065,0.0002652473,0.00089690305],"category_scores_gemma":[0.04542292,0.00018030549,0.00019469904,0.000116666335,0.00033977084,0.0002220956,0.00010412663,0.0011967815,0.000026921436],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065130773,0.0005931873,0.002618556,0.00012912722,0.00042092905,0.00009473434,0.00015019487,0.000008932111,0.0005331107,0.0024245186,0.9588031,0.02771053],"study_design_scores_gemma":[0.023945699,0.0066910516,0.0032980992,0.000059896982,0.0008677571,0.00006322939,0.00011632609,0.0070896363,0.00019711001,0.8676887,0.08951965,0.0004627969],"about_ca_topic_score_codex":0.0000014669198,"about_ca_topic_score_gemma":0.0000013201478,"teacher_disagreement_score":0.86928344,"about_ca_system_score_codex":0.000033065982,"about_ca_system_score_gemma":0.00006799163,"threshold_uncertainty_score":0.98204595},"labels":[],"label_agreement":null},{"id":"W3021463756","doi":"10.1101/2020.05.06.20093237","title":"How robust are the results of one of the first positive trials exploring hydroxychloroquine for treatment of COVID-19?","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Hydroxychloroquine; Coronavirus disease 2019 (COVID-19); Clinical trial; Pandemic; Clinical endpoint; Medicine; Index (typography); Robustness (evolution); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Internal medicine; Computer science","score_opus":0.8593863841429782,"score_gpt":0.5442839242960538,"score_spread":0.3151024598469244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021463756","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25127825,0.0011480338,0.49899894,0.16350055,0.0065866956,0.028243387,0.049362484,0.00020137266,0.00068030285],"genre_scores_gemma":[0.5836564,0.0006237779,0.41222566,0.0001989984,0.0012440657,0.0017054342,0.000029490544,0.00013196468,0.00018423688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99245954,0.0026933125,0.003135775,0.0006941183,0.00073736213,0.00027987294],"domain_scores_gemma":[0.7883522,0.20351484,0.0057024173,0.0018362094,0.0004259825,0.00016837563],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009176237,0.00044113904,0.0035923652,0.00007404863,0.0001022559,0.000026994168,0.0010215687,0.0003363516,0.00002394949],"category_scores_gemma":[0.4780516,0.00023634394,0.0012453361,0.00026354703,0.00054097647,0.000027043812,0.0005018909,0.0002864781,5.8589615e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12111711,0.029848482,0.012558886,0.11873919,0.05202812,0.00017186771,0.089628786,0.014991427,0.02845803,0.45864424,0.021002775,0.05281111],"study_design_scores_gemma":[0.009254866,0.0016442658,0.0015857915,0.0024219833,0.0035426924,0.0000014184675,0.0011762358,0.00054339715,0.18705663,0.7911687,0.0011766917,0.0004273286],"about_ca_topic_score_codex":0.00007667188,"about_ca_topic_score_gemma":0.00004845838,"teacher_disagreement_score":0.46887535,"about_ca_system_score_codex":0.0001634817,"about_ca_system_score_gemma":0.00026469267,"threshold_uncertainty_score":0.9637826},"labels":[],"label_agreement":null},{"id":"W3021699215","doi":"10.1016/b978-0-444-53737-9.50012-8","title":"Sequential and Group Sequential Designs in Clinical Trials Guidelines for Practitioners","year":2011,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l'Économie, de la Science et de l'Innovation - Québec","keywords":"Group (periodic table); Medicine; Computer science; Psychology; Chemistry","score_opus":0.8645984808624373,"score_gpt":0.6273572161966507,"score_spread":0.23724126466578654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021699215","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023657867,0.0005750647,0.10319231,0.0004659033,0.0057216003,0.008120559,0.001074118,0.00020681249,0.88062],"genre_scores_gemma":[0.000016384805,0.00045303453,0.66625196,0.0007169577,0.0033557874,0.00033246,0.000026037435,0.00020766722,0.32863975],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98647624,0.003195902,0.007920593,0.0012689502,0.000577608,0.0005606755],"domain_scores_gemma":[0.91310894,0.08221052,0.002897531,0.00082146004,0.00060671585,0.0003548262],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04928348,0.0007676589,0.0039149425,0.0002635202,0.000110621484,0.000098502045,0.0004282328,0.0017112485,0.00079336594],"category_scores_gemma":[0.22610515,0.0006581993,0.0012027622,0.000021840146,0.0006699985,0.00007918144,0.00026373516,0.0011848831,0.00004280974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057816406,0.000052207404,0.0000024233377,0.00029640066,0.00037089776,0.00003561145,0.00004150907,4.341507e-8,0.000024783043,0.3221383,0.0025016177,0.673958],"study_design_scores_gemma":[0.0023190898,0.00032280068,0.000002406335,0.000710597,0.001050242,0.000014077751,0.000005825209,0.000014484157,0.000028350894,0.7243756,0.27064052,0.00051599153],"about_ca_topic_score_codex":0.0000024418975,"about_ca_topic_score_gemma":0.000050174218,"teacher_disagreement_score":0.673442,"about_ca_system_score_codex":0.00010815882,"about_ca_system_score_gemma":0.00031726647,"threshold_uncertainty_score":0.99958694},"labels":[],"label_agreement":null},{"id":"W3022535777","doi":"10.1002/9781118445112.stat05244","title":"Diagnostic Tests, Likelihood Ratio","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Juravinski Hospital","funders":"","keywords":"Bayes' theorem; Diagnostic test; Test (biology); Pre- and post-test probability; Diagnostic odds ratio; Likelihood ratios in diagnostic testing; Statistics; Sensitivity (control systems); Likelihood-ratio test; Computer science; Value (mathematics); Mathematics; Medicine; Bayesian probability; Receiver operating characteristic; Engineering","score_opus":0.33548165174408023,"score_gpt":0.5105895782106822,"score_spread":0.17510792646660195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022535777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000049568807,0.0006290381,0.83676153,0.00017145202,0.0020579728,0.0016926355,0.08710032,0.0009791475,0.070602916],"genre_scores_gemma":[0.000041752075,0.0032716512,0.858749,0.00043348488,0.002206519,0.00017454942,0.002206262,0.0016248781,0.13129191],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99108124,0.0016427357,0.002640293,0.001671715,0.0015705309,0.001393462],"domain_scores_gemma":[0.90009445,0.09444387,0.0019949737,0.0021664584,0.0004886526,0.00081161904],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0018569505,0.0014125778,0.00293013,0.0004760937,0.00015053924,0.00017897165,0.0013212097,0.0013282758,0.015738536],"category_scores_gemma":[0.21073261,0.0012561172,0.00021037426,0.00046889187,0.0007077555,0.000053963424,0.00043128183,0.0018465598,0.0018015276],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028924089,0.0006494898,0.000055371438,0.00084194617,0.0002376316,0.00010620957,0.000020161096,7.914782e-7,0.000008629407,0.23205602,0.720812,0.045182783],"study_design_scores_gemma":[0.0012318227,0.00047834497,0.000114397946,0.0018538282,0.00061578245,0.000009944527,0.000023502565,0.00031517877,0.0000071651157,0.6903304,0.30382004,0.0011995926],"about_ca_topic_score_codex":0.00018979078,"about_ca_topic_score_gemma":0.0012524963,"teacher_disagreement_score":0.45827436,"about_ca_system_score_codex":0.00018901359,"about_ca_system_score_gemma":0.0005791092,"threshold_uncertainty_score":0.99996823},"labels":[],"label_agreement":null},{"id":"W3022623176","doi":"10.2147/clep.s242097","title":"&lt;p&gt;Synthetic and External Controls in Clinical Trials – A Primer for Researchers&lt;/p&gt;","year":2020,"lang":"en","type":"review","venue":"Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":258,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of British Columbia; Impact","funders":"","keywords":"Medicine; Critical appraisal; Control (management); Set (abstract data type); Key (lock); Computational biology; Computer science; Data science; Alternative medicine; Biology; Pathology; Artificial intelligence","score_opus":0.9492111274371475,"score_gpt":0.7575105690970199,"score_spread":0.19170055834012767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022623176","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011668649,0.87404394,0.108852655,0.0030612524,0.0035742451,0.0091456175,0.0007514943,0.00014782343,0.00041133186],"genre_scores_gemma":[0.0000019493832,0.61564463,0.37731823,0.0013532853,0.004015779,0.0011987565,0.000017695978,0.00018880898,0.00026087527],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6138697,0.31972584,0.056926277,0.005639709,0.0008442439,0.0029941925],"domain_scores_gemma":[0.041003685,0.9437801,0.01053829,0.0022368694,0.00036707008,0.0020739646],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.4770573,0.0014844435,0.045784768,0.00034992685,0.000133862,0.00006247226,0.0020245838,0.0066491365,0.000505089],"category_scores_gemma":[0.98902917,0.00105018,0.0078935,0.00053388556,0.0038202028,0.000074441676,0.0011964813,0.006176051,0.00030124953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012149722,0.00060310203,0.00014529093,0.005978483,0.00095610024,0.000083072504,0.0000070032534,8.94454e-8,5.1414264e-7,0.1445116,0.010506681,0.8359931],"study_design_scores_gemma":[0.0036494737,0.0012585713,0.00007637265,0.0055108923,0.002142259,0.000023900013,0.0000015692088,0.00025714835,5.7250887e-8,0.45852607,0.52802104,0.000532623],"about_ca_topic_score_codex":0.000005281159,"about_ca_topic_score_gemma":0.000013466765,"teacher_disagreement_score":0.8354605,"about_ca_system_score_codex":0.00019277817,"about_ca_system_score_gemma":0.0014599394,"threshold_uncertainty_score":0.9997905},"labels":[],"label_agreement":null},{"id":"W3022690991","doi":"10.1002/sim.8552","title":"Statistical properties of minimal sufficient balance and minimization as methods for controlling baseline covariate imbalance at the design stage of sequential clinical trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Neurological Disorders and Stroke; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences","keywords":"Covariate; Randomness; Minification; Baseline (sea); Computer science; Statistics; Type I and type II errors; Balance (ability); Mathematical optimization; Mathematics; Econometrics; Medicine","score_opus":0.7238147778658908,"score_gpt":0.6262184680458172,"score_spread":0.09759630982007361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022690991","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026605448,0.0005227058,0.98973155,0.0016064568,0.0005687471,0.0024867903,0.0023741738,0.000020659747,0.000028397528],"genre_scores_gemma":[0.03597388,0.00038131562,0.96252567,0.000497505,0.0003629176,0.00009902833,0.000027675367,0.00004432573,0.000087714354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97687715,0.015383214,0.005941861,0.00068476994,0.00068832247,0.000424685],"domain_scores_gemma":[0.70601207,0.291193,0.0017412541,0.00033411762,0.00051460596,0.00020492858],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059862334,0.00030628883,0.0028342188,0.00007136246,0.000077894016,0.000013927836,0.00030805578,0.00020295243,0.00037581133],"category_scores_gemma":[0.7289109,0.00019044073,0.0001083129,0.00027018943,0.0016751151,0.000029979825,0.00014281286,0.00037933793,0.0000013538885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03709179,0.000992804,0.001894428,0.006310393,0.0009153264,0.00005039363,0.0040407134,0.0012931331,0.046821836,0.83277357,0.012793556,0.05502208],"study_design_scores_gemma":[0.016877208,0.00433187,0.00039252988,0.0007607579,0.0012337136,0.0000053063445,0.00073277927,0.62252367,0.011309867,0.34056556,0.00085616094,0.0004105814],"about_ca_topic_score_codex":0.0000306396,"about_ca_topic_score_gemma":0.0000059501344,"teacher_disagreement_score":0.66904855,"about_ca_system_score_codex":0.000043544263,"about_ca_system_score_gemma":0.0002322096,"threshold_uncertainty_score":0.96806955},"labels":[],"label_agreement":null},{"id":"W3023339592","doi":"10.1002/sim.8557","title":"Point and interval estimation in two‐stage adaptive designs with time to event data and biomarker‐driven subpopulation selection","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Medical Research Council; National Institutes of Health; Medical Research Council Canada","keywords":"Estimator; Stage (stratigraphy); Event (particle physics); Population; Statistics; Categorical variable; Interval (graph theory); Hazard ratio; Computer science; Confidence interval; Estimation; Selection (genetic algorithm); Interval estimation; Proportional hazards model; Mathematics; Medicine; Artificial intelligence; Biology","score_opus":0.5202491863090454,"score_gpt":0.5605198589785412,"score_spread":0.0402706726694958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023339592","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016104696,0.000014500228,0.9810173,0.0015248948,0.00004936016,0.0008375586,0.00034028245,0.00002857447,0.00008282265],"genre_scores_gemma":[0.22159629,0.000009146815,0.77801,0.00021593775,0.00005422208,0.000017746708,0.00005007816,0.000021939906,0.00002460288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760205,0.000604624,0.0007835781,0.00048691218,0.00032919642,0.00019361431],"domain_scores_gemma":[0.9888368,0.01047811,0.00020429505,0.00021815527,0.00007951867,0.00018312364],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024023647,0.00017833394,0.0005552427,0.00013787992,0.000032094737,0.000017269562,0.00013769142,0.00005510081,0.00019652222],"category_scores_gemma":[0.048976418,0.00014441097,0.000005994646,0.00037870056,0.00016578352,0.00009400631,0.00015446653,0.000241262,0.0000077275035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013038122,0.00089890155,0.05557501,0.0026338124,0.0005145124,0.0006724216,0.018147133,0.004313083,0.0059569557,0.29323792,0.02675914,0.578253],"study_design_scores_gemma":[0.0024729818,0.0011429616,0.014550734,0.00046727524,0.000087376,0.0000071945565,0.00019999567,0.7764539,0.000026439237,0.2043874,0.000030783136,0.00017294986],"about_ca_topic_score_codex":0.0001439128,"about_ca_topic_score_gemma":0.0004163724,"teacher_disagreement_score":0.7721408,"about_ca_system_score_codex":0.00007972905,"about_ca_system_score_gemma":0.000037300186,"threshold_uncertainty_score":0.95903444},"labels":[],"label_agreement":null},{"id":"W3023355515","doi":"10.1002/0470011815.b2a15147","title":"Simultaneous Confidence Intervals","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Bonferroni correction; Correctness; Robust confidence intervals; Statistics; Mathematics; Multivariate statistics; Confidence region; Multiple comparisons problem; Scheffé's method; Confidence distribution; CDF-based nonparametric confidence interval; Econometrics; Algorithm; Analysis of variance","score_opus":0.17207385457339444,"score_gpt":0.4841045205608725,"score_spread":0.3120306659874781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023355515","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018092339,0.0003805602,0.30145887,0.00006522931,0.0016826743,0.0006624384,0.004026665,0.00024004205,0.6914817],"genre_scores_gemma":[0.000032769065,0.0019768,0.60482204,0.00007844581,0.0010039958,0.000014837942,0.000014983721,0.00046950183,0.3915866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99592143,0.0005406725,0.001740877,0.0006170135,0.0007211033,0.00045889223],"domain_scores_gemma":[0.9307635,0.0663887,0.0014898074,0.0009584699,0.00017226936,0.00022726298],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010350567,0.0005589072,0.0017075024,0.0002334375,0.000026667556,0.000021011423,0.0007006176,0.000729276,0.020734234],"category_scores_gemma":[0.16510896,0.0005133905,0.00020614896,0.00020989716,0.00056598365,0.000018594274,0.0001982592,0.0005433852,0.00040757764],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031019998,0.00018694813,0.000009718954,0.0007554777,0.00016474782,0.000098007185,0.000080738915,8.833226e-7,0.0000053020144,0.14552984,0.7742741,0.07886318],"study_design_scores_gemma":[0.0004867419,0.00018732682,0.0000052832393,0.00087804795,0.00034231582,0.000007212891,0.000025399813,0.000115232964,0.00004914866,0.35111564,0.6462537,0.00053394306],"about_ca_topic_score_codex":0.00007222452,"about_ca_topic_score_gemma":0.000084081286,"teacher_disagreement_score":0.30336317,"about_ca_system_score_codex":0.000048915786,"about_ca_system_score_gemma":0.0001572852,"threshold_uncertainty_score":0.9997318},"labels":[],"label_agreement":null},{"id":"W3025297962","doi":"10.1164/ajrccm-conference.2020.201.1_meetingabstracts.a1025","title":"Potential Discordance Between Bayesian and Frequentist Analyses of Randomized Trials in Critical Care Medicine","year":2020,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; Sunnybrook Hospital; University of Toronto; Sunnybrook Health Science Centre; Mount Sinai Hospital","funders":"","keywords":"Frequentist inference; Randomized controlled trial; Bayesian probability; Computer science; Medicine; Medical physics; Statistics; Artificial intelligence; Bayesian inference; Mathematics; Internal medicine","score_opus":0.7324943587557783,"score_gpt":0.6540411125205944,"score_spread":0.0784532462351839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025297962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009903149,0.0005028231,0.98036754,0.0066149845,0.00019756873,0.00090943003,0.00012694577,0.000040831885,0.0013367545],"genre_scores_gemma":[0.5604868,0.000035452947,0.43900344,0.00011782009,0.0003188467,0.000016140404,0.0000022851927,0.000012576156,0.000006657434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98823106,0.007155265,0.003526635,0.00041289796,0.0004487759,0.000225379],"domain_scores_gemma":[0.7415909,0.25730124,0.00047170473,0.00024227741,0.00014540658,0.00024844092],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011499901,0.00020287503,0.0051499726,0.00008721673,0.000028490103,0.00002015315,0.00019175543,0.00013250885,0.0008818055],"category_scores_gemma":[0.704157,0.00012906815,0.00034972237,0.00026632642,0.0009987087,0.000054156575,0.00009519881,0.00023318197,0.000001874228],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03958022,0.00024546694,0.0061398116,0.004846362,0.001185255,0.00018355838,0.002335649,0.000004978091,0.009536792,0.9070938,0.0017666393,0.027081423],"study_design_scores_gemma":[0.070090674,0.00020221395,0.00055286055,0.00024065028,0.0015976318,0.0000010411242,0.0005762803,0.00044378111,0.0028880995,0.92323405,0.0000042210886,0.000168521],"about_ca_topic_score_codex":0.00013031998,"about_ca_topic_score_gemma":0.000010274792,"teacher_disagreement_score":0.6926571,"about_ca_system_score_codex":0.000013245373,"about_ca_system_score_gemma":0.000032998087,"threshold_uncertainty_score":0.96551514},"labels":[],"label_agreement":null},{"id":"W3026023260","doi":"10.1016/j.jclinepi.2020.04.025","title":"An overview of platform trials with a checklist for clinical readers","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of British Columbia","funders":"","keywords":"Checklist; Medicine; Clinical trial; Medical physics; MEDLINE; Psychology; Pathology; Political science","score_opus":0.9831555363446806,"score_gpt":0.8034965836444816,"score_spread":0.17965895270019894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026023260","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005084929,0.8355852,0.15632899,0.0010826392,0.0038993615,0.0024352733,0.00051908067,0.000033289125,0.00011113122],"genre_scores_gemma":[4.256458e-7,0.52791744,0.46617708,0.00071869744,0.005016352,0.000039113296,0.000008667919,0.00010252253,0.00001968481],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7723377,0.123850875,0.09977867,0.0017824308,0.0010435646,0.0012067975],"domain_scores_gemma":[0.08248743,0.8438683,0.0695947,0.0014285852,0.0011186461,0.0015023124],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.43032318,0.0010594818,0.07683411,0.0002583585,0.00006299204,0.00002143377,0.0022393116,0.003976396,0.00024780937],"category_scores_gemma":[0.96680707,0.00058449,0.015187721,0.00047231655,0.001853308,0.00015999515,0.00019686409,0.005333739,0.000015985977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030868556,0.00097207545,0.000129657,0.020086622,0.003910355,0.0000621636,0.000013100056,5.392331e-7,1.5478335e-8,0.0593193,0.01603388,0.89638543],"study_design_scores_gemma":[0.0032459665,0.008656575,0.00003352133,0.013557683,0.00971359,0.00012658742,0.000018641553,0.000030115107,1.06877316e-7,0.40065846,0.56358707,0.00037165915],"about_ca_topic_score_codex":0.0000037216992,"about_ca_topic_score_gemma":0.0000034786985,"teacher_disagreement_score":0.8960138,"about_ca_system_score_codex":0.00008727506,"about_ca_system_score_gemma":0.002963554,"threshold_uncertainty_score":0.9996607},"labels":[],"label_agreement":null},{"id":"W3026247088","doi":"10.1245/s10434-020-08589-1","title":"ASO Author Reflections: Current Issues in Conduct and Reporting of Noninferiority Randomized Controlled Trials in the Surgical Management of Cancer Patients","year":2020,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University; University of Ottawa; Ottawa Hospital; Princess Margaret Cancer Centre; St Joseph's Health Care; University of Toronto; University Health Network","funders":"","keywords":"Surgical oncology; Medicine; Randomized controlled trial; General surgery; Medical physics; MEDLINE; Oncology; Surgery","score_opus":0.8330263668777088,"score_gpt":0.6983773574515845,"score_spread":0.13464900942612434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026247088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95096797,0.004967573,0.0003888111,0.031374197,0.00078880764,0.0069563794,0.00010435781,0.000023440425,0.0044284686],"genre_scores_gemma":[0.9380455,0.022953615,0.03802944,0.00014043628,0.00019783837,0.00058643275,0.0000033032456,0.000019102963,0.00002432888],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9690577,0.017891534,0.011804026,0.0003906953,0.00056226115,0.00029383262],"domain_scores_gemma":[0.741863,0.24712083,0.010060117,0.00029226666,0.0005276266,0.00013612973],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.070687205,0.0002004879,0.009334988,0.000117220996,0.000022055265,0.000007878781,0.00020260399,0.0002166391,0.00018066078],"category_scores_gemma":[0.18093099,0.00011205231,0.0007401706,0.00042029505,0.0005142938,0.000040107414,0.00013083537,0.00039970587,4.6906962e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5323449,0.007046337,0.013734907,0.0031698942,0.002356247,0.0005388298,0.003173245,0.00003039354,0.00008010948,0.3158735,0.0019040931,0.119747594],"study_design_scores_gemma":[0.48318312,0.0021601154,0.0028380798,0.0012634703,0.0011605273,0.000006607218,0.00059976784,0.00034256178,0.0009939995,0.4899757,0.017135805,0.00034025375],"about_ca_topic_score_codex":0.00010163216,"about_ca_topic_score_gemma":0.00001896023,"teacher_disagreement_score":0.22922929,"about_ca_system_score_codex":0.00002034891,"about_ca_system_score_gemma":0.00009343787,"threshold_uncertainty_score":0.95692307},"labels":[],"label_agreement":null},{"id":"W3026675393","doi":"10.1245/s10434-020-08575-7","title":"Current Issues in Conduct and Reporting of Noninferiority Randomized Controlled Trials in Surgical Management of Cancer Patients","year":2020,"lang":"en","type":"article","venue":"Annals of Surgical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital; Princess Margaret Cancer Centre; University Health Network; St Joseph's Health Care; University of Toronto; London Health Sciences Centre; Western University","funders":"","keywords":"Surgical oncology; Medicine; Randomized controlled trial; Current (fluid); Medical physics; General surgery; Intensive care medicine; Oncology; Surgery","score_opus":0.7576450312823312,"score_gpt":0.6641170561861837,"score_spread":0.09352797509614752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026675393","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98552984,0.0033916002,0.00012352708,0.004961368,0.00038475843,0.0033389132,0.00007179225,0.000012803388,0.002185392],"genre_scores_gemma":[0.9403032,0.030000145,0.029256506,0.000056863828,0.00011455212,0.00023716006,0.0000026743867,0.000017499191,0.000011402131],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.97421324,0.010596443,0.013955848,0.00042003838,0.0004980377,0.00031636222],"domain_scores_gemma":[0.78311414,0.20381963,0.012064311,0.00024967745,0.000541113,0.00021111753],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05098114,0.00022023414,0.013894116,0.00012992123,0.000010125476,0.000004592615,0.00016156651,0.00023451402,0.00030586816],"category_scores_gemma":[0.15833123,0.0001455589,0.00078425073,0.00030537826,0.0005141234,0.00004023051,0.00018699982,0.0003204655,5.037488e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6285195,0.0054550287,0.043718234,0.00414592,0.0019519427,0.0006957049,0.00096379424,0.000026325466,0.00006828048,0.14709921,0.0005724752,0.16678363],"study_design_scores_gemma":[0.6984396,0.0016657312,0.0039196513,0.0016630396,0.00079683115,0.0000026531163,0.00015268104,0.00045273226,0.002015767,0.28439966,0.006132516,0.00035913262],"about_ca_topic_score_codex":0.00010015783,"about_ca_topic_score_gemma":0.000011319647,"teacher_disagreement_score":0.1932232,"about_ca_system_score_codex":0.000021190392,"about_ca_system_score_gemma":0.00009506331,"threshold_uncertainty_score":0.97721463},"labels":[],"label_agreement":null},{"id":"W3028101882","doi":"10.1016/j.jval.2020.04.1748","title":"PCN282 VALIDATION AND CALIBRATION OF A DISCRETE EVENT SIMULATION TREATMENT SEQUENCING MODEL TO ESTIMATE LONG-TERM SURVIVAL OF PATIENTS WITH MULTIPLE MYELOMA","year":2020,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"EVERSANA (Canada)","funders":"","keywords":"Medicine; Survival analysis; Proportional hazards model; Calibration; Population; Event (particle physics); Cancer registry; Overall survival; Oncology; Multiple myeloma; Progression-free survival; Term (time); Covariate; Internal medicine; Statistics; Cancer; Mathematics","score_opus":0.5010529218027832,"score_gpt":0.5316223444785074,"score_spread":0.030569422675724267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028101882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5433307,0.0000038498656,0.45567778,0.00012941785,0.000024605042,0.0007312176,0.0000889599,0.000011471159,0.0000020019515],"genre_scores_gemma":[0.6716194,0.0000036976166,0.32829666,0.000022543867,0.000015060055,0.0000149770685,0.000011892043,0.0000147012415,0.0000010590213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976242,0.0006057973,0.0010221961,0.00026803967,0.0003175665,0.0001622077],"domain_scores_gemma":[0.99271697,0.006394168,0.00047398094,0.00017143077,0.00008788419,0.00015555804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008965019,0.00013298598,0.0005350252,0.00005750725,0.00002910475,0.000008464015,0.000055537083,0.000055849396,0.000004426334],"category_scores_gemma":[0.008268855,0.0001055738,0.000033551863,0.00018402385,0.00003301176,0.00007954814,0.00003382599,0.000061893705,2.658655e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054144114,0.00011985628,0.1441916,0.0008149936,0.000020988498,6.104588e-7,0.0018490808,0.84626603,0.000108374516,0.0023655929,5.7190465e-7,0.0037208775],"study_design_scores_gemma":[0.0016667757,0.0011431924,0.03681279,0.0003072885,0.000028335031,6.523706e-8,0.000019995106,0.93937474,0.0011432476,0.019410541,1.0481117e-7,0.00009294297],"about_ca_topic_score_codex":0.0001812669,"about_ca_topic_score_gemma":0.00002802059,"teacher_disagreement_score":0.1282887,"about_ca_system_score_codex":0.0002196624,"about_ca_system_score_gemma":0.00016688091,"threshold_uncertainty_score":0.9899188},"labels":[],"label_agreement":null},{"id":"W3028357212","doi":"10.1002/sim.8868","title":"The optimal design of clinical trials with potential biomarker effects: A novel computational approach","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Western Canada Research Grid; Compute Canada","keywords":"Computer science; Scalability; Smoothing; Curse of dimensionality; Personalized medicine; Clinical trial; Software; Data mining; Machine learning; Bioinformatics","score_opus":0.6846230401092185,"score_gpt":0.6258049677645551,"score_spread":0.05881807234466341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028357212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036123124,0.00015689149,0.9965329,0.00041538596,0.0009163604,0.0009427323,0.00026003332,0.000022332773,0.0003921047],"genre_scores_gemma":[0.010540942,0.00009384639,0.98858744,0.0001496233,0.00039443077,0.00006452635,0.000029391786,0.000040125506,0.00009969593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9847517,0.008915124,0.0042207763,0.0005461058,0.001183843,0.00038244398],"domain_scores_gemma":[0.6370342,0.36092296,0.0009693226,0.0004093405,0.0005237242,0.00014046098],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045852892,0.0002600168,0.002132037,0.00007999762,0.00009830914,0.00002442552,0.0003226184,0.00020208147,0.00012724796],"category_scores_gemma":[0.5446955,0.00014551367,0.00011535524,0.00046950905,0.0014403674,0.000025450448,0.000103731545,0.0005834949,0.0000026660803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048005427,0.0020645792,0.00061391527,0.00091895135,0.0013098449,0.00044347547,0.00031395914,0.0044371225,0.000436142,0.887408,0.020289378,0.07696406],"study_design_scores_gemma":[0.010758587,0.0008464757,0.0040357225,0.00041492222,0.0006122966,0.000050449515,0.00027157695,0.15804403,0.0000658034,0.8246024,0.00008015383,0.00021755185],"about_ca_topic_score_codex":0.0000101224405,"about_ca_topic_score_gemma":0.0000026747668,"teacher_disagreement_score":0.49884263,"about_ca_system_score_codex":0.000031782987,"about_ca_system_score_gemma":0.00041954056,"threshold_uncertainty_score":0.98249525},"labels":[],"label_agreement":null},{"id":"W3028454688","doi":"10.48550/arxiv.2005.10059","title":"Simultaneous Confidence Tubes for Comparison of Several Multivariate Linear Regression Models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Bayesian multivariate linear regression; Multivariate statistics; Linear regression; Univariate; Confidence interval; Statistics; Linear model; Confidence and prediction bands; Confidence region; Simple linear regression; Inference; Proper linear model; Population; Mathematics; Regression analysis; Regression; Econometrics; Computer science; Artificial intelligence","score_opus":0.7236673051737669,"score_gpt":0.463662656619768,"score_spread":0.26000464855399885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028454688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036039688,0.000023349845,0.9609495,0.00008104482,0.00063546805,0.0012232857,0.00056633964,0.00015669914,0.00032466062],"genre_scores_gemma":[0.59804165,0.000029955616,0.4015442,0.000026603871,0.00012036696,0.000002226971,0.000010061323,0.00003766223,0.00018728188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965916,0.0007387939,0.0010264023,0.0011039209,0.00018905663,0.00035020965],"domain_scores_gemma":[0.94869566,0.04886539,0.0007812335,0.0008903876,0.0005180811,0.00024925894],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009498687,0.000443547,0.0016913121,0.00010084516,0.00009784137,0.000023492657,0.0009292046,0.0005828439,0.00006533547],"category_scores_gemma":[0.039096907,0.00043349908,0.00048867357,0.00021971774,0.00028691298,0.00008271458,0.0010018018,0.0008662523,0.000012397524],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017343889,0.0004252866,0.00009423661,0.0015859781,0.0003293401,0.0001240097,0.00047620767,0.49524656,0.00027588604,0.4986165,0.00047812038,0.00061351765],"study_design_scores_gemma":[0.00072554994,0.00011726421,0.0000029818098,0.00035629215,0.00026461398,4.2334136e-7,0.000068771966,0.50234634,0.0008981819,0.4949787,0.000016147009,0.00022474432],"about_ca_topic_score_codex":0.00007492886,"about_ca_topic_score_gemma":0.000007306405,"teacher_disagreement_score":0.56200194,"about_ca_system_score_codex":0.00010541996,"about_ca_system_score_gemma":0.00018052063,"threshold_uncertainty_score":0.9998117},"labels":[],"label_agreement":null},{"id":"W3031248945","doi":"10.1136/bmjopen-2019-034565","title":"Characteristics and interpretation of subgroup analyses based on tumour characteristics in randomised trials testing target-specific anticancer drugs: design of a systematic survey","year":2020,"lang":"en","type":"article","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Amgen; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Subgroup analysis; Medicine; Clinical trial; Credibility; MEDLINE; Harm; Oncology; Family medicine; Medical physics; Meta-analysis; Internal medicine","score_opus":0.8204918218265521,"score_gpt":0.600694430398597,"score_spread":0.21979739142795507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031248945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055544633,0.000035116544,0.9194437,0.00015174362,0.00028972697,0.023526859,0.0007831274,0.000036086803,0.00018896264],"genre_scores_gemma":[0.6427678,0.000010662896,0.35655048,0.00010857619,0.000064473556,0.0004491796,0.000011404488,0.000034531313,0.000002866106],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97783154,0.015145897,0.0055944445,0.00051081093,0.0006526006,0.0002647009],"domain_scores_gemma":[0.74312353,0.25212318,0.003696822,0.00048350627,0.0004271386,0.00014579279],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045025013,0.00031211993,0.0046837376,0.00016159622,0.000034845452,0.00011604302,0.00056996034,0.0001432771,0.00009944702],"category_scores_gemma":[0.62715745,0.00024550606,0.00015732742,0.000624071,0.00014833841,0.00010006912,0.00017628624,0.00023235564,0.0000044026674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.40450883,0.0055872225,0.10832546,0.32450092,0.0027693429,0.00029132946,0.013716724,0.0015788712,0.104937874,0.010988111,0.0014155065,0.021379825],"study_design_scores_gemma":[0.038583614,0.001868188,0.070342064,0.04037559,0.0011195613,0.0000027746885,0.0004350419,0.8062337,0.009134945,0.03089145,7.681078e-7,0.001012287],"about_ca_topic_score_codex":0.000035176563,"about_ca_topic_score_gemma":0.0000014475386,"teacher_disagreement_score":0.80465484,"about_ca_system_score_codex":0.00004634202,"about_ca_system_score_gemma":0.00020824825,"threshold_uncertainty_score":0.9999997},"labels":[],"label_agreement":null},{"id":"W3031739372","doi":"10.1200/jco.2020.38.15_suppl.e14049","title":"Multistate Markov modelling of long-term outcomes in immunotherapy for metastatic renal cell carcinoma (mRCC) using machine-learned dynamic Bayesian networks.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Renal cell carcinoma; Medicine; Multivariate statistics; Bayesian probability; Bayesian network; Multivariate analysis; Machine learning; Computer science; Statistic; Artificial intelligence; Clinical trial; Nomogram; Immunotherapy; Oncology; Statistics; Internal medicine; Cancer; Mathematics","score_opus":0.6619624007968893,"score_gpt":0.6021213185195662,"score_spread":0.0598410822773231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031739372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30325943,0.00024197451,0.6941115,0.0010393529,0.00074311637,0.00052041165,0.000041625586,0.000008985228,0.000033588414],"genre_scores_gemma":[0.44889498,0.00019428231,0.55018574,0.00044300145,0.00020872378,0.000004901179,0.0000011775303,0.000049114136,0.000018094786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98641515,0.003727799,0.008452573,0.00042420658,0.00047554297,0.00050472806],"domain_scores_gemma":[0.88400775,0.109506674,0.0053970353,0.00031342372,0.00037797578,0.00039714636],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013811081,0.00034679208,0.004517574,0.00016280949,0.000049731734,0.000021740118,0.00064307556,0.00046759038,0.00011881297],"category_scores_gemma":[0.04676788,0.00026729912,0.0012622066,0.00025902956,0.00031309598,0.00012366562,0.00011340388,0.0015408754,0.0000012401513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07192699,0.013914446,0.21954887,0.0027972048,0.0039998214,0.0033187151,0.0014261933,0.13546023,0.0024181094,0.0031321796,0.0003454564,0.5417118],"study_design_scores_gemma":[0.019758714,0.0063939043,0.008791023,0.00016976951,0.0007601045,0.000033623677,0.000056603712,0.87493837,0.00014412426,0.0885697,0.000037733,0.000346307],"about_ca_topic_score_codex":0.000024560619,"about_ca_topic_score_gemma":0.0000375463,"teacher_disagreement_score":0.7394782,"about_ca_system_score_codex":0.00015262149,"about_ca_system_score_gemma":0.0006127536,"threshold_uncertainty_score":0.99997795},"labels":[],"label_agreement":null},{"id":"W3031787110","doi":"10.1200/jco.2020.38.15_suppl.2014","title":"Mapping PRO-CTCAE responses to clinician-graded adverse events, dose reductions, interruptions, and discontinuations in phase I cancer trials.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Baker Hughes (Canada); Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Tolerability; Adverse effect; Clinical trial; Internal medicine","score_opus":0.875711508504094,"score_gpt":0.7220151033976008,"score_spread":0.15369640510649318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031787110","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85647976,0.0002864052,0.042111963,0.09489709,0.004382803,0.0015075781,0.00012464641,0.000037315986,0.00017242758],"genre_scores_gemma":[0.37247118,0.0013346304,0.6172883,0.004478973,0.004069745,0.00009444701,0.0000012403137,0.00004338738,0.00021809424],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97582793,0.012000463,0.01089406,0.0004766175,0.00045630184,0.00034465038],"domain_scores_gemma":[0.8058292,0.1864555,0.0057964073,0.00034482955,0.0005351011,0.0010389498],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042116567,0.00024322695,0.0037105416,0.0003152833,0.0000779257,0.000017039547,0.0004014304,0.00051076413,0.00032987632],"category_scores_gemma":[0.72240084,0.00018674908,0.000692808,0.0005873347,0.00028943637,0.00020662967,0.00019241049,0.0017424,0.000017897046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03948005,0.008272638,0.020717481,0.00020814287,0.001312288,0.00041706505,0.0035882953,0.000038144557,0.0011620037,0.014446139,0.026087472,0.8842703],"study_design_scores_gemma":[0.060159657,0.020619877,0.10499041,0.0018176452,0.0017398838,0.00010563139,0.005643002,0.00067859254,0.0001526825,0.7245816,0.07861512,0.00089589815],"about_ca_topic_score_codex":0.000013660803,"about_ca_topic_score_gemma":0.000062237836,"teacher_disagreement_score":0.8833744,"about_ca_system_score_codex":0.00016172708,"about_ca_system_score_gemma":0.0013110097,"threshold_uncertainty_score":0.98634255},"labels":[],"label_agreement":null},{"id":"W3031903699","doi":"10.1016/j.jamcollsurg.2020.05.012","title":"Selecting the Optimal Level of Clustering: An Approach to Trial Design Decision Making","year":2020,"lang":"en","type":"article","venue":"Journal of the American College of Surgeons","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"","keywords":"Medicine; Cluster analysis; Clinical decision making; Intensive care medicine; Machine learning","score_opus":0.708201247400976,"score_gpt":0.5301255284900998,"score_spread":0.17807571891087626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031903699","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1647329,0.0000070278847,0.8329029,0.0011548181,0.00037741708,0.0005872858,0.00008739612,0.0000075760886,0.00014268914],"genre_scores_gemma":[0.46319926,0.0000027478654,0.5364169,0.00017715187,0.0001729437,0.0000032593948,1.757955e-8,0.000019398638,0.000008350439],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99465823,0.0021526464,0.0019027635,0.0001939252,0.00083683385,0.0002555982],"domain_scores_gemma":[0.9422261,0.05375048,0.00298147,0.00043566094,0.00041318082,0.00019309937],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0080308085,0.0001775248,0.0012463719,0.00009599885,0.00013036508,0.000019534467,0.0010576022,0.000053253494,0.000021930076],"category_scores_gemma":[0.111527756,0.00009946646,0.00045210132,0.001120707,0.0002971443,0.000067737354,0.00028875825,0.00047380116,5.8234156e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5462308,0.006729327,0.0021385006,0.0007235949,0.0036519945,0.00015435621,0.009388527,0.123093836,0.02050002,0.027867882,0.07031675,0.18920444],"study_design_scores_gemma":[0.08630086,0.050009746,0.0123785315,0.004505329,0.0053497585,0.0013721025,0.03469503,0.23428836,0.028082369,0.5377541,0.002137479,0.0031262962],"about_ca_topic_score_codex":0.000011427162,"about_ca_topic_score_gemma":0.000003207254,"teacher_disagreement_score":0.50988626,"about_ca_system_score_codex":0.0000498901,"about_ca_system_score_gemma":0.00027738014,"threshold_uncertainty_score":0.8959562},"labels":[],"label_agreement":null},{"id":"W3031927075","doi":"10.1200/jco.2020.38.15_suppl.e20523","title":"Error propagation in simulated treatment comparisons for multiple myeloma: Results from a simulation.","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Waterloo; McMaster University","funders":"","keywords":"Covariate; Bootstrapping (finance); Statistics; Medicine; Bayesian probability; Parametric statistics; Multiple myeloma; Accelerated failure time model; Survival analysis; Econometrics; Mathematics; Internal medicine","score_opus":0.8640452475509691,"score_gpt":0.6774853501021025,"score_spread":0.18655989744886659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031927075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4743769,0.00005807553,0.49775082,0.02234439,0.002291309,0.0021594898,0.00057441386,0.000060721282,0.0003838889],"genre_scores_gemma":[0.5606444,0.000012529381,0.4376589,0.00057939335,0.0010619336,0.000006111038,0.0000064604583,0.00001748996,0.00001277523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892685,0.0025986715,0.007182269,0.00036398746,0.00033179423,0.00025476838],"domain_scores_gemma":[0.5768291,0.4180616,0.0039772834,0.00022423442,0.0004958385,0.00041193725],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007280251,0.00019888485,0.0025689392,0.00006955355,0.000041949592,0.000016125732,0.00026248305,0.0006272343,0.00006272749],"category_scores_gemma":[0.5843877,0.0001424554,0.000525082,0.00020102123,0.00014775812,0.00009431619,0.000047384874,0.0007266778,0.000015752334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.20074937,0.02170156,0.028938131,0.0001868969,0.002528137,0.0007230035,0.003979917,0.18894693,0.0005053691,0.0052123913,0.024860388,0.5216679],"study_design_scores_gemma":[0.059166692,0.018016689,0.0152423605,0.000111567875,0.00060448336,0.0000023321575,0.00018342467,0.7114657,0.0001577422,0.15372428,0.04105598,0.0002687131],"about_ca_topic_score_codex":0.000023689076,"about_ca_topic_score_gemma":0.00005838587,"teacher_disagreement_score":0.5771075,"about_ca_system_score_codex":0.00019271942,"about_ca_system_score_gemma":0.00064299826,"threshold_uncertainty_score":0.5809163},"labels":[],"label_agreement":null},{"id":"W3034875569","doi":"10.1016/j.jclinepi.2020.05.029","title":"How personalized are benefit and harm results of randomized trials? A systematic review","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Canada Research Chairs; McMaster University; University of Toronto; University of Alberta","funders":"","keywords":"Randomized controlled trial; Medicine; Harm; MEDLINE; Intensive care medicine; Psychology; Internal medicine; Biology","score_opus":0.9177432494998558,"score_gpt":0.7146996155668064,"score_spread":0.20304363393304936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034875569","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9338641e-7,0.9582942,0.023470305,0.009739428,0.001947525,0.0060249385,0.00043797586,0.000021060387,0.00006435853],"genre_scores_gemma":[2.110798e-7,0.723243,0.27361068,0.0012095704,0.0015792262,0.000114425275,0.000003832935,0.00007064724,0.00016841436],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.4358693,0.43535528,0.12505333,0.0014863258,0.0013813012,0.00085447036],"domain_scores_gemma":[0.014416812,0.84759945,0.13495143,0.0009988823,0.001160504,0.0008729144],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.5881517,0.0010405781,0.2009697,0.00026148336,0.000045833764,0.00003397042,0.0013319582,0.0020962167,0.00008006813],"category_scores_gemma":[0.9976561,0.00053492596,0.0228755,0.00042364316,0.0016690743,0.00008478799,0.00032735764,0.0038944017,0.000010538874],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013057623,0.00017902874,7.811785e-7,0.8340548,0.0068499106,0.00009561571,0.000011916457,2.8671563e-8,6.6108607e-9,0.027784396,0.00713951,0.11082637],"study_design_scores_gemma":[0.04119019,0.00045446868,2.9260997e-7,0.5339638,0.053703252,0.00023304381,0.000011537828,0.0000129320415,2.0193646e-8,0.30265218,0.06750135,0.0002769122],"about_ca_topic_score_codex":0.0000018249542,"about_ca_topic_score_gemma":4.6093328e-7,"teacher_disagreement_score":0.4214525,"about_ca_system_score_codex":0.00006848696,"about_ca_system_score_gemma":0.00064286886,"threshold_uncertainty_score":0.9997102},"labels":[],"label_agreement":null},{"id":"W3035249419","doi":"10.1093/biomet/asaa027","title":"Combining <i>p</i>-values via averaging","year":2020,"lang":"en","type":"article","venue":"Biometrika","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Harmonic mean; Bonferroni correction; Scaling; Infinity; Geometric mean; Applied mathematics; Statistics; Combinatorics; Mathematical analysis; Geometry","score_opus":0.6471262439678166,"score_gpt":0.5481434056216933,"score_spread":0.09898283834612331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035249419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01575219,0.00016511606,0.97090983,0.0027498053,0.0010412,0.00040218266,0.000042778454,0.00052635284,0.008410557],"genre_scores_gemma":[0.24431102,0.000013537265,0.75345075,0.0016010202,0.00048765898,0.000009016011,0.0000012052992,0.00003872457,0.00008704747],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977819,0.00039779788,0.0006876177,0.00038163445,0.00043694707,0.00031415818],"domain_scores_gemma":[0.9717535,0.027375756,0.00019747911,0.00029900915,0.00007967739,0.0002945779],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017971466,0.00017316098,0.00054888224,0.00018058755,0.000082400715,0.00005548436,0.00033154496,0.00011905043,0.0005717455],"category_scores_gemma":[0.113450944,0.00015365884,0.00014461402,0.0016854497,0.00011169261,0.000057804962,0.00017615454,0.00023722656,0.00030470188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048013902,0.0008340506,0.005466268,0.0010746347,0.00066016836,0.00022268975,0.0024113082,0.000004458205,0.043755915,0.2708042,0.08036264,0.5939235],"study_design_scores_gemma":[0.0013147991,0.00028751694,0.00029536887,0.000052391344,0.00008704871,0.0000040413875,0.000062235995,0.0016017747,0.014924504,0.9731602,0.0078676855,0.00034241],"about_ca_topic_score_codex":0.0000035848027,"about_ca_topic_score_gemma":7.4201274e-8,"teacher_disagreement_score":0.70235604,"about_ca_system_score_codex":0.000027838098,"about_ca_system_score_gemma":0.000023761166,"threshold_uncertainty_score":0.89401686},"labels":[],"label_agreement":null},{"id":"W3035471511","doi":"10.5539/ijsp.v9n4p49","title":"Statistical Issues on Analysis of Censored Data Due to Detection Limit","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health","keywords":"Censoring (clinical trials); Tobit model; Statistics; Econometrics; Censored regression model; Population; Limit (mathematics); Regression analysis; Mathematics; Computer science; Medicine; Environmental health","score_opus":0.47868598130917284,"score_gpt":0.5482077245377532,"score_spread":0.0695217432285804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035471511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03575512,0.000015348596,0.9534376,0.0028643748,0.00038350225,0.00018461123,0.007279881,0.0000086209675,0.000070919115],"genre_scores_gemma":[0.30744302,0.00002773717,0.6920573,0.00024676247,0.0001950722,0.0000013725538,0.000015702917,0.000008900272,0.0000041341077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99684703,0.00046662864,0.0014216059,0.000312155,0.0008272543,0.00012530143],"domain_scores_gemma":[0.980969,0.016793104,0.00065077934,0.00030502412,0.0010192178,0.00026288038],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024003233,0.00013820319,0.00077238237,0.00015893394,0.000026615919,0.000052561903,0.00057275215,0.00007069938,0.0002873152],"category_scores_gemma":[0.12850383,0.00011293,0.00007978209,0.0002780444,0.00014864198,0.00007141872,0.0002151825,0.00025861265,0.0000033581985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052177464,0.0010872283,0.0049058716,0.00030977005,0.00548754,0.00023411003,0.00093958544,0.00049415795,0.00091918145,0.6678566,0.007670288,0.30487794],"study_design_scores_gemma":[0.0006956292,0.0011479072,0.028971981,0.000054698812,0.0011254187,0.0000087493545,0.000043052012,0.0136728315,0.0006713036,0.9523566,0.0010938122,0.00015801999],"about_ca_topic_score_codex":0.00002168463,"about_ca_topic_score_gemma":0.000025805057,"teacher_disagreement_score":0.30471992,"about_ca_system_score_codex":0.000045789428,"about_ca_system_score_gemma":0.000057036592,"threshold_uncertainty_score":0.87883717},"labels":[],"label_agreement":null},{"id":"W3035701045","doi":"10.1177/1740774520965173","title":"A Bayesian response-adaptive dose-finding and comparative effectiveness trial","year":2020,"lang":"en","type":"preprint","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; London Health Sciences Centre; Western University; University of Manitoba; Children's Hospital Research Institute of Manitoba; Women and Children’s Health Research Institute; University of Alberta; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Children's Hospital Research Institute of Manitoba; Hospital for Sick Children; Ontario Ministry of Economic Development, Job Creation and Trade; Centre hospitalier universitaire Sainte-Justine; Physicians' Services Incorporated Foundation; University of Alberta; Ministero dello Sviluppo Economico; Kidscan Children's Cancer Research; London Health Sciences Foundation; Alberta Children's Hospital Research Institute; Academic Medical Organization of Southwestern Ontario","keywords":"Bayesian probability; Interim analysis; Medicine; Computer science; Type I and type II errors; Statistical power; Early stopping; Clinical trial; Medical physics; Machine learning; Statistics; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.9482633965801534,"score_gpt":0.7194301561646284,"score_spread":0.228833240415525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035701045","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20414132,0.0006076539,0.7214671,0.0037802763,0.027686996,0.034427848,0.0026665956,0.0011517864,0.00407044],"genre_scores_gemma":[0.39806736,0.0001960772,0.5923489,0.0004265988,0.0074654887,0.0011941701,0.000015396416,0.00016711665,0.000118915865],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.786139,0.19573952,0.012410388,0.003512053,0.0012764861,0.00092255085],"domain_scores_gemma":[0.26291838,0.7295115,0.0047467733,0.0014415791,0.00036386237,0.0010178967],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.21905828,0.0012311088,0.013971015,0.00023379213,0.00024132484,0.00036647267,0.0011343105,0.0028227102,0.00032738224],"category_scores_gemma":[0.86610484,0.0010056526,0.0026010324,0.00041065103,0.0014010869,0.000087828696,0.0024743439,0.0050330665,0.000103867504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8753882,0.0013781375,0.00014007618,0.0010103682,0.0034687985,0.00019339992,0.00046053718,0.000009060105,0.00016635309,0.09368379,0.0044896253,0.019611632],"study_design_scores_gemma":[0.08168423,0.0040960927,0.0013500155,0.0014555245,0.0019475408,0.0000036383772,0.000116545045,0.00084392505,0.00027104083,0.9066694,0.00056454533,0.0009975157],"about_ca_topic_score_codex":0.000011668764,"about_ca_topic_score_gemma":0.0000027694678,"teacher_disagreement_score":0.8129856,"about_ca_system_score_codex":0.00019912577,"about_ca_system_score_gemma":0.0010143424,"threshold_uncertainty_score":0.9992394},"labels":[],"label_agreement":null},{"id":"W3036109172","doi":"10.21203/rs.3.rs-923540/v1","title":"Bayesian Updating and Sequential Testing: Overcoming Inferential Limitations of Screening Tests","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Bayes' theorem; Bayesian probability; Mathematics; Logarithm; Sensitivity (control systems); Statistics; Predictive value; Prior probability; Bayesian inference; Applied mathematics; Computer science; Algorithm; Medicine","score_opus":0.8372973666668204,"score_gpt":0.629800301252048,"score_spread":0.20749706541477242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036109172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20240887,0.00032338698,0.78107107,0.000502806,0.0007657663,0.0026055833,0.00054587255,0.00023190324,0.011544747],"genre_scores_gemma":[0.45107135,0.000051526204,0.54838556,0.00000576112,0.00032609436,0.0000628224,0.000022683342,0.0000496712,0.000024541696],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9911021,0.0041802363,0.0015403912,0.00088424736,0.0016066001,0.0006864496],"domain_scores_gemma":[0.7860915,0.2099348,0.0006042471,0.0009852021,0.0020483185,0.00033593626],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0099040475,0.00032648336,0.001084863,0.0003919655,0.00030174525,0.0003855711,0.00047772913,0.00056788017,0.00021278913],"category_scores_gemma":[0.5781189,0.00033453567,0.00022139751,0.0006387722,0.0005104661,0.000101022306,0.0032191759,0.0026248908,0.0000024379385],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046964543,0.0020799362,0.055165004,0.03188977,0.0018402836,0.00055241724,0.004833426,0.0007126201,0.019076241,0.34277406,0.0016788463,0.53892773],"study_design_scores_gemma":[0.0011111147,0.00030764184,0.009285499,0.0087720975,0.00022555192,0.000012835824,0.0023404488,0.01479059,0.0024596255,0.96006733,0.00005658766,0.0005706624],"about_ca_topic_score_codex":0.00022686268,"about_ca_topic_score_gemma":0.00007780201,"teacher_disagreement_score":0.6172933,"about_ca_system_score_codex":0.00009685922,"about_ca_system_score_gemma":0.0008276719,"threshold_uncertainty_score":0.99991065},"labels":[],"label_agreement":null},{"id":"W3036900991","doi":"10.1186/s13063-020-04466-0","title":"Stakeholder perspectives on adaptive clinical trials: a scoping review","year":2020,"lang":"en","type":"review","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; BC Children's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Sample size determination; Stakeholder; Clinical study design; Research design; Clinical trial; Medicine; Inclusion (mineral); Population; External validity; Computer science; Psychology; Social psychology; Public relations; Statistics","score_opus":0.9867389176112797,"score_gpt":0.7843088686461159,"score_spread":0.2024300489651638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036900991","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.2967586e-9,0.94401735,0.02076098,0.00043132377,0.002917872,0.028153455,0.0011258081,0.00033662934,0.0022565925],"genre_scores_gemma":[7.410114e-9,0.7732088,0.21766657,0.0005528495,0.006555892,0.0016170242,0.000011968111,0.00024911133,0.00013780611],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.7491358,0.2149589,0.030431772,0.0029063842,0.0016639498,0.0009032028],"domain_scores_gemma":[0.102470204,0.8768322,0.017122393,0.0023154726,0.0004271366,0.00083261554],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"category_scores_codex":[0.30193725,0.001617024,0.054422773,0.00025118788,0.00014309605,0.00015388025,0.0013950699,0.0016213815,0.0041104658],"category_scores_gemma":[0.9665375,0.0010335139,0.010311547,0.00095499126,0.0004491728,0.0000831923,0.00038394477,0.0031425564,0.0014500545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002882833,0.0003244637,1.5055306e-8,0.11245295,0.0018153725,0.000069112466,0.000042453026,1.3545962e-8,1.07299e-8,0.045478564,0.025208429,0.8143203],"study_design_scores_gemma":[0.0014944378,0.00066518463,1.9741828e-8,0.53886366,0.0141336555,0.000007854042,0.000043110944,9.825596e-7,1.9523493e-7,0.10759325,0.33647096,0.0007267082],"about_ca_topic_score_codex":0.00000200244,"about_ca_topic_score_gemma":8.527846e-7,"teacher_disagreement_score":0.8135936,"about_ca_system_score_codex":0.00029632697,"about_ca_system_score_gemma":0.002125178,"threshold_uncertainty_score":0.99967474},"labels":[],"label_agreement":null},{"id":"W3037072523","doi":"10.2196/19538","title":"Statistical Issues and Lessons Learned From COVID-19 Clinical Trials With Lopinavir-Ritonavir and Remdesivir","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lopinavir/ritonavir; Lopinavir; Coronavirus disease 2019 (COVID-19); Ritonavir; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Virology; Pandemic; Human immunodeficiency virus (HIV); Viral load; Antiretroviral therapy; Internal medicine; Outbreak; Disease","score_opus":0.8432263555532094,"score_gpt":0.6657415311735724,"score_spread":0.17748482437963697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037072523","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067077845,0.0045813145,0.30877924,0.61317164,0.0003535125,0.0027080388,0.002657131,0.00040527803,0.00026604283],"genre_scores_gemma":[0.1677069,0.014423688,0.7764786,0.039265595,0.0015648752,0.00021393607,0.00009742814,0.00011882496,0.00013014363],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9829426,0.012327236,0.0023254685,0.0011977827,0.00051081675,0.00069613673],"domain_scores_gemma":[0.84687865,0.14821744,0.0007068259,0.00041603495,0.00011313786,0.0036679292],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.023535702,0.00035214264,0.0024836562,0.00004846843,0.0002743128,0.00025128011,0.00019722871,0.00031706033,0.00016635617],"category_scores_gemma":[0.31510633,0.00026216995,0.000070078604,0.0002456376,0.000878994,0.00011363862,0.00019253948,0.00073176506,0.000009155932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002266707,0.00032114124,0.18710603,0.0015612103,0.00020952366,0.00008564916,0.001202092,1.3656715e-7,0.0000069692637,0.14737183,0.039886884,0.6199818],"study_design_scores_gemma":[0.010247815,0.0031783571,0.077989824,0.000101206046,0.000024771822,0.000029608273,0.0009239255,0.0010090268,0.0000011220008,0.56402576,0.34154356,0.00092505873],"about_ca_topic_score_codex":0.00019540853,"about_ca_topic_score_gemma":0.00008090032,"teacher_disagreement_score":0.61905676,"about_ca_system_score_codex":0.00004307077,"about_ca_system_score_gemma":0.00095493917,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W3037092793","doi":"10.1007/s13171-023-00328-4","title":"The p-value interpreted as the posterior probability of explaining the data: Applications to multiple testing and to restricted parameter spaces","year":2023,"lang":"en","type":"article","venue":"Sankhya A","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Posterior probability; Null hypothesis; p-value; Statistical hypothesis testing; Null (SQL); False discovery rate; Statistics; Mathematics; Alternative hypothesis; Value (mathematics); Null distribution; Multiple comparisons problem; Econometrics; Test statistic; Computer science; Data mining; Bayesian probability","score_opus":0.6051288594926673,"score_gpt":0.5525536507857383,"score_spread":0.052575208706929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037092793","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93642855,0.000044409953,0.04239501,0.013293871,0.0003161402,0.006211224,0.00045141732,0.0002490525,0.0006103347],"genre_scores_gemma":[0.39810246,0.0000058042615,0.6003989,0.0004574517,0.0001225796,0.00082225114,0.0000027962358,0.000028487497,0.00005924569],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997314,0.0010105782,0.0006959728,0.0004110164,0.00029139486,0.00027706387],"domain_scores_gemma":[0.70870644,0.2889575,0.00024058648,0.0018284894,0.00016134526,0.000105619925],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0049344944,0.00014052828,0.00030103195,0.00003566309,0.00034225185,0.0001305558,0.0009507281,0.00006118012,0.00000789773],"category_scores_gemma":[0.4650714,0.00006598089,0.0000417643,0.00093705574,0.0002787553,0.00004210038,0.0011706488,0.00023557093,0.000030072059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015145806,0.00038694125,0.021890042,0.0006755034,0.00067977497,0.000012401654,0.018574143,0.00019519377,0.019584365,0.12037094,0.017075257,0.79904085],"study_design_scores_gemma":[0.00040181607,0.00029571273,0.021958435,0.00024179672,0.00014452839,0.000007778028,0.0020881621,0.009364382,0.0008520191,0.9610798,0.0033453943,0.00022021288],"about_ca_topic_score_codex":0.00008430333,"about_ca_topic_score_gemma":0.000044314704,"teacher_disagreement_score":0.84070885,"about_ca_system_score_codex":0.000018281362,"about_ca_system_score_gemma":0.00005129355,"threshold_uncertainty_score":0.5394345},"labels":[],"label_agreement":null},{"id":"W3037518813","doi":"10.1186/s12911-020-01149-3","title":"GUIP1: a R package for dose escalation strategies in phase I cancer clinical trials","year":2020,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Institut Bergonié; Institut National Du Cancer; CNIB","keywords":"Health informatics; Medicine; Clinical trial; Medical physics; De-escalation; Phase (matter); Oncology; Internal medicine; Public health; Nursing","score_opus":0.8144911800142475,"score_gpt":0.6977684583328767,"score_spread":0.11672272168137077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037518813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048956733,0.000091501104,0.94868416,0.00020714592,0.0005315362,0.0010405863,0.00009192586,0.000056706107,0.00033968218],"genre_scores_gemma":[0.05866989,0.00025961493,0.93859154,0.0016897521,0.0006605116,0.00009918447,0.0000037183245,0.000023276223,0.0000025153718],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99136937,0.0010880872,0.005901864,0.00029072308,0.00099734,0.00035264407],"domain_scores_gemma":[0.73973596,0.2583298,0.0010432138,0.00026739202,0.00013654088,0.00048711605],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030011414,0.0002374098,0.0016265018,0.00010149185,0.00008270631,0.00020461019,0.0003227929,0.00047282758,0.00050973304],"category_scores_gemma":[0.47704682,0.00016828586,0.000290102,0.00028495997,0.000179929,0.00024965891,0.00021177252,0.0004984769,0.000011483355],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017239478,0.00019624224,0.0002602724,0.0006364266,0.000036952635,0.0000074848786,0.0005228237,0.000028997867,0.0000040962195,0.08316871,0.0042736935,0.90914035],"study_design_scores_gemma":[0.0071558324,0.00025742964,0.000104321705,0.00065364176,0.00006396502,0.000001706076,0.00066002895,0.40189403,0.0000054010907,0.58858293,0.00046070863,0.00016000333],"about_ca_topic_score_codex":0.00000200073,"about_ca_topic_score_gemma":0.00002608546,"teacher_disagreement_score":0.90898037,"about_ca_system_score_codex":0.000026697668,"about_ca_system_score_gemma":0.00043578006,"threshold_uncertainty_score":0.9988074},"labels":[],"label_agreement":null},{"id":"W3037957272","doi":"10.1186/s12874-020-01036-5","title":"Explaining the variation in the attained power of a stepped-wedge trial with unequal cluster sizes","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"Servier; Bayer Canada; Vancouver Coastal Health Research Institute; Biogen; Michael Smith Health Research BC; Compute Canada; Western Canada Research Grid; Heart and Stroke Foundation of Canada","keywords":"Statistics; Intraclass correlation; Mathematics; Linear regression; Cluster (spacecraft); Power (physics); Correlation; Statistical power; Coefficient of variation; Econometrics; Computer science; Physics; Thermodynamics","score_opus":0.920380177653608,"score_gpt":0.6920578964242246,"score_spread":0.22832228122938347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037957272","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0763945,0.000041164523,0.90195423,0.018089935,0.0002791632,0.002316703,0.000011858028,0.000029360108,0.00088310626],"genre_scores_gemma":[0.17465039,0.00002180703,0.822349,0.0017189094,0.00080859306,0.00037947015,0.0000013503208,0.000034517507,0.00003593872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8165442,0.17507286,0.0022426834,0.00077532965,0.004327169,0.0010377897],"domain_scores_gemma":[0.11952629,0.87868667,0.0003594018,0.0007265626,0.00036474236,0.00033636286],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1836931,0.00019598105,0.0010849136,0.00012490894,0.00013695785,0.000034264267,0.0013930604,0.00043513183,0.0011463611],"category_scores_gemma":[0.91482174,0.00009089202,0.00014722286,0.0010862882,0.001448961,0.000047940186,0.0004469536,0.0020213604,0.000020447433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15467694,0.0008605869,0.00036868447,0.0006532761,0.00023154124,0.0001445572,0.03063131,0.000030395433,0.00042791336,0.7869696,0.008867989,0.016137213],"study_design_scores_gemma":[0.06770177,0.007926935,0.0014796329,0.00027012115,0.00012481752,0.000019966092,0.0121214595,0.007800756,0.00028272622,0.9009795,0.0009780943,0.00031420842],"about_ca_topic_score_codex":0.00007027879,"about_ca_topic_score_gemma":0.00012675513,"teacher_disagreement_score":0.73112863,"about_ca_system_score_codex":0.00004099296,"about_ca_system_score_gemma":0.0010082204,"threshold_uncertainty_score":0.9997667},"labels":[],"label_agreement":null},{"id":"W3041396397","doi":"10.1177/0962280220932962","title":"Mixed-effects models for the design and analysis of stepped wedge cluster randomized trials: An overview","year":2020,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"National Center for Advancing Translational Sciences; National Institute on Drug Abuse; National Institute for Health and Care Research","keywords":"Computer science; Confounding; Research design; Cluster (spacecraft); Clinical study design; Econometrics; Management science; Risk analysis (engineering); Data science; Operations research; Medicine; Statistics; Mathematics; Clinical trial; Engineering","score_opus":0.9463831388066777,"score_gpt":0.7778418496968618,"score_spread":0.16854128910981592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041396397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1470226e-8,0.45876813,0.52903146,0.00021834402,0.00031860324,0.011048316,0.000546974,0.000023155177,0.000044997014],"genre_scores_gemma":[9.028888e-8,0.49116793,0.50475293,0.00006965491,0.00020227411,0.0036788674,0.000021273063,0.000088459696,0.000018521947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.51096505,0.47086933,0.009951133,0.0020889873,0.004582991,0.0015425098],"domain_scores_gemma":[0.04442916,0.9503744,0.0015041998,0.0015421334,0.0007138472,0.0014362484],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5551415,0.0009410062,0.026074596,0.0012272828,0.00021299873,0.000166126,0.0022114436,0.0017680826,0.0010115993],"category_scores_gemma":[0.97361684,0.0005055639,0.0024298835,0.004074937,0.0041842386,0.00008597986,0.0010936299,0.0042431825,0.0000061557325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065810704,0.00019482462,2.5796567e-8,0.018890265,0.0032660994,0.000037228216,0.00005871476,0.0000027073675,8.033118e-8,0.38208544,0.0006756268,0.5882079],"study_design_scores_gemma":[0.019673198,0.0003341664,3.2607466e-7,0.00525555,0.020156538,0.0000033610645,0.00002529548,0.25444874,0.0000011147898,0.68005204,0.01971435,0.00033529862],"about_ca_topic_score_codex":0.00004566109,"about_ca_topic_score_gemma":0.000011289847,"teacher_disagreement_score":0.5878726,"about_ca_system_score_codex":0.00020598486,"about_ca_system_score_gemma":0.0014988476,"threshold_uncertainty_score":0.9999016},"labels":[],"label_agreement":null},{"id":"W3041569196","doi":"10.1007/s43441-020-00195-3","title":"Collection of Post-treatment PRO Data in Oncology Clinical Trials","year":2020,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fluidigm (Canada)","funders":"EMD Serono; Merck KGaA; GlaxoSmithKline","keywords":"Clinical trial; Medicine; Pharmacy; Data collection; Descriptive statistics; Modalities; Protocol (science); Medical physics; MEDLINE; Attrition; Research design; Cohort; Family medicine; Alternative medicine; Internal medicine; Statistics","score_opus":0.8903234162451201,"score_gpt":0.6728231352039439,"score_spread":0.21750028104117625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041569196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88630617,0.00006935627,0.096545324,0.010236673,0.001856943,0.0030894214,0.00011484407,0.0001429821,0.0016382702],"genre_scores_gemma":[0.7574873,0.00001545813,0.24062672,0.0015332937,0.00023952204,0.000028582199,0.000005907485,0.000016304128,0.000046893303],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99172455,0.0031596348,0.003430686,0.0007184703,0.00068552926,0.0002811571],"domain_scores_gemma":[0.9481192,0.046460792,0.002400038,0.001603606,0.0012466575,0.0001697056],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05409087,0.00016418486,0.0011061728,0.00028723138,0.000094607836,0.000025113195,0.00082551857,0.00019779145,0.00014880334],"category_scores_gemma":[0.17723998,0.00012644939,0.00006986947,0.003878372,0.0011448633,0.00024575111,0.00019555438,0.00024992917,0.000012521872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011294015,0.00091790565,0.004892977,0.00006821556,0.00009470269,0.000004500309,0.0008872347,0.0000063472953,0.040750496,0.36181098,0.0002749834,0.58916223],"study_design_scores_gemma":[0.007033236,0.0051884945,0.061982468,0.000103173086,0.00022172752,0.0000079543115,0.00055502076,0.013596453,0.030058634,0.87426454,0.0064930785,0.0004952086],"about_ca_topic_score_codex":0.000013137011,"about_ca_topic_score_gemma":0.000009563658,"teacher_disagreement_score":0.58866704,"about_ca_system_score_codex":0.00021475274,"about_ca_system_score_gemma":0.0015838279,"threshold_uncertainty_score":0.9740125},"labels":[],"label_agreement":null},{"id":"W3043363813","doi":"10.1097/jcp.0000000000001266","title":"Statistics Commentary Series. Commentary No. 42: Minimization","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Library science; Psychiatry; Psychology; Computer science","score_opus":0.5103370026933072,"score_gpt":0.6218493604379933,"score_spread":0.11151235774468615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043363813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03267124,0.00024241836,0.4767904,0.4416846,0.043457557,0.00155167,0.0010390437,0.00015633673,0.0024067245],"genre_scores_gemma":[0.0035732905,0.0008218594,0.8091028,0.1780696,0.008303876,0.0000062985955,0.0000072072257,0.00005813602,0.000056922072],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9894373,0.0035856178,0.0056072376,0.00037601948,0.0006053967,0.0003884239],"domain_scores_gemma":[0.9335072,0.061799936,0.0028082642,0.00026193899,0.00075695844,0.0008656974],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053831176,0.00030250347,0.0018878524,0.000077249606,0.00008640607,0.000029593428,0.0007296938,0.00035241278,0.004072483],"category_scores_gemma":[0.0714189,0.00025680882,0.00047762855,0.00025309867,0.00048018375,0.00019826564,0.00016481613,0.0016961722,0.0001310006],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008400567,0.0010054954,0.0016998039,0.00012323564,0.00056684425,0.0002818907,0.00006991893,0.000009099081,0.00016472278,0.0012022028,0.9715781,0.014898082],"study_design_scores_gemma":[0.027703082,0.008166583,0.0015046912,0.00011164906,0.0014546479,0.0000937618,0.000117806485,0.001333299,0.00022490755,0.45244196,0.5062644,0.0005832312],"about_ca_topic_score_codex":0.0000016827,"about_ca_topic_score_gemma":9.833184e-7,"teacher_disagreement_score":0.46531376,"about_ca_system_score_codex":0.000049263883,"about_ca_system_score_gemma":0.000113933,"threshold_uncertainty_score":0.99998844},"labels":[],"label_agreement":null},{"id":"W3044786318","doi":"10.17504/protocols.io.ba4nigve","title":"Protocol for Geostatistical Determination of Radiation Dosimetry Maps of Population-Scale Exposures v1","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Kriging; Dosimetry; Population; Environmental science; Radiation; Sampling (signal processing); Radiation monitoring; Statistics; Remote sensing; Nuclear medicine; Mathematics; Geology; Physics; Medicine; Optics","score_opus":0.5001336756430176,"score_gpt":0.5878721403417746,"score_spread":0.08773846469875701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044786318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020197396,0.0000014086746,0.862385,0.0001237529,0.00030209846,0.134582,0.0018117074,0.000064585765,0.00052749785],"genre_scores_gemma":[0.003938943,8.05108e-7,0.8858618,0.000033760698,0.00027698735,0.109633,0.00013628132,0.00005269586,0.000065716114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951914,0.0007194647,0.0026905136,0.0005633819,0.00061616703,0.00021908864],"domain_scores_gemma":[0.9534143,0.04384436,0.0017487523,0.00055003416,0.00032325147,0.00011926027],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022711204,0.00030656825,0.0013778403,0.00014212786,0.00003284298,0.000025877745,0.00034713122,0.00059059926,0.00032383716],"category_scores_gemma":[0.10049234,0.00027083923,0.00033985524,0.00014848,0.00013212385,0.000042974738,0.00028880598,0.00035017528,0.0000030047922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017924728,0.0011299442,0.005595208,0.028543122,0.00023179576,0.0000026304338,0.00030163745,0.000027580196,0.0007530013,0.55884945,0.012797776,0.38997534],"study_design_scores_gemma":[0.0016202397,0.00037967667,0.0037468867,0.00035015313,0.00021207027,4.461384e-7,0.000014321244,0.0060539525,0.022202317,0.9650183,0.00015419877,0.00024745395],"about_ca_topic_score_codex":0.000050523973,"about_ca_topic_score_gemma":0.0000074745735,"teacher_disagreement_score":0.4061688,"about_ca_system_score_codex":0.00006393344,"about_ca_system_score_gemma":0.000106163774,"threshold_uncertainty_score":0.99997437},"labels":[],"label_agreement":null},{"id":"W3046977721","doi":"10.1158/1538-7445.pedca19-a21","title":"Abstract A21: Time-to-event Bayesian optimal interval design to accelerate phase I pediatric oncology trials","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Medicine; Maximum tolerated dose; Event (particle physics); Interval (graph theory); Accrual; Confidence interval; Clinical trial; Computer science; Oncology; Internal medicine; Statistics; Artificial intelligence; Mathematics","score_opus":0.8968177525830496,"score_gpt":0.72093317679735,"score_spread":0.1758845757856996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046977721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031858478,0.00013379757,0.9280596,0.029595839,0.0007839929,0.006064,0.00054359337,0.00017066723,0.0027900524],"genre_scores_gemma":[0.05780321,0.00012923058,0.9299438,0.002461679,0.0060929866,0.0016421527,0.0000032601636,0.00016279664,0.0017609015],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9880386,0.0068449816,0.0019310651,0.0009396568,0.0011653932,0.0010803188],"domain_scores_gemma":[0.9105026,0.086603664,0.00027376355,0.0005219269,0.0005431153,0.0015549446],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.029385626,0.0002925839,0.0015884865,0.0002872323,0.000158702,0.00016147642,0.001047665,0.00028559545,0.0264753],"category_scores_gemma":[0.23977792,0.00024709955,0.00025911097,0.0012373459,0.00012624201,0.000079319136,0.0005569191,0.0011563322,0.004084078],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014133727,0.0012941658,0.000013957914,0.000518141,0.00029805693,0.00032954843,0.0015692051,0.0007086014,0.035770986,0.0016547552,0.6542891,0.2894197],"study_design_scores_gemma":[0.048395924,0.050061632,0.0003187129,0.0010687654,0.0013073253,0.000020339907,0.0009941785,0.014092249,0.2955474,0.28895488,0.29473662,0.004501992],"about_ca_topic_score_codex":0.0000240674,"about_ca_topic_score_gemma":0.0000022616205,"teacher_disagreement_score":0.35955253,"about_ca_system_score_codex":0.0004846574,"about_ca_system_score_gemma":0.0010505235,"threshold_uncertainty_score":0.99999815},"labels":[],"label_agreement":null},{"id":"W3047282220","doi":"10.1080/19466315.2020.1804444","title":"Clinical Trial Drug Safety Assessment for Studies and Submissions Impacted by COVID-19","year":2020,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Clinical trial; Medicine; Pandemic; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medical emergency; Medical physics; Pathology","score_opus":0.9333092801230759,"score_gpt":0.7976081043465881,"score_spread":0.13570117577648777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047282220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070173675,0.0011106499,0.92999786,0.042713277,0.001235734,0.008122859,0.009129282,0.0001820911,0.00049088604],"genre_scores_gemma":[0.020545535,0.0035873884,0.97128296,0.0030576163,0.0007432725,0.00042423644,0.000038858503,0.00008384158,0.00023626682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98516023,0.008045508,0.0027841514,0.0012070405,0.0015617281,0.0012413681],"domain_scores_gemma":[0.5561916,0.4397702,0.00024623732,0.0004357113,0.0006880656,0.0026681817],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035708155,0.0003616977,0.0014794966,0.00015740834,0.00043944857,0.00012366663,0.0005779733,0.00032910326,0.0005618733],"category_scores_gemma":[0.71159303,0.00029494835,0.00015393656,0.00076791097,0.0021966489,0.00006254579,0.0007321509,0.0023868035,0.000021391743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.055780552,0.0011442754,0.000857811,0.0021050242,0.00037762482,0.00013415783,0.00053521025,0.0000012816234,0.00042920394,0.4798917,0.41919732,0.03954586],"study_design_scores_gemma":[0.052085143,0.0016112524,0.00017114438,0.00007804989,0.0001374959,0.000001675949,0.00060067023,0.0061814096,0.00011174177,0.9019262,0.036722567,0.00037262624],"about_ca_topic_score_codex":0.0000152199,"about_ca_topic_score_gemma":0.000009619626,"teacher_disagreement_score":0.6758849,"about_ca_system_score_codex":0.00041355088,"about_ca_system_score_gemma":0.0010351876,"threshold_uncertainty_score":0.9999503},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3048301534","doi":"10.1002/cpt.2012","title":"Use of Real‐World Data to Emulate a Clinical Trial and Support Regulatory Decision Making: Assessing the Impact of Temporality, Comparator Choice, and Method of Adjustment","year":2020,"lang":"en","type":"article","venue":"Clinical Pharmacology & Therapeutics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Liraglutide; Hazard ratio; Propensity score matching; Confidence interval; Clinical trial; Internal medicine; Comparator; Type 2 diabetes; Diabetes mellitus; Endocrinology","score_opus":0.9099604995971161,"score_gpt":0.7418507534591007,"score_spread":0.16810974613801544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048301534","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96281075,0.00010729349,0.031642947,0.001740717,0.0011798914,0.0020189688,0.00043721034,0.000037186855,0.00002502468],"genre_scores_gemma":[0.43653655,0.0004916638,0.55720115,0.004970198,0.00072691555,0.000011146049,0.000004806698,0.000049674065,0.000007921848],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9848485,0.007960622,0.0054255105,0.00090078043,0.0005049775,0.00035963603],"domain_scores_gemma":[0.7726097,0.22257808,0.0027349533,0.0012612371,0.00036821133,0.00044784072],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017937662,0.00036124772,0.0028218573,0.00009440839,0.000067413726,0.000032257012,0.0009479207,0.00034526087,0.0001114892],"category_scores_gemma":[0.02403508,0.00024002136,0.00044818953,0.00048756666,0.0018334559,0.00014351835,0.0014152864,0.0009077383,0.0000017659489],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10427307,0.009771997,0.41191456,0.000845197,0.012445666,0.00003374195,0.00071595993,0.00017403692,0.007941008,0.0030193916,0.103655025,0.34521034],"study_design_scores_gemma":[0.054408483,0.013809921,0.8298587,0.0003498106,0.009307312,0.0000093191875,0.000088414505,0.031701215,0.00091801264,0.055238184,0.003492601,0.00081799313],"about_ca_topic_score_codex":0.000026398515,"about_ca_topic_score_gemma":0.000008505236,"teacher_disagreement_score":0.5262742,"about_ca_system_score_codex":0.000028294593,"about_ca_system_score_gemma":0.00035377257,"threshold_uncertainty_score":0.9841859},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3049274067","doi":"10.1002/pds.5086","title":"Understanding when real world data can be used to replicate a clinical trial: A cross‐sectional study of medications approved in 2011","year":2020,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Clinical trial; Linagliptin; Family medicine; Database; Internal medicine","score_opus":0.9316882090661378,"score_gpt":0.6753659160930127,"score_spread":0.25632229297312514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049274067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52283096,0.00004854761,0.34060138,0.12415842,0.001855204,0.007329614,0.0016460753,0.00027773544,0.0012520445],"genre_scores_gemma":[0.82824004,0.00014263878,0.16647807,0.004170048,0.0006711993,0.00015456486,0.000039420316,0.00003685676,0.00006717533],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98477834,0.009492429,0.0038483304,0.0012098039,0.00028899722,0.00038208536],"domain_scores_gemma":[0.796953,0.20046811,0.0010065918,0.00095981883,0.000078906625,0.0005335519],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041671626,0.00022475082,0.0015282504,0.000120677294,0.00012595224,0.000010883555,0.0007251808,0.00014140217,0.0002211003],"category_scores_gemma":[0.16403487,0.00019471867,0.000101312355,0.00032819752,0.00053480203,0.0000725615,0.0007057643,0.0008342087,0.000006081348],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.045443114,0.0020766575,0.84529454,0.00013410031,0.00065355597,0.0000152548555,0.002798106,0.000026973426,0.000049134782,0.06209311,0.03985665,0.0015588176],"study_design_scores_gemma":[0.082825445,0.0013747385,0.22473985,0.000056845944,0.0006873703,0.0000030594654,0.0010178476,0.00869674,0.000021541342,0.6774656,0.002489886,0.00062107894],"about_ca_topic_score_codex":0.0008103159,"about_ca_topic_score_gemma":0.0023640245,"teacher_disagreement_score":0.6205547,"about_ca_system_score_codex":0.00007348445,"about_ca_system_score_gemma":0.0001371445,"threshold_uncertainty_score":0.98680073},"labels":[],"label_agreement":null},{"id":"W3081741376","doi":"10.6084/m9.figshare.19091781.v1","title":"Deep historical borrowing framework to prospectively and simultaneously synthesize control information in confirmatory clinical trials with multiple endpoints","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Control (management); Confirmatory factor analysis; Econometrics; Computer science; Data mining; Psychology; Medicine; Artificial intelligence; Structural equation modeling; Internal medicine; Machine learning; Mathematics","score_opus":0.4477339699852482,"score_gpt":0.5281867823554337,"score_spread":0.08045281237018548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081741376","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000067116093,0.00007424272,0.002733307,0.00016055627,0.00054266636,0.004085994,0.99226725,0.0001049722,0.000024320725],"genre_scores_gemma":[0.00012782303,0.000019449162,0.11899111,0.0014260244,0.00058828096,0.0028477188,0.8759011,0.0000835033,0.000015018888],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98764354,0.0059283637,0.0040247147,0.0008181702,0.0010157389,0.0005694752],"domain_scores_gemma":[0.4231208,0.5722806,0.0025540015,0.0011152754,0.00034798542,0.00058132486],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008965822,0.0006298593,0.0034242931,0.0003015076,0.00015671874,0.00012581686,0.0006956322,0.0010936188,0.15328108],"category_scores_gemma":[0.9143973,0.0005304304,0.0003124766,0.00036550846,0.00003532909,0.00019607399,0.00040764682,0.0026293686,0.0003261533],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016631194,0.0002482523,0.000035990524,0.0010030045,0.00015714939,0.0001720041,0.0000993801,0.000035101133,1.3501287e-7,0.000050722796,0.9934559,0.0030792565],"study_design_scores_gemma":[0.0037556028,0.00074435765,0.00021610045,0.0037788115,0.00030909767,0.000028231952,0.000075495336,0.0005690327,0.000002489715,0.015902866,0.9737405,0.0008774238],"about_ca_topic_score_codex":0.000038117952,"about_ca_topic_score_gemma":0.000060177263,"teacher_disagreement_score":0.90543145,"about_ca_system_score_codex":0.0008035764,"about_ca_system_score_gemma":0.00032795686,"threshold_uncertainty_score":0.99971473},"labels":[],"label_agreement":null},{"id":"W3081849395","doi":"10.1002/pst.2067","title":"A stochastically curtailed two‐arm randomised phase<scp>II</scp>trial design for binary outcomes","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Cancer Research UK","keywords":"Interim; Interim analysis; Research design; Early stopping; Sample size determination; Outcome (game theory); Clinical study design; Null hypothesis; Randomized controlled trial; Computer science; Statistics; Medicine; Mathematics; Clinical trial; Surgery; Machine learning; Internal medicine","score_opus":0.6908497330030037,"score_gpt":0.6098577142060511,"score_spread":0.08099201879695261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081849395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002343198,0.000061977524,0.98122233,0.0018888928,0.0016414254,0.008352775,0.0035857907,0.00047793562,0.00042565112],"genre_scores_gemma":[0.017705698,0.000037874834,0.97525585,0.0037602058,0.0015712494,0.0011902684,0.000050376184,0.0002170554,0.00021143278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912089,0.0020359396,0.0028368714,0.0012195533,0.0012454785,0.0014532172],"domain_scores_gemma":[0.74346805,0.2536289,0.00052946876,0.00045844144,0.00045186887,0.0014632603],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00477959,0.00085570256,0.0024429162,0.00010352921,0.00045960344,0.00016624748,0.0008865992,0.0003524349,0.0007576511],"category_scores_gemma":[0.44364116,0.0007284728,0.0005564381,0.00045518664,0.0006340509,0.000119981116,0.00041129428,0.0010721075,0.00017147698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.19980405,0.0073388848,0.000025923537,0.0010784776,0.0016831423,0.00026206675,0.0006714025,0.00022907623,0.002547823,0.643594,0.11669336,0.026071796],"study_design_scores_gemma":[0.31675056,0.0049087764,0.0000030792328,0.000037540496,0.0015550334,0.0000035513451,0.000034936205,0.1364043,0.0018453739,0.5323464,0.0057485187,0.00036187647],"about_ca_topic_score_codex":0.0000018728248,"about_ca_topic_score_gemma":4.5067432e-7,"teacher_disagreement_score":0.43886158,"about_ca_system_score_codex":0.00011983753,"about_ca_system_score_gemma":0.00031714988,"threshold_uncertainty_score":0.9995166},"labels":[],"label_agreement":null},{"id":"W3081949500","doi":"10.1136/bmjopen-2019-036755","title":"Adaptive design methods in dialysis clinical trials: a systematic review protocol","year":2020,"lang":"en","type":"review","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Health Research Board; Canadian Institute for Theoretical Astrophysics; Health Service Executive; Wellcome Trust; Wellcome","keywords":"Medicine; Clinical trial; Data extraction; Protocol (science); MEDLINE; Dialysis; Clinical study design; Meta-analysis; Research design; Medical physics; Adaptive design; Systematic review; Intensive care medicine; Randomized controlled trial; Alternative medicine; Internal medicine; Pathology","score_opus":0.9796589416060499,"score_gpt":0.834885844905228,"score_spread":0.14477309670082195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081949500","genre_codex":"protocol","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.8282806e-12,0.3146276,0.2597245,0.00007231769,0.0001922795,0.4245497,0.00006590594,0.00004274066,0.0007249705],"genre_scores_gemma":[1.25453615e-11,0.30757967,0.34991032,0.00018552723,0.00024383642,0.3418708,0.0000020426269,0.00009225557,0.00011553736],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.42970884,0.5280516,0.037523217,0.002491413,0.0013820719,0.000842816],"domain_scores_gemma":[0.19295202,0.7844736,0.017824119,0.0037592433,0.00031889605,0.0006721258],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.5012028,0.0013408521,0.05798128,0.0002448689,0.000073403295,0.00034032785,0.0047978065,0.0013722618,0.0010449743],"category_scores_gemma":[0.9464198,0.0008302983,0.0049954145,0.0020566927,0.00020572086,0.00015300843,0.0025168043,0.0020315882,0.0005363522],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016601842,0.00019699406,2.9636675e-8,0.58442026,0.0011006634,0.00009421015,0.0000106071875,2.744419e-8,2.227381e-9,0.0025741085,0.0052247597,0.4062123],"study_design_scores_gemma":[0.0012388031,0.00036207147,1.6471562e-8,0.6768839,0.019304823,0.000020025485,0.000008306368,0.000074774995,1.04983684e-7,0.1597098,0.14165188,0.0007455225],"about_ca_topic_score_codex":0.000010126581,"about_ca_topic_score_gemma":0.0000044995413,"teacher_disagreement_score":0.44521692,"about_ca_system_score_codex":0.00034343166,"about_ca_system_score_gemma":0.0026539434,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W3082857472","doi":"10.1128/aac.01597-20","title":"Novel Antibiotics May Be Noninferior but Are They Becoming Less Effective?: a Systematic Review","year":2020,"lang":"en","type":"review","venue":"Antimicrobial Agents and Chemotherapy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre; University of Toronto; McMaster University","funders":"","keywords":"Antibiotics; Medicine; Intensive care medicine; Systematic review; Clinical trial; MEDLINE; Internal medicine; Biology; Microbiology","score_opus":0.40876460531480463,"score_gpt":0.512973886408449,"score_spread":0.10420928109364436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082857472","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000034160945,0.97525436,0.008787524,0.0017032878,0.00081724697,0.011837929,0.001241311,0.00019714452,0.00012704934],"genre_scores_gemma":[0.00000565882,0.9226804,0.06871765,0.0076665585,0.00037918988,0.000052974166,0.000018632247,0.00025904176,0.0002199419],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.99393606,0.001317193,0.002677977,0.0010854321,0.00040643074,0.0005768927],"domain_scores_gemma":[0.9838302,0.012508434,0.002354059,0.00089791813,0.00013309339,0.0002762683],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021958717,0.0011357273,0.009647365,0.00010057234,0.00018620533,0.00018945782,0.0007667174,0.00067025464,0.000108638356],"category_scores_gemma":[0.009890237,0.000805159,0.0012520606,0.00030473678,0.00019677528,0.000063848755,0.00027311873,0.00083730696,0.000045892753],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014936605,0.00028262328,0.000003935447,0.9060235,0.0011522471,0.00006676795,0.00006318681,8.993621e-9,0.000007992258,0.00048003075,0.004917194,0.086987555],"study_design_scores_gemma":[0.0012554378,0.00010866992,0.0000035874432,0.8479469,0.0076900534,0.00024141111,0.000022287308,0.0000072638136,0.000028050637,0.0013152453,0.14025292,0.0011281807],"about_ca_topic_score_codex":0.000020674792,"about_ca_topic_score_gemma":0.0000044607928,"teacher_disagreement_score":0.13533573,"about_ca_system_score_codex":0.00012592874,"about_ca_system_score_gemma":0.00013324634,"threshold_uncertainty_score":0.99943995},"labels":[],"label_agreement":null},{"id":"W3083215408","doi":"","title":"Novel statistical designs for phase I clinical trials","year":2019,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Regina","keywords":"Clinical trial; Computer science; Medical physics; Medicine; Statistics; Mathematics; Internal medicine","score_opus":0.7224308435934372,"score_gpt":0.5831373374677754,"score_spread":0.13929350612566183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083215408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011055393,0.0000348854,0.9759104,0.0002464123,0.003414888,0.0031577963,0.003937781,0.000100819016,0.0021415928],"genre_scores_gemma":[0.0020799784,0.00010092076,0.9929016,0.000040141378,0.00051108387,0.0000058511287,0.00039646536,0.00010776561,0.0038561667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993708,0.0025433498,0.0016953523,0.0008949953,0.00068700366,0.00047127448],"domain_scores_gemma":[0.8224833,0.17361578,0.002327365,0.00073647185,0.00056071056,0.00027634398],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.017077629,0.00046229368,0.003599729,0.00021547654,0.00016909039,0.000035978963,0.00079744693,0.0012513036,0.00022794676],"category_scores_gemma":[0.18392462,0.00051480986,0.0011505813,0.0001831696,0.00027900215,0.00009376615,0.00009649391,0.0007821314,0.00010898227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026396882,0.0075150845,0.00064310734,0.0077392086,0.003807073,0.000093092916,0.00049031357,0.0000050796516,0.0033007206,0.57860744,0.22312014,0.14828183],"study_design_scores_gemma":[0.047106218,0.0061988747,0.0063063446,0.0017408392,0.011649484,0.000007062312,0.02078741,0.004396243,0.0007691403,0.88019216,0.018470306,0.0023759033],"about_ca_topic_score_codex":0.00011066201,"about_ca_topic_score_gemma":0.0066754106,"teacher_disagreement_score":0.30158472,"about_ca_system_score_codex":0.00011540838,"about_ca_system_score_gemma":0.00044513,"threshold_uncertainty_score":0.99973035},"labels":[],"label_agreement":null},{"id":"W3085257600","doi":"10.5539/ijsp.v9n6p9","title":"Confidence Interval for Change Point in Hazard Rate With Staggered Entry","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health","keywords":"Confidence interval; Mathematics; Hazard ratio; Statistics; Interval (graph theory); Coverage probability; Hazard; Limiting; Credible interval; CDF-based nonparametric confidence interval; Point process; Point estimation; Confidence distribution; Confidence region; Probability density function; Econometrics; Combinatorics","score_opus":0.46439962567045334,"score_gpt":0.5083671680932091,"score_spread":0.0439675424227558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085257600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03957125,0.000035622572,0.95213586,0.006286374,0.00043434152,0.00053261215,0.0009408967,0.000007727031,0.00005533412],"genre_scores_gemma":[0.2844721,0.000059193022,0.7145517,0.000590422,0.00028965756,0.00001776424,0.000002227577,0.000011370149,0.000005549748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796426,0.00031263733,0.001021953,0.00020301125,0.00035410776,0.00014404875],"domain_scores_gemma":[0.98389333,0.014422455,0.00058723,0.0000872335,0.0008503296,0.00015939352],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002606242,0.00012859405,0.000467889,0.000046258712,0.00001853016,0.00006626335,0.000259368,0.000056044857,0.000103277176],"category_scores_gemma":[0.043588564,0.00009614977,0.0000582432,0.000058730442,0.00016285846,0.00012119587,0.000069639806,0.00025571143,8.6312264e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008334775,0.0004959539,0.010866146,0.0006892085,0.0003641231,0.00023587793,0.002197859,0.000015574462,0.00019012073,0.92522496,0.0023247171,0.049060687],"study_design_scores_gemma":[0.002231196,0.0008788137,0.0049923114,0.00020883534,0.000044582197,0.000021387772,0.00007762601,0.0016986878,0.0001983407,0.98919564,0.00033941865,0.00011318047],"about_ca_topic_score_codex":0.000009515014,"about_ca_topic_score_gemma":0.000027245203,"teacher_disagreement_score":0.24490085,"about_ca_system_score_codex":0.00006343828,"about_ca_system_score_gemma":0.00009631917,"threshold_uncertainty_score":0.9644677},"labels":[],"label_agreement":null},{"id":"W308741866","doi":"10.22237/jmasm/1099267380","title":"Assessing Treatment Effects in Randomized Longitudinal Two-Group Designs with Missing Observations","year":2004,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Missing data; Covariate; Analysis of covariance; Statistics; Mathematics; Mixed model; Repeated measures design; Longitudinal data; Econometrics; Computer science; Data mining","score_opus":0.6003304797608118,"score_gpt":0.5931426660975935,"score_spread":0.007187813663218301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W308741866","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052233073,0.0001163458,0.9922133,0.00026943558,0.00027992745,0.0011292874,0.000013691268,0.000040343977,0.0007143338],"genre_scores_gemma":[0.13666457,0.000016916016,0.8628527,0.00008160393,0.00021677671,0.00009018966,0.0000015235422,0.00007031544,0.0000054284606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9876102,0.007676757,0.00277066,0.0005109928,0.000818881,0.0006124625],"domain_scores_gemma":[0.80647534,0.1914152,0.0011814306,0.0003446327,0.00020202379,0.00038133466],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.022272425,0.0004885081,0.0031987433,0.00028365356,0.00015057872,0.0002260565,0.00030057313,0.00020491291,0.000046633348],"category_scores_gemma":[0.06636839,0.00032177736,0.0003005146,0.0004284182,0.00051271106,0.00022312392,0.000052495205,0.00077954266,0.0000023546638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009643711,0.0011318172,0.000082598184,0.00017041937,0.0004057775,0.0003731672,0.00030161662,0.0011180517,0.0072733467,0.60679936,0.0000056057143,0.37269452],"study_design_scores_gemma":[0.10474838,0.00056198065,0.0014037307,0.00045958222,0.0009226794,0.00008831516,0.000043411812,0.0052195666,0.001736052,0.88450056,0.0000042142624,0.00031149157],"about_ca_topic_score_codex":0.000018821378,"about_ca_topic_score_gemma":0.0000098890605,"teacher_disagreement_score":0.37238303,"about_ca_system_score_codex":0.0006176703,"about_ca_system_score_gemma":0.0003959941,"threshold_uncertainty_score":0.9999234},"labels":[],"label_agreement":null},{"id":"W3087734770","doi":"10.1038/s41393-020-00547-8","title":"Adaptive trial designs for spinal cord injury clinical trials directed to the central nervous system","year":2020,"lang":"en","type":"review","venue":"Spinal Cord","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Collaboration On Repair Discoveries; University of British Columbia","funders":"","keywords":"Medicine; Clinical trial; Adaptive design; Scope (computer science); Randomized controlled trial; Spinal cord injury; Narrative review; Clinical study design; Physical medicine and rehabilitation; Physical therapy; Risk analysis (engineering); Intensive care medicine; Computer science; Spinal cord; Surgery","score_opus":0.9158807423829161,"score_gpt":0.6974960927440162,"score_spread":0.2183846496388998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087734770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004791759,0.43869504,0.49914306,0.00049011275,0.020759935,0.036125004,0.0036887312,0.0007730173,0.00032030867],"genre_scores_gemma":[0.000023728318,0.39620152,0.5764703,0.0003397956,0.022031577,0.004286034,0.00003356177,0.00037204882,0.00024138961],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9558732,0.028440315,0.011012085,0.0020269812,0.0012294146,0.0014180404],"domain_scores_gemma":[0.8225352,0.16798453,0.00566942,0.0018608968,0.0006049044,0.0013450277],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.039566312,0.0014622376,0.01482772,0.00020164555,0.00036162807,0.0002700902,0.002285546,0.001501822,0.000117712],"category_scores_gemma":[0.47344032,0.00090428244,0.0056293467,0.0011075255,0.00035577687,0.00006017687,0.00057792,0.0022930854,0.00033989115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.26485586,0.00017576874,5.31792e-8,0.0067021265,0.0008187262,0.000052287338,0.0000033935514,2.5644544e-8,1.12632186e-7,0.023906726,0.015278091,0.68820685],"study_design_scores_gemma":[0.009454937,0.083862394,0.000002641331,0.018192582,0.010727363,0.00003494495,0.000048945512,0.000045125835,0.000001238708,0.032870095,0.8436489,0.0011108253],"about_ca_topic_score_codex":0.00002141818,"about_ca_topic_score_gemma":0.000008425579,"teacher_disagreement_score":0.8283708,"about_ca_system_score_codex":0.00058090355,"about_ca_system_score_gemma":0.0017733854,"threshold_uncertainty_score":0.9998127},"labels":[],"label_agreement":null},{"id":"W3089057837","doi":"10.1101/2020.09.25.314138","title":"Improving drug safety predictions by reducing poor analytical practices","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prioris.ai (Canada)","funders":"","keywords":"Risk analysis (engineering); Computer science; Reuse; Simple (philosophy); Drug; Medicine; Engineering; Pharmacology","score_opus":0.19922163310820185,"score_gpt":0.4269110192685788,"score_spread":0.22768938616037693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089057837","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070267186,0.001047452,0.8877925,0.012305301,0.010458161,0.005484684,0.007962383,0.0042825295,0.0003997493],"genre_scores_gemma":[0.3324022,0.00017484461,0.664225,0.0004289236,0.0021922726,0.0002450882,5.724268e-7,0.0003038495,0.000027278835],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9915185,0.0017880448,0.002460094,0.0022201177,0.0010846979,0.000928546],"domain_scores_gemma":[0.9705254,0.022272557,0.0033765577,0.0021350055,0.0007234921,0.00096700573],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006003833,0.000918674,0.0018640881,0.00020564154,0.0003656407,0.0004957885,0.0012137189,0.0010181731,0.00030572576],"category_scores_gemma":[0.23736528,0.000945504,0.00046763793,0.0007730769,0.0003639985,0.0002606389,0.0014550365,0.0032098335,0.00011161634],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014583943,0.0035462882,0.0024983683,0.012155532,0.005127843,0.0005852575,0.00013755394,0.00013882533,0.62117743,0.16837178,0.18466318,0.00013950981],"study_design_scores_gemma":[0.01582103,0.0016671114,0.017793506,0.013375473,0.026373593,6.207893e-7,0.00019990126,0.27903026,0.4920601,0.03734736,0.09577196,0.020559084],"about_ca_topic_score_codex":0.00016094156,"about_ca_topic_score_gemma":0.0000014108442,"teacher_disagreement_score":0.27889144,"about_ca_system_score_codex":0.0005248981,"about_ca_system_score_gemma":0.0010537447,"threshold_uncertainty_score":0.9992995},"labels":[],"label_agreement":null},{"id":"W3089540082","doi":"10.1177/0706743720962277","title":"<i>P</i> Values and Confidence Intervals","year":2020,"lang":"en","type":"letter","venue":"The Canadian Journal of Psychiatry","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University; University of Calgary","funders":"","keywords":"Confidence interval; Statistics; Mathematics","score_opus":0.3290208526229087,"score_gpt":0.4704316059378716,"score_spread":0.1414107533149629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089540082","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005006537,0.0012946106,0.0034039377,0.98682666,0.0068732067,0.00021453828,0.00014585852,0.000009569097,0.0011815478],"genre_scores_gemma":[0.00016479522,0.00005077145,0.3361326,0.6511866,0.011996883,0.0000022482077,6.804492e-7,0.000060896462,0.00040454313],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962841,0.0013177043,0.0013535296,0.000223222,0.00044466797,0.00037674326],"domain_scores_gemma":[0.9817087,0.015883364,0.0012301977,0.00043147267,0.00022865504,0.0005176134],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026520835,0.00028498386,0.0009732205,0.00012769838,0.00019860564,0.00019140782,0.0010109056,0.00046868293,0.0004196819],"category_scores_gemma":[0.029928349,0.00018561647,0.0003089153,0.00013503447,0.00066078425,0.00004890777,0.00004085291,0.0037149775,0.00002553743],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012179562,0.0000029997211,0.00011504509,0.0002028776,0.00017766478,0.00030161472,0.0001589968,6.755314e-8,3.509855e-7,0.0290137,0.9695202,0.0004943062],"study_design_scores_gemma":[0.00023815704,0.0001634605,0.000028524344,0.0006148317,0.0003996124,0.00029389685,0.000055225562,0.000002761075,0.0000031918707,0.884585,0.1134384,0.0001769007],"about_ca_topic_score_codex":0.0008602439,"about_ca_topic_score_gemma":0.008316444,"teacher_disagreement_score":0.8560818,"about_ca_system_score_codex":0.000071453105,"about_ca_system_score_gemma":0.002677203,"threshold_uncertainty_score":0.9985835},"labels":[],"label_agreement":null},{"id":"W3090053916","doi":"10.1016/j.jclinepi.2020.09.035","title":"Prerandomization run-in periods in randomized controlled trials of chronic diseases: a methodological study","year":2020,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University; Population Health Research Institute","funders":"Medical Research Council; Kidney Research UK","keywords":"Medicine; Randomized controlled trial; Randomization; Placebo; Epidemiology; Clinical trial; Internal medicine; Diabetes mellitus; Physical therapy; Alternative medicine; Pathology","score_opus":0.9354975320853159,"score_gpt":0.7636667749138659,"score_spread":0.17183075717145002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090053916","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005274207,0.8527902,0.1303963,0.00057191646,0.0033981667,0.012650947,0.00007589478,0.000017627066,0.0000462177],"genre_scores_gemma":[0.00004131401,0.72782624,0.26903155,0.00012648987,0.0024064532,0.00049293117,0.0000031993,0.000058768208,0.000013059025],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.0970511,0.7723615,0.12778154,0.0011742022,0.0008673416,0.0007643234],"domain_scores_gemma":[0.016890308,0.907364,0.07395164,0.0007474192,0.0004711506,0.0005754992],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad","research_integrity"],"category_scores_codex":[0.7640396,0.0010391249,0.24388911,0.00086252665,0.000028159395,0.000019164425,0.001361219,0.0024011317,0.0006360597],"category_scores_gemma":[0.99741733,0.00052004075,0.02730155,0.0007944478,0.0010913957,0.00008004332,0.00030812778,0.0048576347,0.000007583214],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.363821,0.0040325136,0.00043423593,0.007127185,0.0064994735,0.00030241258,0.000058322956,0.00004823094,3.8263952e-8,0.012260314,0.00028861975,0.6051277],"study_design_scores_gemma":[0.5177563,0.002771136,0.000058084843,0.011159747,0.017730681,0.000026806514,0.000026944725,0.0005845291,2.0456742e-8,0.44277212,0.0067810914,0.00033257564],"about_ca_topic_score_codex":0.000010886968,"about_ca_topic_score_gemma":0.000010256647,"teacher_disagreement_score":0.6047951,"about_ca_system_score_codex":0.00025987637,"about_ca_system_score_gemma":0.0025321555,"threshold_uncertainty_score":0.9997251},"labels":[],"label_agreement":null},{"id":"W3091344383","doi":"10.1186/s13063-020-04767-4","title":"Correction to: Cluster identification, selection, and description in Cluster randomized crossover trials: the PREP-IT trials","year":2020,"lang":"en","type":"erratum","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Identification (biology); Selection (genetic algorithm); Cluster (spacecraft); Medicine; Crossover; Randomized controlled trial; Crossover study; Data mining; Medical physics; Alternative medicine; Information retrieval; Data science; Computational biology; Computer science; Artificial intelligence; Pathology; Biology","score_opus":0.6424532027742019,"score_gpt":0.5850556488844754,"score_spread":0.05739755388972656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091344383","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011785112,0.0013443022,0.6230615,0.024204927,0.2919082,0.053576905,0.0007102109,0.00047465853,0.0046014814],"genre_scores_gemma":[0.001305244,0.005753859,0.25931782,0.013436165,0.08090435,0.020352446,0.00047115685,0.0010228113,0.6174361],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7276058,0.23282465,0.032774996,0.0030463324,0.0025325054,0.0012156662],"domain_scores_gemma":[0.13857746,0.8432728,0.014685123,0.0016799956,0.0012629083,0.0005217073],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.39377677,0.0010819101,0.015714085,0.00057698344,0.00037335037,0.0014046163,0.00081136636,0.0018403825,0.0015237429],"category_scores_gemma":[0.96772265,0.0006815988,0.0022299446,0.0011802708,0.0003886596,0.00030179927,0.0003401655,0.0025097434,0.00022912619],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13061795,0.00013826223,0.000002588883,0.00032001236,0.0008003941,0.0000020453228,0.00070245104,0.000023453282,0.00009661558,0.0017120694,0.8607491,0.004835039],"study_design_scores_gemma":[0.19690308,0.00028727917,0.000041398012,0.0015855816,0.006233746,0.000017067228,0.00016389176,0.003485949,0.000313764,0.62582505,0.16411206,0.0010311429],"about_ca_topic_score_codex":0.00017373991,"about_ca_topic_score_gemma":0.00045668698,"teacher_disagreement_score":0.69663703,"about_ca_system_score_codex":0.0004074507,"about_ca_system_score_gemma":0.000613442,"threshold_uncertainty_score":0.9997915},"labels":[],"label_agreement":null},{"id":"W3092182444","doi":"10.1097/jcp.0000000000001304","title":"Statistics Commentary Series. Commentary No. 44: Internal and External Validity","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Psychopharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Library science; Psychology; Psychiatry; Gerontology; Medicine; Computer science","score_opus":0.5778193067237402,"score_gpt":0.6262655305151876,"score_spread":0.048446223791447474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092182444","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31050175,0.00036322174,0.44049984,0.2104427,0.034984276,0.001103779,0.00094438664,0.0001024097,0.0010576033],"genre_scores_gemma":[0.021532388,0.0014056953,0.8372851,0.12999402,0.0096630305,0.0000053067884,0.0000019159736,0.00005580505,0.00005674862],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901602,0.003651458,0.004786425,0.0004147171,0.00058728363,0.00039989382],"domain_scores_gemma":[0.93741727,0.05851881,0.00233108,0.00022433187,0.000432664,0.0010758723],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007331962,0.00032666474,0.0019034437,0.00006794613,0.000087020715,0.000046252102,0.0007061911,0.0002966625,0.0024562103],"category_scores_gemma":[0.040870022,0.00027011245,0.00041046026,0.00012235527,0.00073028915,0.00020353915,0.00031436395,0.0022718275,0.000046395377],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011929216,0.00090643176,0.012542882,0.00016124596,0.0005534643,0.00056929863,0.00008974175,0.0000010823238,0.0005538905,0.0012423218,0.9479486,0.02350182],"study_design_scores_gemma":[0.029736277,0.011958795,0.007933127,0.00023432795,0.0014790484,0.00037265415,0.00010042905,0.00079053873,0.00038265708,0.7612898,0.185063,0.0006593521],"about_ca_topic_score_codex":0.0000054483125,"about_ca_topic_score_gemma":0.0000017194981,"teacher_disagreement_score":0.7628856,"about_ca_system_score_codex":0.000043244898,"about_ca_system_score_gemma":0.00007721969,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W3092379046","doi":"10.1002/pst.2073","title":"Utilizing Bayesian predictive power in clinical trial design","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of British Columbia","funders":"","keywords":"Bayesian probability; Interim; Interim analysis; Computer science; Adaptive design; Machine learning; Computation; Clinical trial; Predictive power; Clinical study design; Artificial intelligence; Data mining; Algorithm; Medicine","score_opus":0.8404547068645039,"score_gpt":0.6558272472679741,"score_spread":0.1846274595965297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092379046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097506685,0.00004536113,0.9909415,0.0014268296,0.0013527847,0.0020554313,0.00053354783,0.000218129,0.0024513344],"genre_scores_gemma":[0.1562919,0.000082009836,0.8399673,0.002660813,0.0008012603,0.00008532997,0.0000044623243,0.00008477647,0.00002213073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98966694,0.004574076,0.0030749994,0.0009644861,0.00085965585,0.0008598648],"domain_scores_gemma":[0.8824727,0.11550359,0.0003823479,0.00037955327,0.00016700396,0.0010948195],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0071483687,0.0004263998,0.001362138,0.000069876565,0.0000905986,0.00007944616,0.00056141906,0.00037324696,0.0022002957],"category_scores_gemma":[0.26593456,0.00039258576,0.00021986561,0.00051075686,0.00054465095,0.00009896429,0.00026683384,0.0016876936,0.0001870642],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16383407,0.003391318,0.0019951498,0.0004114036,0.0004887429,0.0010731966,0.0007426134,0.000068466354,0.000081182814,0.67907476,0.0532038,0.09563528],"study_design_scores_gemma":[0.051225845,0.0030139578,0.00047096342,0.00006644979,0.00033119056,0.000004289274,0.000088428234,0.09578563,0.00023484784,0.8446875,0.0035114097,0.0005794695],"about_ca_topic_score_codex":0.0000028641448,"about_ca_topic_score_gemma":0.0000011298224,"teacher_disagreement_score":0.2587862,"about_ca_system_score_codex":0.00010132294,"about_ca_system_score_gemma":0.00020987452,"threshold_uncertainty_score":0.9998526},"labels":[],"label_agreement":null},{"id":"W3092430397","doi":"10.1002/pst.2072","title":"The current state of Bayesian methods in nonclinical pharmaceutical statistics: Survey results and recommendations from the <scp>DIA</scp>/<scp>ASA‐BIOP</scp> Nonclinical Bayesian Working Group","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Bayesian probability; Bayesian statistics; Bayesian inference; Medicine; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.5640579803130207,"score_gpt":0.595575910905105,"score_spread":0.0315179305920843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092430397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017597879,0.0013871453,0.9641647,0.0035663527,0.0024203255,0.002112919,0.024013922,0.0001647656,0.0004101127],"genre_scores_gemma":[0.03589484,0.0068155257,0.9530812,0.002235282,0.0010936827,0.00015807258,0.0004399735,0.00022611771,0.000055287714],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9655889,0.020981234,0.0075061233,0.0020792591,0.0017795783,0.00206486],"domain_scores_gemma":[0.49988705,0.49620467,0.0012593488,0.0008607248,0.00042959128,0.0013586086],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.027836036,0.0010792075,0.0024898052,0.00011905553,0.00066911115,0.00045602204,0.0018634371,0.00042243738,0.00008897272],"category_scores_gemma":[0.5384909,0.0007857337,0.0003447849,0.0013098901,0.0028696498,0.00016074587,0.0014067697,0.0051336354,0.000061230574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007859891,0.0013955886,0.010732273,0.00034233462,0.0006940117,0.00010314823,0.0015243507,0.000022795144,0.00016268154,0.04639479,0.056153886,0.8816882],"study_design_scores_gemma":[0.008845013,0.0007033272,0.030314146,0.0004141786,0.001302228,0.000008551772,0.00032124872,0.14712235,0.0006653884,0.6829378,0.12690319,0.00046259898],"about_ca_topic_score_codex":0.00009363052,"about_ca_topic_score_gemma":0.0003621197,"teacher_disagreement_score":0.8812255,"about_ca_system_score_codex":0.00017791486,"about_ca_system_score_gemma":0.00041032516,"threshold_uncertainty_score":0.99984396},"labels":[],"label_agreement":null},{"id":"W3092878192","doi":"10.18433/jpps30872","title":"Influence of Different Populations on Pharmacokinetic Bioequivalence Results: Can We Extrapolate Bioequivalence Results from One Population to Another?","year":2020,"lang":"en","type":"review","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Population; Pharmacokinetics; Medicine; Statistics; Product (mathematics); Econometrics; Pharmacology; Mathematics; Environmental health","score_opus":0.7699958820189934,"score_gpt":0.6330921476008488,"score_spread":0.13690373441814463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092878192","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023817161,0.9250963,0.0063588177,0.017746493,0.005446556,0.006505997,0.014224512,0.00026908252,0.0005351319],"genre_scores_gemma":[0.023097098,0.8874713,0.08727766,0.0006376069,0.0013557269,0.000032071548,0.000013895653,0.00008977605,0.000024873249],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98361474,0.0033986578,0.0076404004,0.0013700287,0.0030235841,0.000952568],"domain_scores_gemma":[0.9550754,0.037207644,0.0053623463,0.00063890044,0.00049037044,0.0012253332],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0061214073,0.0010299291,0.0041818144,0.00077402603,0.0002759233,0.00017154538,0.0028399015,0.00027877698,0.0002544946],"category_scores_gemma":[0.04678503,0.0007350867,0.0010889034,0.0024396284,0.0009185305,0.00035847895,0.00046583771,0.0019837765,0.00004224358],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017891399,0.00093409803,0.000050719038,0.0032162634,0.00039775524,0.000089968766,0.00026106666,0.00036436913,0.0015104617,0.0023229006,0.00063415687,0.9884291],"study_design_scores_gemma":[0.012895959,0.0035983934,0.00039156384,0.06552495,0.014438856,0.000115525065,0.000064952816,0.0030962199,0.007968386,0.16403466,0.72462684,0.0032437092],"about_ca_topic_score_codex":0.000116952826,"about_ca_topic_score_gemma":0.0000071228305,"teacher_disagreement_score":0.9851854,"about_ca_system_score_codex":0.00039623462,"about_ca_system_score_gemma":0.0005061426,"threshold_uncertainty_score":0.99951},"labels":[],"label_agreement":null},{"id":"W3094247318","doi":"10.1016/j.ijrobp.2020.07.2197","title":"Metastasis-Free Survival, but Not Biochemical Failure, is a Strong Surrogate Endpoint for Overall Survival in Recurrent Prostate Cancer: Analysis of NRG Oncology/RTOG 9601","year":2020,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Hamilton Health Sciences","funders":"","keywords":"Medicine; Surrogate endpoint; Prostate cancer; Oncology; Prostatectomy; Internal medicine; Clinical endpoint; Hazard ratio; Radiation therapy; Prostate; Salvage therapy; Urology; Clinical trial; Cancer; Confidence interval; Chemotherapy","score_opus":0.2765794410700233,"score_gpt":0.5097610143098892,"score_spread":0.23318157323986588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094247318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68211585,0.0005376626,0.2619912,0.03368128,0.006569546,0.0016343793,0.01316293,0.00008232471,0.0002248051],"genre_scores_gemma":[0.7012687,0.0011580288,0.29338178,0.0014744537,0.002361779,0.00011109091,0.00015129537,0.00007754486,0.000015336514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99327445,0.0017836622,0.0031651226,0.0005922496,0.00071442785,0.00047005786],"domain_scores_gemma":[0.9708175,0.023372207,0.0036549205,0.00033498326,0.0015382649,0.00028213437],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004706365,0.0003970058,0.002375485,0.00036635066,0.000050751325,0.000036111578,0.001212053,0.00047255526,0.00022165375],"category_scores_gemma":[0.030931331,0.0003586611,0.00097358937,0.0006545716,0.00037149884,0.00020931342,0.0002836721,0.00090718875,0.000004368058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026446193,0.006471666,0.1463079,0.0004628336,0.03752735,0.00015152912,0.0052958615,0.004249173,0.029029634,0.4257937,0.022355601,0.29590857],"study_design_scores_gemma":[0.039541405,0.0062993662,0.01161049,0.0002623556,0.0071916594,0.000014942426,0.0007813069,0.035206143,0.039314862,0.8346155,0.023858353,0.0013036007],"about_ca_topic_score_codex":0.000062804465,"about_ca_topic_score_gemma":0.00007785701,"teacher_disagreement_score":0.40882182,"about_ca_system_score_codex":0.0009593964,"about_ca_system_score_gemma":0.0008940627,"threshold_uncertainty_score":0.9998865},"labels":[],"label_agreement":null},{"id":"W3094687831","doi":"10.1016/j.jclinepi.2020.11.004","title":"New methodological approaches were able to effectively reduce immeasurable time bias in case-only designs","year":2020,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"National Research Foundation of Korea","keywords":"Econometrics; Statistics; Computer science; Economics; Mathematics","score_opus":0.9799927020036421,"score_gpt":0.7030028591691723,"score_spread":0.2769898428344698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094687831","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.106285445,0.0002002569,0.8541237,0.036012717,0.0011424796,0.0008212554,0.000017366041,0.000053515516,0.0013432457],"genre_scores_gemma":[0.02833001,0.000055603396,0.96306187,0.0057914993,0.0024876697,0.000010513714,3.9065247e-7,0.000052506355,0.00020992116],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8842964,0.098598465,0.014308881,0.0011327807,0.00055067346,0.0011127717],"domain_scores_gemma":[0.17530446,0.8173654,0.004498642,0.0005197484,0.0002993673,0.0020123906],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20216893,0.000447492,0.0083990805,0.00016546615,0.000067075955,0.000022621914,0.0008642003,0.0011477593,0.0007764414],"category_scores_gemma":[0.9572718,0.00031076136,0.0013608264,0.000601031,0.00032774615,0.00013252991,0.00027606517,0.0031455716,0.00022750108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020583875,0.002265217,0.08152336,0.00057219557,0.0016277229,0.008434317,0.0006007893,0.0021455695,0.0009930229,0.10533566,0.24238318,0.5335351],"study_design_scores_gemma":[0.00375109,0.0059879115,0.013405878,0.00025118858,0.00030348607,0.0020513637,0.00009446411,0.0015306592,0.00022607746,0.9699163,0.002045667,0.0004359348],"about_ca_topic_score_codex":0.000042171,"about_ca_topic_score_gemma":0.000006909932,"teacher_disagreement_score":0.86458063,"about_ca_system_score_codex":0.0000976761,"about_ca_system_score_gemma":0.0006952489,"threshold_uncertainty_score":0.99993443},"labels":[],"label_agreement":null},{"id":"W3096180835","doi":"","title":"Testing with p*-values: Between p-values and e-values","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Frequentist inference; Statistics; Value (mathematics); Bayesian probability; Expected value; Combinatorics; Bayesian inference","score_opus":0.6909092857363631,"score_gpt":0.4098744284431825,"score_spread":0.2810348572931806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096180835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5668134,0.00006111959,0.42223352,0.00026700005,0.00040533862,0.0012008209,0.0003171327,0.0007343329,0.007967322],"genre_scores_gemma":[0.5597694,0.00004653865,0.43907565,0.00007007761,0.00048015834,0.000001941458,0.0000063629873,0.000079277284,0.00047058563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99577767,0.0011619237,0.0006978537,0.0016275106,0.00024285162,0.00049217016],"domain_scores_gemma":[0.96033597,0.0371457,0.00073891453,0.0010218663,0.00029673596,0.0004608074],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017666749,0.0006089791,0.0015031458,0.000147144,0.00021681158,0.00011970381,0.00080919836,0.00047679147,0.0000762535],"category_scores_gemma":[0.037482753,0.00057329197,0.0001982478,0.0005299925,0.00074016856,0.00011553953,0.0016587912,0.0013283965,0.00004396264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017179776,0.000877123,0.25919378,0.009285974,0.0054158415,0.0047255554,0.0028263512,0.0047771735,0.00018447549,0.6857853,0.006953838,0.018256657],"study_design_scores_gemma":[0.0009670703,0.0003170496,0.004957512,0.00074170716,0.0012986888,0.0000048179577,0.00025114627,0.0077919965,0.00010663145,0.98285174,0.000028790164,0.00068285916],"about_ca_topic_score_codex":0.000057864538,"about_ca_topic_score_gemma":0.0000027589056,"teacher_disagreement_score":0.29706645,"about_ca_system_score_codex":0.00012623233,"about_ca_system_score_gemma":0.0001958661,"threshold_uncertainty_score":0.9996719},"labels":[],"label_agreement":null},{"id":"W3097430058","doi":"10.1016/s0140-6736(20)32259-5","title":"Maintaining confidentiality of emerging results in COVID-19 vaccine trials is essential","year":2020,"lang":"en","type":"article","venue":"The Lancet","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; Bristol-Myers Squibb Canada; World Health Organization; Merck; Bill and Melinda Gates Foundation","keywords":"Clinical trial; Confidentiality; Medicine; Scopus; Vaccine trial; Rigour; Coronavirus disease 2019 (COVID-19); Family medicine; Public health; MEDLINE; Political science; Internal medicine; Nursing; Law; Disease","score_opus":0.6693841573696867,"score_gpt":0.6008950326499123,"score_spread":0.06848912471977442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097430058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11301056,0.00023436517,0.58586365,0.28864774,0.0015148398,0.0025463789,0.0018940388,0.00031575246,0.0059726625],"genre_scores_gemma":[0.78032005,0.0001366721,0.20725107,0.009046206,0.0031504594,0.000024162602,0.0000053868025,0.000031443888,0.00003456027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99253887,0.0041582095,0.0022509492,0.0003423725,0.00039555837,0.00031401456],"domain_scores_gemma":[0.90384585,0.09404018,0.0010884511,0.0007551283,0.00007481225,0.00019559641],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025631452,0.00014798864,0.0017825924,0.000035210578,0.000052531646,0.000036147467,0.0005742182,0.000103239676,0.0009479923],"category_scores_gemma":[0.4515224,0.000100852805,0.00017301035,0.00031123369,0.00009477026,0.00004067752,0.00019464626,0.00036383077,0.000016114836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030796884,0.0004158193,0.0030218882,0.0022605266,0.0008542701,0.000121150166,0.027430711,0.00027768704,0.008836676,0.5908101,0.31904584,0.016128452],"study_design_scores_gemma":[0.010433299,0.00010251017,0.0004150959,0.00013223467,0.00013636163,0.0000016352434,0.00068117346,0.000909619,0.005104586,0.9787459,0.003171481,0.00016610416],"about_ca_topic_score_codex":0.00013790249,"about_ca_topic_score_gemma":0.000024602563,"teacher_disagreement_score":0.66730946,"about_ca_system_score_codex":0.000030371848,"about_ca_system_score_gemma":0.00009058855,"threshold_uncertainty_score":0.99996525},"labels":[],"label_agreement":null},{"id":"W3105212329","doi":"","title":"Parity Violation in pp and np Experiments","year":2008,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Parity (physics); Computer science; Physics; Particle physics","score_opus":0.7657435148298514,"score_gpt":0.6162904214729323,"score_spread":0.14945309335691903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105212329","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84385794,0.00005341282,0.13555032,0.00019109366,0.0002085073,0.00035430232,0.000004544135,0.00007516534,0.019704737],"genre_scores_gemma":[0.3239364,0.00003708675,0.6757218,0.00010185812,0.000033794597,0.000009717166,1.6313457e-7,0.000005432734,0.000153724],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990646,0.00022949168,0.0003444057,0.00014479825,0.0001157318,0.000100953876],"domain_scores_gemma":[0.9893431,0.010414848,0.000046256355,0.00012976566,0.000017072005,0.000048929003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007925259,0.000059506172,0.00020663602,0.000017868822,0.000027886888,0.0000056945387,0.000042309388,0.00007048118,0.00031576262],"category_scores_gemma":[0.021454513,0.000048247734,0.000018057806,0.00006165928,0.000061570514,0.000036943842,0.000038717375,0.00008395812,0.000015729385],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019023912,0.0009118292,0.1662009,0.000092139555,0.00003850185,0.000056956473,0.0010856799,8.608893e-7,0.0020883624,0.7959057,0.011754987,0.021673838],"study_design_scores_gemma":[0.00068289955,0.000036931662,0.024524508,0.000011372975,0.000004427963,0.0000043061887,0.000020679423,0.00033633423,0.002085511,0.972059,0.00015633003,0.00007768619],"about_ca_topic_score_codex":0.000024034796,"about_ca_topic_score_gemma":0.0000047971716,"teacher_disagreement_score":0.5401715,"about_ca_system_score_codex":0.000014656454,"about_ca_system_score_gemma":0.00000798633,"threshold_uncertainty_score":0.9867882},"labels":[],"label_agreement":null},{"id":"W3110510055","doi":"10.1002/cjs.11583","title":"Evaluation of competing risks prediction models using polytomous discrimination index","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute","keywords":"Estimator; Resampling; Covariate; Mathematics; Statistics; Artificial intelligence; Computer science; Econometrics; Machine learning","score_opus":0.8278646031829864,"score_gpt":0.5522095062736628,"score_spread":0.27565509690932355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110510055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033713765,0.00008123098,0.9638066,0.00016073698,0.00050410716,0.00023442405,0.0011636368,0.0000059348504,0.00032955752],"genre_scores_gemma":[0.5663496,0.0000052065716,0.43338686,0.000039018818,0.00019877625,7.354108e-7,0.0000024128185,0.000016462982,9.3825395e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99627835,0.0009925187,0.0013819226,0.00013475354,0.000998668,0.00021378552],"domain_scores_gemma":[0.9908024,0.005151071,0.0011975183,0.00012873275,0.002167403,0.0005528911],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0057309167,0.00012871355,0.0004756597,0.00016964889,0.00008936185,0.00003648826,0.00018781466,0.000113294824,0.00017479996],"category_scores_gemma":[0.088344514,0.00012604473,0.000073843534,0.0002193448,0.00014830138,0.00014233826,0.000014482409,0.00033081506,8.4288735e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003889251,0.00026153843,0.013164439,0.001309381,0.0010713241,0.00024431932,0.013070261,0.1636101,0.0016630415,0.46795532,0.007174141,0.3300872],"study_design_scores_gemma":[0.0006390541,0.0001408421,0.00094339147,0.0001237577,0.0006000895,0.000014743686,0.00035578175,0.48582178,0.00011622968,0.51116514,0.000006974917,0.00007220807],"about_ca_topic_score_codex":0.00076318823,"about_ca_topic_score_gemma":0.00076683465,"teacher_disagreement_score":0.5326358,"about_ca_system_score_codex":0.00031043377,"about_ca_system_score_gemma":0.0016852824,"threshold_uncertainty_score":0.91933477},"labels":[],"label_agreement":null},{"id":"W3111132783","doi":"10.1093/neuonc/noaa215.816","title":"RTID-11. GBM AGILE: A GLOBAL, PHASE 2/3 ADAPTIVE PLATFORM TRIAL TO EVALUATE MULTIPLE REGIMENS IN NEWLY DIAGNOSED AND RECURRENT GLIOBLASTOMA","year":2020,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Clinical trial; Medicine; Clinical endpoint; Agile software development; Glioblastoma; Medical physics; Oncology; Internal medicine; Computer science; Cancer research","score_opus":0.4516531105571223,"score_gpt":0.5440306338959288,"score_spread":0.09237752333880644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111132783","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96233255,0.000049396614,0.015066836,0.012701353,0.002765991,0.0055710217,0.0004712291,0.00024331079,0.0007983326],"genre_scores_gemma":[0.4799692,0.00011053015,0.50686294,0.010186379,0.0017357712,0.0009929492,0.000005575066,0.00012353914,0.000013111105],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99409485,0.0020919298,0.0015872179,0.0010330636,0.0005075565,0.00068540644],"domain_scores_gemma":[0.93069863,0.06748339,0.0004811092,0.0004347524,0.00014889019,0.000753227],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022601513,0.00041014882,0.0015153994,0.000100645026,0.00008122533,0.000040411207,0.0003960345,0.0003985321,0.0001964707],"category_scores_gemma":[0.22669858,0.00034522172,0.00016380384,0.00064944074,0.0002332761,0.000094964824,0.0004451046,0.00063826924,0.00009715957],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.40990913,0.005863876,0.0004384857,0.00021455788,0.00020596244,0.002954117,0.0036931224,0.00006564762,0.010971334,0.024859602,0.06730066,0.4735235],"study_design_scores_gemma":[0.4948066,0.1183823,0.00031279403,0.00023135,0.0006562386,0.00008851945,0.0008335751,0.018203383,0.00445736,0.27071083,0.08991572,0.0014013338],"about_ca_topic_score_codex":0.000030293493,"about_ca_topic_score_gemma":0.0004400103,"teacher_disagreement_score":0.4917961,"about_ca_system_score_codex":0.0003599348,"about_ca_system_score_gemma":0.0003411357,"threshold_uncertainty_score":0.9999},"labels":[],"label_agreement":null},{"id":"W3113630075","doi":"10.1093/aje/kwaa284","title":"Invited Commentary: The Prevalent New-User Design in Pharmacoepidemiology—Challenges and Opportunities","year":2020,"lang":"en","type":"letter","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Pharmacoepidemiology; Context (archaeology); Clinical study design; Computer science; Research design; Population; Medicine; Data science; Management science; Engineering; Clinical trial; Environmental health; Geography; Pathology; Pharmacology","score_opus":0.8104283041242712,"score_gpt":0.5713545399985923,"score_spread":0.23907376412567893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113630075","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007765044,0.0077984333,0.07496194,0.9157862,0.0007994274,0.0004914331,0.000038941216,0.000021594205,0.00002438306],"genre_scores_gemma":[0.000016150052,0.039121896,0.3414439,0.61607856,0.003250913,0.000016754102,0.0000029367827,0.00005358211,0.00001532105],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92813295,0.065641575,0.004516796,0.00059170515,0.00029326955,0.0008237057],"domain_scores_gemma":[0.53092027,0.46377602,0.004434605,0.00044195607,0.00011682538,0.0003103472],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031856295,0.0005915494,0.005003703,0.00027200763,0.000061288025,0.0000090887315,0.0010737885,0.0005248956,0.0000912135],"category_scores_gemma":[0.2751506,0.00036839987,0.000418844,0.00014532509,0.0025220327,0.00006830479,0.00029951584,0.0055393376,0.0000029417783],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033742934,0.0000369496,0.00022537529,0.00012578946,0.0005535935,0.00054740434,0.0003209836,0.000007624076,0.0000017530316,0.0015357924,0.9181327,0.0781746],"study_design_scores_gemma":[0.00065105956,0.0012680792,0.000119822325,0.00023401585,0.00041999633,0.00020852515,0.00024518138,0.00007806431,0.000001814388,0.5462947,0.45024097,0.00023778799],"about_ca_topic_score_codex":0.00008652428,"about_ca_topic_score_gemma":0.0000045571664,"teacher_disagreement_score":0.5447589,"about_ca_system_score_codex":0.00013085175,"about_ca_system_score_gemma":0.00011728483,"threshold_uncertainty_score":0.9998768},"labels":[],"label_agreement":null},{"id":"W3114267183","doi":"10.1016/j.cjca.2020.12.014","title":"Key Issues in the Statistical Interpretation of Randomized Clinical Trials","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé","keywords":"Medicine; Key (lock); Interpretation (philosophy); Randomized controlled trial; Medical physics; Intensive care medicine; Pathology; Linguistics; Computer security","score_opus":0.5325381796824703,"score_gpt":0.6062798786199505,"score_spread":0.07374169893748017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3114267183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007847193,0.0011122901,0.977464,0.0044095432,0.0029688429,0.00050964346,0.00014182333,0.0000032090895,0.005543447],"genre_scores_gemma":[0.705022,0.00028513325,0.2928031,0.00038828718,0.0014449796,0.000009813125,0.0000023944015,0.000014876538,0.00002945059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93694514,0.05789423,0.0045139943,0.00015788311,0.00024667458,0.00024209818],"domain_scores_gemma":[0.6394864,0.35822493,0.0011892818,0.0002863074,0.0005581917,0.00025492124],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.112445556,0.00012325631,0.0039878883,0.00015982991,0.0000257982,0.000025961712,0.00034323096,0.00025514312,0.00018671453],"category_scores_gemma":[0.81664425,0.00007608645,0.0008753511,0.00017780148,0.0007604847,0.00003586683,0.000016554293,0.00064895884,0.000004288271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015976872,0.00004088436,0.003879283,0.0001259699,0.0017416202,0.0015393981,0.0016259598,0.00017128783,0.000036850073,0.84199023,0.04947771,0.083393924],"study_design_scores_gemma":[0.024375195,0.00017105034,0.001220112,0.00011285877,0.0005604265,0.00017395221,0.00042234705,0.00016010186,0.000033569537,0.9686162,0.0040694596,0.0000847102],"about_ca_topic_score_codex":0.00011495066,"about_ca_topic_score_gemma":0.00046648353,"teacher_disagreement_score":0.70419866,"about_ca_system_score_codex":0.000043816995,"about_ca_system_score_gemma":0.0012459116,"threshold_uncertainty_score":0.9139241},"labels":[],"label_agreement":null},{"id":"W3117530769","doi":"10.5539/ijsp.v10n1p79","title":"Decision Criteria During Joint Modelling of Efficacy and Safety With MCP-Mod","year":2020,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mod; Mathematics; Robustness (evolution); Computer science; Mathematical optimization; Reliability engineering; Artificial intelligence; Engineering","score_opus":0.46319094883447925,"score_gpt":0.4847225331444486,"score_spread":0.02153158430996932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117530769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30466422,0.000030275676,0.6942863,0.00046930034,0.00013671885,0.00012319702,0.0002478295,0.000004016697,0.000038136903],"genre_scores_gemma":[0.41596907,0.00009529327,0.5838085,0.000026841919,0.000090600995,5.7534845e-7,5.121035e-7,0.000007290769,0.0000013136784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99777603,0.00018750498,0.0012260316,0.0001866936,0.0005241643,0.000099544595],"domain_scores_gemma":[0.98820263,0.010070995,0.0006441674,0.000097331314,0.000814942,0.00016991203],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015232224,0.000120821634,0.0004964204,0.00004377659,0.000035778616,0.000045360885,0.0001571909,0.000053435473,0.0000837907],"category_scores_gemma":[0.021173293,0.00008775698,0.000042694202,0.00005208878,0.00019103516,0.000079259036,0.000105617655,0.00022949342,3.0359098e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.043267768,0.001883644,0.0101587735,0.003175114,0.0019372818,0.0004814159,0.005005582,0.006640292,0.0057005994,0.6951611,0.0008417909,0.22574665],"study_design_scores_gemma":[0.0026095372,0.00053457974,0.008272886,0.00034017913,0.00008773998,0.000058617345,0.00002665951,0.012240931,0.00054921344,0.9751228,0.00004652281,0.00011031701],"about_ca_topic_score_codex":0.000004012271,"about_ca_topic_score_gemma":0.0000012615676,"teacher_disagreement_score":0.27996174,"about_ca_system_score_codex":0.000031153075,"about_ca_system_score_gemma":0.000055585275,"threshold_uncertainty_score":0.98707175},"labels":[],"label_agreement":null},{"id":"W3120519245","doi":"10.1002/pst.2092","title":"A weighted log‐rank test and associated effect estimator for cancer trials with delayed treatment effect","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"National Institutes of Health","keywords":"Mathematics; Estimator; Statistics; Log-rank test; Test statistic; Statistic; Robustness (evolution); Hazard ratio; Proportional hazards model; Sample size determination; Statistical hypothesis testing; Confidence interval","score_opus":0.4828785734049401,"score_gpt":0.6096617833509836,"score_spread":0.12678320994604353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120519245","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027431263,0.00084407686,0.9466155,0.0008814103,0.00086232234,0.004798785,0.018061131,0.0002949048,0.00021061972],"genre_scores_gemma":[0.034128964,0.00053662993,0.96241254,0.00033841375,0.0004105674,0.001578439,0.00013142364,0.00016124672,0.0003017587],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99273765,0.0036771665,0.001437812,0.0008097189,0.00055108656,0.0007865889],"domain_scores_gemma":[0.6649986,0.33358014,0.0003702053,0.00027004667,0.0003189544,0.00046210407],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0056267804,0.00063791615,0.0026629744,0.000056739213,0.0002550378,0.00014460339,0.00015648371,0.0002862361,0.00063791353],"category_scores_gemma":[0.25941348,0.00040749917,0.00023098852,0.00032483652,0.00034130344,0.000049850045,0.00007960894,0.00037503333,0.000014754532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020005014,0.005312126,0.01978167,0.0044235317,0.01134616,0.0016100471,0.0002415171,0.000019234134,0.0093098655,0.13965596,0.020109825,0.768185],"study_design_scores_gemma":[0.068077974,0.016606841,0.0015490929,0.0008375208,0.024570951,0.000100976176,0.000017556496,0.087560475,0.1358432,0.6535324,0.009216587,0.0020864329],"about_ca_topic_score_codex":0.00002180215,"about_ca_topic_score_gemma":0.000049779897,"teacher_disagreement_score":0.7660986,"about_ca_system_score_codex":0.00031120772,"about_ca_system_score_gemma":0.00024990345,"threshold_uncertainty_score":0.9998377},"labels":[],"label_agreement":null},{"id":"W3120676907","doi":"10.1200/po.20.00214","title":"Revisiting Risk and Benefit in Early Oncology Trials in the Era of Precision Medicine: A Systematic Review and Meta-Analysis of Phase I Trials of Targeted Single-Agent Anticancer Therapies","year":2021,"lang":"en","type":"review","venue":"JCO Precision Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University; Izaak Walton Killam Health Centre; Dalhousie University","funders":"","keywords":"Medicine; Clinical trial; Internal medicine; Oncology; Adverse effect; Meta-analysis; Cancer","score_opus":0.7534315246724375,"score_gpt":0.6499043875348117,"score_spread":0.10352713713762574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120676907","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021292268,0.98417485,0.0037581695,0.0004205573,0.00018731323,0.010249423,0.0009279721,0.000008294651,0.00006050094],"genre_scores_gemma":[0.000103253966,0.90698117,0.09179846,0.00012136106,0.00007680976,0.0008402485,0.000019415183,0.00004502332,0.000014245869],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.8438208,0.12473465,0.028579911,0.0011990778,0.0012369183,0.00042861918],"domain_scores_gemma":[0.42815986,0.5502293,0.019744435,0.001207193,0.0005613231,0.00009788782],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24706167,0.00076370675,0.07393263,0.0011381264,0.000044092176,0.000021931508,0.0008141618,0.0011213863,0.000947232],"category_scores_gemma":[0.71053785,0.00037457098,0.0040557436,0.0028199614,0.00059020997,0.000065807,0.0003567927,0.0011771797,7.264392e-7],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027814467,0.0010063193,0.0000034089767,0.30843216,0.051807452,0.000029563918,0.0011394509,0.0000010692243,0.0000131192,0.0022866153,0.0000806191,0.6349221],"study_design_scores_gemma":[0.00306891,0.0022383505,0.0000083908935,0.13746962,0.8106579,0.00001949379,0.0002402588,0.000020208563,0.000007913918,0.04186647,0.0040933574,0.00030909502],"about_ca_topic_score_codex":0.00009565233,"about_ca_topic_score_gemma":0.000054631186,"teacher_disagreement_score":0.75885046,"about_ca_system_score_codex":0.00021876508,"about_ca_system_score_gemma":0.00036793848,"threshold_uncertainty_score":0.999966},"labels":[],"label_agreement":null},{"id":"W3121261082","doi":"10.2139/ssrn.3569329","title":"Trade-Off between Anytime- and Sometime-Valid Methods for Merging P-Values","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Econometrics; Economics; Business","score_opus":0.3476091649167581,"score_gpt":0.555897448422707,"score_spread":0.20828828350594897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121261082","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049974816,0.0021048447,0.98485154,0.006937682,0.00021526734,0.00050133426,0.000026203215,0.000096523276,0.00026912894],"genre_scores_gemma":[0.01591883,0.0015459112,0.9800382,0.00041250428,0.0017626348,0.000020234625,0.0000014828602,0.00009160924,0.00020854101],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943629,0.0017088017,0.0011170312,0.0004528124,0.00031739246,0.0020410807],"domain_scores_gemma":[0.9654131,0.033436146,0.00047145018,0.00021298563,0.00007784716,0.0003884593],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01671475,0.0002989668,0.0010189721,0.00008438408,0.00028380146,0.00009923326,0.00039802582,0.00020453434,0.00006264123],"category_scores_gemma":[0.06146674,0.00025160433,0.00031512536,0.00024889025,0.00014848496,0.00013141517,0.00009177318,0.0019945784,0.000006526048],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018045784,0.000055349607,0.00029353166,0.000105752195,0.00074950577,0.0000022919135,0.00044775635,0.0000011436865,0.0009832922,0.36975783,0.0007514925,0.6266716],"study_design_scores_gemma":[0.0015659917,0.00091375684,0.00007173574,0.00003595304,0.0005204895,0.0000486383,0.0003813481,0.00087503827,0.0016850961,0.9901365,0.0034750025,0.00029044953],"about_ca_topic_score_codex":0.0000016368139,"about_ca_topic_score_gemma":0.0000010133241,"teacher_disagreement_score":0.62638116,"about_ca_system_score_codex":0.00021516293,"about_ca_system_score_gemma":0.0005980168,"threshold_uncertainty_score":0.9999936},"labels":[],"label_agreement":null},{"id":"W3122044757","doi":"10.1101/2021.01.22.21250343","title":"Adaptive design methods in dialysis clinical trials – a systematic review","year":2021,"lang":"en","type":"review","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Health Research Board; Health Service Executive; Wellcome Trust; Canadian Institute for Theoretical Astrophysics","keywords":"Adaptive design; Dialysis; Medicine; Clinical trial; Kidney disease; Clinical study design; Systematic review; Data extraction; Intensive care medicine; Population; Psychological intervention; MEDLINE; Research design; Meta-analysis; Internal medicine; Statistics","score_opus":0.9494002544362373,"score_gpt":0.7573277967330597,"score_spread":0.1920724577031776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122044757","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.6770478e-9,0.575639,0.41507745,0.000031484164,0.000966298,0.008007142,0.000058402904,0.00006907113,0.00015112638],"genre_scores_gemma":[2.7042002e-9,0.50911444,0.48780695,0.00012397475,0.00032344638,0.0023346834,0.000004706917,0.00012303083,0.00016878544],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.52295655,0.44607875,0.026994493,0.0020113422,0.0011211553,0.00083768816],"domain_scores_gemma":[0.1246674,0.8611956,0.009822009,0.003375483,0.0004179279,0.00052155624],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.44199216,0.0013173748,0.057527125,0.00043450113,0.00006344035,0.00009882864,0.001671201,0.0016560394,0.0010014601],"category_scores_gemma":[0.9551612,0.00085147715,0.008156091,0.0025401365,0.000269742,0.00006390327,0.0004993346,0.0025094613,0.00025757283],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008268273,0.00022378576,4.5445324e-7,0.63355565,0.0015706883,0.00014521774,0.0000082823235,4.291888e-8,1.704169e-8,0.003898732,0.0008474553,0.3597414],"study_design_scores_gemma":[0.000425921,0.00011220496,1.4579231e-7,0.82766885,0.047695495,0.000029123961,0.000008566318,0.000029743878,4.9232597e-7,0.099864736,0.023411313,0.00075343077],"about_ca_topic_score_codex":0.0000031726906,"about_ca_topic_score_gemma":0.0000023573932,"teacher_disagreement_score":0.51316905,"about_ca_system_score_codex":0.00027109927,"about_ca_system_score_gemma":0.0010362546,"threshold_uncertainty_score":0.99995774},"labels":[],"label_agreement":null},{"id":"W3122202300","doi":"10.2139/ssrn.3166304","title":"Combining P-Values Via Averaging","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Statistics","score_opus":0.25536434585189527,"score_gpt":0.5120301952593337,"score_spread":0.2566658494074384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122202300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046701588,0.0001986951,0.9445104,0.00058069616,0.0012358315,0.00014998748,0.0000018324351,0.00011043883,0.0065105306],"genre_scores_gemma":[0.6879643,0.00027516688,0.30789194,0.00025396337,0.002344448,0.0000043855175,2.319522e-7,0.000057902693,0.0012076537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99562275,0.0007051579,0.0007648185,0.00025469164,0.0004276401,0.002224942],"domain_scores_gemma":[0.99057144,0.008420121,0.00035710004,0.000301198,0.00020584335,0.0001442866],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012110041,0.00018679665,0.00044299476,0.00008871819,0.0003523411,0.00007242819,0.00039920196,0.00011696788,0.00031370166],"category_scores_gemma":[0.023839062,0.00015520582,0.00016339225,0.00019011197,0.00021975073,0.000107046406,0.00008457406,0.00212746,0.00016260952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007908555,0.00008417836,0.00033140052,0.000009274399,0.00019516917,0.0000062664762,0.00020249304,3.7142874e-7,0.00036672936,0.917229,0.00047814063,0.08101789],"study_design_scores_gemma":[0.00086378964,0.0005657771,0.000062435705,0.000052330954,0.00007975997,0.0003059843,0.00027546473,0.00034726536,0.0006278813,0.99628675,0.00034582408,0.00018670812],"about_ca_topic_score_codex":0.000007972186,"about_ca_topic_score_gemma":0.00002569618,"teacher_disagreement_score":0.6412627,"about_ca_system_score_codex":0.0004459027,"about_ca_system_score_gemma":0.0006331622,"threshold_uncertainty_score":0.9843836},"labels":[],"label_agreement":null},{"id":"W3123183430","doi":"10.2196/14563","title":"Investigating the Food and Drug Administration Biotherapeutics Review and Approval Process: Narrative Review","year":2021,"lang":"en","type":"review","venue":"JMIR Formative Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Narrative review; Food and drug administration; CLARITY; Medicine; Scope (computer science); Process (computing); Drug approval; Risk analysis (engineering); Computer science; Drug; Pharmacology; Intensive care medicine","score_opus":0.7375027176121746,"score_gpt":0.6856095940546295,"score_spread":0.05189312355754505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123183430","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000030635729,0.98825675,0.0002301258,0.0027233348,0.00007409838,0.0077834767,0.00018630843,0.00004128565,0.00070156064],"genre_scores_gemma":[0.000002999158,0.9745817,0.021689454,0.00062830024,0.0001631863,0.0027099457,0.000030280282,0.00007509547,0.000119030745],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98264796,0.012338627,0.0023654131,0.00075473014,0.0012828873,0.00061038963],"domain_scores_gemma":[0.9330075,0.06339353,0.0013276878,0.0008848815,0.0010761106,0.0003102841],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.021632884,0.00060090714,0.0037741656,0.00013069762,0.00058294076,0.0002356794,0.00061190187,0.00033147278,0.00010267986],"category_scores_gemma":[0.07149933,0.00034594137,0.00031466284,0.0015146075,0.001399306,0.00022105512,0.0004888588,0.0027343878,0.000013708313],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015370689,0.000068111956,1.7977509e-7,0.46500108,0.00025086614,0.0000022088864,0.0018251796,6.297712e-10,3.0250277e-8,0.015943222,0.00783028,0.5090773],"study_design_scores_gemma":[0.0002145547,0.0004768789,4.862191e-7,0.43900377,0.0012530674,0.00010730868,0.0011891765,0.000005790806,0.0000034730829,0.15032172,0.40695232,0.00047146276],"about_ca_topic_score_codex":0.0000010156637,"about_ca_topic_score_gemma":0.0000032187022,"teacher_disagreement_score":0.50860584,"about_ca_system_score_codex":0.00011593523,"about_ca_system_score_gemma":0.0010742123,"threshold_uncertainty_score":0.99989927},"labels":[],"label_agreement":null},{"id":"W3123899533","doi":"10.1111/insr.12008","title":"Minimax‐Optimal Strength of Statistical Evidence for a Composite Alternative Hypothesis","year":2013,"lang":"fr","type":"article","venue":"International Statistical Review","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Mathematics; Minimax; Frequentist inference; Bayes factor; Statistics; Randomness; Bayes' theorem; Prior probability; Posterior probability; Applied mathematics; Bayesian probability; Mathematical optimization; Bayesian inference","score_opus":0.6110049862240545,"score_gpt":0.5925262097017526,"score_spread":0.0184787765223019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123899533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020540706,0.02763427,0.934717,0.010950783,0.0029522975,0.00370675,0.017994728,0.00004612313,0.0017926142],"genre_scores_gemma":[0.0020062437,0.039787024,0.9526131,0.001494505,0.0008284503,0.00086165516,0.000080731494,0.000108348184,0.002219921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9902648,0.0019731328,0.0041309334,0.0010957904,0.0016593578,0.00087602297],"domain_scores_gemma":[0.7236271,0.27226081,0.0012212729,0.00058037566,0.0017455122,0.0005649036],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0037315825,0.0007027936,0.0025098627,0.00012754033,0.00009779665,0.00016044464,0.0012761272,0.00031514312,0.03395405],"category_scores_gemma":[0.38831568,0.0006399306,0.00055430457,0.00028363633,0.0014473022,0.00037517093,0.00037266602,0.00064032595,0.0012048702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023515106,0.0008566403,0.000056430184,0.009264394,0.00068166445,0.000030928528,0.000036323676,0.000004594113,0.00007229962,0.56502086,0.07061898,0.35312176],"study_design_scores_gemma":[0.001559306,0.0009977019,0.0014479434,0.03053492,0.001872924,0.000042568012,0.000025971643,0.015918095,0.00035911275,0.91649497,0.029979149,0.000767335],"about_ca_topic_score_codex":0.00036019975,"about_ca_topic_score_gemma":0.0000072292687,"teacher_disagreement_score":0.3845841,"about_ca_system_score_codex":0.00036599897,"about_ca_system_score_gemma":0.00028811168,"threshold_uncertainty_score":0.9996052},"labels":[],"label_agreement":null},{"id":"W3125544665","doi":"10.1016/j.ctro.2021.01.006","title":"Statistical fundamentals on cancer research for clinicians: Working with your statisticians","year":2021,"lang":"en","type":"review","venue":"Clinical and Translational Radiation Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Public Health Ontario","funders":"","keywords":"Sample size determination; Statistical power; Observational study; Research design; Clinical study design; Medicine; Statistical model; Equivalence (formal languages); Interim; Confounding; Statistics; Meta-analysis; Medical physics; Statistical hypothesis testing; Clinical trial; Computer science; Econometrics; Mathematics; Pathology","score_opus":0.9241338570362616,"score_gpt":0.751358831585494,"score_spread":0.17277502545076762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125544665","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008818341,0.8234378,0.16169755,0.0020085599,0.0019707913,0.003934237,0.005726459,0.00007303748,0.0011427514],"genre_scores_gemma":[0.000014734401,0.68998367,0.306121,0.0003550951,0.0019013677,0.00102237,0.00028634784,0.00009903379,0.00021642224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9859692,0.007214993,0.0038260187,0.0014166513,0.000869824,0.0007033025],"domain_scores_gemma":[0.6765435,0.32178578,0.0007168363,0.000295617,0.00034408408,0.0003142062],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.012433964,0.0005475994,0.004318384,0.00026258972,0.00037200394,0.00010528236,0.00031705783,0.0013326064,0.00071508746],"category_scores_gemma":[0.053053755,0.00041704293,0.0005384974,0.0004939868,0.0012690533,0.00005090458,0.00005421612,0.0020078695,0.00003196022],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003019356,0.0005303876,0.00011755718,0.0017673988,0.00050896936,0.00003054261,0.000031450425,0.0000017318848,9.777741e-9,0.28085414,0.0032764086,0.7125795],"study_design_scores_gemma":[0.002049466,0.0013476963,0.00014939212,0.0039407443,0.0013322777,0.0000102071845,0.000028212897,0.0000625457,7.846745e-8,0.27717376,0.71355206,0.00035354783],"about_ca_topic_score_codex":0.000008640537,"about_ca_topic_score_gemma":0.00006957248,"teacher_disagreement_score":0.7122259,"about_ca_system_score_codex":0.0001657899,"about_ca_system_score_gemma":0.0024273302,"threshold_uncertainty_score":0.9999639},"labels":[],"label_agreement":null},{"id":"W3129770065","doi":"10.1016/j.ctrv.2021.102167","title":"Fragility index of trials supporting approval of anti-cancer drugs in common solid tumours","year":2021,"lang":"en","type":"review","venue":"Cancer Treatment Reviews","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Clinical endpoint; Randomized controlled trial; Statistical significance; Informed consent; Internal medicine; Clinical trial; Sample size determination; Prostate cancer; Surgery; Cancer; Alternative medicine; Pathology","score_opus":0.7670505635966346,"score_gpt":0.678180220305882,"score_spread":0.08887034329075261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129770065","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014306871,0.99028116,0.0004550799,0.000025730644,0.0007612182,0.006639783,0.0013816768,0.000022216938,0.0002900425],"genre_scores_gemma":[0.000019185018,0.9580275,0.037962228,0.000017506822,0.0003786268,0.0032873177,0.000049469712,0.00009949529,0.00015867993],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9732021,0.011873809,0.012699669,0.0010752697,0.00056036114,0.0005887668],"domain_scores_gemma":[0.9470171,0.039342973,0.011731146,0.0015298019,0.00019116708,0.00018786268],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017887358,0.0010006111,0.028387811,0.0002137897,0.000035727804,0.000022193037,0.00058355246,0.0006284071,0.0014044244],"category_scores_gemma":[0.037325576,0.0006438465,0.0035761097,0.00087047607,0.00026830434,0.000053952434,0.0001896161,0.0005971043,0.000007112064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021634743,0.0007398632,0.0005821839,0.061359596,0.0006710926,0.0000085822985,0.00010423661,6.345348e-7,0.0000016097384,0.00063328707,0.00035403465,0.9355233],"study_design_scores_gemma":[0.0030447314,0.00031877673,0.000041944,0.17765313,0.014650937,0.0000047838726,0.000051734238,0.000010271184,0.0004197892,0.024851836,0.77785885,0.0010932338],"about_ca_topic_score_codex":0.00043134822,"about_ca_topic_score_gemma":0.00008985487,"teacher_disagreement_score":0.93443,"about_ca_system_score_codex":0.00088978384,"about_ca_system_score_gemma":0.0012729949,"threshold_uncertainty_score":0.9996013},"labels":[],"label_agreement":null},{"id":"W3132836732","doi":"10.1002/cam4.3732","title":"Does biomarker use in oncology improve clinical trial failure risk? A large‐scale analysis","year":2021,"lang":"en","type":"article","venue":"Cancer Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Cancer Care Ontario; St. Michael's Hospital; Public Health Ontario; University of Toronto","funders":"","keywords":"Medicine; Oncology; Clinical trial; Biomarker; Internal medicine; Hazard ratio; Breast cancer; Lung cancer; Cancer; Confidence interval","score_opus":0.5516949384392401,"score_gpt":0.6380658190628812,"score_spread":0.08637088062364107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132836732","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7681579,0.0007584293,0.1800915,0.025408922,0.020398749,0.002477757,0.0011947033,0.00021856636,0.0012934823],"genre_scores_gemma":[0.109298564,0.0029532583,0.8689675,0.004452101,0.009906569,0.00065481843,0.000047341764,0.0001259957,0.0035938837],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99153626,0.004061134,0.002520458,0.00088620273,0.00048606386,0.0005098576],"domain_scores_gemma":[0.91449267,0.08340085,0.0006993047,0.00085798715,0.00023410367,0.000315088],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010495457,0.00026603718,0.0023690662,0.00020564381,0.00005840054,0.000020520381,0.00027155402,0.0005535231,0.004280738],"category_scores_gemma":[0.26297757,0.00015043054,0.0004529827,0.0014909193,0.00046446844,0.000066803856,0.0001700716,0.0009179286,0.000012880615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06472857,0.007185416,0.3772899,0.0005284133,0.011828462,0.0019432548,0.003371002,0.000008142716,0.0013056629,0.010349231,0.11825428,0.40320766],"study_design_scores_gemma":[0.23899432,0.0024053438,0.050222572,0.00053272484,0.014482327,0.0000050356757,0.002500604,0.003093861,0.0004736846,0.55633914,0.12998424,0.000966138],"about_ca_topic_score_codex":0.000252346,"about_ca_topic_score_gemma":0.009465588,"teacher_disagreement_score":0.688876,"about_ca_system_score_codex":0.00019188023,"about_ca_system_score_gemma":0.00039319898,"threshold_uncertainty_score":0.9966295},"labels":[],"label_agreement":null},{"id":"W3133223479","doi":"10.1080/02664763.2021.1887102","title":"Negligible interaction test for continuous predictors","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Null hypothesis; Interaction; Equivalence (formal languages); Econometrics; Null (SQL); Psychology; Test (biology); Statistics; Mathematics; Computer science; Data mining","score_opus":0.3108828984686719,"score_gpt":0.5234423770236948,"score_spread":0.21255947855502288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133223479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022973064,0.000021067004,0.9916658,0.00014381047,0.0015395514,0.00027535128,0.00068619876,0.000022272983,0.003348655],"genre_scores_gemma":[0.020967012,0.00005026047,0.97765297,0.0001583663,0.00083796086,0.0000132609775,0.0000056293597,0.000041196523,0.00027335263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751776,0.00010797257,0.0015354416,0.00017991773,0.00041533506,0.00024359104],"domain_scores_gemma":[0.92153,0.076108806,0.0010794012,0.00021490408,0.0008981255,0.000168785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016946737,0.00016370021,0.00076997036,0.0000732418,0.000068136906,0.00007374762,0.00017785678,0.00013086463,0.0002539843],"category_scores_gemma":[0.10111865,0.00014120292,0.00014308596,0.00015116204,0.00007875454,0.0000515093,0.0000450516,0.00038854603,0.000009048028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007837556,0.00092983263,0.00026939285,0.00043512104,0.00037871415,0.00015866249,0.0002935723,0.000038030194,0.005496537,0.7664307,0.17275959,0.052026127],"study_design_scores_gemma":[0.0017347488,0.0004459617,0.00011792108,0.00008459774,0.00035515122,0.0000661122,0.0003458898,0.00036944944,0.00902899,0.97557515,0.011724606,0.00015143766],"about_ca_topic_score_codex":4.2828307e-7,"about_ca_topic_score_gemma":0.0000020629273,"teacher_disagreement_score":0.20914447,"about_ca_system_score_codex":0.000080747195,"about_ca_system_score_gemma":0.00021196358,"threshold_uncertainty_score":0.906453},"labels":[],"label_agreement":null},{"id":"W3134172846","doi":"10.1186/s13063-021-05164-1","title":"A novel preference-informed complementary trial (PICT) design for clinical trial research influenced by strong patient preferences","year":2021,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Children's Hospital Research Institute of Manitoba; Hospital for Sick Children; University of Toronto; Children’s Health Research Institute; Institute of Health Economics; Women and Children’s Health Research Institute; University of Alberta","funders":"Canadian Institutes of Health Research; Hospital for Sick Children; Centre hospitalier universitaire Sainte-Justine; Children's Health Research Institute; Women and Children's Health Research Institute; Research Manitoba; Alberta Children's Hospital Research Institute; CHEO Research Institute; Kidscan Children's Cancer Research","keywords":"External validity; Preference; Internal validity; Research design; Clinical study design; Randomized controlled trial; Clinical trial; Medicine; Psychological intervention; Population; Sample size determination; Comparative effectiveness research; Alternative medicine; Psychology; Applied psychology; Management science; Computer science; Social psychology; Psychiatry; Surgery; Engineering; Statistics","score_opus":0.9740774375883522,"score_gpt":0.7368860082694295,"score_spread":0.23719142931892268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134172846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15722084,0.00031015516,0.76510876,0.0010853084,0.01357068,0.053983152,0.0052489657,0.0003739276,0.0030981991],"genre_scores_gemma":[0.011419784,0.00023370182,0.9800825,0.00025556405,0.002959822,0.00450786,0.00012304548,0.0000805306,0.00033718045],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96464396,0.021051114,0.009420965,0.0014038468,0.0021579047,0.0013222318],"domain_scores_gemma":[0.43384472,0.56079787,0.0020742451,0.0013244067,0.0013946035,0.00056418125],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.078882426,0.000506149,0.00356521,0.00016600937,0.0003973336,0.000326954,0.0009486597,0.0006453811,0.0017690042],"category_scores_gemma":[0.69134015,0.0003973006,0.00091336784,0.00055786147,0.00052505126,0.00020890844,0.00046434588,0.0010185312,0.00004449014],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7135234,0.0040621012,0.00001919245,0.00021629034,0.00090938195,0.0000065363092,0.00034908234,0.000004338536,0.000692273,0.037448928,0.1579116,0.08485689],"study_design_scores_gemma":[0.4234906,0.010936193,0.000009656425,0.00019311193,0.00041193338,0.000001431402,0.00045224946,0.00010033882,0.004628443,0.5472859,0.012044366,0.0004457502],"about_ca_topic_score_codex":0.00003948295,"about_ca_topic_score_gemma":0.000029720306,"teacher_disagreement_score":0.61245775,"about_ca_system_score_codex":0.00020184195,"about_ca_system_score_gemma":0.0021232518,"threshold_uncertainty_score":0.9998479},"labels":[],"label_agreement":null},{"id":"W3134342065","doi":"10.1002/sim.8922","title":"uTPI: A utility‐based toxicity probability interval design for phase I/II dose‐finding trials","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Maximum tolerated dose; Confidence interval; Clinical trial; Toxicity; Parametric statistics; Computer science; Medicine; Clinical study design; Optimal design; Interval (graph theory); Statistics; Mathematics; Machine learning; Internal medicine","score_opus":0.8161295342178478,"score_gpt":0.6464013638722923,"score_spread":0.16972817034555554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134342065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004259951,0.00007497799,0.98721325,0.0015183463,0.0015810947,0.0028658214,0.0020031652,0.000094236915,0.0003891443],"genre_scores_gemma":[0.0342875,0.000016417274,0.96387166,0.00055966125,0.00060302333,0.00036751849,0.000064702865,0.000058774902,0.00017072354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9875488,0.006127494,0.0038640224,0.0009507215,0.000816349,0.00069255556],"domain_scores_gemma":[0.7319252,0.26553187,0.0007782212,0.00084455585,0.0006309847,0.00028917924],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042760212,0.00042899934,0.0028199053,0.0001663469,0.00018557032,0.00003368394,0.0003952579,0.000299996,0.0022849943],"category_scores_gemma":[0.78428996,0.00034797296,0.00021347406,0.00056064106,0.00067211187,0.000051714447,0.00015943358,0.0006250103,0.000004648573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007650217,0.0076645636,0.00029276084,0.003913257,0.00043185693,0.00045449368,0.0016814333,0.000035548932,0.0060388944,0.6786689,0.06544595,0.22772211],"study_design_scores_gemma":[0.0154341655,0.0024642008,0.00006725569,0.00064499857,0.00040325843,0.0000050135877,0.0001494943,0.022434251,0.0059623946,0.951409,0.0007109344,0.00031502167],"about_ca_topic_score_codex":0.000014571951,"about_ca_topic_score_gemma":0.00004298498,"teacher_disagreement_score":0.7415297,"about_ca_system_score_codex":0.00022276696,"about_ca_system_score_gemma":0.00052526494,"threshold_uncertainty_score":0.99989724},"labels":[],"label_agreement":null},{"id":"W3134974081","doi":"10.1002/cjs.11609","title":"Interim analysis of sequential estimation‐adjusted urn models with sample size re‐estimation","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Cancer Prevention and Research Institute of Texas","keywords":"Estimator; Sequential estimation; Sequential analysis; Sample size determination; Mathematics; Statistics; Type I and type II errors; Statistic; Interim; Test statistic; Computer science; Interim analysis; Statistical hypothesis testing; Null hypothesis; Algorithm; Law","score_opus":0.48964839276930866,"score_gpt":0.48982060248538173,"score_spread":0.00017220971607306845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134974081","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069941557,0.000035612327,0.9888993,0.00021906858,0.00034139946,0.00012013441,0.0031134347,0.000007676749,0.0002692326],"genre_scores_gemma":[0.24511193,0.0000103224465,0.7546444,0.00007796892,0.000052253963,0.0000018772603,0.000023660197,0.000025345662,0.00005223249],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967082,0.0005408448,0.0017235526,0.00020356574,0.00051993853,0.0003039111],"domain_scores_gemma":[0.96325505,0.032652475,0.0013070033,0.00038505113,0.0017911944,0.00060921616],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015014098,0.00019559881,0.001068897,0.0003954603,0.00009022314,0.00008705019,0.00025727236,0.00013002657,0.0014541856],"category_scores_gemma":[0.119979,0.0001754287,0.00017704324,0.0009921668,0.00026229813,0.00015630483,0.000021583644,0.00033335396,0.0000020369432],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041565098,0.0003212052,0.0017224886,0.0007585546,0.007888847,0.0016396667,0.0026003234,0.21151297,0.00029154832,0.7147705,0.009555285,0.04852297],"study_design_scores_gemma":[0.0007083591,0.00022802783,0.0008586528,0.00019255359,0.0036200336,0.000045515022,0.00023028869,0.24102703,0.0004053775,0.75248104,0.000024061841,0.00017904477],"about_ca_topic_score_codex":0.0011371701,"about_ca_topic_score_gemma":0.013464664,"teacher_disagreement_score":0.23811777,"about_ca_system_score_codex":0.00022580767,"about_ca_system_score_gemma":0.002010645,"threshold_uncertainty_score":0.9994586},"labels":[],"label_agreement":null},{"id":"W3137022898","doi":"10.1002/pst.2119","title":"Treatment allocation strategies for umbrella trials in the presence of multiple biomarkers: A comparison of methods","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Fakultet Medicinskih Nauka, Univerziteta U Kragujevcu; Newcastle University; Medical Research Council Canada; Cancer Research UK","keywords":"Biomarker; Context (archaeology); Bayesian probability; Set (abstract data type); Medicine; Matching (statistics); Computer science; Hierarchy; Artificial intelligence; Pathology","score_opus":0.8703654930178174,"score_gpt":0.7163172398238357,"score_spread":0.15404825319398174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137022898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022062468,0.00045181357,0.99358344,0.00035356914,0.00031226152,0.0014139536,0.0014036294,0.000015074358,0.0002599929],"genre_scores_gemma":[0.17610484,0.00017962672,0.82339746,0.000037090344,0.00006447841,0.00016734528,0.000018836407,0.000018433164,0.000011868885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98759013,0.008542736,0.0027971652,0.0003565204,0.00038988568,0.00032357508],"domain_scores_gemma":[0.6510043,0.34766757,0.0006078456,0.0003259863,0.00032161883,0.00007262942],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0118394075,0.00021820211,0.0015879616,0.000058148013,0.00004687268,0.000039870272,0.00029461453,0.00013452879,0.0001282308],"category_scores_gemma":[0.28698254,0.0001481312,0.00022975348,0.0003531744,0.00034851732,0.0000436882,0.000057441084,0.00017764636,0.000001296908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011480475,0.002825758,0.0009004755,0.0013871227,0.0004920107,0.000008999194,0.001452315,0.000088084504,0.015607862,0.7596883,0.0016802875,0.21472074],"study_design_scores_gemma":[0.0035294658,0.00043673863,0.0002590501,0.00009306623,0.00073825865,0.0000031006593,0.0016265017,0.08186059,0.08109551,0.82848334,0.0017082271,0.00016613177],"about_ca_topic_score_codex":0.000035098536,"about_ca_topic_score_gemma":0.000030855423,"teacher_disagreement_score":0.33912483,"about_ca_system_score_codex":0.00005586753,"about_ca_system_score_gemma":0.0002565307,"threshold_uncertainty_score":0.7190235},"labels":[],"label_agreement":null},{"id":"W3137427440","doi":"10.1001/jamaoncol.2021.0379","title":"Evolution of the Randomized Clinical Trial in the Era of Precision Oncology","year":2021,"lang":"en","type":"article","venue":"JAMA Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":202,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; NOSM University; Kingston Health Sciences Centre; Thunder Bay Regional Health Sciences Centre","funders":"","keywords":"Medicine; Randomized controlled trial; Internal medicine; Surrogate endpoint; Breast cancer; Oncology; Clinical endpoint; Colorectal cancer; Cohort; Lung cancer; Cancer","score_opus":0.5062045424251019,"score_gpt":0.6209226704404257,"score_spread":0.11471812801532377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137427440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83963454,0.0003715813,0.08502742,0.026179377,0.011927771,0.0062959855,0.000067591216,0.000032271426,0.030463452],"genre_scores_gemma":[0.5210251,0.00020166356,0.47635272,0.00096374034,0.0010998411,0.00021237669,0.0000013460326,0.00002051707,0.00012268499],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9402244,0.05465157,0.003985956,0.000373084,0.0005025108,0.0002624496],"domain_scores_gemma":[0.49803796,0.4993135,0.0014771716,0.000783174,0.00034338536,0.00004478564],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05315469,0.00013246945,0.0022340522,0.00004143551,0.000038874234,0.0000070851142,0.00061336113,0.0008016671,0.00029630575],"category_scores_gemma":[0.63886446,0.000068504414,0.0007018838,0.00044375102,0.0010423915,0.00003077283,0.0002822258,0.0011719987,0.000006891917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.4461532,0.0035255328,0.00029784345,0.00006444454,0.00013709738,0.000030624473,0.0005928125,0.0000060487214,0.00021824005,0.36191893,0.005017311,0.1820379],"study_design_scores_gemma":[0.33916354,0.0009580592,0.0010836303,0.000059987717,0.0001985243,0.000011948933,0.00021166934,0.00022992946,0.00021460709,0.6550515,0.0027654222,0.000051152998],"about_ca_topic_score_codex":0.000032311462,"about_ca_topic_score_gemma":0.00011364509,"teacher_disagreement_score":0.58570975,"about_ca_system_score_codex":0.00018518619,"about_ca_system_score_gemma":0.001152006,"threshold_uncertainty_score":0.9749765},"labels":[],"label_agreement":null},{"id":"W3137662054","doi":"10.1093/jnci/djab051","title":"Application of Value Frameworks to the Design of Clinical Trials: The Canadian Cancer Trials Group Experience","year":2021,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; Kingston General Hospital; NOSM University; Thunder Bay Regional Health Sciences Centre","funders":"","keywords":"Clinical trial; Medicine; Randomized controlled trial; Clinical endpoint; Cancer; Oncology; Internal medicine","score_opus":0.8710794279076426,"score_gpt":0.6981097536076074,"score_spread":0.17296967430003518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137662054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065587093,0.0013595299,0.93587446,0.03909181,0.014027363,0.002101725,0.0006569116,0.000007856174,0.00032163374],"genre_scores_gemma":[0.5004866,0.0007833497,0.48248112,0.007182498,0.008486449,0.0004098245,0.0000013110558,0.00003886836,0.00012994447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9825725,0.009736123,0.005304856,0.00025912758,0.0018879888,0.00023941032],"domain_scores_gemma":[0.8552013,0.1340717,0.0062776445,0.00063146156,0.0035333114,0.00028460586],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07144913,0.00018005156,0.0015516445,0.00009101803,0.00026557784,0.00005374094,0.0013132829,0.0003547112,0.0001997666],"category_scores_gemma":[0.551624,0.000084177984,0.0007793071,0.00077691936,0.0004964214,0.00012301655,0.00011711752,0.0011432826,0.0000019200772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022619115,0.0005350717,0.001784974,0.00015796401,0.0020984157,0.000008738542,0.0021990726,0.067526974,0.00279218,0.66707593,0.064018965,0.1895398],"study_design_scores_gemma":[0.0023349551,0.00015569587,0.0053903717,0.0007897118,0.0009888677,0.000026858459,0.00021081649,0.0037464085,0.007878019,0.9188333,0.05939497,0.00024999713],"about_ca_topic_score_codex":0.0035271805,"about_ca_topic_score_gemma":0.011479509,"teacher_disagreement_score":0.49392793,"about_ca_system_score_codex":0.00040502634,"about_ca_system_score_gemma":0.004711969,"threshold_uncertainty_score":0.9561385},"labels":[],"label_agreement":null},{"id":"W3141609381","doi":"10.1016/j.cjca.2021.03.014","title":"Bayesian Analyses of Cardiovascular Trials—Bringing Added Value to the Table","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé","keywords":"Frequentist inference; Bayesian probability; Prior probability; Medicine; Bayesian statistics; Bayesian inference; Statistical inference; Inference; Fiducial inference; Terminology; Clinical trial; Machine learning; Artificial intelligence; Computer science; Statistics; Mathematics","score_opus":0.7671074513781243,"score_gpt":0.6053204456467588,"score_spread":0.1617870057313655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141609381","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.9081147e-7,0.6948133,0.30075336,0.0000787565,0.0021613657,0.0005116207,0.00028146664,0.000003800083,0.0013960318],"genre_scores_gemma":[0.000034338456,0.8577993,0.1370242,0.000056646335,0.0048937276,0.00002852085,0.0000046682053,0.00008996439,0.00006866189],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9768542,0.017167052,0.0044274833,0.00041100066,0.00050061435,0.0006396598],"domain_scores_gemma":[0.93457776,0.060378302,0.0021307229,0.0012921501,0.0007312242,0.00088982406],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032105744,0.00047940575,0.015000688,0.00067912653,0.00012104823,0.000059896916,0.0012169217,0.00064588245,0.00015863604],"category_scores_gemma":[0.32515693,0.00029962094,0.007251711,0.0009939978,0.0002452574,0.000032734824,0.00009127621,0.0011602845,0.000008318011],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000117717445,0.000003782093,0.0000018279591,0.0031368602,0.023435252,0.0006788471,0.00004663455,0.00322442,5.309949e-7,0.006767543,0.03531672,0.9273758],"study_design_scores_gemma":[0.00027976796,0.00010270659,7.131844e-7,0.0058024023,0.01946526,0.00054989633,0.00004421079,0.000004027063,0.000005676706,0.016238052,0.95724875,0.00025854525],"about_ca_topic_score_codex":0.0005322417,"about_ca_topic_score_gemma":0.00012531987,"teacher_disagreement_score":0.9271173,"about_ca_system_score_codex":0.000302117,"about_ca_system_score_gemma":0.0054923478,"threshold_uncertainty_score":0.9999456},"labels":[],"label_agreement":null},{"id":"W3141835365","doi":"10.1016/j.cct.2021.106390","title":"Estimation of the binomial probabilities in a two-stage phase II clinical trial with two co-primary endpoints","year":2021,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Statistics; Clinical trial; Stage (stratigraphy); Clinical endpoint; Estimation; Mathematics; Internal medicine","score_opus":0.8464320325661006,"score_gpt":0.6867826734505976,"score_spread":0.15964935911550293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141835365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9569254,0.00021195994,0.01577036,0.0019952785,0.005931687,0.008755522,0.0008395917,0.00016226438,0.009407946],"genre_scores_gemma":[0.7553713,0.00007382785,0.2392252,0.0010500478,0.0025783863,0.00034086252,0.000042443946,0.00011030177,0.001207657],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92944664,0.050308537,0.016865129,0.0014997402,0.0012736566,0.00060628966],"domain_scores_gemma":[0.5578812,0.43256402,0.005956269,0.0026000524,0.00051093975,0.00048756943],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11693651,0.0005907034,0.006202133,0.00013211658,0.00017894841,0.000092145885,0.0009528613,0.00057647773,0.00062040926],"category_scores_gemma":[0.66165984,0.00037882375,0.001954256,0.00071445375,0.0019433371,0.00028762646,0.0005846095,0.0017110842,0.000021455353],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.51230955,0.044713184,0.016881343,0.0014386469,0.002274961,0.0005985616,0.0006179023,0.000110145156,0.00055363274,0.12704954,0.01860283,0.27484968],"study_design_scores_gemma":[0.47620514,0.0067136334,0.0007128579,0.00096857507,0.0005144978,0.00000970792,0.00017040696,0.00087113807,0.0026700837,0.5083579,0.0021080205,0.0006980517],"about_ca_topic_score_codex":0.000033511387,"about_ca_topic_score_gemma":0.000040134495,"teacher_disagreement_score":0.54472333,"about_ca_system_score_codex":0.000108061875,"about_ca_system_score_gemma":0.0032243638,"threshold_uncertainty_score":0.99986637},"labels":[],"label_agreement":null},{"id":"W3141957935","doi":"10.1158/2159-8290.cd-20-1301","title":"The Future of Clinical Trial Design in Oncology","year":2021,"lang":"en","type":"article","venue":"Cancer Discovery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute","keywords":"Clinical trial; Drug development; Clinical research; Clinical study design; Clinical Oncology; Alternative medicine; Cancer; Action (physics); Cancer treatment","score_opus":0.7164940707419735,"score_gpt":0.6567688773125598,"score_spread":0.059725193429413626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141957935","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32703367,0.0144473715,0.5403861,0.020477282,0.0776288,0.0047432855,0.00042946747,0.0001125516,0.014741492],"genre_scores_gemma":[0.051381774,0.012508227,0.9192193,0.0013203169,0.011968667,0.0005292245,0.0000023006799,0.000081428756,0.00298872],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99390596,0.0036620817,0.0016493169,0.00030307038,0.00024713718,0.00023246101],"domain_scores_gemma":[0.87123847,0.12771939,0.0004197676,0.00046136786,0.000099988276,0.000060989183],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007321524,0.00011029547,0.000839656,0.000016942638,0.0000392779,0.000028623845,0.00027021606,0.00025597526,0.00016086051],"category_scores_gemma":[0.07911735,0.000070309376,0.00023853776,0.0002237097,0.00027567433,0.00006150381,0.000113527436,0.00044464978,0.000004131485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04670157,0.0010705781,0.0011269017,0.00011187044,0.00022797218,0.00010549388,0.00011898426,0.000024312656,0.00010328424,0.38804895,0.025740093,0.53662],"study_design_scores_gemma":[0.020258283,0.00048271441,0.0007675693,0.00007885439,0.00008098399,0.000001390885,0.00023921313,0.000047176938,0.0008753894,0.95885086,0.01820446,0.00011308361],"about_ca_topic_score_codex":0.000007615961,"about_ca_topic_score_gemma":0.00013557145,"teacher_disagreement_score":0.5708019,"about_ca_system_score_codex":0.00007628282,"about_ca_system_score_gemma":0.0011609788,"threshold_uncertainty_score":0.92863965},"labels":[],"label_agreement":null},{"id":"W3145268223","doi":"10.1016/j.euf.2021.03.014","title":"Interpreting and Appraising Noninferiority Trials: A Guide for Urologists and Clinicians","year":2021,"lang":"en","type":"editorial","venue":"European Urology Focus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; Hamilton General Hospital; Centre Hospitalier Universitaire de Sherbrooke","funders":"","keywords":"Medicine; Medical physics; Clinical trial; Clinical Practice; Intensive care medicine; Family medicine; Internal medicine","score_opus":0.4301438841794418,"score_gpt":0.577601906328857,"score_spread":0.14745802214941517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3145268223","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024995953,0.0028111506,0.27449337,0.0010501338,0.7090289,0.00150379,0.0010975094,0.00029571942,0.009469447],"genre_scores_gemma":[0.00033873235,0.0007422027,0.48611176,0.0003584846,0.51173997,0.000053462467,0.000030928193,0.0002447842,0.00037966945],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97746414,0.016260587,0.0035127471,0.0016259102,0.00041939248,0.0007171965],"domain_scores_gemma":[0.56381553,0.43291974,0.0018178832,0.000788247,0.0004127791,0.00024580132],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047350645,0.0006833643,0.0034873628,0.0001434013,0.0002292751,0.0002290096,0.000528087,0.0013830977,0.00004742001],"category_scores_gemma":[0.84436864,0.00061448495,0.00045740092,0.00011172645,0.0008494243,0.0000533511,0.0009990345,0.0021235198,0.000014567462],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008294486,0.00009832236,0.000043218788,0.0003361218,0.0004346765,0.00026642554,0.000230909,2.5748767e-7,0.00003147158,0.0035118193,0.91341364,0.080803715],"study_design_scores_gemma":[0.0027129292,0.0010690133,0.000030185334,0.00018083608,0.001252866,0.000023684297,0.000025868643,0.000092951086,0.000011167615,0.15219593,0.8418608,0.0005437861],"about_ca_topic_score_codex":0.0000111580175,"about_ca_topic_score_gemma":0.000024792032,"teacher_disagreement_score":0.797018,"about_ca_system_score_codex":0.000038524584,"about_ca_system_score_gemma":0.00023340099,"threshold_uncertainty_score":0.99991333},"labels":[],"label_agreement":null},{"id":"W3149114446","doi":"10.1016/j.cjca.2021.03.013","title":"Issues in Designing and Interpreting Small Clinical Trials","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Clinical trial; Intensive care medicine; Randomized controlled trial; Test (biology); Psychological intervention; Medical physics; Clinical study design; Research design; Alternative medicine; Internal medicine; Pathology","score_opus":0.8831990272913192,"score_gpt":0.6847381371232508,"score_spread":0.19846089016806834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149114446","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000050883127,0.9545623,0.041282713,0.0001404587,0.0027678928,0.0003928337,0.000049840324,0.000004109348,0.00079475064],"genre_scores_gemma":[0.0000059460294,0.7557775,0.24139054,0.000059627793,0.0026794695,0.000008136852,0.0000011657394,0.00004495692,0.00003265172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9541958,0.03820951,0.006634323,0.00037778678,0.00012185751,0.00046072397],"domain_scores_gemma":[0.7564538,0.23971158,0.0025204218,0.0003265328,0.00023860991,0.0007490419],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07788448,0.00036109213,0.012914743,0.0005182261,0.000041686617,0.000071201524,0.0004674875,0.0011562577,0.00005581202],"category_scores_gemma":[0.6878321,0.00027666904,0.0017313417,0.00022491162,0.00036652372,0.000028863906,0.00007138942,0.0021142454,0.0000038444555],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009502299,0.0000020196449,0.00022101268,0.0015171941,0.0006674408,0.0011231889,0.00003560935,7.7204345e-7,3.1814146e-8,0.00275622,0.005832297,0.9878347],"study_design_scores_gemma":[0.0004342145,0.00016621596,0.000009232112,0.02014799,0.0016750827,0.0007899632,0.00005515351,0.0000010549754,1.347433e-7,0.08449361,0.8919817,0.00024562204],"about_ca_topic_score_codex":0.00009148832,"about_ca_topic_score_gemma":0.00034730323,"teacher_disagreement_score":0.98758906,"about_ca_system_score_codex":0.00017860759,"about_ca_system_score_gemma":0.0031563242,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W3152465836","doi":"10.1002/sim.8949","title":"Optimizing subgroup selection in two‐stage adaptive enrichment and umbrella designs","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Horizon 2020 Framework Programme; H2020 Marie Skłodowska-Curie Actions; Innovative Medicines Initiative; Medical Research Council Canada; National Institute for Health and Care Research; Springworks Therapeutics; Medical Research Council; European Federation of Pharmaceutical Industries and Associations","keywords":"Type I and type II errors; Computer science; Selection (genetic algorithm); Word error rate; Population; Subgroup analysis; Adaptive design; Interim analysis; Bayesian probability; Multiple comparisons problem; Clinical trial; Statistics; Mathematical optimization; Medicine; Mathematics; Machine learning; Artificial intelligence; Internal medicine; Confidence interval","score_opus":0.4502326642966361,"score_gpt":0.553600628135857,"score_spread":0.10336796383922087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152465836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005563106,0.00028549787,0.9909262,0.00025997005,0.00038263225,0.00041985294,0.00008895138,0.000032180917,0.002041613],"genre_scores_gemma":[0.0699938,0.000363665,0.92877394,0.00022850266,0.00018845516,0.00003676326,0.0000068237023,0.000033070595,0.00037496677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99635726,0.0011575263,0.001105011,0.0005066892,0.00044831473,0.00042520536],"domain_scores_gemma":[0.95999897,0.039295007,0.00021022375,0.00019646283,0.00015663663,0.00014272961],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004309305,0.00022486948,0.0008096652,0.000171437,0.00005620758,0.000017832172,0.00010680057,0.00010233665,0.00054771424],"category_scores_gemma":[0.0633664,0.00020580603,0.000021678034,0.00055388646,0.00026252843,0.000036780908,0.00010338508,0.0005676767,0.0000046506925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024269575,0.00031227697,0.004044248,0.00033945678,0.00006161452,0.0008143724,0.0020133054,0.00015771571,0.002209064,0.9682703,0.0020075787,0.019527398],"study_design_scores_gemma":[0.004001283,0.00036814142,0.0030827164,0.0005148454,0.00008531522,0.000019210578,0.0010796132,0.014545921,0.0005297356,0.9753933,0.00012834033,0.0002515709],"about_ca_topic_score_codex":0.00015874607,"about_ca_topic_score_gemma":0.00072433945,"teacher_disagreement_score":0.0644307,"about_ca_system_score_codex":0.0001935947,"about_ca_system_score_gemma":0.000102586615,"threshold_uncertainty_score":0.9445233},"labels":[],"label_agreement":null},{"id":"W3153031932","doi":"","title":"re:Linde et al. (2021) -- The Bayes factor, HDI-ROPE and frequentist equivalence testing are actually all equivalent","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Frequentist inference; Bayes factor; Equivalence (formal languages); Bayesian probability; Statistics; Mathematics; Bayes' theorem; Rope; Credible interval; Null hypothesis; Econometrics; Applied mathematics; Bayesian inference; Algorithm; Discrete mathematics","score_opus":0.7218629674920117,"score_gpt":0.4252998144024907,"score_spread":0.296563153089521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153031932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4732859,0.00044912778,0.5141357,0.002632423,0.0023316918,0.00171548,0.0007951875,0.00036716004,0.00428729],"genre_scores_gemma":[0.8192249,0.0015827913,0.1764096,0.0017381477,0.00019325087,0.0000062931504,0.000015171486,0.00010452692,0.00072533375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99366283,0.0024156298,0.00093711674,0.0018908579,0.00038186743,0.0007116997],"domain_scores_gemma":[0.9521986,0.043778867,0.0011897637,0.0019403781,0.00052619306,0.00036614647],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031366276,0.00069884106,0.0012399246,0.00012587354,0.00026966617,0.0003735038,0.001444071,0.000469946,0.00080244534],"category_scores_gemma":[0.069899075,0.0006076265,0.00038688583,0.00044003007,0.0006297559,0.00019092583,0.003890594,0.0020706332,0.000034946308],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015767987,0.00506355,0.09216681,0.01153638,0.010274012,0.025017867,0.007964167,0.012579795,0.003027892,0.7547525,0.035125736,0.040914454],"study_design_scores_gemma":[0.0014566132,0.00020186437,0.0066472683,0.002698874,0.0011208461,0.000021948155,0.0018952416,0.010562864,0.00030334404,0.97260284,0.0010021076,0.001486213],"about_ca_topic_score_codex":0.00015435237,"about_ca_topic_score_gemma":0.0001815623,"teacher_disagreement_score":0.34593898,"about_ca_system_score_codex":0.0002434048,"about_ca_system_score_gemma":0.00032806874,"threshold_uncertainty_score":0.9996375},"labels":[],"label_agreement":null},{"id":"W3153092758","doi":"10.1002/sim.8991","title":"Computing the polytomous discrimination index","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Polytomous Rasch model; Categorical variable; Outcome (game theory); Ranking (information retrieval); Pairwise comparison; Computer science; Statistics; Index (typography); Econometrics; Mathematics; Data mining; Artificial intelligence; Item response theory; Psychometrics","score_opus":0.4309870051715288,"score_gpt":0.5813675000711929,"score_spread":0.15038049489966404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153092758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017563967,0.00011217736,0.9872806,0.003605525,0.0011753871,0.00023333728,0.000079105186,0.000039238876,0.005718208],"genre_scores_gemma":[0.22473183,0.00005258107,0.77321035,0.0008883252,0.00060260587,0.000008849042,0.000013048507,0.000028243227,0.0004641673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969151,0.00096368464,0.0009484464,0.00029659088,0.00058645586,0.0002897023],"domain_scores_gemma":[0.93126714,0.06779366,0.00021556648,0.00042560755,0.00021933166,0.00007868739],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038159566,0.00015388135,0.0005133603,0.000062837345,0.000098164004,0.000019908148,0.00023311326,0.000090235786,0.00061453873],"category_scores_gemma":[0.21079598,0.00009953028,0.000029011748,0.0004067745,0.00041522237,0.000020184798,0.0001244089,0.0004978186,0.0000125891875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022308293,0.00009574076,0.0013037911,0.00012606865,0.00002510893,0.00020699235,0.00094506715,0.000007543986,0.00007713386,0.91124594,0.013741715,0.0722026],"study_design_scores_gemma":[0.001014772,0.00006817349,0.010178843,0.00022460353,0.0000691511,0.00002042001,0.0009029141,0.0055730497,0.000095638796,0.981312,0.00042482704,0.00011564297],"about_ca_topic_score_codex":0.000049396756,"about_ca_topic_score_gemma":0.00014606383,"teacher_disagreement_score":0.22297543,"about_ca_system_score_codex":0.00006790626,"about_ca_system_score_gemma":0.000081348,"threshold_uncertainty_score":0.7958518},"labels":[],"label_agreement":null},{"id":"W3156132131","doi":"10.1136/bmjopen-2020-044480","title":"Testing for non-inferior mortality: a systematic review of non-inferiority margin sizes and trial characteristics","year":2021,"lang":"en","type":"review","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Institute of Health Services and Policy Research; University of Toronto; Public Health Ontario; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Medicine; MEDLINE; Relative risk; Clinical trial; Randomized controlled trial; Absolute risk reduction; Meta-analysis; Internal medicine; Confidence interval","score_opus":0.7776344837777283,"score_gpt":0.6670337339442063,"score_spread":0.11060074983352197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156132131","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000028956183,0.84452134,0.00818498,0.000034960936,0.0012019514,0.14314349,0.0020655943,0.000039147802,0.0008056189],"genre_scores_gemma":[1.13494124e-7,0.59945434,0.38312694,0.000092302245,0.00048099973,0.0165518,0.000042677926,0.00010855498,0.00014226497],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98635143,0.0034829949,0.008016233,0.00096373504,0.00070269476,0.00048288226],"domain_scores_gemma":[0.82227045,0.1665898,0.0075235697,0.0024497986,0.00087416905,0.0002921837],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028938536,0.000833367,0.01984003,0.00008974759,0.00011108511,0.00030715516,0.0013399189,0.000595812,0.00012855051],"category_scores_gemma":[0.6075324,0.00062428246,0.0011585795,0.00052185316,0.00016575855,0.00010716883,0.0015479528,0.0005300254,0.00001256658],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017384818,0.00014773208,0.000002651951,0.91941386,0.0007034724,0.000025803578,0.0000116348865,4.0122325e-10,2.6578897e-7,0.0013358163,0.0003863319,0.07779858],"study_design_scores_gemma":[0.004737761,0.00041174976,0.0000063476464,0.9631181,0.016558718,0.000036516845,0.000010001901,0.000016306269,5.7688925e-7,0.009880811,0.0045248894,0.0006982586],"about_ca_topic_score_codex":0.000018730265,"about_ca_topic_score_gemma":0.0000026527093,"teacher_disagreement_score":0.57859385,"about_ca_system_score_codex":0.00010181751,"about_ca_system_score_gemma":0.0015492389,"threshold_uncertainty_score":0.99991214},"labels":[],"label_agreement":null},{"id":"W3156228170","doi":"10.21203/rs.3.rs-340897/v1","title":"TRAFIC: Statistical Plan for a Pragmatic Early Phase 1/2 Bayesian Adaptive Dose Escalation Trial in Rheumatoid Arthritis","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Rheumatoid arthritis; Bayesian probability; Medicine; Computer science; Internal medicine; Artificial intelligence","score_opus":0.5593154670783043,"score_gpt":0.6104900259288792,"score_spread":0.05117455885057498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156228170","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08443577,0.00034146977,0.8901051,0.00048524482,0.0011715939,0.0168898,0.0057910844,0.0001765344,0.00060339127],"genre_scores_gemma":[0.30839342,0.000398314,0.684928,0.000014340447,0.00066379074,0.004977353,0.00039743813,0.00016445915,0.00006288958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98091614,0.010329581,0.0031237132,0.0016818579,0.0025039462,0.001444744],"domain_scores_gemma":[0.83477366,0.16205801,0.0005067159,0.0011706816,0.0009403281,0.0005506173],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02101079,0.0006211163,0.0024418915,0.0006744148,0.00023890621,0.00059038575,0.00074147194,0.0012656043,0.0009833392],"category_scores_gemma":[0.30604154,0.0006126495,0.00049099716,0.0006817643,0.0005306894,0.00014504945,0.0007707307,0.0037519943,0.0000311],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14829253,0.0138332285,0.00014972236,0.010325709,0.0008606773,0.001356233,0.0066800085,0.00009668787,0.00011354015,0.45871407,0.0064236303,0.35315397],"study_design_scores_gemma":[0.073206976,0.0036979793,0.00026820257,0.005672551,0.00004676265,0.0000071449986,0.0009029396,0.019035868,0.0000795533,0.89636374,0.00009722333,0.0006210796],"about_ca_topic_score_codex":0.00020104562,"about_ca_topic_score_gemma":0.0003561532,"teacher_disagreement_score":0.43764967,"about_ca_system_score_codex":0.0005626524,"about_ca_system_score_gemma":0.001543949,"threshold_uncertainty_score":0.9999299},"labels":[],"label_agreement":null},{"id":"W3156868405","doi":"10.1016/s2214-109x(20)30540-4","title":"Randomised trials at the level of the individual","year":2021,"lang":"en","type":"review","venue":"The Lancet Global Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"British Columbia Centre on Substance Use; McMaster University; Hospital for Sick Children; Impact; University of British Columbia","funders":"Bill and Melinda Gates Foundation","keywords":"Clinical trial; Protocol (science); Research design; Computer science; Scale (ratio); Clinical study design; Data collection; Management science; Operations research; Medical physics; Risk analysis (engineering); Data science; Medicine; Alternative medicine; Statistics; Engineering; Mathematics","score_opus":0.9420801402174879,"score_gpt":0.7067034445368613,"score_spread":0.23537669568062658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156868405","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002125786,0.9715195,0.0018047462,0.005810451,0.0024037608,0.005408776,0.011402469,0.00003740077,0.0016108034],"genre_scores_gemma":[9.1820345e-7,0.95678294,0.038214974,0.002203408,0.0020415343,0.00022710995,0.000019802585,0.00004400862,0.00046528963],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95069623,0.042372663,0.0044872793,0.0005154068,0.0011913356,0.0007371009],"domain_scores_gemma":[0.7693907,0.22303976,0.004699032,0.002597339,0.000126032,0.00014710605],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06918428,0.00051801413,0.010217123,0.000016076703,0.00038353435,0.00005864599,0.0025600172,0.0004033811,0.0004040317],"category_scores_gemma":[0.24191722,0.00018054854,0.0021011992,0.00072024437,0.00058227364,0.0000133014155,0.0010940833,0.0009954581,0.000042334643],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021252189,0.00005909319,0.0000011136879,0.0062462157,0.00064091856,0.0000013000997,0.000051219842,1.5316405e-7,7.637537e-9,0.09642679,0.13638721,0.75997347],"study_design_scores_gemma":[0.0047005652,0.00004789123,0.000019069013,0.008501532,0.0021400217,0.000029103965,0.00001958513,6.233659e-7,6.7187693e-7,0.32614717,0.6582207,0.00017307303],"about_ca_topic_score_codex":0.00007020644,"about_ca_topic_score_gemma":0.000094800074,"teacher_disagreement_score":0.7598004,"about_ca_system_score_codex":0.00045582125,"about_ca_system_score_gemma":0.0020280958,"threshold_uncertainty_score":0.95847064},"labels":[],"label_agreement":null},{"id":"W3157114989","doi":"10.1002/9781118445112.stat05961.pub2","title":"Simultaneous Confidence Intervals and Regions","year":2017,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Confidence interval; Confidence distribution; Robust confidence intervals; Confidence and prediction bands; CDF-based nonparametric confidence interval; Statistics; Confidence region; Mathematics; Correctness; Inference; Range (aeronautics); Computer science; Artificial intelligence; Algorithm; Engineering","score_opus":0.4863328770071612,"score_gpt":0.5518108231821175,"score_spread":0.06547794617495628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157114989","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000059882123,0.0011745587,0.83008784,0.00023621829,0.0013254768,0.0013502219,0.082510725,0.000557171,0.08275183],"genre_scores_gemma":[0.00008534184,0.007786914,0.69653165,0.00016126376,0.0005388337,0.000042243704,0.00038021628,0.00061788573,0.29385567],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945893,0.00083662476,0.0014600437,0.0013674558,0.0009060285,0.0008405365],"domain_scores_gemma":[0.951394,0.043232128,0.0021394081,0.002216051,0.00040958385,0.000608828],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011748194,0.0009838031,0.0023207027,0.0002904373,0.00023401921,0.00024210196,0.0012345513,0.0009721006,0.0032083038],"category_scores_gemma":[0.14192878,0.0008685066,0.000120237826,0.000118382144,0.0015731113,0.00006070171,0.00058078085,0.0013951529,0.00016274882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006806871,0.00024863216,0.0000088051165,0.000746356,0.0002361078,0.00036106078,0.000047751382,3.7644986e-7,0.000008773317,0.35872883,0.5814594,0.058085866],"study_design_scores_gemma":[0.0007598908,0.00029208983,0.0000081217195,0.0029634105,0.0003837456,0.000027921335,0.00003421217,0.00048070785,0.000004572475,0.681006,0.31326753,0.0007717699],"about_ca_topic_score_codex":0.00041014265,"about_ca_topic_score_gemma":0.0017503713,"teacher_disagreement_score":0.32227722,"about_ca_system_score_codex":0.000093969764,"about_ca_system_score_gemma":0.0003264542,"threshold_uncertainty_score":0.9993766},"labels":[],"label_agreement":null},{"id":"W3157357664","doi":"10.1186/s12859-022-04693-z","title":"Evaluation of statistical approaches for association testing in noisy drug screening data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Université du Québec à Montréal; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Syöpäjärjestöt; Academy of Finland; European Commission","keywords":"Concordance; False positive paradox; Computer science; Statistical hypothesis testing; Pearson product-moment correlation coefficient; Data mining; Spearman's rank correlation coefficient; Correlation; Rank correlation; Statistics; Parametric statistics; Noise (video); Machine learning; Medicine; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.8876184499002661,"score_gpt":0.574548024450978,"score_spread":0.3130704254492881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157357664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024086956,0.000016824088,0.99223655,0.00006267713,0.00024597888,0.0014852169,0.0020927119,0.00004129368,0.0014100687],"genre_scores_gemma":[0.009410935,6.9392115e-7,0.99006885,0.000032100248,0.0000745474,0.00020442298,0.00015646273,0.000022903205,0.000029065446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99394774,0.0015842383,0.001943328,0.0002526901,0.00193416,0.0003378606],"domain_scores_gemma":[0.89470595,0.102798216,0.0012825753,0.0007308084,0.00041614275,0.000066288485],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05248438,0.000143663,0.00051334815,0.00013030325,0.00013486607,0.000033052,0.00054482406,0.0000801559,0.000102970924],"category_scores_gemma":[0.4063524,0.0001437612,0.000053035517,0.00042227725,0.00004715417,0.00019677677,0.0005439152,0.0002984733,0.0000024354792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040647184,0.0013516832,0.027298031,0.0034873884,0.0003511808,0.0000011389196,0.0035114938,0.030962944,0.0000160468,0.19977963,0.020258794,0.7125752],"study_design_scores_gemma":[0.0012766455,0.000058009497,0.001024588,0.000033018612,0.00023418665,8.531361e-7,0.00095513306,0.69781375,0.000011545431,0.29840866,0.00007057895,0.00011305826],"about_ca_topic_score_codex":0.000016209091,"about_ca_topic_score_gemma":0.000030407684,"teacher_disagreement_score":0.7124621,"about_ca_system_score_codex":0.00031974723,"about_ca_system_score_gemma":0.00034807675,"threshold_uncertainty_score":0.9756667},"labels":[],"label_agreement":null},{"id":"W3158746796","doi":"10.1002/0471266949.bmc276","title":"Clinical Development – A Primer","year":2021,"lang":"en","type":"other","venue":"Burger's Medicinal Chemistry and Drug Discovery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Clinical trial; Biosimilar; Regulatory science; Drug development; Medicine; New product development; Product (mathematics); Business; Agency (philosophy); Quality (philosophy); Process management; Drug; Pharmacology; Marketing; Pathology","score_opus":0.2737468116283632,"score_gpt":0.506332284310644,"score_spread":0.23258547268228086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158746796","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031622408,0.011126939,0.023579093,0.0006399952,0.0038207795,0.0008231223,0.00020452363,0.00037167818,0.95627165],"genre_scores_gemma":[0.00023805999,0.00096182054,0.22728176,0.00038098975,0.004028519,0.000059668262,0.0000628796,0.00036558983,0.7666207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995934,0.00039913488,0.0015264148,0.0009862914,0.0007112439,0.00044291417],"domain_scores_gemma":[0.982136,0.015967993,0.00068858726,0.0007148027,0.00005507593,0.00043755514],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029776772,0.00054154085,0.0017737512,0.000032841435,0.00006346692,0.000061066035,0.0002964776,0.00073337386,0.0077261175],"category_scores_gemma":[0.03048627,0.00043906446,0.0002805511,0.00012899529,0.00055138837,0.000029562487,0.0003121812,0.00090112694,0.000015834406],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011239345,0.00051941857,0.0010698431,0.0038867407,0.00074074365,0.0004235692,0.00006424779,1.3520705e-8,0.00014596949,0.0011438243,0.9664085,0.025484735],"study_design_scores_gemma":[0.0017407038,0.000029428737,0.00019333616,0.0069285193,0.0006475187,0.00006547733,0.00022532871,0.000004035346,0.002908582,0.05505076,0.9310778,0.0011285413],"about_ca_topic_score_codex":0.000017449045,"about_ca_topic_score_gemma":0.0000037744226,"teacher_disagreement_score":0.20370267,"about_ca_system_score_codex":0.00004382549,"about_ca_system_score_gemma":0.0005655286,"threshold_uncertainty_score":0.9998061},"labels":[],"label_agreement":null},{"id":"W3159307809","doi":"10.1002/sim.9593","title":"Dose finding studies for therapies with late‐onset toxicities: A comparison study of designs","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Maximum tolerated dose; Medicine; Clinical trial; Early stopping; Confidence interval; Set (abstract data type); Toxicity; Interval (graph theory); Computer science; Statistics; Oncology; Mathematics; Internal medicine; Machine learning","score_opus":0.7531072275672495,"score_gpt":0.6337813978697665,"score_spread":0.11932582969748295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159307809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38044393,0.00042580595,0.6132714,0.00038555104,0.00077476026,0.0032722794,0.0012232007,0.0000571174,0.00014595967],"genre_scores_gemma":[0.4860441,0.00002120566,0.513218,0.00007408069,0.00006203168,0.00042554294,0.000006376627,0.000031514835,0.000117155345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99587137,0.0012619467,0.0014561395,0.00034586608,0.00075415196,0.0003105204],"domain_scores_gemma":[0.8945138,0.104342915,0.0005451295,0.0003429955,0.000198761,0.000056406752],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00495545,0.00022986456,0.0014729573,0.00020507365,0.00019365852,0.000006439983,0.0002927654,0.000038629478,0.0002863553],"category_scores_gemma":[0.0516793,0.00016606583,0.000028742621,0.0003928278,0.00046761698,0.000019768104,0.00013661993,0.00037839537,4.074529e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010327777,0.009777225,0.047557782,0.003968431,0.0038729294,0.0004985912,0.35886082,0.0014766025,0.00035662472,0.4739273,0.064258456,0.025117472],"study_design_scores_gemma":[0.0072840624,0.011105066,0.0014786583,0.00023130445,0.0003424721,0.0000041295384,0.1212131,0.0010049857,0.00003786096,0.85696834,0.00012044146,0.00020958215],"about_ca_topic_score_codex":0.000052341766,"about_ca_topic_score_gemma":0.00017827358,"teacher_disagreement_score":0.38304105,"about_ca_system_score_codex":0.000119415745,"about_ca_system_score_gemma":0.00006453939,"threshold_uncertainty_score":0.9563088},"labels":[],"label_agreement":null},{"id":"W3159320036","doi":"10.1002/sim.9000","title":"Score tests for scale effects, with application to genomic analysis","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Toronto; University of Waterloo; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Statistics; Mathematics; Type I and type II errors; Permutation (music); Scale (ratio); Gaussian; Applied mathematics","score_opus":0.24350483640801132,"score_gpt":0.5516258013485317,"score_spread":0.3081209649405203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159320036","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0098336255,0.000052730178,0.98740244,0.00067646167,0.00018464272,0.0010948705,0.00037417188,0.00003599307,0.00034506863],"genre_scores_gemma":[0.028015349,0.000018479439,0.9704478,0.0005735064,0.000279175,0.00035525163,0.00006687421,0.000039250295,0.00020431726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976738,0.00030180826,0.0007977134,0.0005289817,0.00038777024,0.00030990996],"domain_scores_gemma":[0.94478166,0.053918704,0.00018442246,0.0005859075,0.00033773057,0.0001916031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020543342,0.00019165628,0.0009906305,0.00020469769,0.00005276336,0.000013703415,0.00018987633,0.000092161245,0.00012328199],"category_scores_gemma":[0.07830169,0.00014890124,0.000048939986,0.0012251183,0.0001666364,0.000014365998,0.000055960078,0.00018841105,0.000011996218],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084075035,0.0007978883,0.0422677,0.0027031726,0.0013882603,0.00023984323,0.0013897127,0.00030869155,0.0082898075,0.679282,0.025160179,0.23733202],"study_design_scores_gemma":[0.002142477,0.0005333531,0.034376867,0.00022880318,0.0016028706,0.0000039628617,0.0000899203,0.002437699,0.00088265655,0.9569789,0.0004894605,0.00023303609],"about_ca_topic_score_codex":0.000030912153,"about_ca_topic_score_gemma":0.00067783345,"teacher_disagreement_score":0.2776969,"about_ca_system_score_codex":0.00010363583,"about_ca_system_score_gemma":0.000084486186,"threshold_uncertainty_score":0.92946213},"labels":[],"label_agreement":null},{"id":"W3162211911","doi":"10.31234/osf.io/urgtn","title":"Z-Curve 2.0: Estimating Replication Rates and Discovery Rates","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Replication (statistics); Confidence interval; False discovery rate; Selection (genetic algorithm); Statistics; False positive paradox; Multiple comparisons problem; Computer science; Range (aeronautics); Extension (predicate logic); Econometrics; Mathematics; Artificial intelligence; Biology; Engineering","score_opus":0.6573930739385597,"score_gpt":0.6101719849647902,"score_spread":0.04722108897376953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162211911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007418945,0.000072319934,0.98218447,0.004710577,0.0008843412,0.0010623733,0.00017384056,0.00031482906,0.003178294],"genre_scores_gemma":[0.01541293,0.00004614999,0.98271227,0.00035016492,0.00071169704,0.00014706739,0.000023645849,0.00006499072,0.0005311028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99611163,0.0008232045,0.0013339128,0.0011838671,0.00030536653,0.00024204198],"domain_scores_gemma":[0.940866,0.056895103,0.00073536066,0.0012015841,0.00013380592,0.0001681422],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033791682,0.0003682369,0.001085557,0.00004567106,0.00007880101,0.0003686439,0.00035283138,0.0004006306,0.00015124802],"category_scores_gemma":[0.30096525,0.00029800565,0.00015108776,0.00010784228,0.0001849766,0.00009914986,0.0013129491,0.0008230063,0.000029092436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015510613,0.00021758306,0.0021212928,0.0044706976,0.00045995877,0.000021282722,0.0005314289,0.00004275489,0.0008995952,0.9237765,0.019058859,0.04824491],"study_design_scores_gemma":[0.00025339532,0.00004838019,0.0006036334,0.00033162712,0.00016520797,0.0000023304171,0.00003133276,0.02328195,0.0020154952,0.97287476,0.000061050945,0.00033080624],"about_ca_topic_score_codex":0.00003524028,"about_ca_topic_score_gemma":0.0000036449424,"teacher_disagreement_score":0.29758608,"about_ca_system_score_codex":0.000040807958,"about_ca_system_score_gemma":0.0000955945,"threshold_uncertainty_score":0.9999472},"labels":[],"label_agreement":null},{"id":"W3162765094","doi":"10.1101/2021.05.21.445109","title":"Analyzing Biomarker Discovery: Estimating the Reproducibility of Biomarker Sets","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Reproducibility; Univariate; Biomarker; Biomarker discovery; Computer science; Binary number; False discovery rate; Statistics; Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics; Machine learning; Multivariate statistics; Biology; Proteomics","score_opus":0.24158997134797427,"score_gpt":0.43529941552131596,"score_spread":0.19370944417334168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162765094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7383804,0.00071634114,0.25390735,0.00056026055,0.003841564,0.0015772529,0.0006687665,0.00032301285,0.000025063388],"genre_scores_gemma":[0.5262742,0.00003048534,0.47314918,0.000050870258,0.0002599256,0.00011286969,2.0967545e-7,0.00011933313,0.000002898956],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.98857576,0.0033232635,0.0029771356,0.0033977875,0.0009450529,0.0007810307],"domain_scores_gemma":[0.96332467,0.022395054,0.002554325,0.010191355,0.0012473251,0.00028728208],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025419591,0.0008487205,0.0021615697,0.00021102747,0.0002498624,0.0004848316,0.0013954426,0.00083090237,0.0001495228],"category_scores_gemma":[0.26396015,0.00066704047,0.00074349606,0.0012249703,0.000736648,0.0002252483,0.00228811,0.0013772496,0.000009677118],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056042935,0.0028118864,0.054264437,0.014214807,0.0061630313,0.0003566125,0.00014136443,0.00018505176,0.89541924,0.022394128,0.0030024727,0.00048651357],"study_design_scores_gemma":[0.0027062325,0.00017067058,0.5110065,0.009406033,0.004490869,2.086805e-7,0.000052537693,0.024650052,0.41780087,0.025052937,0.00027448978,0.00438865],"about_ca_topic_score_codex":0.0000804208,"about_ca_topic_score_gemma":0.0000029831856,"teacher_disagreement_score":0.4776184,"about_ca_system_score_codex":0.00026203052,"about_ca_system_score_gemma":0.0008293983,"threshold_uncertainty_score":0.99957806},"labels":[],"label_agreement":null},{"id":"W3164440149","doi":"10.1038/s41598-021-90403-3","title":"Efficacy, safety and tolerability of drugs studied in phase 3 randomized controlled trials in solid tumors over the last decade","year":2021,"lang":"en","type":"review","venue":"Scientific Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Tolerability; Discontinuation; Internal medicine; Clinical endpoint; Hazard ratio; Adverse effect; Randomized controlled trial; Oncology; Odds ratio; Confidence interval; Surgery","score_opus":0.39046670261632127,"score_gpt":0.5871024553318834,"score_spread":0.19663575271556216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164440149","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002188891,0.96637046,0.001277712,0.000059350034,0.007047529,0.02236699,0.00010063047,0.00003485143,0.0005536053],"genre_scores_gemma":[0.00066941563,0.96940583,0.027412638,0.00002134551,0.00028394812,0.0016391589,0.0000385145,0.000098764634,0.0004304003],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8943461,0.06526879,0.034804948,0.0026754644,0.002065407,0.0008392643],"domain_scores_gemma":[0.29844594,0.6832464,0.014788851,0.0028346041,0.00045200696,0.00023225255],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36027652,0.0006624294,0.039363854,0.00044978174,0.0001323641,0.00021907952,0.00040069126,0.00044107685,0.00030299512],"category_scores_gemma":[0.8351779,0.00033672116,0.003386679,0.001374087,0.0017664725,0.000051789866,0.00041901355,0.00089746,0.0000016824051],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.048111923,0.004692908,0.00002367508,0.019322667,0.0031004595,0.0012089513,0.0016437232,0.000008084317,0.000009143659,0.008934187,0.0018695652,0.9110747],"study_design_scores_gemma":[0.43243766,0.00007378958,0.000013575259,0.037441768,0.007531089,0.00008610538,0.0001716328,0.000087729866,0.000028611204,0.46923417,0.05204318,0.0008507031],"about_ca_topic_score_codex":0.00001608369,"about_ca_topic_score_gemma":0.000029750136,"teacher_disagreement_score":0.910224,"about_ca_system_score_codex":0.00016918547,"about_ca_system_score_gemma":0.0010797592,"threshold_uncertainty_score":0.9999085},"labels":[],"label_agreement":null},{"id":"W3165960112","doi":"10.1200/jco.2021.39.15_suppl.e18616","title":"Optimism bias in the design of phase III randomized control trials (RCTs) evaluating PD-1/PD-L1 targeting monoclonal antibodies (mAbs).","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Randomized controlled trial; Hazard ratio; Internal medicine; Monoclonal antibody; Confidence interval; Oncology; Clinical endpoint; Clinical trial; non-small cell lung cancer (NSCLC); Lung cancer; Antibody; Immunology","score_opus":0.8947952863249296,"score_gpt":0.7201853843460729,"score_spread":0.17460990197885662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165960112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20118551,0.0016513834,0.7802129,0.008453226,0.0045690374,0.0026381577,0.000051019248,0.000021538175,0.001217263],"genre_scores_gemma":[0.18635088,0.0010436984,0.8089414,0.0015074103,0.0020368635,0.00003835366,0.0000012213768,0.0000339186,0.000046235615],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80198115,0.16410074,0.030572386,0.0006292675,0.0019680501,0.0007483982],"domain_scores_gemma":[0.09068836,0.88982445,0.016762685,0.00051039946,0.0019096711,0.00030445025],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43835115,0.00037317458,0.012532473,0.00018644331,0.00010308782,0.000052199368,0.0008128593,0.0008275659,0.0007647198],"category_scores_gemma":[0.9448312,0.00021181398,0.0026116907,0.00037981084,0.0009390558,0.00013890321,0.00014072278,0.0023293027,0.0000067430487],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.73132294,0.01403453,0.0004848598,0.00031293873,0.005399372,0.0023360366,0.0014750478,0.0034816882,0.003727288,0.03450192,0.010564981,0.19235836],"study_design_scores_gemma":[0.477835,0.0040606,0.00011212971,0.00033735746,0.00248752,0.00010051114,0.0005179367,0.016317733,0.0005220104,0.4971989,0.0002974597,0.00021283347],"about_ca_topic_score_codex":0.0000078266485,"about_ca_topic_score_gemma":0.0000024602507,"teacher_disagreement_score":0.7257237,"about_ca_system_score_codex":0.00009342053,"about_ca_system_score_gemma":0.0025881813,"threshold_uncertainty_score":0.99997234},"labels":[],"label_agreement":null},{"id":"W3170430205","doi":"10.1016/j.cjca.2021.05.017","title":"Understanding the Merits and Drawbacks of Noninferiority Trials in Cardiovascular Medicine","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Clinical trial; Intensive care medicine; Medical physics; Margin (machine learning); Placebo; Clinical study design; Population; Risk analysis (engineering); Alternative medicine; Internal medicine; Computer science; Pathology","score_opus":0.8160412747036927,"score_gpt":0.5877581272960044,"score_spread":0.2282831474076883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170430205","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018200187,0.91195357,0.0842685,0.00018059569,0.0017466702,0.0004670766,0.00008759002,0.0000016309259,0.0012925332],"genre_scores_gemma":[0.00020346812,0.98535734,0.012448284,0.00002200855,0.0019125487,0.000008554006,0.0000015823161,0.000037963953,0.000008228887],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97723585,0.017778534,0.004025886,0.00027143833,0.00032081536,0.00036744552],"domain_scores_gemma":[0.89413935,0.10281839,0.0018443993,0.0005460584,0.0002551771,0.00039662945],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050002404,0.00033185005,0.01507602,0.00046243353,0.000065941436,0.000020755957,0.0004663127,0.0006512247,0.000055202672],"category_scores_gemma":[0.3070261,0.00019433995,0.0021938358,0.00043082848,0.0010444128,0.000027140266,0.00004999104,0.0012213058,5.105601e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002638235,0.0000044865433,0.00012818503,0.009845088,0.011431245,0.0015780941,0.0003592837,0.000021045329,3.4327064e-7,0.12156981,0.0064823544,0.84855366],"study_design_scores_gemma":[0.0008272681,0.00015797614,0.000020755662,0.013415026,0.007220896,0.0010400537,0.00022603582,4.4790744e-7,2.0474312e-7,0.26217064,0.7147171,0.00020363349],"about_ca_topic_score_codex":0.00027132643,"about_ca_topic_score_gemma":0.00039048985,"teacher_disagreement_score":0.84835005,"about_ca_system_score_codex":0.00038868704,"about_ca_system_score_gemma":0.0028439618,"threshold_uncertainty_score":0.99954623},"labels":[],"label_agreement":null},{"id":"W3170898643","doi":"10.5435/jaaos-d-20-00919","title":"Bounding the Implications of Noncompliance in Randomized Controlled Trials in Orthopaedics: An Example in Arthroscopic Surgery","year":2021,"lang":"en","type":"article","venue":"Journal of the American Academy of Orthopaedic Surgeons","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Object Research Systems (Canada)","funders":"","keywords":"Randomized controlled trial; Bounding overwatch; MEDLINE; Arthroscopy; Clinical trial","score_opus":0.43124608346711946,"score_gpt":0.5184680659260174,"score_spread":0.0872219824588979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170898643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836023,0.000963705,0.0049438924,0.008281568,0.00060232554,0.0014085817,0.00003680262,0.000008161739,0.00015268032],"genre_scores_gemma":[0.9569176,0.0022110858,0.039724,0.000786898,0.00019426322,0.00010462994,5.6550016e-7,0.000036682748,0.000024301871],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95812094,0.02926767,0.010812605,0.00034722444,0.00095392053,0.0004976084],"domain_scores_gemma":[0.42381752,0.5597026,0.015243577,0.0006989997,0.0003322277,0.00020509171],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12142823,0.00029730884,0.010470445,0.0006487189,0.00006734916,0.000026413541,0.00073863566,0.00015553166,0.00010716334],"category_scores_gemma":[0.45022047,0.00016531727,0.0026676094,0.0023279546,0.0015096168,0.00014518978,0.00015250308,0.0013549111,6.034086e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06737083,0.0025121614,0.84492224,0.0003725534,0.0014701552,0.00008029708,0.0013361585,0.00044758452,0.004260267,0.037841205,0.0013285702,0.038057975],"study_design_scores_gemma":[0.112342104,0.00011258026,0.34627357,0.0027315156,0.00085643446,0.00007435137,0.0012844537,0.00029235356,0.00094488665,0.53452945,0.00021171106,0.00034657188],"about_ca_topic_score_codex":0.0002503577,"about_ca_topic_score_gemma":0.0002488527,"teacher_disagreement_score":0.5343035,"about_ca_system_score_codex":0.00011869125,"about_ca_system_score_gemma":0.00084726495,"threshold_uncertainty_score":0.90467453},"labels":[],"label_agreement":null},{"id":"W3176043026","doi":"10.1016/j.cmpb.2021.106255","title":"CRTpowerdist: An R package to calculate attained power and construct the power distribution for cross-sectional stepped-wedge and parallel cluster randomized trials","year":2021,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Statistics; Poisson distribution; Randomization; Cluster (spacecraft); Randomized controlled trial; Statistical power; Restricted randomization; Mathematics; Cluster randomised controlled trial; Computer science; Binary number; Sample size determination; Power (physics); Medicine; Arithmetic; Surgery","score_opus":0.4115676118938668,"score_gpt":0.579553687405701,"score_spread":0.1679860755118342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176043026","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072958566,0.0005842849,0.9199235,0.001548611,0.0012820394,0.0034630229,0.00016893486,0.000047800513,0.000023228315],"genre_scores_gemma":[0.026826572,0.000063905565,0.9715769,0.0007002922,0.00038548684,0.0003074046,0.000064198786,0.000030225952,0.000044991215],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9891972,0.007422403,0.0018864833,0.000785479,0.00027987844,0.00042856907],"domain_scores_gemma":[0.91920954,0.07939781,0.00035933344,0.00041763255,0.0002975164,0.0003181813],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03874291,0.00034454308,0.002067144,0.00008407053,0.0002019504,0.00029833303,0.00015929097,0.00027869063,0.00004710317],"category_scores_gemma":[0.05084574,0.00020463117,0.00021381886,0.00033418796,0.0012788804,0.000079003854,0.00030940832,0.00028534353,4.3676124e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.047968645,0.0007337158,0.007131558,0.00077241205,0.00097925,0.000073404735,0.0020009254,0.000002560867,0.0008237791,0.17746122,0.0015696698,0.76048285],"study_design_scores_gemma":[0.13450922,0.0013046688,0.016860036,0.0002739311,0.00036623873,0.00019036747,0.00018231057,0.005715294,0.00013743275,0.8350403,0.0048837513,0.00053648156],"about_ca_topic_score_codex":0.00000794245,"about_ca_topic_score_gemma":0.0000026973182,"teacher_disagreement_score":0.75994635,"about_ca_system_score_codex":0.00003224839,"about_ca_system_score_gemma":0.000046653164,"threshold_uncertainty_score":0.9898165},"labels":[],"label_agreement":null},{"id":"W3176721814","doi":"10.6000/1929-6029.2019.08.08","title":"Meta-Analysis of Incidence Rate Data in the Presence of Zero-Event and Single-Arm Studies","year":2019,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Negative binomial distribution; Bivariate analysis; Poisson distribution; Statistics; Univariate; Binomial distribution; Continuity correction; Count data; Mathematics; Dispersion (optics); Context (archaeology); Random effects model; Event (particle physics); Meta-analysis; Econometrics; Beta-binomial distribution; Multivariate statistics; Medicine; Physics","score_opus":0.8980292824772418,"score_gpt":0.7181876361161611,"score_spread":0.1798416463610807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176721814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40059617,0.004978759,0.57496154,0.013478181,0.0015159211,0.0013206057,0.002486567,0.0000053794683,0.00065682916],"genre_scores_gemma":[0.77774113,0.0015922076,0.22046614,0.00009208272,0.00005390066,0.000005676679,0.0000032953512,0.000007999935,0.000037566126],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98621297,0.004788835,0.0026486586,0.00028578215,0.005815682,0.00024808693],"domain_scores_gemma":[0.67563593,0.32046145,0.0009274491,0.0005691225,0.0022908908,0.00011515468],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06922055,0.0001110535,0.0013498517,0.00072826335,0.000015522746,0.000030174846,0.002479356,0.0000945283,0.0006544172],"category_scores_gemma":[0.518826,0.00006609284,0.00014797598,0.0008156336,0.00093245786,0.00011461746,0.00092163484,0.0010203035,0.0000016677034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018165194,0.005100103,0.018149108,0.0009592238,0.10594572,0.0019774337,0.005718157,0.00040589646,0.00065907213,0.80993813,0.0056391642,0.043691486],"study_design_scores_gemma":[0.0008354363,0.0004985509,0.004366614,0.0002866426,0.004434202,0.000017368968,0.00093945593,0.007991806,0.0001393164,0.98033947,0.00007632058,0.000074834505],"about_ca_topic_score_codex":0.00009109704,"about_ca_topic_score_gemma":0.00016648653,"teacher_disagreement_score":0.44960546,"about_ca_system_score_codex":0.00007646462,"about_ca_system_score_gemma":0.00029126627,"threshold_uncertainty_score":0.95843333},"labels":[],"label_agreement":null},{"id":"W3179197834","doi":"10.1002/jac5.1501","title":"A practical introduction to conducting and using <scp>case‐control</scp> studies","year":2021,"lang":"en","type":"article","venue":"JACCP JOURNAL OF THE AMERICAN COLLEGE OF CLINICAL PHARMACY","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; University Health Network","funders":"","keywords":"Context (archaeology); Observational study; Control (management); Odds; Selection (genetic algorithm); Key (lock); Selection bias; Computer science; Medicine; Management science; Risk analysis (engineering); Engineering; Artificial intelligence; Pathology; Computer security; Internal medicine","score_opus":0.7397074335350374,"score_gpt":0.6636276825376554,"score_spread":0.07607975099738207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179197834","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558379,0.0002882881,0.020233136,0.019728264,0.003346522,0.00039994196,0.0000949307,0.000014853856,0.00005617487],"genre_scores_gemma":[0.37171492,0.00025280277,0.62269425,0.0014462633,0.003775286,0.000002549743,3.362923e-8,0.000033705623,0.000080179096],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9888331,0.005819789,0.0038861572,0.00040931583,0.0007081976,0.00034341172],"domain_scores_gemma":[0.7689137,0.22193323,0.005834897,0.00062778447,0.0021790029,0.00051137805],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015098872,0.00025403433,0.002439532,0.00010691923,0.00017786681,0.000032729422,0.0003194928,0.00006583365,0.000041671057],"category_scores_gemma":[0.6486942,0.00017296284,0.00061308494,0.0008696252,0.001039437,0.0002097451,0.00041093733,0.0012135432,0.0000021058681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010953115,0.011220151,0.05602403,0.0022402082,0.029744286,0.02548481,0.0026576524,0.0007112963,0.07858681,0.07957658,0.5040913,0.19870973],"study_design_scores_gemma":[0.027670993,0.0041412697,0.003287326,0.0013951551,0.013172688,0.055202518,0.029741237,0.003916117,0.044867534,0.7820079,0.033802874,0.00079440395],"about_ca_topic_score_codex":0.0000061372484,"about_ca_topic_score_gemma":0.0000030270874,"teacher_disagreement_score":0.7024313,"about_ca_system_score_codex":0.00007303581,"about_ca_system_score_gemma":0.0006188952,"threshold_uncertainty_score":0.70532197},"labels":[],"label_agreement":null},{"id":"W3179918017","doi":"10.1016/j.cjca.2021.06.023","title":"Adaptive Trials in Cardiology: Some Considerations and Examples","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Clinical trial; Psychological intervention; Adaptive design; Intensive care medicine; Medical physics; Pathology; Psychiatry","score_opus":0.8343656043618171,"score_gpt":0.5921486225287705,"score_spread":0.24221698183304652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179918017","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032978207,0.98570627,0.009835858,0.00016118473,0.0021362,0.0005950869,0.0005808209,0.000004579512,0.0009766726],"genre_scores_gemma":[0.000054223674,0.9054391,0.091031365,0.000077276905,0.0032917298,0.00003443515,0.000004800821,0.000047362963,0.000019724876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97261226,0.022284554,0.004083284,0.0003871352,0.00014259134,0.0004901506],"domain_scores_gemma":[0.8120389,0.18509759,0.0016032062,0.00035469906,0.0003042735,0.0006013134],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.020571196,0.00040899424,0.014147315,0.00072640675,0.00008348137,0.00005507231,0.00025472,0.0010532904,0.000078797566],"category_scores_gemma":[0.41665745,0.0003192904,0.0015131594,0.00020053625,0.000609537,0.00005918016,0.000049878774,0.0013804547,0.0000046686737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016077649,0.0000037720076,0.000055957044,0.0018857293,0.0037019348,0.00548554,0.00007838985,0.000023886394,1.8345658e-7,0.37002823,0.038059372,0.58066094],"study_design_scores_gemma":[0.00038899772,0.00010595984,0.000013003701,0.0027668427,0.0018005884,0.0020372425,0.000051830182,2.3742555e-7,8.186581e-8,0.45522422,0.5374081,0.00020286394],"about_ca_topic_score_codex":0.00012399987,"about_ca_topic_score_gemma":0.0006137199,"teacher_disagreement_score":0.58045805,"about_ca_system_score_codex":0.00029229902,"about_ca_system_score_gemma":0.0061745346,"threshold_uncertainty_score":0.9999259},"labels":[],"label_agreement":null},{"id":"W3186606527","doi":"10.1093/biostatistics/kxab028","title":"Bayesian adaptive model selection design for optimal biological dose finding in phase I/II clinical trials","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Bayesian probability; Selection (genetic algorithm); Computer science; Model selection; Maximum tolerated dose; Adaptive design; Econometrics; Clinical trial; Statistics; Artificial intelligence; Mathematics; Medicine; Internal medicine","score_opus":0.8908728524028277,"score_gpt":0.6664937251343948,"score_spread":0.2243791272684329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186606527","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039624567,0.000039655453,0.9917418,0.0002154732,0.0007368213,0.0017321598,0.001368112,0.000099326986,0.000104212726],"genre_scores_gemma":[0.0538286,0.00008840015,0.9449158,0.00020963153,0.00051194517,0.00018978189,0.000033647924,0.000056367306,0.00016586512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98808724,0.0065437914,0.0035497139,0.0008700064,0.00033213155,0.0006171061],"domain_scores_gemma":[0.79702663,0.20119098,0.0007914509,0.00033213847,0.00038880424,0.00026997994],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024386188,0.00036257037,0.001949607,0.00012169524,0.00020693197,0.00006682968,0.0002398582,0.0006444564,0.00021714927],"category_scores_gemma":[0.52557033,0.00031241903,0.0003744748,0.00042410722,0.00023807952,0.000064516484,0.00014980373,0.00057578343,0.000009114299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008612515,0.006640166,0.0002037286,0.00018875508,0.00046630244,0.00022056537,0.00036834908,0.003975763,0.0031145061,0.7750022,0.022990128,0.17821707],"study_design_scores_gemma":[0.005946103,0.0017504512,0.000028112418,0.000062801664,0.00016230406,0.000006674365,0.00005614398,0.4448297,0.0013039482,0.5454979,0.00008538425,0.00027048966],"about_ca_topic_score_codex":0.0000024876654,"about_ca_topic_score_gemma":0.000006091979,"teacher_disagreement_score":0.50118417,"about_ca_system_score_codex":0.00014072841,"about_ca_system_score_gemma":0.0005129743,"threshold_uncertainty_score":0.99993277},"labels":[],"label_agreement":null},{"id":"W3187015499","doi":"10.37394/23206.2021.20.6","title":"Comparison of Accuracy Properties for Confidence Intervals of the Cross-Product Ratio of Binomial Proportions under Direct-Direct Sampling Scheme","year":2021,"lang":"en","type":"article","venue":"WSEAS TRANSACTIONS ON MATHEMATICS","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Thammasat University","keywords":"Confidence interval; Statistics; Mathematics; Coverage probability; Estimator; Credible interval; Binomial proportion confidence interval; CDF-based nonparametric confidence interval; Robust confidence intervals; Binomial distribution; Sampling (signal processing); Closeness; Ratio estimator; Negative binomial distribution; Poisson distribution; Bias of an estimator; Computer science","score_opus":0.6763638074114466,"score_gpt":0.5815413325732214,"score_spread":0.09482247483822526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187015499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045248996,0.000111414214,0.95082283,0.00023667674,0.0004912727,0.0014877173,0.0009928007,0.000053711206,0.0005545742],"genre_scores_gemma":[0.5058626,0.000014036813,0.49356896,0.000011646887,0.000035849604,0.00011766237,0.0000022543213,0.000030930245,0.00035609055],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99624854,0.0003640429,0.0022689214,0.0003501034,0.00053885055,0.00022951234],"domain_scores_gemma":[0.97199583,0.024659876,0.0012503511,0.00096848834,0.0010612749,0.00006415933],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001627058,0.0002346867,0.0012021774,0.000077423974,0.00016842583,0.000036166904,0.00038763223,0.0001345359,0.00051646767],"category_scores_gemma":[0.04909469,0.00016684421,0.0005173129,0.0004120025,0.0006054328,0.0000950069,0.00002506086,0.00027439924,0.0000026127855],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012777634,0.019617237,0.0005980118,0.031221086,0.0031526536,0.0000018104441,0.0109771015,0.013593849,0.51697177,0.3870881,0.0013842541,0.014116408],"study_design_scores_gemma":[0.0006504818,0.00016262257,0.00012592034,0.0015983651,0.00042642638,0.0000031394543,0.00085234916,0.0047723027,0.77115905,0.2199869,0.000069382135,0.0001930743],"about_ca_topic_score_codex":0.0000054343245,"about_ca_topic_score_gemma":0.000017895423,"teacher_disagreement_score":0.46061358,"about_ca_system_score_codex":0.000048358197,"about_ca_system_score_gemma":0.00035378744,"threshold_uncertainty_score":0.9589152},"labels":[],"label_agreement":null},{"id":"W3187855084","doi":"10.1016/j.ejca.2021.07.001","title":"Real-world outcomes associated with new cancer medicines approved by the Food and Drug Administration and European Medicines Agency: A retrospective cohort study","year":2021,"lang":"en","type":"article","venue":"European Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Economic and Social Research Council; National Institute for Health and Care Research; UK Research and Innovation","keywords":"Medicine; Reimbursement; Clinical trial; Food and drug administration; Cancer drugs; Family medicine; Cancer; Internal medicine; Intensive care medicine; Oncology; Pharmacology; Health care","score_opus":0.18552405241209738,"score_gpt":0.4727837509154125,"score_spread":0.2872596985033151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187855084","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9692716,0.0021588122,0.0021959,0.016546762,0.0009299123,0.00082376203,0.00008390895,0.00004186574,0.007947485],"genre_scores_gemma":[0.9862943,0.0012249582,0.0073147276,0.00072447606,0.0009494693,0.00000852235,0.0000012209529,0.000084537496,0.003397756],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9945132,0.0031656015,0.0010528711,0.0003162411,0.0007547605,0.00019731368],"domain_scores_gemma":[0.9920759,0.0057298867,0.0011378069,0.00025534673,0.00057163055,0.00022942015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006967609,0.00024104046,0.000837527,0.000049759667,0.00012632704,0.000080129656,0.00020531348,0.000018549112,0.00013954274],"category_scores_gemma":[0.021476133,0.00013066141,0.00006546507,0.00028543727,0.00023406104,0.00008140274,0.000078714664,0.000470608,5.0157104e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034019226,0.0003187316,0.91716987,0.000048595528,0.0022328827,0.00039566748,0.003916524,0.0000012590322,0.0002310173,0.00053735333,0.0533984,0.021409525],"study_design_scores_gemma":[0.003645629,0.0010728876,0.98379725,0.00047739793,0.0013173809,0.000021522732,0.00073576276,0.000006139316,0.00017892977,0.007861025,0.00069481705,0.0001912742],"about_ca_topic_score_codex":0.00006454841,"about_ca_topic_score_gemma":0.001883851,"teacher_disagreement_score":0.06662738,"about_ca_system_score_codex":0.00009101642,"about_ca_system_score_gemma":0.00024341235,"threshold_uncertainty_score":0.9867664},"labels":[],"label_agreement":null},{"id":"W3191279957","doi":"10.1080/00401706.2021.1945335","title":"Statistical Modeling in Biomedical Research: Contemporary Topics and Voices in the Field","year":2021,"lang":"en","type":"article","venue":"Technometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Sleep Society","funders":"","keywords":"Field (mathematics); Data science; Computer science; Statistics; Mathematics","score_opus":0.882836036075885,"score_gpt":0.6436383879955951,"score_spread":0.23919764808028987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191279957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16525266,0.002112668,0.8004357,0.020736946,0.000395994,0.0010214582,0.000112561014,0.00012944495,0.009802527],"genre_scores_gemma":[0.5446326,0.00017556467,0.45463252,0.00038224887,0.00009485165,0.000034174886,0.0000023268872,0.000012438103,0.000033262233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99688643,0.0009182169,0.0007780641,0.00034845856,0.0007389289,0.00032992684],"domain_scores_gemma":[0.86233866,0.13694122,0.00005724254,0.00045845477,0.00011599554,0.000088435896],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0104805995,0.000105985404,0.0003916206,0.0007192255,0.00005427872,0.00006719987,0.00034851264,0.0002684865,0.00006359756],"category_scores_gemma":[0.408055,0.00007802009,0.000029539318,0.00398795,0.00022354079,0.00004499924,0.00027381195,0.0011124243,0.000004532104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046992045,0.0007328216,0.0067537213,0.00029051528,0.000014096007,0.0007913724,0.00036155898,0.0000014702886,0.000028514482,0.85742086,0.00588846,0.12766962],"study_design_scores_gemma":[0.00051801145,0.000100443336,0.0005547864,0.00007667245,0.0000058273613,0.0000063746947,0.0007734308,0.007750157,0.00005330855,0.9880777,0.0019821264,0.00010113251],"about_ca_topic_score_codex":0.00006171105,"about_ca_topic_score_gemma":0.000031551714,"teacher_disagreement_score":0.3975744,"about_ca_system_score_codex":0.000044940243,"about_ca_system_score_gemma":0.00011781177,"threshold_uncertainty_score":0.5969312},"labels":[],"label_agreement":null},{"id":"W3191733181","doi":"10.1214/21-aoas1501","title":"The ASA president’s task force statement on statistical significance and replicability","year":2021,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Task force; Statement (logic); Task (project management); Statistical analysis; Statistics; Computer science; Econometrics; Natural language processing; Mathematics; Political science; Law; Management; Economics","score_opus":0.5158428041741353,"score_gpt":0.5546070747217429,"score_spread":0.03876427054760756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191733181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011356819,0.00017529243,0.96797323,0.005667308,0.00037971724,0.0019437192,0.005576773,0.00008641865,0.0068407287],"genre_scores_gemma":[0.18610907,0.0009365461,0.8101794,0.0014905841,0.00019465594,0.00023886444,0.000024251567,0.0000757114,0.0007508836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953939,0.0009812603,0.0015855256,0.000621802,0.00088643667,0.00053108315],"domain_scores_gemma":[0.8735695,0.12391846,0.0005614384,0.0013569982,0.0004141421,0.00017947296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0066540404,0.00029111234,0.0007043376,0.00002070479,0.00037172934,0.00011155499,0.00046640157,0.000105157786,0.00014429659],"category_scores_gemma":[0.05931144,0.00017731966,0.00007224241,0.00018885879,0.0011372487,0.000023588424,0.00028463968,0.0004574249,0.00001908618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006102726,0.00020423938,0.000014912231,0.00018435014,0.00013760234,0.000012530055,0.00024071686,0.00001912398,0.00046803715,0.9313173,0.038859095,0.027931785],"study_design_scores_gemma":[0.00046382847,0.0002302706,0.0016106653,0.00003591525,0.00010925178,0.0000020438272,0.00038576117,0.00044011284,0.008744556,0.9844792,0.0033013776,0.00019704516],"about_ca_topic_score_codex":0.000015997744,"about_ca_topic_score_gemma":0.000025311198,"teacher_disagreement_score":0.17475225,"about_ca_system_score_codex":0.00002943506,"about_ca_system_score_gemma":0.0001794265,"threshold_uncertainty_score":0.9486124},"labels":[],"label_agreement":null},{"id":"W3192068715","doi":"10.18433/jpps31872","title":"Professor Endrenyi’s Legacy: An Evaluation of the Regulatory Requirement “Fixed Effects, Rather Than Random Effects, Should Be Used for All Terms”","year":2021,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Restricted maximum likelihood; Replicate; Statistics; Linear model; Econometrics; Estimator; Mixed model; Variance (accounting); Random effects model; Covariate; Mathematics; Range (aeronautics); Maximum likelihood; Economics; Engineering","score_opus":0.70756735418934,"score_gpt":0.6395058819187417,"score_spread":0.06806147227059833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192068715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95315504,0.0015991544,0.021581179,0.0122245345,0.0066169705,0.004333521,0.000040840925,0.00004499992,0.00040373695],"genre_scores_gemma":[0.8942461,0.00009914264,0.10285795,0.0016504583,0.0009177555,0.000116131574,9.793995e-7,0.00004074814,0.00007071629],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9860691,0.0076618274,0.0018919408,0.0004929891,0.0032963438,0.0005878384],"domain_scores_gemma":[0.958147,0.038739394,0.0013212125,0.00042610778,0.00095924945,0.00040706855],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03665792,0.00033137787,0.0010558695,0.00011264777,0.00028389008,0.0001492087,0.0010805158,0.00011952438,0.00036969082],"category_scores_gemma":[0.05165354,0.00019724347,0.00064814644,0.0005437935,0.0008594193,0.0006141149,0.0002004696,0.0006364672,0.0000015964727],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026506924,0.0031003638,0.0031840722,0.0016708452,0.0010248973,0.000042302523,0.0011860788,0.0000980442,0.8161901,0.031275027,0.004276543,0.135301],"study_design_scores_gemma":[0.018569333,0.00048821405,0.00061006844,0.00039280448,0.0028235668,0.000034081047,0.00011977128,0.010356576,0.78812367,0.17317425,0.005032937,0.00027472817],"about_ca_topic_score_codex":0.0000030190224,"about_ca_topic_score_gemma":0.0000051879574,"teacher_disagreement_score":0.14189921,"about_ca_system_score_codex":0.00017987884,"about_ca_system_score_gemma":0.0008358516,"threshold_uncertainty_score":0.9919634},"labels":[],"label_agreement":null},{"id":"W3192414848","doi":"10.1097/mcc.0000000000000854","title":"How cutting-edge trial design can assess outcomes","year":2021,"lang":"en","type":"review","venue":"Current Opinion in Critical Care","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto; University Health Network","funders":"","keywords":"Generalizability theory; Medicine; Frequentist inference; Sample size determination; Randomized controlled trial; Research design; Statistical power; Randomization; Clinical study design; Medical physics; Gold standard (test); Psychological intervention; Clinical trial; Risk analysis (engineering); Bayesian probability; Computer science; Statistics; Artificial intelligence; Bayesian inference; Surgery; Nursing","score_opus":0.9460330292868914,"score_gpt":0.7274511415560364,"score_spread":0.21858188773085496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192414848","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.136708e-8,0.87302715,0.08519137,0.00044871587,0.037350517,0.002853651,0.0008871177,0.00012977229,0.000111625246],"genre_scores_gemma":[0.0000023668188,0.79685235,0.19840617,0.000017524673,0.0032618465,0.0011224301,0.00013739674,0.00016561999,0.000034316643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98463726,0.008792728,0.0029203158,0.0015058795,0.001154126,0.0009896839],"domain_scores_gemma":[0.8074755,0.1897875,0.0004809127,0.0012035357,0.0005850762,0.00046744186],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035563253,0.0010540693,0.0066562286,0.00030348208,0.0001301842,0.0004949711,0.00097255077,0.0011527508,0.00022140561],"category_scores_gemma":[0.45135745,0.0008514442,0.0017040498,0.0007131774,0.00038808852,0.000093638046,0.00053772604,0.0025730266,0.000025220967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010331709,0.0004144895,0.0000047347785,0.0815408,0.000069892514,0.000021749676,0.000054516957,5.993177e-8,4.1811354e-9,0.14894053,0.004706089,0.7641438],"study_design_scores_gemma":[0.006301968,0.00032338058,6.505936e-7,0.05282986,0.001063301,0.000010736255,0.00025063736,0.0000051604884,6.160764e-7,0.1366858,0.80143714,0.0010907353],"about_ca_topic_score_codex":0.0000020402242,"about_ca_topic_score_gemma":9.405917e-7,"teacher_disagreement_score":0.79673105,"about_ca_system_score_codex":0.00055652484,"about_ca_system_score_gemma":0.001128512,"threshold_uncertainty_score":0.9997281},"labels":[],"label_agreement":null},{"id":"W3193585774","doi":"10.1016/j.jclinepi.2021.08.010","title":"The fragility index can be used for sample size calculations in clinical trials","year":2021,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Institute of Allergy and Infectious Diseases; Cornell University; Patient-Centered Outcomes Research Institute","keywords":"Index (typography); Sample size determination; Fragility; Statistics; Sample (material); Clinical trial; Medicine; Mathematics; Computer science; Internal medicine; Physics; Thermodynamics","score_opus":0.9328040477738299,"score_gpt":0.7552170319925443,"score_spread":0.17758701578128555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193585774","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.116906494,0.0002977865,0.7591231,0.111432925,0.010476242,0.0012167139,0.00037291733,0.000030025865,0.00014379181],"genre_scores_gemma":[0.08150492,0.0008310563,0.90582824,0.007318762,0.0042879716,0.000044168744,0.0000027894232,0.00004363462,0.00013846654],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76783985,0.18225761,0.047243327,0.0009232272,0.0006796693,0.00105632],"domain_scores_gemma":[0.0061995867,0.9798992,0.011011907,0.001005443,0.00121956,0.0006642494],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.546707,0.00030046082,0.009328758,0.00006358137,0.00018057083,0.000030926676,0.0007604477,0.0013240478,0.0002997264],"category_scores_gemma":[0.9979534,0.00018184571,0.0038673088,0.0003399364,0.0010861938,0.00006222762,0.00020084615,0.0029768178,0.0000029684666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027931205,0.0015839112,0.584811,0.000093997805,0.00094922545,0.000058928,0.0000508483,0.00009655962,0.000008462099,0.307454,0.022023443,0.08007653],"study_design_scores_gemma":[0.0049660513,0.0005258479,0.16072714,0.00007656523,0.000263361,0.000016351698,0.00006663128,0.0015146952,0.000008308883,0.8155723,0.016115233,0.00014749172],"about_ca_topic_score_codex":0.000042171407,"about_ca_topic_score_gemma":0.0005776126,"teacher_disagreement_score":0.79764163,"about_ca_system_score_codex":0.00008378665,"about_ca_system_score_gemma":0.0013938872,"threshold_uncertainty_score":0.99997246},"labels":[],"label_agreement":null},{"id":"W3194892752","doi":"10.21037/atm-21-2626","title":"Surgical clinical trials with non-inferiority design: a cross-sectional bibliometric analysis","year":2021,"lang":"en","type":"article","venue":"Annals of Translational Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Medicine; Cross-sectional study; Clinical trial; MEDLINE; Internal medicine; Pathology; Biology","score_opus":0.8995151469040102,"score_gpt":0.7085750270952446,"score_spread":0.19094011980876568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194892752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09444287,0.00066744327,0.89682347,0.00476853,0.0006115445,0.0005965951,0.0002777197,0.00005742147,0.0017544061],"genre_scores_gemma":[0.49614978,0.0004937112,0.5013371,0.0003539293,0.0013828867,0.000032598986,0.00004815383,0.00003110478,0.00017074632],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98697394,0.005195407,0.0047565494,0.0007249341,0.0019712143,0.0003779474],"domain_scores_gemma":[0.71764934,0.27760795,0.0012111667,0.0005974623,0.0024874297,0.0004466567],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051731322,0.00030431792,0.0030214624,0.008688214,0.00010374476,0.00003859816,0.00029141098,0.00038939647,0.0044934736],"category_scores_gemma":[0.19761601,0.00020879235,0.0010209541,0.052335504,0.0008556644,0.00013229281,0.000033841152,0.0005341893,0.0000108346585],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006442068,0.002052208,0.8857029,0.00036321097,0.010216908,0.0003679917,0.00009747082,0.0006525069,0.00016897108,0.055684038,0.002818001,0.03543373],"study_design_scores_gemma":[0.0046872683,0.0007219574,0.67124116,0.000103291975,0.0014982927,0.000028565757,0.000008251525,0.0010990811,0.000573175,0.3192825,0.00052993855,0.00022653773],"about_ca_topic_score_codex":0.000018191324,"about_ca_topic_score_gemma":0.000007953029,"teacher_disagreement_score":0.40170693,"about_ca_system_score_codex":0.000009831334,"about_ca_system_score_gemma":0.00042468487,"threshold_uncertainty_score":0.99641657},"labels":[],"label_agreement":null},{"id":"W3196269529","doi":"10.1016/j.jclinepi.2021.08.018","title":"Response to Weinfurt and Cappelleri on “Patient reported outcome measures in clinical trials should be initially analyzed as continuous outcomes for statistical significance and responder analyses should be reserved as secondary analyses”","year":2021,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; University of Manitoba; McMaster University; Population Health Research Institute","funders":"","keywords":"Clinical trial; Randomization; Outcome (game theory); Medicine; Statistical significance; Statistical power; Baseline (sea); Patient-reported outcome; Clinical significance; Physical therapy; Statistics; Internal medicine; Quality of life (healthcare); Mathematics","score_opus":0.9500332984706102,"score_gpt":0.7334671665296986,"score_spread":0.21656613194091168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196269529","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12932205,0.0007261349,0.051812895,0.80696446,0.004482487,0.0042899963,0.0019502395,0.00008009175,0.00037165475],"genre_scores_gemma":[0.009716562,0.0009134417,0.40375346,0.5810184,0.0034067999,0.00016643996,0.00006300638,0.00024833152,0.00071357685],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.68330884,0.244938,0.0635458,0.0035648413,0.002630694,0.0020118116],"domain_scores_gemma":[0.100060135,0.8705854,0.02302443,0.001794613,0.0027077915,0.0018276374],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.40102667,0.001668679,0.03377798,0.001515746,0.00019747161,0.00017618416,0.0012747592,0.00659106,0.0007394861],"category_scores_gemma":[0.9881882,0.0011922269,0.0046137827,0.00087064103,0.0021105257,0.0001680435,0.00067273015,0.0136718815,0.000008830328],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15362808,0.0019122364,0.025627162,0.0007655681,0.011867286,0.022105597,0.00018443888,0.00009158942,0.0002520032,0.0033800658,0.76212895,0.018056992],"study_design_scores_gemma":[0.032345884,0.034005903,0.11869044,0.0021851002,0.012027589,0.0010873734,0.00059617945,0.00037100352,0.00010965981,0.5885821,0.20678325,0.0032155016],"about_ca_topic_score_codex":0.00023088517,"about_ca_topic_score_gemma":0.00009361682,"teacher_disagreement_score":0.62564737,"about_ca_system_score_codex":0.0002501601,"about_ca_system_score_gemma":0.0027782298,"threshold_uncertainty_score":0.999606},"labels":[],"label_agreement":null},{"id":"W3196393057","doi":"10.1016/j.ejps.2021.105987","title":"The Global Bioequivalence Harmonisation Initiative (GBHI): Report of EUFEPS/AAPS fourth conference","year":2021,"lang":"en","type":"review","venue":"European Journal of Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"","keywords":"Bioequivalence; Political science; Pharmaceutical industry; Engineering ethics; Management science; Library science; Medicine; Computer science; Pharmacology; Engineering; Bioavailability","score_opus":0.8902116010456285,"score_gpt":0.6706597382928954,"score_spread":0.21955186275273308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196393057","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014013177,0.91413873,0.06581821,0.0008747997,0.0026579814,0.0005208402,0.00011682868,0.000021843553,0.01583675],"genre_scores_gemma":[0.00012733389,0.8219491,0.17720982,0.00007087464,0.00056320947,0.0000022652184,8.497111e-7,0.00002419027,0.00005233931],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9799718,0.012681698,0.0044720317,0.0005326421,0.0018160072,0.0005257729],"domain_scores_gemma":[0.9478037,0.045127466,0.005236558,0.00043366873,0.0009776712,0.00042093487],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03535551,0.0004304797,0.0022864456,0.0000909398,0.0003048803,0.00027631666,0.0020453807,0.00010742583,0.00029268835],"category_scores_gemma":[0.13109328,0.00023667705,0.00091858185,0.0010848659,0.0029145388,0.00019047054,0.0004918472,0.0011053279,0.000026972017],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023504426,0.0001401901,0.000012069922,0.0014958433,0.00027229378,0.0013076618,0.000049258088,7.4219685e-7,0.0000023274426,0.064331494,0.0015623383,0.9308023],"study_design_scores_gemma":[0.00052314304,0.00057350425,0.000016617143,0.013415869,0.0021182483,0.00208307,0.00016913743,0.000057887595,0.00005409062,0.12196172,0.8585924,0.000434315],"about_ca_topic_score_codex":7.3700187e-7,"about_ca_topic_score_gemma":3.7664793e-7,"teacher_disagreement_score":0.93036795,"about_ca_system_score_codex":0.00014184945,"about_ca_system_score_gemma":0.0014116751,"threshold_uncertainty_score":0.99979895},"labels":[],"label_agreement":null},{"id":"W3197540963","doi":"10.1212/wnl.94.15_supplement.2868","title":"Quetiapine is Not Tolerable to People with MS in Doses Potentially Required to Enhance Myelin Repair (2868)","year":2020,"lang":"en","type":"article","venue":"Neurology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Quetiapine; Medicine; Psychiatry; Schizophrenia (object-oriented programming)","score_opus":0.24267221957399535,"score_gpt":0.477174994915734,"score_spread":0.23450277534173866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197540963","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6848058,0.000016744836,0.20206629,0.10854619,0.0005720805,0.001547049,0.00006379288,0.00040463993,0.0019773974],"genre_scores_gemma":[0.2610135,0.00001125733,0.6665664,0.07166558,0.00038947028,0.00012384467,9.653228e-7,0.000064703374,0.00016428054],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965124,0.0008120083,0.0009295406,0.0008932188,0.00033225433,0.0005205859],"domain_scores_gemma":[0.9892696,0.009483211,0.0001562846,0.00060537504,0.00012372951,0.00036179836],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009818379,0.0002451637,0.0009107271,0.00008487214,0.000043819564,0.000022724089,0.00039735297,0.00020759625,0.0006890453],"category_scores_gemma":[0.04411143,0.0002146852,0.0000969499,0.0006027563,0.00006598967,0.000045749734,0.00025382332,0.00043411256,0.00033428465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15136026,0.0050195414,0.02672887,0.0031669368,0.0010097292,0.0059620086,0.030129397,0.0039759735,0.21062,0.16643633,0.27692798,0.118662976],"study_design_scores_gemma":[0.011214881,0.059716962,0.04890235,0.00041410534,0.00056532316,0.0001504499,0.00009698355,0.0070740036,0.11598781,0.6519879,0.10035462,0.003534598],"about_ca_topic_score_codex":0.00018072284,"about_ca_topic_score_gemma":0.0005761133,"teacher_disagreement_score":0.4855516,"about_ca_system_score_codex":0.000015699583,"about_ca_system_score_gemma":0.000072356255,"threshold_uncertainty_score":0.96394044},"labels":[],"label_agreement":null},{"id":"W3197690460","doi":"10.1136/bmj.n1959","title":"Regulatory and clinical consequences of negative confirmatory trials of accelerated approval cancer drugs: retrospective observational study","year":2021,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Arnold Ventures; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Medicine; Clinical trial; Clinical endpoint; Observational study; Food and drug administration; Clinical research; Cancer drugs; Institutional review board; Bevacizumab; Cancer; Drug approval; Drug; Internal medicine; Surgery; Pharmacology","score_opus":0.8431418914078215,"score_gpt":0.6564634035258948,"score_spread":0.18667848788192665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197690460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941196,0.00014205005,0.0010047349,0.00064944196,0.00076814194,0.0017049403,0.0005143728,0.000029719557,0.001066988],"genre_scores_gemma":[0.7712432,0.000056838908,0.22798577,0.00010971092,0.00032132326,0.00010200891,0.000002419758,0.000019260036,0.00015942931],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886498,0.0063545182,0.003753952,0.00044705675,0.000635684,0.000158981],"domain_scores_gemma":[0.88931465,0.10629947,0.0024123366,0.00043062062,0.0014306706,0.00011226228],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01935026,0.00017457828,0.002011538,0.000045107427,0.000046323003,0.000016890172,0.00016087042,0.00019436383,0.00059962645],"category_scores_gemma":[0.31495368,0.00014346025,0.00022654694,0.00029129375,0.00105977,0.00006857007,0.0001221265,0.0002796378,0.0000011323625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034036308,0.0049300753,0.5457532,0.00093312236,0.005964451,0.000088792316,0.004643889,0.00000739107,0.009542931,0.3935361,0.017970659,0.0132257985],"study_design_scores_gemma":[0.004586957,0.00040579683,0.31810516,0.00025195398,0.0005342519,0.0000032124203,0.0028527256,0.000070322305,0.023664603,0.649281,0.000031881427,0.00021210656],"about_ca_topic_score_codex":0.000059751295,"about_ca_topic_score_gemma":0.000021940179,"teacher_disagreement_score":0.29560342,"about_ca_system_score_codex":0.000046333244,"about_ca_system_score_gemma":0.00086701545,"threshold_uncertainty_score":0.69081676},"labels":[],"label_agreement":null},{"id":"W3198867954","doi":"10.15626/mp.2020.2506","title":"What to make of equivalence testing with a post-specified margin?","year":2021,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Margin (machine learning); Equivalence (formal languages); Frequentist inference; Post hoc; Statistical hypothesis testing; Computer science; Econometrics; Mathematics; Statistics; Machine learning; Artificial intelligence; Bayesian probability; Medicine; Bayesian inference","score_opus":0.8258386333211938,"score_gpt":0.6156700248907838,"score_spread":0.21016860843040996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198867954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09944557,0.0013887373,0.84288526,0.021668922,0.004187721,0.0016496319,0.00022473492,0.0002600442,0.028289411],"genre_scores_gemma":[0.012488746,0.000050853498,0.9814989,0.0047565624,0.00016582172,0.00008772543,0.000001480232,0.00004990491,0.00090001913],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596673,0.001346258,0.0010957182,0.000740532,0.00040719786,0.0004435752],"domain_scores_gemma":[0.962277,0.035305165,0.00035598417,0.001203404,0.00067236705,0.00018609011],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003040569,0.00025817228,0.001420514,0.00009937153,0.000042168227,0.00004431875,0.00042107547,0.00018257693,0.0022243904],"category_scores_gemma":[0.08739571,0.00019023131,0.00020505025,0.0007113859,0.00021781893,0.00006997745,0.00019644374,0.00032229995,0.00010080415],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038513313,0.003917559,0.0023804868,0.0011941895,0.0074361516,0.0023722912,0.0015742136,0.000019569445,0.09283659,0.33029857,0.012714991,0.54140407],"study_design_scores_gemma":[0.002188158,0.0015713755,0.011870046,0.00024967632,0.0022157212,0.00025877106,0.00026842186,0.000014153516,0.0089241695,0.963473,0.008414783,0.00055169594],"about_ca_topic_score_codex":0.0000036473375,"about_ca_topic_score_gemma":0.000016717337,"teacher_disagreement_score":0.6331744,"about_ca_system_score_codex":0.000014530268,"about_ca_system_score_gemma":0.00006747173,"threshold_uncertainty_score":0.9986877},"labels":[],"label_agreement":null},{"id":"W3203927528","doi":"10.22541/au.162130250.08942848/v1","title":"Using Bayesian Modeling to Optimize Antipsychotic Dosage in Clinical Practice","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Risperidone; Olanzapine; Confidence interval; Schizophrenia (object-oriented programming); Antipsychotic; Medicine; Paliperidone Palmitate; Mean squared error; Pharmacology; Mathematics; Statistics; Psychiatry","score_opus":0.854550838656159,"score_gpt":0.6956619534737186,"score_spread":0.15888888518244038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203927528","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012915772,0.000070465634,0.9712465,0.0012694265,0.0046445923,0.0015455416,0.000029539355,0.00015794422,0.008120254],"genre_scores_gemma":[0.018531183,0.00015099141,0.97837013,0.0017851358,0.0008494424,0.000053058557,0.0000037528478,0.00013984733,0.0001164307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9858878,0.005505939,0.0051657055,0.00185584,0.00087626174,0.00070841453],"domain_scores_gemma":[0.8907393,0.105381,0.0008074767,0.0020500105,0.0005046088,0.0005175986],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.02139473,0.00059321534,0.0026319097,0.00024344322,0.000060816164,0.0003352522,0.0008380327,0.0013584155,0.0009042358],"category_scores_gemma":[0.47930875,0.00057052675,0.0006254342,0.00048620644,0.00008995808,0.00013718256,0.0018697581,0.0031896995,0.00003733119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054015964,0.014197864,0.0012247793,0.0058473097,0.002981345,0.0054647983,0.0027099478,0.66058505,0.00022816987,0.19277434,0.004284227,0.10430054],"study_design_scores_gemma":[0.0009098941,0.00005320689,0.000019355357,0.0012777051,0.00033479847,0.000016962933,0.0003288671,0.5363825,0.000015833639,0.46007925,0.000028386068,0.0005532228],"about_ca_topic_score_codex":0.00016611561,"about_ca_topic_score_gemma":0.000037822723,"teacher_disagreement_score":0.45791402,"about_ca_system_score_codex":0.0001961995,"about_ca_system_score_gemma":0.000532149,"threshold_uncertainty_score":0.999938},"labels":[],"label_agreement":null},{"id":"W3204160225","doi":"10.1007/s00266-021-02617-5","title":"Invited Response on: “Statistical P values have No Guiding Significance in Clinical Trials of Plastic Surgery with Small Sample Sizes”","year":2021,"lang":"en","type":"letter","venue":"Aesthetic Plastic Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Plastic surgery; Medicine; Otorhinolaryngology; Sample size determination; Sample (material); Statistical significance; Head and neck surgery; Statistical analysis; Medical physics; Surgery; Statistics; Internal medicine; Mathematics","score_opus":0.6705682810529509,"score_gpt":0.5065888963247374,"score_spread":0.1639793847282135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204160225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22129737,0.0006089845,0.56542844,0.13416687,0.05344463,0.007002626,0.016716871,0.0010535354,0.00028065394],"genre_scores_gemma":[0.017942019,0.00085182063,0.8021903,0.16217898,0.011435836,0.0016691915,0.0013154766,0.0019876142,0.00042873426],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9244651,0.05383106,0.014576826,0.002691255,0.0025055967,0.001930125],"domain_scores_gemma":[0.07969487,0.9116422,0.0052041463,0.002083794,0.00084207003,0.0005329255],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.08484481,0.001620983,0.012644295,0.0013394312,0.0001347601,0.00017400054,0.00081401656,0.002758312,0.0010440877],"category_scores_gemma":[0.95901287,0.0013319701,0.0022783119,0.0011098557,0.0018866926,0.00007605951,0.0002697726,0.0039583477,0.000095130956],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015897108,0.0013287523,0.006516403,0.0018613334,0.0007158994,0.009290659,0.000059826663,0.000047862675,0.000027274662,0.0004859662,0.956157,0.00761188],"study_design_scores_gemma":[0.021277716,0.009300113,0.041595142,0.108679056,0.014231065,0.001279501,0.0005732552,0.005394878,0.0010476502,0.52202183,0.25601,0.018589796],"about_ca_topic_score_codex":0.0000832082,"about_ca_topic_score_gemma":0.000019005607,"teacher_disagreement_score":0.8741681,"about_ca_system_score_codex":0.0003197204,"about_ca_system_score_gemma":0.0019852805,"threshold_uncertainty_score":0.9998691},"labels":[],"label_agreement":null},{"id":"W3204184651","doi":"10.1016/s1470-2045(21)00344-2","title":"Guidelines for cellular and molecular pathology content in clinical trial protocols: the SPIRIT-Path extension","year":2021,"lang":"en","type":"review","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Women's College Hospital","funders":"Medical Research Council; Health and Care Research Wales; Blood Cancer UK; Prostate Cancer UK; Public Health Agency; Chief Scientist Office; Breast Cancer Now; Department of Health and Social Care; Cancer Research UK; Tenovus; National Institute for Health and Care Research; National Cancer Research Institute","keywords":"Path (computing); Extension (predicate logic); Clinical trial; Pathology; Content (measure theory); Computer science; Medicine; Mathematics; Computer network; Mathematical analysis; Programming language","score_opus":0.9511569958424636,"score_gpt":0.7335990082767821,"score_spread":0.21755798756568145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204184651","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039948052,0.8975975,0.024104621,0.008137752,0.0023295681,0.06735722,0.0001661122,0.000057191566,0.00021007533],"genre_scores_gemma":[1.9578953e-7,0.6407349,0.32576507,0.0025816113,0.003194983,0.027552713,0.000011217425,0.000070965754,0.00008833606],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.973631,0.019419184,0.0050186,0.000989573,0.00029534855,0.0006462996],"domain_scores_gemma":[0.847387,0.14864425,0.0017931508,0.0015844172,0.00048754213,0.00010364299],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04518654,0.0005106911,0.00773464,0.0000561438,0.000102890794,0.0000463658,0.0010057382,0.0013307518,0.00005535458],"category_scores_gemma":[0.34640202,0.00024592382,0.0009883696,0.00020124044,0.0007652511,0.000012860386,0.00059666706,0.0015712328,0.00001123781],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025756268,0.0003766016,0.0000010063081,0.0036239678,0.00016812998,0.00031913302,0.000020814787,9.803007e-8,0.000002211944,0.07198895,0.016542101,0.90438133],"study_design_scores_gemma":[0.015290791,0.0013379903,0.0000010833718,0.0032058952,0.00087153044,0.000072118346,0.00002026476,0.000020691476,0.0000013417489,0.23692311,0.74204,0.00021516896],"about_ca_topic_score_codex":0.000005723622,"about_ca_topic_score_gemma":0.000014519596,"teacher_disagreement_score":0.90416616,"about_ca_system_score_codex":0.000099659075,"about_ca_system_score_gemma":0.00062505086,"threshold_uncertainty_score":0.9999993},"labels":[],"label_agreement":null},{"id":"W3204448385","doi":"10.1002/bimj.202000148","title":"Simultaneous confidence tubes for comparing several multivariate linear regression models","year":2021,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian multivariate linear regression; Multivariate statistics; Linear regression; Univariate; Statistics; Confidence interval; Confidence and prediction bands; Linear model; Confidence region; Mathematics; Proper linear model; Population; Regression analysis; Confidence distribution; Simple linear regression; Inference; Econometrics; Computer science; Artificial intelligence","score_opus":0.6564104560714082,"score_gpt":0.5789961873239685,"score_spread":0.07741426874743973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204448385","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010900713,0.00027489613,0.9864485,0.0003967746,0.0013067728,0.00026233846,0.000056486486,0.00006965341,0.00028381808],"genre_scores_gemma":[0.23723827,0.0000791044,0.76143646,0.00014209938,0.0008321572,0.0000074949558,0.0000018205561,0.000034300203,0.00022831777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99611276,0.0008005701,0.001354273,0.0004324326,0.0007635826,0.0005363602],"domain_scores_gemma":[0.89302653,0.10475187,0.00034167207,0.00036755312,0.0009866053,0.00052575406],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002980615,0.0002541198,0.0009492531,0.00036983896,0.00027890105,0.000179973,0.00038893797,0.00027448605,0.00018655999],"category_scores_gemma":[0.26619473,0.00018848524,0.0003672943,0.0013552214,0.00011940158,0.0001425192,0.0001974185,0.0006480542,0.000018333663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052199718,0.0060900375,0.001078354,0.0012987524,0.0018832703,0.0049035847,0.0008943839,0.009782978,0.0419727,0.4582854,0.021799415,0.44679114],"study_design_scores_gemma":[0.001971371,0.00017664269,0.00004113834,0.00021407957,0.00010054448,0.00027529008,0.00003694567,0.3068582,0.0042780414,0.6852069,0.0006019756,0.00023891071],"about_ca_topic_score_codex":0.0000042588345,"about_ca_topic_score_gemma":5.4136035e-7,"teacher_disagreement_score":0.44655225,"about_ca_system_score_codex":0.00012936509,"about_ca_system_score_gemma":0.00016474712,"threshold_uncertainty_score":0.7686205},"labels":[],"label_agreement":null},{"id":"W3205319133","doi":"10.1186/s13063-021-05686-8","title":"Confidence interval of risk difference by different statistical methods and its impact on the study conclusion in antibiotic non-inferiority trials","year":2021,"lang":"en","type":"review","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Toronto; McMaster University; University Health Network; Queen's University","funders":"","keywords":"Medicine; Confidence interval; Interquartile range; Relative risk; Statistical significance; Statistics; Internal medicine; Mathematics","score_opus":0.7716989371751232,"score_gpt":0.707918448498792,"score_spread":0.06378048867633113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205319133","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005581301,0.8301266,0.13370928,0.000040878505,0.0020380772,0.019252772,0.009146133,0.0000541814,0.000050797084],"genre_scores_gemma":[0.004537111,0.9386559,0.056029283,0.000019003359,0.0003462109,0.00024913086,0.000026384458,0.00010718531,0.000029777793],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81104803,0.17425156,0.011494881,0.0014460746,0.00110513,0.0006543273],"domain_scores_gemma":[0.21714903,0.77467644,0.006286897,0.0013446085,0.00023799753,0.00030500395],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14089823,0.001226685,0.02503285,0.00024621416,0.00012778991,0.00017954006,0.0009844291,0.0008141173,0.0009084263],"category_scores_gemma":[0.83611524,0.00059044885,0.0016304334,0.0005255495,0.00037445332,0.000039170674,0.0008780382,0.0019411317,0.000010683339],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007953705,0.002289808,0.00006351925,0.007022716,0.0017467792,0.00004562536,0.00037863865,1.1876298e-7,0.00008074835,0.026891489,0.00061913155,0.9600661],"study_design_scores_gemma":[0.016868826,0.007845436,0.0022315946,0.09942271,0.03622891,0.00003091988,0.0007041316,0.00034600095,0.001135479,0.82932585,0.0025748033,0.0032853093],"about_ca_topic_score_codex":0.000121162564,"about_ca_topic_score_gemma":0.000009401427,"teacher_disagreement_score":0.95678073,"about_ca_system_score_codex":0.00023589973,"about_ca_system_score_gemma":0.00049162155,"threshold_uncertainty_score":0.9996547},"labels":[],"label_agreement":null},{"id":"W3205679927","doi":"10.1128/aac.01627-21","title":"Secondary Analysis of a Systematic Review: Are Antifungal Noninferiority Trials at Risk of Eroding Effectiveness Because of Biocreep?","year":2022,"lang":"en","type":"article","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Queen's University; McMaster University Medical Centre","funders":"","keywords":"Randomized controlled trial; Antifungal; Meta-analysis; Medicine; Sample size determination; Risk analysis (engineering); Internal medicine; Statistics; Mathematics","score_opus":0.4895739377797945,"score_gpt":0.50269071982329,"score_spread":0.013116782043495534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205679927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94985765,0.009586093,0.014242854,0.000044609264,0.00085248647,0.013945348,0.01106342,0.00007298779,0.0003345577],"genre_scores_gemma":[0.9687787,0.00079532486,0.026472658,0.000028190483,0.000040307106,0.0037820286,0.000013648321,0.000041712457,0.000047403733],"study_design_codex":"systematic_review","study_design_gemma":"observational","domain_scores_codex":[0.97175276,0.022157969,0.004402479,0.0004348625,0.0009354389,0.0003164885],"domain_scores_gemma":[0.8332081,0.15879029,0.0064476654,0.0011014942,0.00033339474,0.000119052216],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07273319,0.0002449659,0.0072493325,0.00040151822,0.00009637011,0.0000077030445,0.0005044673,0.00010362144,0.00045396175],"category_scores_gemma":[0.45016375,0.00019828092,0.0014115156,0.0018060425,0.00018599941,0.000045025943,0.00049247826,0.00033657838,8.356141e-7],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014062297,0.0012524704,0.054805227,0.91138524,0.022049319,0.000019418176,0.00021213022,0.00006164884,0.00082762825,0.0044570263,0.00040765855,0.003116012],"study_design_scores_gemma":[0.00770221,0.0005674861,0.6136175,0.039985675,0.20063001,0.000011999033,0.0003626696,0.00052215747,0.03684194,0.098592594,0.00001739226,0.0011483947],"about_ca_topic_score_codex":0.00004428115,"about_ca_topic_score_gemma":0.000010602216,"teacher_disagreement_score":0.8713996,"about_ca_system_score_codex":0.00016705244,"about_ca_system_score_gemma":0.000054755867,"threshold_uncertainty_score":0.95481634},"labels":[],"label_agreement":null},{"id":"W3206821549","doi":"10.1007/978-3-030-72437-5_8","title":"Controlling the False Discovery Rate of Grouped Hypotheses","year":2021,"lang":"en","type":"book-chapter","venue":"Emerging topics in statistics and biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"False discovery rate; Ranking (information retrieval); Multiple comparisons problem; Statistical hypothesis testing; Computer science; Statistical power; Data mining; Statistics; Control (management); Econometrics; Machine learning; Mathematics; Artificial intelligence; Biology","score_opus":0.3198293956828958,"score_gpt":0.4647653564048828,"score_spread":0.144935960721987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206821549","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002969377,0.002376108,0.94691116,0.00086753065,0.0025888484,0.0013269298,0.016845096,0.000051008767,0.028736409],"genre_scores_gemma":[0.0014610931,0.006034192,0.9238147,0.0003691398,0.0007154078,0.000024649738,0.00013506712,0.00016892601,0.06727683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957463,0.0004728721,0.0021840876,0.0006536357,0.0005038629,0.0004392491],"domain_scores_gemma":[0.9387154,0.05906105,0.0010512744,0.00070964446,0.00034949108,0.00011313379],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024834317,0.00058158446,0.0016930111,0.00015281378,0.00014463517,0.00015283588,0.00038685702,0.0004158823,0.00033864222],"category_scores_gemma":[0.042801872,0.00044703204,0.00015181565,0.000099718985,0.0008237412,0.000047910708,0.0003255546,0.00091812667,0.0000029114403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006511747,0.000053631447,0.00006912675,0.00061644573,0.00019730884,0.0001753335,0.00014709064,0.0000052390874,0.000019111338,0.97889185,0.0033600377,0.016399728],"study_design_scores_gemma":[0.0008128375,0.00012228968,0.00018157676,0.0007392112,0.0004287671,0.0000071364107,0.00008119085,0.000915318,0.00004043475,0.98056257,0.01562149,0.00048716122],"about_ca_topic_score_codex":0.00004936008,"about_ca_topic_score_gemma":0.00014874528,"teacher_disagreement_score":0.05858818,"about_ca_system_score_codex":0.00006490625,"about_ca_system_score_gemma":0.00016826308,"threshold_uncertainty_score":0.9997981},"labels":[],"label_agreement":null},{"id":"W3207990795","doi":"10.1016/j.euf.2021.10.008","title":"Evidence-based Urology: Surrogate Endpoints – Con","year":2021,"lang":"en","type":"article","venue":"European Urology Focus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Toronto; Ottawa Hospital; University Health Network","funders":"Sanofi","keywords":"Surrogate endpoint; Medicine; Clinical endpoint; Endpoint Determination; Clinical trial; Intensive care medicine; Internal medicine; Urology","score_opus":0.5554115302791838,"score_gpt":0.4974384165797888,"score_spread":0.05797311369939495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207990795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14848655,0.0058360454,0.5811664,0.04918795,0.009460511,0.0016119693,0.000269437,0.0019305364,0.2020506],"genre_scores_gemma":[0.7046713,0.0001104546,0.28679982,0.00670294,0.0006894547,0.000016919632,0.0000040571053,0.00013573229,0.00086931355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98609173,0.011128789,0.0010354369,0.00082708854,0.00030399987,0.000612973],"domain_scores_gemma":[0.92731494,0.070863254,0.00033304642,0.001014121,0.00023866468,0.00023595005],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0064716535,0.0003056557,0.00075801567,0.00008524036,0.00011916785,0.000041891843,0.0005161222,0.00020742329,0.0028930993],"category_scores_gemma":[0.20636435,0.00028328566,0.00024877387,0.00027182925,0.00051799824,0.00006919593,0.0003194837,0.00071057753,0.0018371748],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003888182,0.002454113,0.008667415,0.00042569547,0.0010669582,0.030684732,0.00053211255,0.00011921947,0.02036843,0.6015889,0.066188954,0.2640153],"study_design_scores_gemma":[0.0033686082,0.0011164328,0.006035176,0.000081857426,0.0005193335,0.0001820941,0.000015957645,0.00038321226,0.010604214,0.95222557,0.02485568,0.000611888],"about_ca_topic_score_codex":0.0000020965526,"about_ca_topic_score_gemma":0.0000067658784,"teacher_disagreement_score":0.55618477,"about_ca_system_score_codex":0.000028121642,"about_ca_system_score_gemma":0.00014397931,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W3208070779","doi":"10.1007/s43441-021-00344-2","title":"Increased Patient’s Risk Associated with the Canadian Bioequivalence Guidance Due to Outlier Removal","year":2021,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Confidence interval; Outlier; Guideline; Medical prescription; Pharmacy; Medicine; Affect (linguistics); Actuarial science; Relative risk; Statistics; Econometrics; Risk analysis (engineering); Psychology; Family medicine; Business; Mathematics; Internal medicine; Pharmacology","score_opus":0.259008446994859,"score_gpt":0.44041596730977783,"score_spread":0.18140752031491886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208070779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95460707,0.00004246527,0.036877036,0.003908191,0.00061720784,0.00074884895,0.00009083143,0.000117809366,0.0029905324],"genre_scores_gemma":[0.8665138,9.373838e-7,0.12758662,0.0054410216,0.0000731673,0.000035311372,0.0000021890037,0.000028061595,0.0003189066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99551356,0.0009855503,0.0007950933,0.00066446,0.0013932586,0.00064806343],"domain_scores_gemma":[0.98952675,0.00610883,0.0005730251,0.0011678749,0.0023762323,0.00024727936],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01048383,0.00023416895,0.00038369276,0.00028365236,0.0010584141,0.00021400972,0.0007419788,0.00012785807,0.00017763571],"category_scores_gemma":[0.05190128,0.00016178761,0.00004602619,0.006634684,0.0013362026,0.00019380836,0.00011442122,0.0003796792,0.00003702129],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013785093,0.00022220875,0.0050531514,0.000025952546,0.00016207321,0.00013569095,0.0017538018,0.00007860049,0.02004329,0.85493225,0.0020455301,0.11540959],"study_design_scores_gemma":[0.0011124944,0.0003753364,0.23931944,0.00025528745,0.0001629005,0.0000787533,0.00048760333,0.0012053717,0.025927663,0.7241681,0.0060889916,0.0008180255],"about_ca_topic_score_codex":0.0012623686,"about_ca_topic_score_gemma":0.009551062,"teacher_disagreement_score":0.23426628,"about_ca_system_score_codex":0.00055953517,"about_ca_system_score_gemma":0.0024487989,"threshold_uncertainty_score":0.95608497},"labels":[],"label_agreement":null},{"id":"W3208418228","doi":"10.1016/j.euf.2021.10.001","title":"Evidence-based Urology: Subgroup Analysis in Randomized Controlled Trials","year":2021,"lang":"en","type":"review","venue":"European Urology Focus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Subgroup analysis; Medicine; Randomized controlled trial; MEDLINE; Clinical trial; Internal medicine; Meta-analysis","score_opus":0.6689512465479116,"score_gpt":0.5724885016657867,"score_spread":0.09646274488212492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208418228","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016293562,0.9005968,0.087377205,0.00053889246,0.0013441656,0.0063595576,0.00011578744,0.00018043364,0.0034855152],"genre_scores_gemma":[0.000052172218,0.9276841,0.06921757,0.0005890293,0.0009118491,0.00096505345,0.000034996705,0.00024168211,0.00030349538],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.6732046,0.3106944,0.012822297,0.0017541931,0.00062616146,0.00089836906],"domain_scores_gemma":[0.41682318,0.5754054,0.005668283,0.0016370319,0.00022325637,0.00024281794],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.23368855,0.0014656592,0.07433712,0.0020818182,0.00009799211,0.00013751302,0.001552672,0.0012730033,0.0033908137],"category_scores_gemma":[0.88935673,0.00093586714,0.018406754,0.0025558698,0.0009962987,0.000063080064,0.0004515979,0.0024848168,0.00041314165],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0715205,0.00076682464,0.000008437559,0.0035852715,0.036663823,0.0035607314,0.000043517262,0.0000285224,3.1001218e-7,0.04131284,0.0016008805,0.84090835],"study_design_scores_gemma":[0.36942583,0.00050440355,0.0000038660937,0.0058609466,0.32504064,0.000040240866,0.000003991296,0.00040029478,4.9838144e-7,0.12838528,0.1687427,0.0015913117],"about_ca_topic_score_codex":0.000011594109,"about_ca_topic_score_gemma":0.000019057088,"teacher_disagreement_score":0.839317,"about_ca_system_score_codex":0.00012912818,"about_ca_system_score_gemma":0.00065770024,"threshold_uncertainty_score":0.9998165},"labels":[],"label_agreement":null},{"id":"W3209165885","doi":"10.1016/j.ecosta.2021.10.015","title":"A Markov decision process for response adaptive designs","year":2021,"lang":"en","type":"article","venue":"Econometrics and Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Mathematical optimization; Markov chain; Markov process; Operator (biology); Process (computing); Partially observable Markov decision process; Mathematics; Markov model; Value (mathematics); Computer science; Statistics","score_opus":0.7140437471766378,"score_gpt":0.566349235593182,"score_spread":0.1476945115834558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209165885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008414102,0.0001688013,0.9871852,0.00010734804,0.00039335253,0.00041908093,0.0028509146,0.000027490558,0.00043373168],"genre_scores_gemma":[0.022553807,0.00012120648,0.9765137,0.00013391978,0.000096094875,0.00006910137,0.000008195159,0.00003824854,0.00046574473],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99787194,0.0003666872,0.00079438975,0.00047027488,0.00019559807,0.00030109714],"domain_scores_gemma":[0.82164353,0.17727417,0.00021180612,0.00025434536,0.00042939244,0.00018678921],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038805194,0.00018027764,0.0005861951,0.0002264616,0.00013917689,0.00010109484,0.0001342832,0.00014201974,0.000283566],"category_scores_gemma":[0.3365588,0.00017378635,0.00006903885,0.00061959855,0.000103115504,0.000053744894,0.000078421865,0.00015488538,0.000008613755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002552474,0.0003229445,0.00043154028,0.00027418957,0.00013519514,0.0000788084,0.00018161064,0.000008551521,0.00002849874,0.6997948,0.008746716,0.28744462],"study_design_scores_gemma":[0.001211991,0.00042829427,0.0012140089,0.000035955658,0.00008883172,0.000009904941,0.0001435681,0.007351267,0.00023803292,0.98752755,0.0015188967,0.00023169037],"about_ca_topic_score_codex":7.2459346e-7,"about_ca_topic_score_gemma":0.0000035441296,"teacher_disagreement_score":0.3326783,"about_ca_system_score_codex":0.00005850427,"about_ca_system_score_gemma":0.00019345035,"threshold_uncertainty_score":0.70868015},"labels":[],"label_agreement":null},{"id":"W3209678742","doi":"10.1001/jamanetworkopen.2021.31503","title":"Evaluation of Planned Subgroup Analysis in Protocols of Randomized Clinical Trials","year":2021,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Subgroup analysis; Randomized controlled trial; Medicine; Computer science; Internal medicine; Meta-analysis","score_opus":0.8170536911804726,"score_gpt":0.6931271877617244,"score_spread":0.12392650341874811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209678742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16046675,0.00071055884,0.5054648,0.0027648518,0.001969383,0.2841507,0.00047084832,0.00008506653,0.043917045],"genre_scores_gemma":[0.13482279,0.000060685634,0.85149163,0.000120116354,0.00059745496,0.012738406,0.000022680411,0.00003090555,0.00011530857],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6700749,0.305532,0.019482361,0.0011951156,0.0030728215,0.0006428014],"domain_scores_gemma":[0.54334426,0.45014325,0.0039123655,0.001024641,0.0014588408,0.00011668147],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5561007,0.00018619315,0.0071828137,0.00011802724,0.000025039515,0.000079257,0.0006729795,0.000393187,0.0020782952],"category_scores_gemma":[0.8264023,0.00014252079,0.0012420011,0.0016975866,0.00021060371,0.00010470356,0.00041563515,0.00035916863,0.000004526651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3727097,0.0048237415,0.07222284,0.0006455953,0.022500688,0.000041374875,0.000435893,0.005948616,0.0000853376,0.2579454,0.011055226,0.2515856],"study_design_scores_gemma":[0.15526001,0.00012222303,0.006024272,0.0005688068,0.006806568,3.6614858e-7,0.000041181993,0.030308707,0.0003051182,0.80039024,0.00003578072,0.00013672709],"about_ca_topic_score_codex":0.00003888179,"about_ca_topic_score_gemma":0.00013536053,"teacher_disagreement_score":0.5424448,"about_ca_system_score_codex":0.000046483015,"about_ca_system_score_gemma":0.00050955976,"threshold_uncertainty_score":0.99883395},"labels":[],"label_agreement":null},{"id":"W3211251719","doi":"10.1101/2021.10.31.21265690","title":"Estimating treatment effect for individuals with progressive multiple sclerosis using deep learning","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NeuroRx Research (Canada); Mila - Quebec Artificial Intelligence Institute; McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Medicine; Clinical trial; Multiple sclerosis; Leverage (statistics); Internal medicine; Oncology; Machine learning; Immunology; Computer science","score_opus":0.5159298482799332,"score_gpt":0.5238606871304021,"score_spread":0.007930838850468969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211251719","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55113745,0.00017231902,0.44551206,0.000022542263,0.0005369471,0.002385092,0.00006205189,0.00014868402,0.000022850902],"genre_scores_gemma":[0.1813734,0.000008716555,0.8163925,0.000013512043,0.0005148132,0.0014938082,0.00002820708,0.00015397802,0.000021089696],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942502,0.00226422,0.0011646817,0.0011428469,0.0005683105,0.0006097445],"domain_scores_gemma":[0.90925056,0.088312894,0.001238725,0.0007326718,0.000268665,0.00019649335],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004035766,0.00070628565,0.0020740188,0.00011395912,0.00029432727,0.00030122782,0.00036121995,0.00052378734,0.00008460587],"category_scores_gemma":[0.14783897,0.00049529853,0.0004680422,0.00019151322,0.00018287663,0.000051825078,0.0005103561,0.0007976241,0.000003312626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094185414,0.0017652065,0.5756641,0.011269592,0.006261416,0.00030652166,0.004341385,0.029684858,0.0020457301,0.00087102957,0.000022058164,0.36682624],"study_design_scores_gemma":[0.018580595,0.0062662526,0.009167896,0.024419498,0.0103356335,0.00006849117,0.0006127872,0.67878544,0.053946923,0.19409217,0.00009283018,0.0036314612],"about_ca_topic_score_codex":0.000020625168,"about_ca_topic_score_gemma":0.0000077435525,"teacher_disagreement_score":0.6491006,"about_ca_system_score_codex":0.00026059567,"about_ca_system_score_gemma":0.0001741169,"threshold_uncertainty_score":0.99974984},"labels":[],"label_agreement":null},{"id":"W3212660444","doi":"10.33137/utjph.v2i2.36751","title":"Covariate Adjustment in Randomized Controlled Trials","year":2021,"lang":"en","type":"article","venue":"University of Toronto Journal of Public Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Covariate; Statistics; Comparability; Null hypothesis; Econometrics; Statistical significance; Statistical power; Sample size determination; Type I and type II errors; Randomized controlled trial; Null (SQL); Correlation; Mathematics; Medicine; Internal medicine; Data mining; Computer science","score_opus":0.5869802407866622,"score_gpt":0.5330015748332305,"score_spread":0.053978665953431704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212660444","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074133608,0.01130019,0.9354815,0.029656924,0.0029805822,0.0026377167,0.00008969157,0.000027355065,0.010412683],"genre_scores_gemma":[0.028509669,0.0074896314,0.9626698,0.00035464787,0.0002934108,6.919713e-7,0.0000010978613,0.000014109286,0.0006669364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9634217,0.031265225,0.00403688,0.00019037844,0.0007209289,0.00036489693],"domain_scores_gemma":[0.7588218,0.22898424,0.009154582,0.0004848618,0.0017511311,0.0008034033],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1190626,0.00013985885,0.007416959,0.00010509789,0.000049340066,0.000018283094,0.00030181182,0.00012637043,0.0043252814],"category_scores_gemma":[0.38318482,0.000108043205,0.0012516541,0.00009768453,0.00013896925,0.00020583748,0.00007742252,0.00025824044,0.0000018226481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11521702,0.0027450428,0.000095154035,0.00048807272,0.0038807462,0.00029871895,0.0056434334,0.0000138922705,0.000088600216,0.7627246,0.009352153,0.09945257],"study_design_scores_gemma":[0.74470353,0.00044429884,0.0007944856,0.00043642864,0.00056215236,0.000028146267,0.004142582,0.0002571333,0.000015871075,0.24551228,0.0029331122,0.00016995246],"about_ca_topic_score_codex":0.0011098217,"about_ca_topic_score_gemma":0.0010973363,"teacher_disagreement_score":0.62948656,"about_ca_system_score_codex":0.00071357377,"about_ca_system_score_gemma":0.0022649704,"threshold_uncertainty_score":0.9965849},"labels":[],"label_agreement":null},{"id":"W3212678746","doi":"10.1002/sim.9233","title":"Estimation of standard deviations and inverse‐variance weights from an observed range","year":2021,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Statistics; Standard deviation; Standard error; Contrast (vision); Variance (accounting); Mathematics; Sample size determination; Inverse; Range (aeronautics); Mean squared error; Population variance; Sample (material); Econometrics; Population; Computer science; Medicine","score_opus":0.6336011764395778,"score_gpt":0.6039632280292192,"score_spread":0.029637948410358605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212678746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004337767,0.47093943,0.5229176,0.000044989807,0.0005350604,0.0006640032,0.0047619725,0.000020824962,0.0001117543],"genre_scores_gemma":[0.0000010145725,0.48812672,0.51124924,0.00003069328,0.00017753588,0.000040788746,0.0003096709,0.00003756952,0.000026773927],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99333274,0.0023360401,0.0027418758,0.0006288719,0.0006995628,0.00026091546],"domain_scores_gemma":[0.91774905,0.07987754,0.0011965248,0.00072473305,0.0002593885,0.00019275644],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035134472,0.00043812828,0.004462377,0.00020413299,0.000053664302,0.000020855072,0.00030256517,0.00043347772,0.0007171771],"category_scores_gemma":[0.15988487,0.00034613747,0.00009396333,0.0005005224,0.0004871917,0.000064561915,0.0001078139,0.0006597833,0.000004194544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018104976,0.00007389076,0.000012081857,0.009223619,0.0001431722,0.00007425913,0.00023741207,9.270612e-7,1.10178725e-7,0.30784768,0.0021914307,0.68017733],"study_design_scores_gemma":[0.0013096915,0.00022162935,0.000037084996,0.029232424,0.0020466547,0.0000052775963,0.000054649958,0.0011918935,5.9957273e-7,0.92777085,0.037816964,0.00031227022],"about_ca_topic_score_codex":0.00011960338,"about_ca_topic_score_gemma":0.00020582258,"teacher_disagreement_score":0.67986506,"about_ca_system_score_codex":0.00014374446,"about_ca_system_score_gemma":0.00036280075,"threshold_uncertainty_score":0.9998991},"labels":[],"label_agreement":null},{"id":"W3213490299","doi":"10.1371/journal.pcbi.1009477","title":"The meaning of significant mean group differences for biomarker discovery","year":2021,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital; McGill University; Canadian Institute for Advanced Research","funders":"Innovative Medicines Initiative; Autism Speaks; Simons Foundation Autism Research Initiative; Medical Research Council; European Federation of Pharmaceutical Industries and Associations; European Commission","keywords":"Biomarker; Standard deviation; Sample size determination; Skewness; Statistics; Biomarker discovery; Autism; Psychology; Cognitive psychology; Medicine; Mathematics; Biology; Psychiatry; Genetics","score_opus":0.5298808508182706,"score_gpt":0.5065571551470807,"score_spread":0.02332369567118997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213490299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085366294,0.00007904588,0.9120898,0.00084167026,0.00049048103,0.00034385436,0.00031627025,0.000029902127,0.0004426729],"genre_scores_gemma":[0.45704332,0.000009785044,0.5426879,0.00006742542,0.00008515494,0.0000398834,0.000020024598,0.00000932422,0.000037204045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979501,0.00076451065,0.0006745178,0.00026491637,0.00016036766,0.00018559433],"domain_scores_gemma":[0.8585697,0.14078209,0.00023607345,0.00014453125,0.00023379756,0.000033812878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010813152,0.00010815647,0.00040193435,0.000024684374,0.0001226761,0.000028603397,0.00019385945,0.00008569068,0.000036928304],"category_scores_gemma":[0.037678804,0.0000673556,0.00013264817,0.000111717505,0.00032588374,0.000026081962,0.00009142676,0.00008472612,0.0000024342248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009320903,0.00015564826,0.0010065548,0.000056620167,0.00022566227,0.0000012034316,0.00004857883,0.000007804057,0.006088781,0.9867092,0.00017058775,0.005436161],"study_design_scores_gemma":[0.00040653528,0.00012237974,0.0022390746,0.000031438223,0.00005963983,0.0000014393332,0.00007956161,0.0051806294,0.0016114941,0.99011314,0.00006807603,0.00008659812],"about_ca_topic_score_codex":0.0000018329913,"about_ca_topic_score_gemma":0.000004789359,"teacher_disagreement_score":0.37167704,"about_ca_system_score_codex":0.000014810714,"about_ca_system_score_gemma":0.00007060712,"threshold_uncertainty_score":0.9704272},"labels":[],"label_agreement":null},{"id":"W3214073505","doi":"10.33137/utjph.v2i2.36844","title":"The impact of ignoring Interval censoring in progression-free survival in cancer trials: a systematic review","year":2021,"lang":"en","type":"review","venue":"University of Toronto Journal of Public Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"","keywords":"Censoring (clinical trials); Confidence interval; Hazard ratio; Statistics; Estimator; Medicine; Econometrics; Mathematics","score_opus":0.7748204287433228,"score_gpt":0.6498241711814696,"score_spread":0.12499625756185317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214073505","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008800547,0.9954249,0.0015620495,0.0003612673,0.0005540846,0.0018681727,0.000110825786,0.0000046742457,0.0001052267],"genre_scores_gemma":[0.000006477071,0.9699182,0.029871173,0.0000058498404,0.00013995549,0.0000031570141,8.885398e-7,0.000024309913,0.000029996363],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.95493704,0.034956813,0.007964402,0.0003241588,0.0011976608,0.00061990257],"domain_scores_gemma":[0.8658865,0.11252308,0.018785823,0.0011798847,0.0010837929,0.0005409021],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.095518686,0.00033391302,0.012015226,0.00018688537,0.00006501698,0.000029035149,0.0015790176,0.00023751312,0.00024105956],"category_scores_gemma":[0.2750547,0.00020399381,0.002024133,0.00035762542,0.00013027835,0.00022036773,0.00037074275,0.00087305164,2.852679e-7],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002875088,0.00028345129,0.000027268416,0.6149959,0.0007621035,0.00004466462,0.00041029652,5.065696e-7,2.4218258e-8,0.0015649338,0.0005338633,0.38134825],"study_design_scores_gemma":[0.0011413163,0.0003695544,0.000026970098,0.9884646,0.000943577,0.000025893778,0.0010447305,0.000008152835,3.6407556e-8,0.0015318975,0.0062671294,0.00017613206],"about_ca_topic_score_codex":0.0041616606,"about_ca_topic_score_gemma":0.003872372,"teacher_disagreement_score":0.38117212,"about_ca_system_score_codex":0.003720784,"about_ca_system_score_gemma":0.0051577976,"threshold_uncertainty_score":0.9729721},"labels":[],"label_agreement":null},{"id":"W3215120638","doi":"10.2196/30368","title":"The Successful Synchronized Orchestration of an Investigator-Initiated Multicenter Trial Using a Clinical Trial Management System and Team Approach: Design and Utility Study","year":2021,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Cincinnati","keywords":"Clinical trial; Accrual; Generalizability theory; Electronic data capture; Harmonization; Biostatistics; Data management; Standardization; Medicine; Protocol (science); Medical physics; Computer science; Data mining; Public health; Business; Alternative medicine; Nursing; Psychology; Pathology; Accounting","score_opus":0.8257128808207094,"score_gpt":0.6524649867461586,"score_spread":0.17324789407455077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215120638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90658516,0.000026363992,0.08260725,0.000031700067,0.00029353678,0.009839977,0.000025068643,0.00004178489,0.00054916926],"genre_scores_gemma":[0.75364643,0.000022662001,0.24566443,0.0000053545473,0.00014790733,0.00048039592,0.0000027332978,0.000020133873,0.000009929514],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9626199,0.032926068,0.002209642,0.0005734608,0.0012060986,0.00046480092],"domain_scores_gemma":[0.9333889,0.064323515,0.0005222629,0.00070876896,0.00069458067,0.00036197534],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.048948456,0.00021714078,0.0008853005,0.00011065047,0.00048959255,0.0002796183,0.00031943526,0.00020778031,0.000009156503],"category_scores_gemma":[0.04989119,0.00014571435,0.00010055165,0.0004935022,0.0011048376,0.0002853286,0.0004873159,0.00079297816,0.0000014709293],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8265173,0.025648907,0.0012062455,0.005699833,0.0024381462,0.00011008223,0.014337219,0.000009077421,0.00012309273,0.055388644,0.0008222399,0.06769925],"study_design_scores_gemma":[0.5500085,0.014153566,0.0026373619,0.00057178456,0.00048136438,0.000016396687,0.05859844,0.26500204,0.0006492337,0.10735028,0.0000410251,0.00049004954],"about_ca_topic_score_codex":0.000015124694,"about_ca_topic_score_gemma":0.00000433772,"teacher_disagreement_score":0.2765088,"about_ca_system_score_codex":0.000111465575,"about_ca_system_score_gemma":0.0003455976,"threshold_uncertainty_score":0.9793077},"labels":[],"label_agreement":null},{"id":"W3215501451","doi":"10.1177/09622802211055856","title":"Impact of minimal sufficient balance, minimization, and stratified permuted blocks on bias and power in the estimation of treatment effect in sequential clinical trials with a binary endpoint","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences","keywords":"Covariate; Statistics; Restricted randomization; Randomization; Econometrics; Predictability; Mathematics; Selection bias; Minification; Clinical trial; Medicine; Mathematical optimization","score_opus":0.686350801538035,"score_gpt":0.717561028463486,"score_spread":0.031210226925451057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215501451","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79450786,0.000097308955,0.20255795,0.0005207043,0.000097801814,0.001620686,0.000256292,0.000007878632,0.00033350123],"genre_scores_gemma":[0.47264802,0.0001374428,0.52702206,0.00002104905,0.00003193752,0.00010546392,0.000010546113,0.000016981327,0.0000064553205],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89229393,0.09926508,0.0044318,0.000999809,0.0022582961,0.0007510997],"domain_scores_gemma":[0.40963176,0.5887896,0.0004020772,0.0005282532,0.00029138592,0.00035693593],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.121122964,0.0003039556,0.0022885394,0.00043822557,0.000047508474,0.000045050212,0.0002649986,0.00043810657,0.0008034641],"category_scores_gemma":[0.7212409,0.00016438031,0.00014956587,0.0012916963,0.0018580745,0.000036707308,0.00015655189,0.0013108809,6.596541e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028312596,0.012760579,0.07703592,0.0015145233,0.0005888199,0.0027213783,0.0039113215,0.0003391545,0.0012000247,0.19387706,0.0006069522,0.67713165],"study_design_scores_gemma":[0.019087182,0.030266978,0.387677,0.0019851937,0.0002200435,0.000049785256,0.0010767311,0.14143158,0.001416653,0.4163388,0.000012921858,0.00043711378],"about_ca_topic_score_codex":0.00013997122,"about_ca_topic_score_gemma":0.00006862518,"teacher_disagreement_score":0.6766946,"about_ca_system_score_codex":0.00018927807,"about_ca_system_score_gemma":0.0011910324,"threshold_uncertainty_score":0.9049888},"labels":[],"label_agreement":null},{"id":"W3216520163","doi":"10.1161/circ.144.suppl_1.10351","title":"Abstract 10351: Validity and Relevance of Clinical Worsening as a Composite Endpoint in Pulmonary Arterial Hypertension Trials","year":2021,"lang":"en","type":"article","venue":"Circulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut universitaire de cardiologie et de pneumologie de Québec","funders":"","keywords":"Medicine; Pulmonary hypertension; Relevance (law); Clinical endpoint; Clinical trial; Library science; Humanities; Cardiology; Internal medicine; Law; Political science","score_opus":0.7147325077477392,"score_gpt":0.5719521662243257,"score_spread":0.14278034152341357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216520163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98354715,0.00004162296,0.014508441,0.00013860123,0.0009043977,0.00034575758,0.000023680408,0.000029413231,0.00046094952],"genre_scores_gemma":[0.8212745,0.000059474223,0.17822656,0.000048967442,0.00035315502,0.0000072817984,0.000008838253,0.000015959875,0.000005241739],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937621,0.0026184772,0.0026923784,0.0004331768,0.00032513327,0.00016876556],"domain_scores_gemma":[0.9018384,0.09661702,0.0008894201,0.00036598393,0.00018854486,0.000100635254],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011299055,0.00014047182,0.0012859373,0.00005627525,0.00003916205,0.000025666746,0.00006767978,0.00026076395,0.00019548938],"category_scores_gemma":[0.27207673,0.0001319109,0.00020071582,0.00017362306,0.00010793218,0.000090619505,0.00006849119,0.00029006178,0.000010978736],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004575198,0.002902546,0.17003618,0.0012960407,0.00021806937,0.0010768938,0.00039474797,0.00019023505,0.3679089,0.039195325,0.0001902731,0.4120156],"study_design_scores_gemma":[0.0012426252,0.000023075174,0.5087599,0.00024761,0.00007170894,0.000017195152,0.00002478622,0.0016774,0.0026813445,0.48509657,0.000044114695,0.00011366441],"about_ca_topic_score_codex":0.00001338571,"about_ca_topic_score_gemma":0.0000052884834,"teacher_disagreement_score":0.44590124,"about_ca_system_score_codex":0.000025702582,"about_ca_system_score_gemma":0.00007935427,"threshold_uncertainty_score":0.73405486},"labels":[],"label_agreement":null},{"id":"W3217122674","doi":"10.1186/s12874-021-01446-z","title":"On clinical trial fragility due to patients lost to follow up","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"National Institutes of Health; National Institute of Allergy and Infectious Diseases; Patient-Centered Outcomes Research Institute","keywords":"Fragility; Medicine; MEDLINE; Clinical trial; Psychology; Internal medicine; Political science","score_opus":0.9626865098308511,"score_gpt":0.7740116613576609,"score_spread":0.18867484847319027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217122674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31137505,0.000013266129,0.6708959,0.0045611467,0.007423459,0.0021600646,0.000079459525,0.00007247865,0.0034192],"genre_scores_gemma":[0.00386114,0.000032259435,0.9861766,0.0050851023,0.0024210173,0.000339268,0.000007960959,0.00007819598,0.0019984317],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.82181555,0.16471924,0.003716581,0.0021242953,0.0057721306,0.001852183],"domain_scores_gemma":[0.1008938,0.89060646,0.00023955216,0.0021976882,0.0020379159,0.0040245904],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.22639984,0.0003762003,0.0027322548,0.00034612676,0.00021569207,0.00006627431,0.0015585418,0.001397213,0.01350969],"category_scores_gemma":[0.99322975,0.0003030162,0.0006322579,0.0015180358,0.0009031102,0.000036931386,0.001991822,0.0034178009,0.003046144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12405844,0.004978548,0.002626533,0.0003378787,0.00025186015,0.00075202325,0.00026504477,0.0000013282503,0.000043025517,0.31499386,0.15191804,0.39977342],"study_design_scores_gemma":[0.034747425,0.00658231,0.004368527,0.00022879666,0.000048232418,0.000007990189,0.000073439325,0.000046879108,0.0004940464,0.94368374,0.009382378,0.00033620984],"about_ca_topic_score_codex":0.00006602308,"about_ca_topic_score_gemma":0.00049729605,"teacher_disagreement_score":0.7668299,"about_ca_system_score_codex":0.0002176238,"about_ca_system_score_gemma":0.0026759582,"threshold_uncertainty_score":0.9999422},"labels":[],"label_agreement":null},{"id":"W346993280","doi":"10.4244/eijv11i1a22","title":"Novel approaches to composite endpoints in clinical trials","year":2015,"lang":"en","type":"article","venue":"EuroIntervention","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"","keywords":"Medicine; Clinical trial; MEDLINE; Composite number; Intensive care medicine; Medical physics; Internal medicine; Composite material","score_opus":0.9757598246986171,"score_gpt":0.6827295059097276,"score_spread":0.2930303187888895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W346993280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10702446,0.00002243796,0.88436615,0.0012534669,0.0019574028,0.0010391691,0.000051704483,0.000107813685,0.0041773785],"genre_scores_gemma":[0.15278293,0.0000015831548,0.84593123,0.00018585417,0.0004428773,0.000016454327,0.0000042522906,0.000039049595,0.0005957818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882389,0.0069637313,0.0036007254,0.0005106617,0.00040425462,0.00028172767],"domain_scores_gemma":[0.96660787,0.031789806,0.0006528438,0.0004974823,0.00007998574,0.00037200472],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062501065,0.00018107795,0.0011355844,0.00015018297,0.000019080893,0.00005701702,0.00029538648,0.00014275144,0.00012859049],"category_scores_gemma":[0.3367768,0.00015685569,0.00054715184,0.0002638395,0.0000668953,0.000079268895,0.00020394466,0.00036549853,0.00030455593],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006603923,0.015131137,0.0378168,0.0008490971,0.0005797331,0.00018507792,0.0014348564,0.00009538616,0.0038321335,0.5823751,0.06367147,0.28742525],"study_design_scores_gemma":[0.0059495894,0.0009062028,0.028788041,0.00054828956,0.00011022839,0.000017641178,0.00009728073,0.0012089689,0.0008606381,0.96028143,0.00091161043,0.00032008532],"about_ca_topic_score_codex":0.000012314836,"about_ca_topic_score_gemma":0.000023868131,"teacher_disagreement_score":0.3779063,"about_ca_system_score_codex":0.00007012075,"about_ca_system_score_gemma":0.00003243166,"threshold_uncertainty_score":0.9653524},"labels":[],"label_agreement":null},{"id":"W4200543014","doi":"10.1002/pst.2181","title":"A dose‐finding design for dual‐agent trials with patient‐specific doses for one agent with application to an opiate detoxification trial","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Clinical trial; Medicine; Maximum tolerated dose; Dosing; Detoxification (alternative medicine); Clinical study design; Medical physics; Pharmacology; Computer science; Internal medicine; Alternative medicine; Pathology","score_opus":0.8261641552162479,"score_gpt":0.618695554779733,"score_spread":0.20746860043651483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200543014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00377152,0.00005341326,0.9795985,0.0006277207,0.000576871,0.012216694,0.0029697744,0.00014695391,0.00003855111],"genre_scores_gemma":[0.020644844,0.00008003296,0.9718991,0.00049098773,0.00079675793,0.005657903,0.00021235585,0.00015061944,0.00006739939],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927463,0.0021746082,0.0022097495,0.0011651717,0.0009030569,0.00080114236],"domain_scores_gemma":[0.91762364,0.07918989,0.00075858296,0.00069838064,0.0010076341,0.0007218735],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006444635,0.0004896733,0.0015054948,0.00011153178,0.0003500099,0.00025727536,0.00028461553,0.00020325946,0.00020392606],"category_scores_gemma":[0.051348194,0.0003937728,0.00016444367,0.0004863907,0.00017197123,0.000117363445,0.00007842117,0.00030098335,0.000024770641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16453162,0.0045289984,0.000018309924,0.0008951019,0.00083074055,0.00004119465,0.00065091206,0.00070006726,0.009681208,0.4478247,0.0047252923,0.36557186],"study_design_scores_gemma":[0.084885694,0.010668269,0.00007005586,0.00028773595,0.003017275,0.000020577223,0.00031490196,0.019322403,0.08636992,0.75805295,0.03549572,0.0014944867],"about_ca_topic_score_codex":0.0000025478632,"about_ca_topic_score_gemma":0.000009263332,"teacher_disagreement_score":0.3640774,"about_ca_system_score_codex":0.00026548037,"about_ca_system_score_gemma":0.00028571335,"threshold_uncertainty_score":0.9998514},"labels":[],"label_agreement":null},{"id":"W4200631872","doi":"10.1002/sim.9439","title":"Using principal stratification in analysis of clinical trials","year":2022,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Principal (computer security); Computer science; Variety (cybernetics); Observational study; Set (abstract data type); Addendum; Key (lock); Data science; Stratification (seeds); Management science; Machine learning; Risk analysis (engineering); Artificial intelligence; Mathematics; Engineering; Statistics; Medicine; Programming language; Biology","score_opus":0.9143698492728977,"score_gpt":0.7492055652700645,"score_spread":0.16516428400283312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200631872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030293917,0.00015175325,0.9579756,0.0002059761,0.003484231,0.0020059228,0.004324238,0.000032446093,0.0015259158],"genre_scores_gemma":[0.053052306,0.00033794748,0.94554174,0.0000650581,0.00049228943,0.00011717025,0.00027836757,0.000052822532,0.00006227599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95695114,0.02266446,0.016767139,0.0013154163,0.0018188283,0.0004829932],"domain_scores_gemma":[0.7335626,0.25951988,0.0051143304,0.0013434016,0.00029161855,0.00016821177],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12264726,0.00042691518,0.007768412,0.0015097834,0.00003562956,0.000014772293,0.00076434074,0.0006518047,0.004294911],"category_scores_gemma":[0.7008931,0.00037392715,0.00043501623,0.0018262134,0.0006704637,0.000020543275,0.0006515215,0.002806242,0.0000010372654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009830398,0.0016429914,0.057725206,0.0021521833,0.0035271037,0.00023446692,0.0015250212,0.009093306,0.00008156372,0.88359594,0.0014669601,0.037972186],"study_design_scores_gemma":[0.0019199917,0.00018625666,0.027375618,0.0004769447,0.004826011,4.1539963e-7,0.00033710495,0.0903461,0.0000062512195,0.87420225,0.00004852608,0.00027450008],"about_ca_topic_score_codex":0.0006187393,"about_ca_topic_score_gemma":0.0005772582,"teacher_disagreement_score":0.5782458,"about_ca_system_score_codex":0.00028832172,"about_ca_system_score_gemma":0.00062505685,"threshold_uncertainty_score":0.99987125},"labels":[],"label_agreement":null},{"id":"W4205384482","doi":"10.1080/0284186x.2022.2025613","title":"Comparing treatment modalities for hepatocellular carcinoma: the value of network meta-analyses","year":2022,"lang":"en","type":"article","venue":"Acta Oncologica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Juravinski Cancer Centre; London Health Sciences Centre; McMaster University; University of Toronto","funders":"","keywords":"Medicine; Hepatocellular carcinoma; Value (mathematics); Treatment modality; Oncology; Carcinoma; Modalities; Internal medicine; Statistics","score_opus":0.9068505943037609,"score_gpt":0.5961386937513271,"score_spread":0.3107119005524338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205384482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8580581,0.0027084514,0.10708528,0.0063385526,0.0018889091,0.0076947645,0.0009029111,0.00027729815,0.015045746],"genre_scores_gemma":[0.6859176,0.00001064055,0.3123924,0.0001575264,0.00015370415,0.0009887238,0.000003595538,0.000015324687,0.00036046456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955866,0.002441955,0.00097091444,0.00031398283,0.0003597919,0.0003267919],"domain_scores_gemma":[0.9112179,0.08753926,0.000557599,0.00055856764,0.0000719783,0.000054687305],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00438322,0.00021289305,0.0016027167,0.000026437672,0.0004151117,0.000018707771,0.00050866813,0.00006899094,0.00080221327],"category_scores_gemma":[0.012632989,0.00011182229,0.0008385675,0.00019252255,0.00017632531,0.000019796935,0.00030800537,0.00017475324,0.0000012337223],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008295883,0.0017274991,0.007291866,0.00014357218,0.01079173,0.000029653896,0.0007835353,0.00419719,0.00060301146,0.9549857,0.017165454,0.0014512102],"study_design_scores_gemma":[0.00083763996,0.0014598626,0.00049785053,0.0000023423497,0.008485226,0.0000037922932,0.00037851633,0.00998727,0.0007982316,0.96837395,0.009027463,0.00014785815],"about_ca_topic_score_codex":0.000092568065,"about_ca_topic_score_gemma":0.000004939587,"teacher_disagreement_score":0.20530713,"about_ca_system_score_codex":0.00018362477,"about_ca_system_score_gemma":0.000084740816,"threshold_uncertainty_score":0.995684},"labels":[],"label_agreement":null},{"id":"W4205604600","doi":"10.1016/j.ahj.2021.12.012","title":"Clinical events classification (CEC) in clinical trials: Report on the current landscape and future directions — proceedings from the CEC Summit 2018","year":2021,"lang":"en","type":"article","venue":"American Heart Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Janssen Pharmaceuticals; Fonds de Recherche du Québec - Santé; Eli Lilly Canada; Johnson and Johnson; National Institutes of Health; Alberta Innovates; Novo Nordisk; Daiichi-Sankyo; AstraZeneca; CSL Behring; National Heart, Lung, and Blood Institute; Pfizer; Cardiovascular Research Foundation; Merck; GlaxoSmithKline; Australian Carbon Innovation; Bayer; Boehringer Ingelheim; Amgen; U.S. Department of Defense; Sanofi; Abbott Laboratories","keywords":"Adjudication; Medicine; Clinical trial; Summit; Scope (computer science); Event (particle physics); Process management; Process (computing); Computer science; Business; Political science; Pathology","score_opus":0.6752052022394748,"score_gpt":0.625192007218712,"score_spread":0.050013195020762735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205604600","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88417464,0.0012696994,0.0018522295,0.10113025,0.0094126025,0.0011123236,0.000114691284,0.00007760963,0.0008559669],"genre_scores_gemma":[0.41673383,0.05359278,0.44923708,0.008437727,0.07091157,0.00033346895,0.000026183132,0.00027890367,0.0004484715],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98533946,0.0088811945,0.0041138753,0.000626131,0.00068420713,0.00035512942],"domain_scores_gemma":[0.82931155,0.16714133,0.0021501712,0.0006501338,0.00039008056,0.00035673915],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04389215,0.0002414993,0.0014293302,0.000052041047,0.0003455427,0.00016882223,0.00031342712,0.00016495495,0.00029760489],"category_scores_gemma":[0.26789582,0.00012979297,0.00059061864,0.0005338227,0.0005451646,0.00008111173,0.00012203312,0.0027948243,0.000029657904],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033696825,0.00089396775,0.4972718,0.000010368703,0.00022891487,0.000048250644,0.00014392854,8.9789545e-8,0.000013653478,0.0039745914,0.100991145,0.3960863],"study_design_scores_gemma":[0.0009861289,0.00031600037,0.65116,0.00023342107,0.00026736665,0.00015923659,0.0016590127,0.00012378086,0.000009728285,0.13891605,0.20596224,0.00020703187],"about_ca_topic_score_codex":0.00001904543,"about_ca_topic_score_gemma":0.000028521235,"teacher_disagreement_score":0.4674408,"about_ca_system_score_codex":0.000056640816,"about_ca_system_score_gemma":0.00031297843,"threshold_uncertainty_score":0.99950576},"labels":[],"label_agreement":null},{"id":"W4205784267","doi":"10.1016/s0828-282x(20)30967-3","title":"Announcement: Focus Issue on New Concepts in Clinical Trials","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Focus (optics); Clinical trial; Intensive care medicine; Medical physics; Internal medicine","score_opus":0.7579590472111477,"score_gpt":0.6219129327023554,"score_spread":0.13604611450879234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205784267","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02260557,0.0025828744,0.6795458,0.15595469,0.028566608,0.0030747764,0.0007646364,0.00006837925,0.10683663],"genre_scores_gemma":[0.67309624,0.00030054312,0.26318407,0.011646699,0.05136637,0.000009705517,0.0000022561444,0.0000952936,0.00029882326],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882913,0.0074756085,0.0033435936,0.00025870447,0.00021953911,0.0004112537],"domain_scores_gemma":[0.9357257,0.061079632,0.0009995736,0.00025397012,0.00018069777,0.0017604525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01909465,0.00017790875,0.0025694922,0.00015072024,0.000032112966,0.000024936868,0.00044126238,0.00036709927,0.00047574393],"category_scores_gemma":[0.459485,0.00014304958,0.0005897335,0.00021262726,0.00025614808,0.00004042227,0.000020065796,0.0009551899,0.00008475],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009209512,0.000012250207,0.006953678,0.000033189204,0.0005318732,0.001315463,0.0003957526,0.00023763397,0.000030518408,0.058586434,0.66972625,0.26125598],"study_design_scores_gemma":[0.004392019,0.0019075117,0.001735678,0.000104065206,0.00017873516,0.000044006847,0.00011329289,0.000018733863,0.00005463781,0.53328675,0.45796397,0.0002005646],"about_ca_topic_score_codex":0.00016416571,"about_ca_topic_score_gemma":0.0002901942,"teacher_disagreement_score":0.65049064,"about_ca_system_score_codex":0.00011406137,"about_ca_system_score_gemma":0.0018367146,"threshold_uncertainty_score":0.66178626},"labels":[],"label_agreement":null},{"id":"W4205987659","doi":"10.1111/rssb.12489","title":"False Discovery Rate Control with E-values","year":2022,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"False discovery rate; Multiple comparisons problem; Null hypothesis; Null (SQL); Bayes' theorem; Calibration; Statistics; Control (management); Mathematics; Positive control; Computer science; Algorithm; Bayesian probability; Data mining; Artificial intelligence; Medicine; Chemistry","score_opus":0.30725195796834714,"score_gpt":0.4782703869736066,"score_spread":0.17101842900525943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205987659","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004368611,0.00010736963,0.9857867,0.0037090986,0.0022475643,0.0007014841,0.0027149832,0.00005858292,0.0003056337],"genre_scores_gemma":[0.035425153,0.000020801599,0.96052456,0.0020909135,0.0006041519,0.00007737132,0.0000047723224,0.000108519685,0.0011437803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9760099,0.017952045,0.0026186612,0.00065461855,0.0017614252,0.0010033312],"domain_scores_gemma":[0.812447,0.18431933,0.0016239425,0.0006847086,0.00045024513,0.0004747392],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020033596,0.00060127856,0.0023115485,0.000059329523,0.001054889,0.00017491053,0.0014047332,0.00025023424,0.0023438393],"category_scores_gemma":[0.16569579,0.00036249595,0.0007349357,0.00052243547,0.0025982205,0.00021456533,0.000704594,0.0028243365,0.000008609616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006568162,0.0007147899,0.00076840166,0.00023437974,0.0014129769,0.0003564791,0.00043517575,0.001109119,0.00022796982,0.91944003,0.063010514,0.00572202],"study_design_scores_gemma":[0.0034934487,0.0028489232,0.0043261047,0.000058996415,0.0014001926,0.00032758302,0.0010262943,0.0014517875,0.00016453509,0.9799455,0.00444353,0.0005131032],"about_ca_topic_score_codex":0.00003111691,"about_ca_topic_score_gemma":0.0000057345064,"teacher_disagreement_score":0.16636729,"about_ca_system_score_codex":0.0004386585,"about_ca_system_score_gemma":0.0004774327,"threshold_uncertainty_score":0.9998827},"labels":[],"label_agreement":null},{"id":"W4206057704","doi":"10.1002/9780470059876.ch43","title":"<i>N</i> ‐of‐1 Randomized Clinical Trials in Pharmacoepidemiology","year":2006,"lang":"en","type":"other","venue":"Pharmacoepidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph's Hospital; McMaster University","funders":"","keywords":"Pharmacoepidemiology; Randomized controlled trial; Medicine; Clinical trial; Research design; Medical physics; Internal medicine; Statistics; Pharmacology; Mathematics","score_opus":0.7866977188173409,"score_gpt":0.7053510560370935,"score_spread":0.08134666278024738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206057704","genre_codex":"other","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005485415,0.010113191,0.3919196,0.004778941,0.019130757,0.010818028,0.0015075165,0.0009186937,0.5607584],"genre_scores_gemma":[0.00031628372,0.014184042,0.8739168,0.005340513,0.0090869935,0.0013657933,0.00010208944,0.0015954905,0.094092004],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3966562,0.55766666,0.03989596,0.0029188758,0.0006958608,0.0021664535],"domain_scores_gemma":[0.09105482,0.89172524,0.015427143,0.0012124222,0.00014758932,0.000432785],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.49649835,0.0011862693,0.03525469,0.0010631836,0.000028151948,0.000006939096,0.0012784713,0.0030862715,0.006918398],"category_scores_gemma":[0.90979075,0.00089606096,0.004541071,0.00050452194,0.0027559754,0.000033022618,0.0003831961,0.0029974966,0.0001318224],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01306834,0.0005877863,0.0015603504,0.00059493823,0.0013264295,0.000053240827,0.000006410621,0.000005228646,0.00003450614,0.10371394,0.8694371,0.009611755],"study_design_scores_gemma":[0.11062385,0.00007286029,0.000019198349,0.00036656254,0.0020300418,0.000009268335,0.000002568815,0.0007951731,0.000058177815,0.63517964,0.25021145,0.0006311944],"about_ca_topic_score_codex":0.00090616255,"about_ca_topic_score_gemma":0.000115601346,"teacher_disagreement_score":0.6192256,"about_ca_system_score_codex":0.00008183442,"about_ca_system_score_gemma":0.00024558973,"threshold_uncertainty_score":0.999958},"labels":[],"label_agreement":null},{"id":"W4206103426","doi":"10.1016/j.annonc.2020.10.469","title":"Cautionary tails","year":2020,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; NOSM University; Princess Margaret Cancer Centre; Thunder Bay Regional Health Sciences Centre","funders":"","keywords":"Medicine","score_opus":0.909316191993618,"score_gpt":0.6858299607201127,"score_spread":0.2234862312735053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206103426","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0887906,0.0004361732,0.24746612,0.3562402,0.0020421848,0.0014330737,0.00041123095,0.00041901146,0.30276138],"genre_scores_gemma":[0.17630029,0.000087965054,0.8111245,0.011841327,0.00048307102,0.000015942223,0.0000012588739,0.000018708402,0.00012692614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982773,0.0005898267,0.00062359875,0.00017954582,0.00015344111,0.00017626416],"domain_scores_gemma":[0.9721281,0.02716391,0.00023941167,0.00016392398,0.00015482235,0.00014985962],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013166904,0.00007962018,0.00053783046,0.000021269809,0.000020257025,0.0000024164635,0.00019006556,0.00016190611,0.0010134456],"category_scores_gemma":[0.089273,0.000069487214,0.000115608345,0.00012942783,0.00018120087,0.000025691317,0.00008889064,0.0001654952,0.00009820067],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029213837,0.0003592418,0.00018591178,0.00012817829,0.0001065989,0.000055488395,0.00027185873,0.0000022097786,0.0010800957,0.6529319,0.2219321,0.12265426],"study_design_scores_gemma":[0.00041761607,0.0014216685,0.00029094407,0.0000088951665,0.0000272625,0.000003047897,0.00003696812,0.000070131726,0.0030324971,0.9278173,0.066801056,0.00007264442],"about_ca_topic_score_codex":0.0000027292876,"about_ca_topic_score_gemma":6.1557773e-7,"teacher_disagreement_score":0.5636584,"about_ca_system_score_codex":0.000006986072,"about_ca_system_score_gemma":0.00009554235,"threshold_uncertainty_score":0.99989974},"labels":[],"label_agreement":null},{"id":"W4206238712","doi":"10.3389/fonc.2021.695936","title":"Application of Real-World Data to External Control Groups in Oncology Clinical Trial Drug Development","year":2022,"lang":"en","type":"review","venue":"Frontiers in Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Pfizer","keywords":"Clinical trial; Medicine; Drug development; Surrogate endpoint; Randomized controlled trial; Psychological intervention; Clinical endpoint; Oncology; Intensive care medicine; Internal medicine; Drug; Medical physics; Pharmacology","score_opus":0.7239719814468016,"score_gpt":0.6562492200867943,"score_spread":0.06772276136000732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206238712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000065508015,0.3551229,0.5941312,0.00047554792,0.025216864,0.020209908,0.0010106575,0.000117140764,0.0036503123],"genre_scores_gemma":[0.0000022820627,0.44015813,0.55689293,0.00015762364,0.00069466943,0.0018486172,0.00007157343,0.00006512389,0.00010904858],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9686918,0.018389704,0.009635897,0.0018334441,0.00066598714,0.00078312185],"domain_scores_gemma":[0.8492551,0.14401439,0.0040834956,0.0022405712,0.00007619231,0.00033025618],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040741917,0.00058730016,0.010274834,0.001029229,0.000055427776,0.000012827427,0.0031533737,0.00095137523,0.00023097353],"category_scores_gemma":[0.08503592,0.00054719247,0.00045007534,0.0012277917,0.00046578023,0.000053368905,0.0016308709,0.0025980023,0.000029507817],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0074518244,0.001946921,0.0002859682,0.0015727822,0.0002443801,0.000090938105,0.00009257589,0.0000010570557,3.7595346e-8,0.004261338,0.018254295,0.9657979],"study_design_scores_gemma":[0.01988229,0.001087181,0.00007837877,0.0008438556,0.00062460214,0.000005610429,0.000057673366,0.00009637663,8.2994916e-8,0.059574097,0.91732794,0.00042193726],"about_ca_topic_score_codex":0.00013398212,"about_ca_topic_score_gemma":0.0016296135,"teacher_disagreement_score":0.96537596,"about_ca_system_score_codex":0.0030692727,"about_ca_system_score_gemma":0.0032784962,"threshold_uncertainty_score":0.99970305},"labels":[],"label_agreement":null},{"id":"W4206415959","doi":"10.1097/00001888-900000000-97702","title":"Ensuring the Quality of Multiple-Choice Tests","year":2019,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Quality (philosophy); MEDLINE; Computer science; Psychology; Political science; Law","score_opus":0.7559799505273994,"score_gpt":0.6478034277877435,"score_spread":0.10817652273965594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206415959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9777879,0.00027385345,0.009469621,0.004106185,0.0012622668,0.000838544,0.000015466485,0.00007867007,0.006167458],"genre_scores_gemma":[0.96861666,0.000081385006,0.028500794,0.0008424289,0.0008373122,0.000014394427,6.6671504e-7,0.000023977987,0.0010823502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99630123,0.0010328239,0.0014991971,0.00026551678,0.00065499736,0.00024623095],"domain_scores_gemma":[0.70192516,0.29693595,0.00047397052,0.00050221174,0.000085721964,0.00007697525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011730989,0.00014472089,0.00077368575,0.000037821774,0.00003111387,0.0000014633529,0.00050725555,0.00023653077,0.0006674626],"category_scores_gemma":[0.6028991,0.000078674464,0.00006605378,0.00020252046,0.0003575668,0.000030668463,0.00012572775,0.0008940931,0.000054769127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025880573,0.00005925665,0.43051654,0.001500874,0.00022546841,0.000002975358,0.0034571446,0.0000054793272,0.07002019,0.4598424,0.017798215,0.016312638],"study_design_scores_gemma":[0.0024058514,0.00013835306,0.08217745,0.0005724479,0.00009457145,0.0000032286998,0.00041310172,0.00017051166,0.002077033,0.90972805,0.0020697988,0.0001495777],"about_ca_topic_score_codex":0.000077287325,"about_ca_topic_score_gemma":0.00000345115,"teacher_disagreement_score":0.5911681,"about_ca_system_score_codex":0.000021886995,"about_ca_system_score_gemma":0.000025585763,"threshold_uncertainty_score":0.7308247},"labels":[],"label_agreement":null},{"id":"W4206518892","doi":"10.1016/j.jval.2021.11.040","title":"P42 Comparison of Estimation Methods for Single-Arm Trials in Rare Diseases with Historical Control Groups","year":2022,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Propensity score matching; Confidence interval; Confounding; Statistics; Estimator; Sample size determination; Randomization; Weighting; Medicine; Inverse probability weighting; Standard error; Coverage probability; Placebo; Type I and type II errors; Population; Mean squared error; Mathematics; Average treatment effect; Randomized controlled trial; Internal medicine","score_opus":0.7588654549010957,"score_gpt":0.6388849453975496,"score_spread":0.1199805095035461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206518892","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005808178,0.0008539742,0.9874778,0.0015971384,0.0007405426,0.0031373794,0.00030144962,0.00004829642,0.000035267443],"genre_scores_gemma":[0.18981831,0.0000064586884,0.80934155,0.0001310551,0.000080336176,0.00057268294,0.000007465999,0.000032435473,0.000009718053],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97336316,0.021065075,0.004120259,0.00047539297,0.0005345103,0.00044159553],"domain_scores_gemma":[0.7263369,0.27140406,0.0016541722,0.00036618012,0.00007842566,0.00016029799],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031712025,0.0001832748,0.0026043814,0.00024299834,0.000098785305,0.000011521871,0.00023257644,0.00008295539,0.000077048324],"category_scores_gemma":[0.23750795,0.00015654524,0.00018292808,0.0004943672,0.00006215146,0.000042713855,0.00005595753,0.00036546445,3.402958e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013950767,0.018782416,0.01680931,0.007186121,0.00019790711,0.000017954659,0.0036144012,0.075190924,0.000245838,0.4073402,0.0034140088,0.45325014],"study_design_scores_gemma":[0.0066443738,0.0040639485,0.00046882758,0.000247118,0.00010767412,0.0000025441311,0.00023729923,0.15968464,0.00008729696,0.8276915,0.0005744713,0.00019033134],"about_ca_topic_score_codex":0.00038151533,"about_ca_topic_score_gemma":0.000010943922,"teacher_disagreement_score":0.45305982,"about_ca_system_score_codex":0.0014746885,"about_ca_system_score_gemma":0.00032611756,"threshold_uncertainty_score":0.99705625},"labels":[],"label_agreement":null},{"id":"W4206654168","doi":"10.1055/s-0041-1733826","title":"Pharmacoeconomics","year":2021,"lang":"en","type":"article","venue":"Indian Journal of Medical and Paediatric Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Pertuzumab; Trastuzumab; Cancer drugs; Cancer; Lapatinib; Intensive care medicine; Breast cancer; Internal medicine","score_opus":0.31117710199269705,"score_gpt":0.5683089048943771,"score_spread":0.2571318029016801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206654168","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8204263,0.008154343,0.05184086,0.096393906,0.015723566,0.00028665483,0.000056817225,0.00004262633,0.007074969],"genre_scores_gemma":[0.1136003,0.013632955,0.85313976,0.007686057,0.011639802,0.0000048411366,9.039969e-7,0.000040231556,0.00025512374],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969374,0.001073229,0.0011876097,0.00014314154,0.00043732228,0.00022129838],"domain_scores_gemma":[0.9555834,0.04294766,0.0005485765,0.000100794925,0.00011646746,0.00070313225],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055200993,0.000102317186,0.0007159355,0.000094947296,0.00004025025,0.000017760962,0.00025880602,0.00038122069,0.002713423],"category_scores_gemma":[0.06458694,0.000078409445,0.00014456971,0.00015933637,0.0001825904,0.0000442495,0.000108698274,0.0008450317,0.00001237069],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001312975,0.0004232891,0.0016406649,0.00013011422,0.00018327229,0.013408459,0.00029939538,3.18017e-7,0.00002365846,0.023283605,0.018953703,0.94152224],"study_design_scores_gemma":[0.004098525,0.0006336498,0.0003291991,0.000052119598,0.00024456994,0.0071277884,0.00028325227,0.000045139546,0.00023166617,0.917492,0.069312476,0.00014966851],"about_ca_topic_score_codex":5.1470363e-7,"about_ca_topic_score_gemma":0.0000019463118,"teacher_disagreement_score":0.9413726,"about_ca_system_score_codex":0.00003358673,"about_ca_system_score_gemma":0.00092295016,"threshold_uncertainty_score":0.9981982},"labels":[],"label_agreement":null},{"id":"W4206744863","doi":"10.1128/aac.01627-21","title":"Secondary Analysis of a Systematic Review: Are Antifungal Noninferiority Trials at Risk of Eroding Effectiveness Because of Biocreep?","year":2021,"lang":"en","type":"review","venue":"Antimicrobial Agents and Chemotherapy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; McMaster University","funders":"","keywords":"Randomized controlled trial; Antifungal; Meta-analysis; Medicine; Sample size determination; Systematic review; MEDLINE; Internal medicine; Statistics; Biology; Mathematics","score_opus":0.45017736816912357,"score_gpt":0.55016297879332,"score_spread":0.09998561062419642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206744863","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004549279,0.9830368,0.0018095932,0.000011817605,0.00028491498,0.0042520794,0.006012278,0.000019072682,0.00002417509],"genre_scores_gemma":[0.000115031864,0.98158705,0.017925266,0.00008413318,0.000057363046,0.000052104344,0.000067043504,0.00007861007,0.00003337559],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98235506,0.010203834,0.0059711053,0.00073392387,0.00044717497,0.00028888774],"domain_scores_gemma":[0.9415186,0.04668429,0.010131079,0.0011369657,0.00042268663,0.000106355736],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.015266255,0.00068052654,0.024242578,0.00037929887,0.000071628536,0.00002452336,0.00047389662,0.0005559462,0.0005609748],"category_scores_gemma":[0.041295473,0.00048260344,0.0039048425,0.0013342008,0.0003065079,0.000041545303,0.00023387457,0.00040502514,0.0000014809642],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075505755,0.0004020423,0.0003521928,0.9591394,0.021421466,0.000008871963,0.00004471049,1.2705988e-7,0.00007640377,0.00011903589,0.0008114261,0.017548786],"study_design_scores_gemma":[0.0016375408,0.00013697418,0.0002667563,0.85618013,0.1370086,0.000011174513,0.000011529373,0.000006000267,0.0015189147,0.0005556644,0.002065192,0.00060153],"about_ca_topic_score_codex":0.000035738703,"about_ca_topic_score_gemma":0.000006449181,"teacher_disagreement_score":0.11558714,"about_ca_system_score_codex":0.000072277995,"about_ca_system_score_gemma":0.00016308662,"threshold_uncertainty_score":0.99976254},"labels":[],"label_agreement":null},{"id":"W4206897392","doi":"10.1002/sim.9317","title":"Response adaptive intervention allocation in stepped‐wedge cluster randomized trials","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Intervention (counseling); Randomized controlled trial; Cluster (spacecraft); Adaptability; Computer science; Medicine; Cluster randomised controlled trial; Research design; Risk analysis (engineering); Reliability engineering; Operations management; Statistics; Mathematics; Engineering; Nursing; Surgery","score_opus":0.5051541458839005,"score_gpt":0.5887984476152415,"score_spread":0.08364430173134096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206897392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00686227,0.00019316676,0.98349184,0.0025279596,0.001994271,0.003753854,0.00046033037,0.000046553403,0.00066975545],"genre_scores_gemma":[0.124927826,0.00007358928,0.8715321,0.00072386774,0.0002638263,0.0014241533,0.000050053306,0.000061539875,0.0009430399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9300193,0.061969593,0.00556605,0.00067045365,0.0012759751,0.00049860886],"domain_scores_gemma":[0.63574773,0.3626168,0.0009962231,0.00039841377,0.00014424296,0.00009654431],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14169292,0.00026041837,0.00270409,0.00054335,0.00008313631,0.000013107983,0.00033408494,0.00011403248,0.0030642226],"category_scores_gemma":[0.68957555,0.00021413251,0.00015772019,0.0006173889,0.000451469,0.00004751842,0.00022465452,0.0008388166,0.000014662091],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.45750085,0.0007589312,0.00008295803,0.00018272034,0.00016105929,0.00019044879,0.0028527586,0.00013490274,0.00013608228,0.47978234,0.02920063,0.02901633],"study_design_scores_gemma":[0.17626363,0.0006208569,0.00028772093,0.0002644007,0.000178215,0.0000051652482,0.0012244068,0.007475678,0.000019577843,0.81316304,0.00032167707,0.00017561625],"about_ca_topic_score_codex":0.00013864432,"about_ca_topic_score_gemma":0.00011759516,"teacher_disagreement_score":0.5478826,"about_ca_system_score_codex":0.00045323966,"about_ca_system_score_gemma":0.00010403233,"threshold_uncertainty_score":0.99784714},"labels":[],"label_agreement":null},{"id":"W4212803564","doi":"10.1111/jep.13669","title":"Attitudes towards open‐label versus placebo‐control designs in oncology randomized trials: A survey of medical oncologists","year":2022,"lang":"en","type":"article","venue":"Journal of Evaluation in Clinical Practice","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Placebo; Randomized controlled trial; Clinical trial; Clinical endpoint; Alternative medicine; Quality of life (healthcare); Research design; Family medicine; Physical therapy; Internal medicine; Nursing","score_opus":0.9347106082382033,"score_gpt":0.7699680953360512,"score_spread":0.16474251290215214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212803564","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22988872,0.0044012466,0.50005174,0.14134483,0.06009779,0.03787717,0.0005074245,0.000082272,0.025748823],"genre_scores_gemma":[0.4217118,0.00085767667,0.5749488,0.0014419464,0.00054302264,0.00043407807,0.0000033591884,0.000039092487,0.000020237403],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.2198469,0.73201174,0.03547386,0.0010837177,0.010773398,0.0008104028],"domain_scores_gemma":[0.01413973,0.9678589,0.014560089,0.0005229488,0.0025838318,0.0003344708],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8348282,0.00026389203,0.0064085727,0.000390204,0.00008591903,0.000065115775,0.0015928608,0.0006389432,0.0040650396],"category_scores_gemma":[0.99368465,0.00020601923,0.0005534727,0.00090412004,0.00058726146,0.00044252299,0.00066018855,0.003649766,0.0000071037994],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.84520316,0.012965057,0.0011736966,0.000055270746,0.0012264377,0.00029705273,0.00023024702,0.0005970383,0.0000062172203,0.010547626,0.004811655,0.122886516],"study_design_scores_gemma":[0.72875524,0.0065306937,0.0063146804,0.00019064892,0.0020342853,0.000076546545,0.00039770702,0.015528407,0.000004013825,0.2390739,0.0008525594,0.00024129849],"about_ca_topic_score_codex":0.0005400973,"about_ca_topic_score_gemma":0.00057442056,"teacher_disagreement_score":0.23584722,"about_ca_system_score_codex":0.0010227083,"about_ca_system_score_gemma":0.007522763,"threshold_uncertainty_score":0.9986489},"labels":[],"label_agreement":null},{"id":"W4213200746","doi":"10.2106/00004623-200601000-00006","title":"HOW MANY PATIENTS? HOW MANY LIMBS? ANALYSIS OF PATIENTS OR LIMBS IN THE ORTHOPAEDIC LITERATURE","year":2006,"lang":"en","type":"article","venue":"Journal of Bone and Joint Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Hamilton General Hospital; McMaster University; Juravinski Hospital; Western University","funders":"","keywords":"Medicine; Orthopedic surgery; Physical therapy; Cohort study; Psychological intervention; Cohort; Impact factor; Observational study; Clinical trial; Physical medicine and rehabilitation; Surgery; Internal medicine","score_opus":0.19537956523774144,"score_gpt":0.39446439068485895,"score_spread":0.1990848254471175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213200746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99278814,0.00043216473,0.004049835,0.001838204,0.00046896495,0.00022009377,0.00011961737,0.0000066916336,0.000076277065],"genre_scores_gemma":[0.9648579,0.0005037937,0.033716653,0.00027981677,0.0003582207,0.0000055220994,0.000010973111,0.000024611802,0.00024253118],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995249,0.0011669272,0.0021994393,0.00021045902,0.000886782,0.00028740786],"domain_scores_gemma":[0.97046083,0.0261305,0.002434595,0.00032195076,0.0005439925,0.000108127555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006814979,0.00022908916,0.001995672,0.00095384556,0.00005435491,0.00016720514,0.00008764517,0.00019835528,0.000051190127],"category_scores_gemma":[0.044001237,0.000126274,0.001000485,0.0012335196,0.00011708458,0.00022555914,0.000058872327,0.00053907454,4.621797e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00239963,0.009647898,0.87677765,0.0013653372,0.0018848812,0.00088766264,0.0009214515,0.000008044457,0.00007967435,0.0062414226,0.059894618,0.03989175],"study_design_scores_gemma":[0.0016827588,0.00079421926,0.9222689,0.00088122766,0.0016245976,0.000017392813,0.00020848359,0.00009446219,0.000071701266,0.070804395,0.0012820109,0.00026984286],"about_ca_topic_score_codex":0.000004746046,"about_ca_topic_score_gemma":0.000013414759,"teacher_disagreement_score":0.06456297,"about_ca_system_score_codex":0.000031893862,"about_ca_system_score_gemma":0.000051127932,"threshold_uncertainty_score":0.96405154},"labels":[],"label_agreement":null},{"id":"W4213371100","doi":"10.21203/rs.3.rs-72749/v1","title":"Highly Specific and Ultrasensitive Plasma Test Detects Abeta(1-42) and Abeta(1-40) in Alzheimer’s Disease","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"GIESKES-STRIJBIS FONDS; Amsterdam Neuroscience; Weston Brain Institute; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Alzheimer Nederland; ZonMw; European Commission; EU Joint Programme – Neurodegenerative Disease Research","keywords":"Biomarker; Internal medicine; Medicine; Molecular biology; Chemistry; Biochemistry; Biology","score_opus":0.6201465268939442,"score_gpt":0.5731417075215786,"score_spread":0.04700481937236567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213371100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92771065,0.012834674,0.0064004324,0.016102985,0.0016534207,0.017658869,0.011383091,0.0008123425,0.005443559],"genre_scores_gemma":[0.8430934,0.0029065956,0.15252799,0.000085071646,0.00079220405,0.00033359329,0.00003886702,0.00016643183,0.0000558565],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9897177,0.0040706065,0.0013734973,0.001966545,0.0017396306,0.0011319784],"domain_scores_gemma":[0.8507188,0.14606872,0.00028032655,0.0010842929,0.00049639883,0.0013514608],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007032529,0.000656693,0.0016936132,0.0004801222,0.00021064877,0.00038616627,0.00055033754,0.0006853034,0.00015055574],"category_scores_gemma":[0.18701366,0.00060815003,0.00020569873,0.00060236,0.0012266203,0.00008587668,0.002102639,0.0039564245,0.00009651698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020204466,0.009242134,0.076211244,0.051502015,0.00414116,0.03238224,0.00993773,0.00011903575,0.009809447,0.2775344,0.044305917,0.46461022],"study_design_scores_gemma":[0.0023046217,0.00052911224,0.051772397,0.002793412,0.00023739217,0.000009018684,0.0003467535,0.0026545695,0.0022787394,0.9356971,0.0005352587,0.0008416569],"about_ca_topic_score_codex":0.000086840024,"about_ca_topic_score_gemma":0.000046303554,"teacher_disagreement_score":0.65816265,"about_ca_system_score_codex":0.00017281639,"about_ca_system_score_gemma":0.00042429657,"threshold_uncertainty_score":0.999637},"labels":[],"label_agreement":null},{"id":"W4214485800","doi":"10.1177/01632787211070811","title":"A Randomization Permutation Test for Single Subject Mediation","year":2022,"lang":"en","type":"article","venue":"Evaluation & the Health Professions","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute on Drug Abuse","keywords":"Mediation; Resampling; Permutation (music); Type I and type II errors; Confidence interval; Test (biology); Randomization; Statistical hypothesis testing; Statistics; Outcome (game theory); Computer science; Mathematics; Clinical trial; Medicine; Internal medicine","score_opus":0.7565974041509078,"score_gpt":0.6584428920063305,"score_spread":0.09815451214457727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214485800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008562353,0.00018903923,0.89281166,0.07438777,0.0044249343,0.018119955,0.00042564634,0.00025248033,0.0008261961],"genre_scores_gemma":[0.6509285,0.000022818567,0.3276032,0.0037110266,0.0008475527,0.015641699,0.0002914866,0.000087218614,0.0008665428],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9874736,0.009509759,0.0012166203,0.00032528932,0.0011563109,0.00031840033],"domain_scores_gemma":[0.88197315,0.11580734,0.0011138272,0.00043338275,0.0005646963,0.00010759819],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037128557,0.00013537442,0.0003731159,0.00010124218,0.0020804692,0.000025633086,0.00021611826,0.00006826609,0.0010845624],"category_scores_gemma":[0.23153877,0.0000981476,0.000114267226,0.00048380665,0.000054694774,0.000083350205,0.000095064264,0.00034249414,0.000012674925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005345313,0.0056189587,0.001207629,0.0013637774,0.00025148495,0.0000011709582,0.04484345,0.005972622,0.0044907467,0.32650524,0.22310637,0.38129324],"study_design_scores_gemma":[0.006456613,0.00059533684,0.0004973201,0.0000484801,0.00013363923,0.0000027594122,0.0019920194,0.061877996,0.000100007834,0.92705685,0.0011049968,0.00013399957],"about_ca_topic_score_codex":0.000008029157,"about_ca_topic_score_gemma":0.0000145247195,"teacher_disagreement_score":0.6423661,"about_ca_system_score_codex":0.0005595015,"about_ca_system_score_gemma":0.00085168664,"threshold_uncertainty_score":0.9998286},"labels":[],"label_agreement":null},{"id":"W4214522216","doi":"10.1002/cjs.11695","title":"Penalized likelihood ratio test for a biomarker threshold effect in clinical trials based on generalized linear models","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Likelihood-ratio test; Mathematics; Covariate; Score test; Generalized linear model; Test statistic; Statistics; Poisson distribution; Null hypothesis; Asymptotic distribution; Statistical hypothesis testing; Logistic regression; Likelihood function; Homogeneity (statistics); Applied mathematics; Estimation theory","score_opus":0.5768239438874719,"score_gpt":0.5500446198563916,"score_spread":0.026779324031080298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214522216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055339085,0.00008845906,0.9776269,0.0010861031,0.0025327818,0.0020765977,0.010724719,0.000013853416,0.0003166845],"genre_scores_gemma":[0.09328125,0.000013972797,0.9040475,0.001663101,0.0006017101,0.00015477427,0.00003579563,0.00010495788,0.00009694829],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9836859,0.008609177,0.0058167474,0.00041506405,0.0008121133,0.00066101627],"domain_scores_gemma":[0.7253917,0.2701471,0.002328769,0.00053591654,0.0005194181,0.0010771172],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0722392,0.0003570062,0.0026525303,0.00059828884,0.00025811137,0.0000967964,0.00065005425,0.00021633667,0.0013288304],"category_scores_gemma":[0.4537541,0.0002973461,0.00070209475,0.00042566605,0.00019768778,0.000065795975,0.000037899295,0.0010782867,0.000005128739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014560528,0.0021058484,0.009967028,0.00080494117,0.0010434672,0.0031534515,0.00041110112,0.017163068,0.00027514182,0.3654909,0.50939906,0.07562546],"study_design_scores_gemma":[0.012541784,0.0030313975,0.0002898829,0.00011755251,0.0003737314,0.000016044482,0.000029131494,0.2656078,0.000050594204,0.7160633,0.0015764785,0.00030227326],"about_ca_topic_score_codex":0.00020539903,"about_ca_topic_score_gemma":0.0011419837,"teacher_disagreement_score":0.5078226,"about_ca_system_score_codex":0.0004276035,"about_ca_system_score_gemma":0.003054372,"threshold_uncertainty_score":0.99994785},"labels":[],"label_agreement":null},{"id":"W4214694118","doi":"10.2165/00128415-200510600-00003","title":"Canadian Depo-Provera label updated with risk of BMD loss","year":2005,"lang":"en","type":"article","venue":"Reactions Weekly","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Gynecology","score_opus":0.25921033267680466,"score_gpt":0.48286728202167195,"score_spread":0.2236569493448673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214694118","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48961997,0.00012018649,0.382758,0.011132409,0.0015372384,0.0024133637,0.002656843,0.0006177694,0.10914423],"genre_scores_gemma":[0.18014339,0.0000622036,0.816853,0.000068207046,0.00022413254,0.000021825866,0.0000051439897,0.000038604645,0.0025835226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982495,0.0002966353,0.0006642313,0.00024923793,0.00024349848,0.00029690147],"domain_scores_gemma":[0.9923703,0.0062745092,0.00034749293,0.0005357397,0.00019425177,0.0002777187],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010050586,0.0001490892,0.0003917271,0.00012294685,0.00011768627,0.000016857897,0.00017319422,0.00015192293,0.0008262945],"category_scores_gemma":[0.015321842,0.00012108517,0.00006960841,0.00034375914,0.00010017036,0.00009027553,0.000020532698,0.00035288872,0.0001278631],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008713517,0.0033074967,0.03410729,0.00047316274,0.0020794428,0.00013882239,0.0005500561,0.00019196104,0.003669394,0.6083225,0.1310555,0.21523304],"study_design_scores_gemma":[0.0048038242,0.00072600256,0.0119502535,0.00025566458,0.0013284927,0.00012423225,0.00029311082,0.0033458234,0.0070558474,0.8098298,0.15928449,0.0010024816],"about_ca_topic_score_codex":0.025381463,"about_ca_topic_score_gemma":0.065803476,"teacher_disagreement_score":0.43409497,"about_ca_system_score_codex":0.0002023502,"about_ca_system_score_gemma":0.00025161763,"threshold_uncertainty_score":0.9929725},"labels":[],"label_agreement":null},{"id":"W4214947828","doi":"10.5430/jha.v10n6p34","title":"In vitro diagnostic tests: Ensuring test accuracy and patient safety when used as companion diagnostics","year":2022,"lang":"en","type":"article","venue":"Journal of Hospital Administration","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Medicine; Documentation; Patient safety; Medical physics; Adverse effect; Intensive care medicine; Health care; Medical emergency; Computer science; Pharmacology","score_opus":0.13433963109243355,"score_gpt":0.4408524147442388,"score_spread":0.30651278365180523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214947828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931948,0.0001746629,0.0017928429,0.0028161635,0.0011895074,0.0005401172,0.00013362282,0.000016492048,0.0001417593],"genre_scores_gemma":[0.9075551,0.00011670843,0.09186736,0.00018686248,0.0002139636,0.00002320805,0.0000034166894,0.000023755762,0.000009630397],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966221,0.0005579756,0.0016726044,0.0002120138,0.00071320636,0.00022210527],"domain_scores_gemma":[0.84953725,0.14870685,0.0012235466,0.00019189263,0.00016875257,0.00017170318],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018288246,0.00018436933,0.0005495888,0.0001150758,0.000143714,0.000075886404,0.00019749218,0.000071399656,0.00017144646],"category_scores_gemma":[0.31728488,0.00017144874,0.00010331199,0.00016148933,0.000079118305,0.0002552584,0.00014693357,0.00062962837,0.0000036646366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011825217,0.0847863,0.39973202,0.0020697794,0.0011722915,0.021354653,0.036558017,0.0005993762,0.024140848,0.1717662,0.04940315,0.19659212],"study_design_scores_gemma":[0.003369208,0.02292118,0.027052358,0.00026393248,0.00019098865,0.00039054643,0.001659537,0.00022449915,0.009561721,0.9325486,0.001309132,0.0005082946],"about_ca_topic_score_codex":0.0000069527146,"about_ca_topic_score_gemma":0.0000036895676,"teacher_disagreement_score":0.7607824,"about_ca_system_score_codex":0.00019713139,"about_ca_system_score_gemma":0.00017419936,"threshold_uncertainty_score":0.6991477},"labels":[],"label_agreement":null},{"id":"W4220825028","doi":"10.21203/rs.3.rs-1195468/v1","title":"Practical Guidance for Running Late-Phase Platform Protocols for Clinical Trials: Lessons From Experienced UK Clinical Trials Units","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"Health Technology Assessment Programme; Medical Research Council; National Institute for Health and Care Research; Schweizerische Arbeitsgemeinschaft für Klinische Krebsforschung; Cancer Research UK","keywords":"Clinical trial; Phase (matter); Medical physics; Computer science; Medicine; Pathology","score_opus":0.9850195401990167,"score_gpt":0.8458956437897659,"score_spread":0.13912389640925082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220825028","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006252376,0.00028849265,0.7074653,0.0053537134,0.0061947056,0.24567062,0.027738517,0.0004971601,0.00053914223],"genre_scores_gemma":[0.0016193029,0.0003627995,0.7100859,0.0001921946,0.008080849,0.27813068,0.00054202136,0.0003260806,0.00066015375],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7939194,0.15314393,0.035358965,0.0066960133,0.006866024,0.0040157135],"domain_scores_gemma":[0.14216474,0.8402446,0.007388733,0.0041309185,0.0043524927,0.0017185366],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.6147422,0.0012391486,0.012341459,0.0005470779,0.0012868342,0.0010084818,0.0032804622,0.0038227744,0.004176499],"category_scores_gemma":[0.9842302,0.0010240634,0.0047410885,0.0010578951,0.0017052864,0.0002374019,0.0048394334,0.0110630635,0.000045485172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09628096,0.011545579,0.00092276535,0.0074944873,0.0041512037,0.00027834426,0.0013644041,0.00003270836,0.00015325598,0.26045668,0.38331103,0.23400857],"study_design_scores_gemma":[0.027347863,0.00618588,0.00010024511,0.0033541303,0.0007901599,0.0000023361517,0.0018929744,0.007967448,0.00040999366,0.8633971,0.087387614,0.0011642226],"about_ca_topic_score_codex":0.0000619377,"about_ca_topic_score_gemma":0.000023376957,"teacher_disagreement_score":0.68710065,"about_ca_system_score_codex":0.0006653806,"about_ca_system_score_gemma":0.007443453,"threshold_uncertainty_score":0.99922097},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4220832872","doi":"10.1002/psp4.12775","title":"Trapezoid bioequivalence: A rational bioavailability evaluation approach on account of the pharmaceutical‐driven balance of population average and variability","year":2022,"lang":"en","type":"article","venue":"CPT Pharmacometrics & Systems Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Bioequivalence; Context (archaeology); Bioavailability; Population; Econometrics; Statistics; Mathematics; Variance (accounting); Weighting; Pharmacology; Medicine; Economics; Accounting; Geography","score_opus":0.44227961583645825,"score_gpt":0.543427230074723,"score_spread":0.1011476142382648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220832872","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95892316,0.0006146722,0.022738557,0.0005746766,0.007180072,0.007167834,0.0016835488,0.000089780355,0.001027719],"genre_scores_gemma":[0.98798573,0.00007499387,0.010677965,0.00025702425,0.00024890443,0.0006704119,0.000020008487,0.000033331347,0.000031604006],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98374546,0.01100747,0.0021241945,0.0007974243,0.001923745,0.00040170443],"domain_scores_gemma":[0.96555465,0.031615607,0.0014856992,0.0005643138,0.00061697495,0.00016275006],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022292502,0.00032105958,0.0010474423,0.0004672396,0.00030688464,0.000021123577,0.0007576815,0.00015836018,0.0011834988],"category_scores_gemma":[0.018358592,0.00026108016,0.00023667376,0.002576444,0.0005992409,0.0001130485,0.0004781204,0.0008482747,0.0000018851684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071583693,0.02375311,0.24205992,0.015545433,0.0034241027,0.0000142505,0.0021861154,0.07203267,0.36491716,0.20976782,0.020674028,0.03846703],"study_design_scores_gemma":[0.014418288,0.00085465156,0.027949711,0.000079783444,0.0027527162,0.00005440696,0.00019353305,0.82212263,0.020276552,0.10810904,0.0022780448,0.0009106155],"about_ca_topic_score_codex":0.000033255023,"about_ca_topic_score_gemma":1.2021725e-7,"teacher_disagreement_score":0.75009,"about_ca_system_score_codex":0.00054498494,"about_ca_system_score_gemma":0.00020778648,"threshold_uncertainty_score":0.99998415},"labels":[],"label_agreement":null},{"id":"W4223957058","doi":"10.1038/s41598-022-09921-3","title":"A quantitative approach to the spread of variance in translational research using Monte Carlo simulation","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"National Eye Institute; Canadian Institutes of Health Research; National Institutes of Health; Canada Research Chairs","keywords":"Sample size determination; Monte Carlo method; Computer science; Variance (accounting); Statistical power; Sample (material); Statistics; Statistical physics; Mathematics; Physics","score_opus":0.8138005483659161,"score_gpt":0.6331666631537534,"score_spread":0.18063388521216273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223957058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48841044,0.00006733437,0.5029584,0.0003831484,0.0034474758,0.002301566,0.00006769531,0.000025087404,0.0023388239],"genre_scores_gemma":[0.5936347,8.788862e-8,0.4060718,0.000006548842,0.000023710816,0.000058759226,0.000001058637,0.000008661237,0.00019465534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941652,0.0022462364,0.001098922,0.0005911926,0.0016337297,0.0002647199],"domain_scores_gemma":[0.9788858,0.019624392,0.00033384128,0.00072241627,0.00037405358,0.000059481237],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03649918,0.00007957388,0.0002858381,0.00024333881,0.00039374636,0.00005947451,0.00023883746,0.000036971058,0.00008941923],"category_scores_gemma":[0.047457747,0.000062885505,0.00007411295,0.0018241807,0.00028132394,0.0000640882,0.00015789129,0.0003412775,0.0000014027306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018466583,0.0005291516,0.0009051694,0.00008240737,0.000027282746,0.000046019988,0.0067407754,0.9110183,0.0021991124,0.075546525,0.0012252732,0.001495318],"study_design_scores_gemma":[0.00012407031,0.000046485507,0.00041686321,0.000026578287,0.00001153356,0.000009247292,0.0005778272,0.2889998,0.00016654439,0.70892787,0.00062386715,0.000069340495],"about_ca_topic_score_codex":0.00009370996,"about_ca_topic_score_gemma":0.000019527452,"teacher_disagreement_score":0.6333813,"about_ca_system_score_codex":0.000087729335,"about_ca_system_score_gemma":0.00022488277,"threshold_uncertainty_score":0.9921268},"labels":[],"label_agreement":null},{"id":"W4223973975","doi":"10.1002/cjs.11699","title":"Estimating design operating characteristics in Bayesian adaptive clinical trials","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Context (archaeology); Adaptive design; Clinical trial; Computer science; Sequential analysis; Coronavirus disease 2019 (COVID-19); Machine learning; Artificial intelligence; Operations research; Medicine; Statistics; Mathematics; Disease; Geography","score_opus":0.755651736606096,"score_gpt":0.5781911638527113,"score_spread":0.17746057275338467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223973975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020966385,0.0000535265,0.9916551,0.0002540207,0.003599202,0.0005519809,0.0015974707,0.000010090751,0.00018197122],"genre_scores_gemma":[0.11770186,0.000007373476,0.8810257,0.00032362068,0.0008097862,0.000020260064,0.0000042658357,0.000059327213,0.000047852427],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97838604,0.013638487,0.006391179,0.00032202995,0.00063510594,0.000627146],"domain_scores_gemma":[0.80499774,0.18837357,0.0041273055,0.00044502923,0.00065099326,0.0014053832],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06413665,0.0002762842,0.002145249,0.00042571183,0.00038144883,0.00012358383,0.0006367991,0.0001501358,0.001614567],"category_scores_gemma":[0.49763513,0.00026691056,0.00023549626,0.000419003,0.0002533339,0.00009713243,0.000077093566,0.0018624688,0.000005988555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009875247,0.00068208657,0.023093602,0.0002679891,0.0008166585,0.012155758,0.0033491447,0.006262061,0.000056126806,0.39860845,0.08049932,0.4732213],"study_design_scores_gemma":[0.0024042358,0.0015289139,0.0024243086,0.00024227297,0.00030044236,0.0002408762,0.0007439108,0.09570954,0.000011265467,0.8953925,0.0005550971,0.0004466848],"about_ca_topic_score_codex":0.00035072854,"about_ca_topic_score_gemma":0.00057038903,"teacher_disagreement_score":0.49678403,"about_ca_system_score_codex":0.00052524515,"about_ca_system_score_gemma":0.0036850874,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W4224861098","doi":"10.5539/jmr.v14n3p1","title":"Identification of Maximum Safe Dose Based on Ratio of Normally Distributed Data under Heteroscedasticity","year":2022,"lang":"en","type":"article","venue":"Journal of Mathematics Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Heteroscedasticity; Mathematics; Confidence interval; Homogeneity (statistics); Statistics; Sample size determination; Population; Variance (accounting); Econometrics; Medicine","score_opus":0.7813520910010063,"score_gpt":0.6307216090813719,"score_spread":0.15063048191963446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224861098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07177359,0.000018509254,0.92478,0.0006926278,0.00032733186,0.00060670933,0.0015040956,0.000009204007,0.00028794006],"genre_scores_gemma":[0.63020796,0.000012897245,0.36954662,0.000022822853,0.00008757298,0.000012929202,0.000014199322,0.00003478139,0.0000602242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894725,0.0028417977,0.0034000757,0.00026645671,0.003674885,0.00034430562],"domain_scores_gemma":[0.9348444,0.05998707,0.0022668613,0.0014141434,0.001332505,0.00015507027],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03748893,0.00016010796,0.0009251803,0.0004377154,0.00017185703,0.000046946,0.0018520384,0.0000971814,0.00072392356],"category_scores_gemma":[0.1260975,0.00013205844,0.00019324632,0.0007026387,0.00033696514,0.0001261485,0.0007522539,0.0011375626,0.0000065542395],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077468446,0.045170367,0.0008365097,0.013682282,0.0018668358,0.00024766914,0.0021675657,0.036367025,0.24800958,0.59081566,0.042520914,0.010568726],"study_design_scores_gemma":[0.0019015664,0.0013085592,0.00048934843,0.00028493546,0.00013968332,0.000021393897,0.00075118564,0.09531146,0.0150633855,0.8845228,0.000061278195,0.00014437975],"about_ca_topic_score_codex":0.0000040500627,"about_ca_topic_score_gemma":0.0000015691395,"teacher_disagreement_score":0.55843437,"about_ca_system_score_codex":0.00019026487,"about_ca_system_score_gemma":0.00045796577,"threshold_uncertainty_score":0.9911077},"labels":[],"label_agreement":null},{"id":"W4225282897","doi":"10.1016/j.respe.2022.03.064","title":"Performances de méthodes de sélection de variables en présence de risques compétitifs : une étude de simulation","year":2022,"lang":"fr","type":"article","venue":"Revue d Épidémiologie et de Santé Publique","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Humanities; Physics; Gynecology; Philosophy; Medicine","score_opus":0.333810114509006,"score_gpt":0.5376623575554921,"score_spread":0.20385224304648608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225282897","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1847849,0.00094747695,0.8044015,0.005030383,0.0013244877,0.00083869393,0.00029294493,0.00041308737,0.001966522],"genre_scores_gemma":[0.4146893,0.0024928765,0.57924414,0.0016274414,0.0011409053,0.00035141382,0.000021752294,0.000077334975,0.000354815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96711576,0.027775798,0.0017673043,0.00090277864,0.00038944077,0.0020489295],"domain_scores_gemma":[0.8620206,0.13552517,0.00092583086,0.00075205276,0.0002907104,0.0004856352],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046382915,0.00059018366,0.001324986,0.00028490866,0.00063551456,0.00028811453,0.0010882156,0.0010207149,0.00073926325],"category_scores_gemma":[0.22490108,0.00064375065,0.00038082706,0.0009490688,0.0004433106,0.0004650059,0.0005974934,0.0024523302,0.000015516056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006487877,0.0011502788,0.124201864,0.002384012,0.0003792347,0.00022604276,0.0052048946,0.5033781,0.0034989126,0.32151034,0.0038785322,0.033539023],"study_design_scores_gemma":[0.00052893267,0.00051728974,0.027791707,0.00039119477,0.00024634766,0.0002850453,0.00058859325,0.40454313,0.0015923401,0.56066304,0.0023849611,0.00046744256],"about_ca_topic_score_codex":0.0011993585,"about_ca_topic_score_gemma":0.00012962749,"teacher_disagreement_score":0.23915268,"about_ca_system_score_codex":0.004922066,"about_ca_system_score_gemma":0.0035290932,"threshold_uncertainty_score":0.9998491},"labels":[],"label_agreement":null},{"id":"W4225575052","doi":"10.1371/journal.pone.0262114","title":"How informative were early SARS-CoV-2 treatment and prevention trials? a longitudinal cohort analysis of trials registered on ClinicalTrials.gov","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Narodowe Centrum Nauki","keywords":"Medicine; Clinical trial; Cohort; Cohort study; Confidence interval; Internal medicine","score_opus":0.8767356703854782,"score_gpt":0.5903454968283405,"score_spread":0.2863901735571377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225575052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98478836,0.000082085164,0.0071097733,0.00086648547,0.0002510956,0.0045640753,0.0016289378,0.00008904661,0.0006201204],"genre_scores_gemma":[0.6755796,0.00042421324,0.32028246,0.00014303294,0.00053448335,0.0014835515,0.000081275975,0.000074065996,0.0013972993],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9792702,0.012951596,0.0053105,0.0007428585,0.0013499315,0.00037491575],"domain_scores_gemma":[0.8467369,0.1461646,0.005528002,0.0011587393,0.0002638897,0.00014783393],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041500904,0.0003884677,0.006679937,0.0005071508,0.00019203927,0.0001253719,0.0003120633,0.00021309867,0.00040744984],"category_scores_gemma":[0.29754135,0.0003015242,0.0013337821,0.0008603641,0.0002131199,0.00014889325,0.00021179671,0.00039815405,0.000005773068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.093659155,0.073495716,0.087965205,0.0027830133,0.39819616,0.00012174499,0.0060071293,0.000035569497,0.031514157,0.18953842,0.005612835,0.111070886],"study_design_scores_gemma":[0.028892973,0.02325872,0.0236273,0.00072030036,0.123413816,0.0000031735592,0.00050296984,0.00093691965,0.054032527,0.74311537,0.00033239726,0.0011635114],"about_ca_topic_score_codex":0.000055561908,"about_ca_topic_score_gemma":0.000025035015,"teacher_disagreement_score":0.55357695,"about_ca_system_score_codex":0.00024644652,"about_ca_system_score_gemma":0.00011748008,"threshold_uncertainty_score":0.9999437},"labels":[],"label_agreement":null},{"id":"W4225639596","doi":"10.2139/ssrn.4077740","title":"Subgroup Analyses in Randomised Controlled Trials Frequently Categorise Continuous Subgroup Information","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Subgroup analysis; Continuous variable; Categorical variable; Medicine; Sample size determination; Randomized controlled trial; Statistics; Mathematics; Internal medicine; Meta-analysis","score_opus":0.29665572459186607,"score_gpt":0.505947069141978,"score_spread":0.2092913445501119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225639596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3140183,0.005410997,0.65962654,0.0022692415,0.004097806,0.009273727,0.00017416188,0.00029781938,0.004831387],"genre_scores_gemma":[0.97337353,0.0015142852,0.022832979,0.00035834347,0.0006707889,0.0006727447,0.000017076634,0.00006347531,0.00049674587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97697604,0.013212499,0.0056054755,0.00033712067,0.0012766398,0.0025922107],"domain_scores_gemma":[0.9140406,0.08133109,0.0036010584,0.0004974569,0.00029830303,0.00023148736],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0947191,0.00038556635,0.0036831617,0.00059815746,0.00038949715,0.00017814612,0.00067000435,0.00016548358,0.0010216375],"category_scores_gemma":[0.20882969,0.0002932376,0.0011539815,0.00066956156,0.00008918745,0.0004130313,0.00012320772,0.0038724577,0.000024453839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05257046,0.00089121994,0.00057327957,0.000054124197,0.002685452,0.000058557016,0.000806557,0.0003034331,0.0012812897,0.9008926,0.0014410906,0.038441908],"study_design_scores_gemma":[0.117578894,0.0006203735,0.000050894152,0.000016379272,0.0006233801,0.0001334212,0.002564955,0.00046939164,0.00008495007,0.8772991,0.00026899492,0.00028926996],"about_ca_topic_score_codex":0.00014911532,"about_ca_topic_score_gemma":0.00015231081,"teacher_disagreement_score":0.6593552,"about_ca_system_score_codex":0.0018265354,"about_ca_system_score_gemma":0.0019072247,"threshold_uncertainty_score":0.99995196},"labels":[],"label_agreement":null},{"id":"W4226051615","doi":"10.1093/jnci/djac067","title":"The Futility of Futility Analyses in Adjuvant Trials in Hormone Receptor–Positive Breast Cancer","year":2022,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Queen's University; Statistics Canada; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Western University","funders":"","keywords":"Interim analysis; Interim; Breast cancer; Clinical trial; Medicine; Adjuvant; Oncology; Cancer; Hormone receptor; Internal medicine; Intensive care medicine; Gynecology; Political science","score_opus":0.728041108609859,"score_gpt":0.6365238527165834,"score_spread":0.09151725589327564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226051615","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9443926,0.0054076635,0.0018990862,0.023655048,0.012751032,0.0018664483,0.009072487,0.000015678017,0.00093994313],"genre_scores_gemma":[0.9878283,0.0007086535,0.010094392,0.00032304903,0.0008571921,0.00011193411,0.0000013120675,0.000014070567,0.00006105986],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98955613,0.004920116,0.0031700307,0.00022291548,0.0018851378,0.00024564698],"domain_scores_gemma":[0.96737766,0.028663581,0.002696745,0.00023742857,0.0009482384,0.000076323326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027183946,0.000173117,0.0011858677,0.00017162737,0.00023792987,0.000024228913,0.00083577994,0.000081055296,0.00039144396],"category_scores_gemma":[0.077370726,0.00009915815,0.000490095,0.0009674969,0.00040208246,0.00017440645,0.0002616972,0.0009839103,4.739042e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07772775,0.009050492,0.12620993,0.00079457817,0.0068298047,0.00010560676,0.006267261,0.07808768,0.04099155,0.22837836,0.11292468,0.3126323],"study_design_scores_gemma":[0.004144095,0.00014292689,0.3860569,0.00030182474,0.00027917064,0.000031993863,0.0003057016,0.00047909256,0.0023503571,0.6027327,0.0029586828,0.00021650553],"about_ca_topic_score_codex":0.000589351,"about_ca_topic_score_gemma":0.000903229,"teacher_disagreement_score":0.3743544,"about_ca_system_score_codex":0.0015708981,"about_ca_system_score_gemma":0.0015057302,"threshold_uncertainty_score":0.9421467},"labels":[],"label_agreement":null},{"id":"W4229024550","doi":"10.1093/biostatistics/kxac029","title":"A flexible approach for predictive biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Computer science; False positive paradox; Estimator; Inference; Identification (biology); Nonparametric statistics; False positives and false negatives; Metric (unit); Biomarker discovery; Multiple comparisons problem; Predictive inference; Biomarker; Data mining; False discovery rate; Truncation (statistics); Machine learning; Artificial intelligence; Statistics; Frequentist inference; Mathematics; Bayesian probability; Bayesian inference","score_opus":0.5564742844991701,"score_gpt":0.5379670415846817,"score_spread":0.018507242914488464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229024550","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002054326,0.000036215206,0.9808348,0.00011647489,0.00087976444,0.001298468,0.012697919,0.00015194195,0.003778973],"genre_scores_gemma":[0.017495252,0.0000060027096,0.9787448,0.000253806,0.0002067643,0.0008528697,0.00010460835,0.00007007119,0.0022658494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997259,0.00060254283,0.0007280234,0.0004941092,0.00051097816,0.00040531665],"domain_scores_gemma":[0.96538717,0.033646982,0.00028447926,0.0004508413,0.0001112302,0.00011932063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023526617,0.00021546865,0.00050689775,0.00008806228,0.0003520396,0.000065288696,0.00035502817,0.00008013376,0.00027379327],"category_scores_gemma":[0.044077322,0.00020128555,0.00015261101,0.00029862364,0.00018862993,0.00006244162,0.00031454355,0.00024870882,0.0000045918005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009384062,0.00078870193,0.00014564168,0.00029305377,0.00021288129,0.000011367391,0.00015883976,0.000063853826,0.00023309197,0.8488368,0.13774206,0.010575344],"study_design_scores_gemma":[0.0013284115,0.00056383415,0.0002771264,0.000008812118,0.00019764883,0.000009783034,0.00032922497,0.016282814,0.00026673943,0.97274876,0.007691543,0.0002953025],"about_ca_topic_score_codex":0.0000057634015,"about_ca_topic_score_gemma":3.0804776e-7,"teacher_disagreement_score":0.13005051,"about_ca_system_score_codex":0.00014212095,"about_ca_system_score_gemma":0.000120657394,"threshold_uncertainty_score":0.96397483},"labels":[],"label_agreement":null},{"id":"W4229505696","doi":"10.1002/0470011815.b2a09032","title":"Multiple Comparisons","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Encyclopedia; Citation; Library science; Information retrieval; Computer science","score_opus":0.26345245358521446,"score_gpt":0.49223434116298875,"score_spread":0.2287818875777743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229505696","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001406224,0.00026152717,0.2891884,0.000057159516,0.0014373289,0.00057096663,0.00557438,0.0002277786,0.702681],"genre_scores_gemma":[0.000013587132,0.0010532652,0.6674164,0.000040686195,0.0010913282,0.000018954297,0.00003361122,0.0004980658,0.32983413],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99657166,0.0004328143,0.0014502358,0.0005111835,0.0006083545,0.00042573415],"domain_scores_gemma":[0.96051407,0.037055865,0.0012424588,0.00087288226,0.0000988949,0.00021583754],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007621288,0.00048836594,0.0016135236,0.00023360964,0.00003228129,0.000013643996,0.0005194206,0.0006575688,0.012502585],"category_scores_gemma":[0.073828995,0.00045365206,0.00019305349,0.00021367785,0.00043205716,0.000014257479,0.00016296013,0.0005123365,0.00032850492],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019967629,0.00025924176,0.00021790086,0.00041781194,0.00013793717,0.000014393229,0.000031125106,2.684851e-7,0.000002142011,0.06772928,0.9061634,0.02500654],"study_design_scores_gemma":[0.0007672809,0.000098100354,0.00011689938,0.00035621398,0.00032528673,0.0000021448814,0.000021095992,0.00009488135,0.000023080313,0.1039797,0.893741,0.00047430917],"about_ca_topic_score_codex":0.000085384934,"about_ca_topic_score_gemma":0.00019521925,"teacher_disagreement_score":0.37822795,"about_ca_system_score_codex":0.000039297407,"about_ca_system_score_gemma":0.00012861135,"threshold_uncertainty_score":0.9997915},"labels":[],"label_agreement":null},{"id":"W4230212973","doi":"10.1002/0470011815.b2a04035","title":"Pharmacoepidemiology, Overview","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pharmacoepidemiology; Observational study; Confounding; Context (archaeology); Medicine; Medical prescription; Randomized controlled trial; Causality (physics); Intensive care medicine; Pharmacology; Internal medicine; Geography","score_opus":0.4083885934717475,"score_gpt":0.5661111938450196,"score_spread":0.15772260037327213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230212973","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.242691e-7,0.003178486,0.11182916,0.00019581507,0.0024819295,0.00074171065,0.0055284565,0.0002716451,0.87577206],"genre_scores_gemma":[0.0000010710016,0.021341907,0.6546831,0.00022880684,0.0017044886,0.00002396882,0.000027648965,0.00049989927,0.32148913],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953825,0.0011786281,0.001868296,0.0006007994,0.0004779392,0.0004918394],"domain_scores_gemma":[0.9486031,0.048587818,0.0016588933,0.0008233853,0.00009411332,0.00023269681],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021321254,0.0005547626,0.0021012046,0.0002317568,0.000025877125,0.0000074325917,0.0005888595,0.0007856171,0.03234557],"category_scores_gemma":[0.099045195,0.0004920686,0.0002556322,0.00023108721,0.0005023482,0.000016652297,0.00019426235,0.00060775934,0.00037228645],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000141332075,0.00013658043,0.00003465304,0.00080747093,0.00016395125,0.000017095981,0.000015745974,1.0651142e-7,0.0000018547571,0.15928179,0.7700592,0.0694674],"study_design_scores_gemma":[0.00045907777,0.00007015747,0.000028028691,0.0004093309,0.00039643035,0.0000031654151,0.0000049076107,0.000018997418,0.000010998627,0.3023477,0.69589555,0.00035565783],"about_ca_topic_score_codex":0.000063018255,"about_ca_topic_score_gemma":0.000037372676,"teacher_disagreement_score":0.55428296,"about_ca_system_score_codex":0.000042943895,"about_ca_system_score_gemma":0.00013943792,"threshold_uncertainty_score":0.9997531},"labels":[],"label_agreement":null},{"id":"W4231132425","doi":"10.1002/0470011815.b2a15081","title":"Loss Function","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Minimax; Frequentist inference; Decision theory; Bayesian probability; Function (biology); Computer science; Econometrics; Mathematics; Mathematical economics; Statistics; Bayesian inference","score_opus":0.1799803768011715,"score_gpt":0.47104558435221394,"score_spread":0.2910652075510425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231132425","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001389438,0.0002371907,0.2952416,0.000048533297,0.0021948179,0.00043397723,0.002457346,0.00020202721,0.6991831],"genre_scores_gemma":[0.0000069680877,0.0014446971,0.5931199,0.000054074306,0.0016802114,0.000015048424,0.000025092724,0.00044412387,0.40320984],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969434,0.00036993067,0.0012373759,0.00048514077,0.0006076562,0.00035647533],"domain_scores_gemma":[0.9811135,0.016720096,0.0011326555,0.000757325,0.000107759864,0.00016867448],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008345839,0.00043471085,0.0011897642,0.00023137237,0.000026335329,0.000012289238,0.0003512859,0.000696335,0.02110708],"category_scores_gemma":[0.038834948,0.0003995513,0.00016730344,0.00021956953,0.00036004122,0.00001800295,0.000109779634,0.0004311236,0.0003822555],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033040607,0.00014322299,0.000037216552,0.00044338242,0.00013027675,0.000016163853,0.000018299692,1.1237391e-7,0.0000014505425,0.17075858,0.75857633,0.069841914],"study_design_scores_gemma":[0.0004100921,0.00012911632,0.000060065155,0.0002401377,0.00034980732,0.0000021608823,0.000007881714,0.000008326449,0.0000086853415,0.36156604,0.6369115,0.0003061457],"about_ca_topic_score_codex":0.000032963144,"about_ca_topic_score_gemma":0.000045574157,"teacher_disagreement_score":0.29787835,"about_ca_system_score_codex":0.0000397576,"about_ca_system_score_gemma":0.00011638407,"threshold_uncertainty_score":0.9998456},"labels":[],"label_agreement":null},{"id":"W4232687588","doi":"10.21203/rs.3.rs-278523/v1","title":"Simple compared to covariate-constrained randomization methods in balancing baseline characteristics: a case study of randomly allocating 72 hemodialysis centers in a cluster trial","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Lawson Health Research Institute; McMaster University","funders":"Ontario Ministry of Health and Long-Term Care; Kidney Foundation of Canada; Cancer Care Ontario; Dialysis Clinics; McMaster University; Canadian Institutes of Health Research; Lawson Health Research Institute; Heart and Stroke Foundation of Canada","keywords":"Covariate; Baseline (sea); Randomization; Simple (philosophy); Cluster (spacecraft); Cluster randomised controlled trial; Hemodialysis; Statistics; Randomized controlled trial; Computer science; Medicine; Mathematics; Surgery; Political science","score_opus":0.5087550135397779,"score_gpt":0.6203859256365204,"score_spread":0.11163091209674247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232687588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5638941,0.000017141441,0.42534846,0.00010945055,0.00038441777,0.009959117,0.00021919828,0.000032751348,0.000035344143],"genre_scores_gemma":[0.57165337,0.000012970524,0.42661986,0.000027232592,0.00023982274,0.001296214,0.00007583511,0.00006380899,0.000010879122],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9245601,0.06457487,0.0061699343,0.0016749206,0.0018328158,0.001187332],"domain_scores_gemma":[0.8002782,0.19565396,0.00093556277,0.0013158764,0.0014861653,0.00033026483],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09990467,0.00052989257,0.004414759,0.0014526065,0.00012737191,0.00026559568,0.0006250989,0.0005410236,0.00028286088],"category_scores_gemma":[0.5214138,0.00050940266,0.00043277047,0.0018616344,0.00015159916,0.0000760511,0.0018267783,0.002294199,0.0000022657166],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7274186,0.029677061,0.016163984,0.019007139,0.0030105468,0.013274061,0.082835004,0.018315926,0.0027309428,0.0005513914,0.00042422808,0.08659108],"study_design_scores_gemma":[0.5938225,0.0013905857,0.00068770535,0.0055119283,0.00060808304,0.00004546282,0.033271156,0.332701,0.00035298776,0.030507285,0.000006643088,0.0010947081],"about_ca_topic_score_codex":0.0037039034,"about_ca_topic_score_gemma":0.002638982,"teacher_disagreement_score":0.42150912,"about_ca_system_score_codex":0.00056465174,"about_ca_system_score_gemma":0.0007656026,"threshold_uncertainty_score":0.9997358},"labels":[],"label_agreement":null},{"id":"W4234159860","doi":"10.5489/cuaj.658","title":"Demographic analysis: an update of randomized controlled studies in prostatic oncology","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Randomized controlled trial; Prostate cancer; Cohort; Clinical trial; MEDLINE; Internal medicine; Meta-analysis; Cohort study; Cancer","score_opus":0.24606686045104398,"score_gpt":0.4896707143038224,"score_spread":0.24360385385277844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234159860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96466964,0.00066562585,0.01053438,0.018409513,0.0009508879,0.0037132555,0.000059392398,0.00004498437,0.00095233053],"genre_scores_gemma":[0.88101524,0.00028248373,0.116806656,0.0014358585,0.00014539708,0.0002406751,0.000002775078,0.000011642938,0.00005925818],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9853827,0.010683259,0.0027216699,0.00024189072,0.0004485615,0.0005219243],"domain_scores_gemma":[0.9144393,0.08154313,0.002210353,0.00018364048,0.0010377159,0.00058581727],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025102034,0.00019127803,0.0040880824,0.00079729035,0.000105512925,0.00006129685,0.00026305823,0.00037571928,0.00089058507],"category_scores_gemma":[0.31761652,0.00012384485,0.0007701939,0.00089990423,0.00027598793,0.0001255765,0.000021523485,0.00069832074,0.00001970592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05797773,0.0023069642,0.56868464,0.00016339155,0.059015624,0.00041103602,0.004074443,0.0010114048,0.0001277328,0.27726436,0.013191318,0.015771382],"study_design_scores_gemma":[0.08391559,0.00023566459,0.013408748,0.000014454955,0.0020331757,0.0000059223084,0.0002715235,0.0024994349,0.0000017865732,0.8974237,0.000054952863,0.00013505845],"about_ca_topic_score_codex":0.0004652868,"about_ca_topic_score_gemma":0.0021573938,"teacher_disagreement_score":0.6201593,"about_ca_system_score_codex":0.0005422891,"about_ca_system_score_gemma":0.00032676134,"threshold_uncertainty_score":0.9751282},"labels":[],"label_agreement":null},{"id":"W4234888114","doi":"10.1002/9781118445112.stat03700","title":"Bioequivalence","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Bioavailability; Nonparametric statistics; Econometrics; Mathematics; Pharmacology; Medicine","score_opus":0.5472939468508446,"score_gpt":0.5590037520661518,"score_spread":0.011709805215307179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234888114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000030350582,0.00038578373,0.78133917,0.00012250521,0.0017640055,0.00096635823,0.07192673,0.00088984513,0.14260255],"genre_scores_gemma":[0.000012349555,0.0023856428,0.7314825,0.00029418105,0.0012579018,0.00005861018,0.0008606814,0.0011795334,0.2624686],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99234337,0.0013121036,0.0021632628,0.0015553063,0.001462407,0.001163547],"domain_scores_gemma":[0.96883327,0.026191205,0.0018328901,0.0021295494,0.00036813784,0.0006449714],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017221728,0.0011897958,0.0025595722,0.00045637912,0.00011336457,0.000115919334,0.0014255209,0.0012011688,0.02195249],"category_scores_gemma":[0.059636664,0.0010427912,0.0001892164,0.00041855843,0.00091479416,0.00004124615,0.00044852315,0.0015555222,0.0015802116],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038957758,0.00032492445,0.000015497702,0.0007631383,0.0001534344,0.00005284793,0.000012113026,2.9134506e-7,0.000011304881,0.31967676,0.6455672,0.033383563],"study_design_scores_gemma":[0.0007307931,0.000290383,0.000016990576,0.0011677974,0.00034399948,0.000006690723,0.000014488084,0.00020615823,0.00000798782,0.5930119,0.40332934,0.00087343936],"about_ca_topic_score_codex":0.00015637357,"about_ca_topic_score_gemma":0.0004361061,"teacher_disagreement_score":0.27333516,"about_ca_system_score_codex":0.00014104634,"about_ca_system_score_gemma":0.0003522522,"threshold_uncertainty_score":0.99920225},"labels":[],"label_agreement":null},{"id":"W4235353007","doi":"10.1016/s0197-2456(03)00102-8","title":"The role of the pharmacy coordinating center in the DIG trial","year":2003,"lang":"en","type":"article","venue":"Controlled Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster Children's Hospital","funders":"National Heart, Lung, and Blood Institute; U.S. Food and Drug Administration","keywords":"Pharmacy; Clinical trial; Veterans Affairs; Dig; Medicine; Digitalis; Family medicine; Heart failure; Internal medicine; Computer science","score_opus":0.7327062424795008,"score_gpt":0.6624181601478359,"score_spread":0.07028808233166484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235353007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42818508,0.0070465575,0.027588826,0.045568097,0.077512436,0.12174698,0.0007568549,0.00048468597,0.2911105],"genre_scores_gemma":[0.9782769,0.00029488953,0.016010918,0.0013080207,0.0024929454,0.000957727,5.633279e-7,0.00006303931,0.0005949605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8773749,0.10814971,0.011732254,0.00067090115,0.0012807708,0.0007914898],"domain_scores_gemma":[0.11721157,0.876935,0.0038037503,0.001619325,0.00028013234,0.00015020948],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.222163,0.00033950075,0.0034958348,0.00004192573,0.00033691892,0.000140278,0.0016070029,0.0002756333,0.00026013926],"category_scores_gemma":[0.9133597,0.00013008926,0.0023283951,0.0004672852,0.0007212789,0.000052803694,0.00016204735,0.0012508042,0.000019985011],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10298442,0.0026546747,0.0040513217,0.00003059209,0.00086060923,0.000006107621,0.00018690997,0.0000029222647,0.0001350342,0.7865272,0.003151244,0.09940898],"study_design_scores_gemma":[0.24647073,0.00024881712,0.00011137575,0.00006501526,0.00040168478,0.0000015561412,0.00022463966,0.00018407954,0.00023033793,0.7305729,0.02135073,0.00013816271],"about_ca_topic_score_codex":0.000008203233,"about_ca_topic_score_gemma":0.0000124795215,"teacher_disagreement_score":0.7687853,"about_ca_system_score_codex":0.000033874636,"about_ca_system_score_gemma":0.00024952076,"threshold_uncertainty_score":0.8009469},"labels":[],"label_agreement":null},{"id":"W4235450985","doi":"10.1002/cncy.20147","title":"Biospecimen reporting for improved study quality (BRISQ)","year":2011,"lang":"en","type":"article","venue":"Cancer Cytopathology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":191,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Cancer Institute; U.S. Public Health Service; National Institutes of Health","keywords":"Medicine; Quality (philosophy); Consistency (knowledge bases); Data science; Medical physics; Computer science","score_opus":0.9032678520110035,"score_gpt":0.6778586125422745,"score_spread":0.22540923946872893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235450985","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69489473,0.00009809386,0.2915048,0.00032608598,0.003430731,0.0035472673,0.00024413457,0.0003340895,0.0056200647],"genre_scores_gemma":[0.2662402,0.000007955752,0.73168004,0.00029961785,0.00051596895,0.0008131709,9.608879e-7,0.00005023952,0.0003918578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953949,0.00087680836,0.002514813,0.0006516391,0.00012351316,0.00043836524],"domain_scores_gemma":[0.98602,0.01084123,0.0020173327,0.0007460323,0.00025428872,0.000121079596],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009173804,0.00020658842,0.0010639459,0.000049145183,0.00009879432,0.000012259243,0.00029472078,0.00019029774,0.00052540796],"category_scores_gemma":[0.13587593,0.00017638228,0.00018247087,0.00013237026,0.00017706992,0.00004037108,0.00014197042,0.00023198694,0.000008965491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040637585,0.0058889277,0.2850852,0.0009034093,0.00083202525,0.00047097934,0.011064227,5.479925e-7,0.041551776,0.37683877,0.005841225,0.26745912],"study_design_scores_gemma":[0.0018672638,0.0007878745,0.0491371,0.000017911498,0.00021203689,0.000012473157,0.00046675946,0.00002067784,0.0055064913,0.94140077,0.00028025327,0.00029037724],"about_ca_topic_score_codex":0.00008754418,"about_ca_topic_score_gemma":0.000055001146,"teacher_disagreement_score":0.564562,"about_ca_system_score_codex":0.000083100116,"about_ca_system_score_gemma":0.00008694465,"threshold_uncertainty_score":0.871403},"labels":[],"label_agreement":null},{"id":"W4236034644","doi":"10.21203/rs.3.rs-15483/v1","title":"Explaining the variation in the attained power of a stepped-wedge trial with unequal cluster sizes","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Variation (astronomy); Wedge (geometry); Cluster (spacecraft); Computer science; Econometrics; Mathematics; Physics; Optics; Computer network; Astrophysics","score_opus":0.6774186248520271,"score_gpt":0.6187126014312694,"score_spread":0.0587060234207577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236034644","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46244544,0.00030683048,0.422301,0.047657363,0.0023405124,0.050874732,0.0013452239,0.0002971153,0.012431798],"genre_scores_gemma":[0.8746406,0.00002576139,0.122853406,0.00015559538,0.00087999215,0.0012779855,0.000013001239,0.00007813404,0.00007554222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97539055,0.018755987,0.0016028086,0.0007541412,0.002845842,0.00065066724],"domain_scores_gemma":[0.7699707,0.22735082,0.0005538563,0.0013969654,0.0006153747,0.00011226531],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035701483,0.00031755326,0.0010539112,0.00018968344,0.00017000748,0.00019359526,0.0014545086,0.0004691434,0.0002412729],"category_scores_gemma":[0.26163998,0.00015890725,0.00024082398,0.00080833473,0.00048172954,0.00004919046,0.00127508,0.0033787694,0.000018936706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17458089,0.0027441524,0.00042929818,0.006892549,0.0010304312,0.00024826272,0.090953685,0.0005364586,0.0001928284,0.69802356,0.01915969,0.0052082078],"study_design_scores_gemma":[0.025374167,0.0026928894,0.001400388,0.0013596597,0.000120201876,0.0000017958216,0.007259026,0.0024314423,0.00006624931,0.9587416,0.00022842578,0.0003241525],"about_ca_topic_score_codex":0.000099797624,"about_ca_topic_score_gemma":0.000045915247,"teacher_disagreement_score":0.41219515,"about_ca_system_score_codex":0.00013456326,"about_ca_system_score_gemma":0.0006222544,"threshold_uncertainty_score":0.9989205},"labels":[],"label_agreement":null},{"id":"W4237144453","doi":"10.22215/etd/2005-08367","title":"Practical and theoretical issues in randomization","year":2005,"lang":"en","type":"dissertation","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Humanities; Computer science; Philosophy","score_opus":0.37546711397863414,"score_gpt":0.6328438617958215,"score_spread":0.2573767478171874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237144453","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04151088,0.000739817,0.22767279,0.017357102,0.004135944,0.0072519053,0.000082790975,0.00068922114,0.70055956],"genre_scores_gemma":[0.0064484905,0.0005333757,0.986623,0.00012045853,0.0004411047,0.000068991954,0.000026682823,0.000056546924,0.0056813653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99682915,0.0010904183,0.0010734318,0.00042105786,0.000358411,0.00022753204],"domain_scores_gemma":[0.9350535,0.064310275,0.00021497985,0.00023293105,0.00009036182,0.000097926946],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034564175,0.0002494041,0.0009836757,0.00011464854,0.000028011278,0.00005989945,0.00009145215,0.0006570563,0.0036835026],"category_scores_gemma":[0.23531277,0.00019386418,0.000082979364,0.00012276549,0.00015160024,0.00006389,0.000026179123,0.00057374546,0.00003804382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010617097,0.00014347106,0.000020937272,0.00015270001,0.000024988634,0.000010406818,0.00012740886,8.517783e-8,0.0000085921665,0.98793954,0.0026501091,0.00786007],"study_design_scores_gemma":[0.0028520885,0.000049596958,0.00018746562,0.0001715539,0.00013353243,0.0000038435774,0.00025741468,0.0004452151,0.00032842538,0.9950638,0.00028191798,0.00022517181],"about_ca_topic_score_codex":0.000004669421,"about_ca_topic_score_gemma":0.00010614617,"teacher_disagreement_score":0.7589502,"about_ca_system_score_codex":0.000031559386,"about_ca_system_score_gemma":0.00008758473,"threshold_uncertainty_score":0.99722725},"labels":[],"label_agreement":null},{"id":"W4237822279","doi":"10.1007/978-0-387-79948-3_1322","title":"Processing Speed Index","year":2010,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Mental Health & Substance Use Services; University of British Columbia","funders":"","keywords":"Index (typography); Computer science; World Wide Web","score_opus":0.6467283912063748,"score_gpt":0.5728770627260245,"score_spread":0.07385132848035036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237822279","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002146883,0.000020049138,0.123738736,0.00014698232,0.0007068098,0.00039339426,0.00003095049,0.00021879715,0.87474215],"genre_scores_gemma":[0.000026567646,0.0000072350304,0.5182693,0.00017222555,0.00072204735,0.0000021457329,0.0000010050978,0.00008721856,0.4807123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99760664,0.00005437639,0.0010608193,0.0004949136,0.0005270186,0.00025624826],"domain_scores_gemma":[0.9779612,0.02051642,0.0005165667,0.0006355675,0.00019641247,0.00017387589],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016747781,0.00038223114,0.0010396652,0.000088730994,0.00006466699,0.00006724462,0.00036435164,0.001310741,0.017277049],"category_scores_gemma":[0.035259966,0.00029786144,0.00022857613,0.000021198377,0.0002839687,0.000031531334,0.00016391349,0.0015428119,0.0005502496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021815105,0.000021870279,0.0000020628377,0.00021141428,0.000041425625,0.000018813802,0.000010137441,1.1987122e-8,0.000036757894,0.93172413,0.0027729,0.065138645],"study_design_scores_gemma":[0.00028321444,0.00003249322,0.0000028110337,0.00023690016,0.00012804056,0.000006205719,0.0000016131077,0.00003431082,0.00013939684,0.9337682,0.06501578,0.00035104042],"about_ca_topic_score_codex":0.0000018288102,"about_ca_topic_score_gemma":0.000007471964,"teacher_disagreement_score":0.39453053,"about_ca_system_score_codex":0.000030504623,"about_ca_system_score_gemma":0.00012084548,"threshold_uncertainty_score":0.99998575},"labels":[],"label_agreement":null},{"id":"W4238275793","doi":"10.1515/iupac.76.0288","title":"Mean Residence Time (MRT) (in Pharmacokinetics)","year":2016,"lang":"en","type":"dataset","venue":"IUPAC Standards Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Glossary; Toxicokinetics; Residence; Computer science; Medicine; Pharmacology; Pharmacokinetics; Demography; Philosophy; Sociology","score_opus":0.24687759512160248,"score_gpt":0.6191891602427578,"score_spread":0.3723115651211554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238275793","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026134805,0.0002174062,0.005255594,0.00083016447,0.0012986569,0.0008608649,0.991221,0.00012203511,0.00016816148],"genre_scores_gemma":[0.0000027793171,0.0013892773,0.10241404,0.0005655879,0.00317973,0.00006666254,0.8904692,0.00017990475,0.0017328397],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99176484,0.00168733,0.0023360488,0.0011264759,0.0022167317,0.0008685858],"domain_scores_gemma":[0.9575238,0.03894189,0.00084827124,0.0017404908,0.0005762676,0.00036925],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008242732,0.00076261046,0.0021716694,0.00034512283,0.00007062792,0.00007440286,0.0012970649,0.0008192003,0.020623293],"category_scores_gemma":[0.15689337,0.00058031146,0.00032593837,0.00039841127,0.00044272162,0.00007859628,0.0005062081,0.0013290005,0.0000430394],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046758662,0.00040194544,0.0000022088773,0.0004022714,0.0001026294,0.00031253905,0.000009110464,3.6499563e-7,0.00004106823,0.0007681668,0.9915767,0.005915413],"study_design_scores_gemma":[0.0018349665,0.00018940624,0.000006165923,0.0015915831,0.0002526282,0.000008423337,0.0000036491158,0.00001550944,0.00009045457,0.3206045,0.6748707,0.0005319986],"about_ca_topic_score_codex":0.000043468255,"about_ca_topic_score_gemma":0.00019559498,"teacher_disagreement_score":0.31983635,"about_ca_system_score_codex":0.00056669815,"about_ca_system_score_gemma":0.00069176033,"threshold_uncertainty_score":0.99966484},"labels":[],"label_agreement":null},{"id":"W4240438654","doi":"10.1002/9780470057339.vae051","title":"Exact Randomization Technique","year":2001,"lang":"en","type":"other","venue":"Encyclopedia of Environmetrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Randomization; Shuffling; Statistic; Bootstrapping (finance); Test statistic; Exact test; Resampling; Computer science; Restricted randomization; Statistical hypothesis testing; Sufficient statistic; Statistics; Exact statistics; Algorithm; Mathematics; Econometrics; Randomized controlled trial; Medicine","score_opus":0.16955150666592317,"score_gpt":0.4456667374287705,"score_spread":0.27611523076284733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240438654","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014852637,0.00033376674,0.47386664,0.000009318797,0.00044614362,0.0008716605,0.000111179164,0.00011501093,0.5242448],"genre_scores_gemma":[0.0000039332917,0.012281888,0.62275624,0.000015859874,0.00059431314,0.000088857676,0.000009912116,0.00048982067,0.3637592],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966721,0.00069854857,0.001181577,0.0004967448,0.00064731855,0.00030373147],"domain_scores_gemma":[0.97058624,0.027133973,0.0012232498,0.0008970266,0.00002310085,0.00013642377],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022067109,0.00040552192,0.0014386073,0.0008390405,0.00002181799,0.000008392443,0.00044908214,0.0010147708,0.017774304],"category_scores_gemma":[0.10919739,0.00036511105,0.0002731408,0.00091115735,0.00023160917,0.00002490922,0.0001394821,0.00047834346,0.00013771497],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007755942,0.0005360888,0.0005770728,0.0006028793,0.00018422134,0.00003287996,0.000017802136,0.0000026898986,0.000023214183,0.010787011,0.92527664,0.06188192],"study_design_scores_gemma":[0.0016915567,0.000090000576,0.000042005064,0.00020930532,0.00029394554,0.0000037264222,0.0000049374958,0.0000056150607,0.00011827966,0.19798785,0.79913574,0.00041702678],"about_ca_topic_score_codex":0.000041189687,"about_ca_topic_score_gemma":0.0000034762556,"teacher_disagreement_score":0.18720084,"about_ca_system_score_codex":0.00005953508,"about_ca_system_score_gemma":0.000037966696,"threshold_uncertainty_score":0.9998801},"labels":[],"label_agreement":null},{"id":"W4240638944","doi":"10.1002/9781118445112.stat07380","title":"Exact Randomization Technique","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Randomization; Statistic; Shuffling; Exact test; Bootstrapping (finance); Test statistic; Resampling; Computer science; Restricted randomization; Statistical hypothesis testing; Statistics; Sufficient statistic; Exact statistics; Algorithm; Mathematics; Randomized controlled trial; Econometrics; Medicine","score_opus":0.34320022993230137,"score_gpt":0.5218161486622073,"score_spread":0.1786159187299059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240638944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.0263746e-7,0.00016569575,0.872789,0.00006078052,0.0009085854,0.0021447116,0.033287805,0.00080070354,0.089842],"genre_scores_gemma":[0.000014419658,0.0018596963,0.8364213,0.00018385221,0.0010837645,0.0002743845,0.0018571793,0.0012648946,0.1570405],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924391,0.0020265353,0.0022513545,0.0012600886,0.0011709892,0.0008519511],"domain_scores_gemma":[0.96734774,0.028129367,0.0020177742,0.001653631,0.00040190568,0.00044958634],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002624987,0.0010647036,0.0027397193,0.00051220914,0.000107489825,0.00010668576,0.0009102062,0.0013432375,0.014361958],"category_scores_gemma":[0.0725945,0.00092127,0.00018776319,0.00040404132,0.0005128206,0.000043378594,0.00026248174,0.0013899851,0.00047530967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022477812,0.00041120517,0.0000085615,0.0008946706,0.00020547697,0.000037539427,0.000013470238,0.0000014200943,0.00003673003,0.24168485,0.72738314,0.02909814],"study_design_scores_gemma":[0.0029440348,0.0002647506,0.0000069016482,0.0015040392,0.00042105172,0.000008604281,0.000009634746,0.0003820288,0.00003770043,0.6965111,0.2969934,0.0009167681],"about_ca_topic_score_codex":0.00011112064,"about_ca_topic_score_gemma":0.00027862232,"teacher_disagreement_score":0.45482624,"about_ca_system_score_codex":0.00015788784,"about_ca_system_score_gemma":0.0003173183,"threshold_uncertainty_score":0.9999532},"labels":[],"label_agreement":null},{"id":"W4241385021","doi":"10.32920/ryerson.14664120.v1","title":"Effective Multi-level Monte Carlo Methods for Stochastic Biochemical Kinetics","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Memorial University of Newfoundland","funders":"","keywords":"Monte Carlo method; Stochastic modelling; Stochastic simulation; Stochastic process; Computer science; Mathematical optimization; Kinetic Monte Carlo; Statistical physics; Applied mathematics; Mathematics; Physics; Statistics","score_opus":0.7206932361431452,"score_gpt":0.6524587646822684,"score_spread":0.0682344714608768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241385021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013794006,0.00035973298,0.98846596,0.00019841603,0.0033540246,0.0049776156,0.0008059194,0.00026140362,0.00019750053],"genre_scores_gemma":[0.0041740695,0.000015986156,0.99169356,0.00019138475,0.00076137745,0.0021888583,0.00002099881,0.00019810627,0.0007556818],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925141,0.0028165905,0.0019363256,0.0016068609,0.00042907047,0.0006970665],"domain_scores_gemma":[0.7985335,0.19840072,0.00058898854,0.0013341062,0.00081657525,0.00032613223],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0058836653,0.00081466924,0.0026846027,0.00012614448,0.0000689574,0.00015853679,0.00079530093,0.0016181108,0.00023441241],"category_scores_gemma":[0.44707802,0.0007100076,0.0010650568,0.00018748386,0.00031419657,0.000024522567,0.0019326989,0.0015619079,0.000008327925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016464771,0.007590835,0.00001658409,0.01652574,0.007252871,0.00007671753,0.0017384575,0.0016339634,0.052244067,0.08016651,0.016998114,0.8141097],"study_design_scores_gemma":[0.0028996246,0.00030242946,0.00008708996,0.0009094415,0.0016901548,0.000008680176,0.00013183132,0.06880131,0.044492424,0.87937874,0.000083834486,0.0012144732],"about_ca_topic_score_codex":0.000030251727,"about_ca_topic_score_gemma":0.000009344932,"teacher_disagreement_score":0.8128952,"about_ca_system_score_codex":0.0002519223,"about_ca_system_score_gemma":0.00018884886,"threshold_uncertainty_score":0.999678},"labels":[],"label_agreement":null},{"id":"W4241404344","doi":"10.1002/9781118707999.ch26","title":"Novel Approaches to Pharmacoepidemiology Study Design and Statistical Analysis","year":2006,"lang":"en","type":"other","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Pharmacoepidemiology; Statistical analysis; Data science; Computer science; Econometrics; Statistics; Mathematics; Medicine; Pharmacology","score_opus":0.8881543021552973,"score_gpt":0.614771297198156,"score_spread":0.2733830049571413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241404344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003862991,0.000030728883,0.8905062,0.00012684138,0.00017553272,0.0021840078,0.00037652807,0.000227167,0.10636913],"genre_scores_gemma":[0.00007513646,0.000005424116,0.8619922,0.00021402704,0.00034416106,0.00019734881,0.000008892713,0.00031270616,0.13685012],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99363244,0.0032047932,0.0012729757,0.001079095,0.00035807537,0.00045263697],"domain_scores_gemma":[0.8935176,0.10522531,0.00034420384,0.0005906146,0.000025202693,0.0002970621],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0071373316,0.0004912846,0.0025764403,0.0005215402,0.000036918864,0.000034767654,0.00031589138,0.0004462571,0.0033674869],"category_scores_gemma":[0.049872447,0.00037170222,0.00015204563,0.00054630515,0.00019790395,0.000009032587,0.00021663656,0.0003823183,0.0000567836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008389474,0.0013348568,0.00067501207,0.0001068731,0.0036976072,0.000020255824,0.000029114897,0.000037292866,0.0000038977996,0.1359466,0.85299534,0.005069253],"study_design_scores_gemma":[0.004044702,0.0012316906,0.0021704594,0.00007447607,0.025393609,0.0000075352436,0.00013854892,0.00842171,0.000015621974,0.9275876,0.028947808,0.0019661926],"about_ca_topic_score_codex":0.0004388391,"about_ca_topic_score_gemma":0.00021917377,"teacher_disagreement_score":0.8240475,"about_ca_system_score_codex":0.000032581545,"about_ca_system_score_gemma":0.000033548586,"threshold_uncertainty_score":0.9998735},"labels":[],"label_agreement":null},{"id":"W4241578860","doi":"10.3410/f.726487212.793523113","title":"Faculty Opinions recommendation of Lasso adjustments of treatment effect estimates in randomized experiments.","year":2016,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Lasso (programming language); Randomized controlled trial; Econometrics; Computer science; Medical physics; Statistics; Psychology; Data science; Medicine; Mathematics; Internal medicine; World Wide Web","score_opus":0.22809546198827504,"score_gpt":0.5440523231835097,"score_spread":0.3159568611952347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241578860","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014104369,0.0007313318,0.0003606844,0.026146552,0.001177246,0.004755762,0.96672535,0.000030127134,0.00007156713],"genre_scores_gemma":[0.0000036543818,0.0006322118,0.031936448,0.00043891525,0.00016324487,0.0012038454,0.9652586,0.000038535734,0.0003245238],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9886464,0.0042048804,0.0045356695,0.00076824013,0.0014326817,0.00041212203],"domain_scores_gemma":[0.9662225,0.023958681,0.0044440823,0.0019552375,0.0031269423,0.0002925359],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007862119,0.0007663261,0.0044246563,0.00044159437,0.00008360501,0.000045900037,0.0013605224,0.0008880742,0.0007852276],"category_scores_gemma":[0.25604612,0.00037879447,0.0014467649,0.0012399023,0.00076102145,0.00017411298,0.00044354133,0.00060294534,0.000021804077],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008598727,0.0010468698,0.0000061295523,0.00932871,0.0005471759,3.177746e-7,0.000076641954,2.5982862e-8,0.0000039189804,0.0016945511,0.9817392,0.004696585],"study_design_scores_gemma":[0.029161654,0.000530745,0.00009938112,0.027395677,0.0007854922,0.000005958619,0.000008508854,0.0000087944245,0.0003077337,0.00468186,0.93668777,0.00032642458],"about_ca_topic_score_codex":0.000063532956,"about_ca_topic_score_gemma":0.000002642105,"teacher_disagreement_score":0.248184,"about_ca_system_score_codex":0.00033240288,"about_ca_system_score_gemma":0.00042281995,"threshold_uncertainty_score":0.9998664},"labels":[],"label_agreement":null},{"id":"W4243395900","doi":"10.36401/2590-017x-2.4.152","title":"Meeting Proceedings of the “Phase I: Where Science Becomes Medicine” Conference, Manchester, UK","year":2019,"lang":"en","type":"article","venue":"Journal of Immunotherapy and Precision Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Engineering ethics; Library science; Engineering physics; Engineering; Computer science","score_opus":0.2982155178811179,"score_gpt":0.5469405263810965,"score_spread":0.24872500849997858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243395900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98795265,0.0009123004,0.0019409122,0.002224913,0.0015178435,0.0003524813,0.0000031184538,0.0000050347603,0.0050907764],"genre_scores_gemma":[0.70430034,0.0023979098,0.29209095,0.00040865003,0.00027614683,0.000003809835,2.7163106e-8,0.000020448624,0.0005017049],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975028,0.00024891767,0.0013768644,0.00016340503,0.00053038093,0.00017763248],"domain_scores_gemma":[0.9772451,0.019883703,0.00181758,0.00017903106,0.0007976951,0.00007689323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010308947,0.00012559918,0.0008376169,0.00013779642,0.00008879777,0.000026789163,0.0006188287,0.00014834186,0.00078258873],"category_scores_gemma":[0.01603603,0.00006520983,0.00011366592,0.0002826474,0.00078430225,0.00013018178,0.000109522996,0.00040027848,0.0000016376222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003037677,0.0006240398,0.005896265,0.00019920463,0.00018344058,0.000004471819,0.0050811116,0.0000010112897,0.26461744,0.075100794,0.00350407,0.64175045],"study_design_scores_gemma":[0.010190875,0.006049628,0.0037723733,0.0021671595,0.00009111982,0.00025937794,0.0018521937,0.00007998926,0.014332445,0.9452304,0.015808804,0.0001655861],"about_ca_topic_score_codex":0.000002260508,"about_ca_topic_score_gemma":6.959436e-7,"teacher_disagreement_score":0.87012964,"about_ca_system_score_codex":0.00005293492,"about_ca_system_score_gemma":0.00021965693,"threshold_uncertainty_score":0.9922523},"labels":[],"label_agreement":null},{"id":"W4244187033","doi":"10.3410/f.734877429.793573545","title":"Faculty Opinions recommendation of Using simulation studies to evaluate statistical methods.","year":2020,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Medical Research Council","keywords":"Computer science; Terminology; Key (lock); Presentation (obstetrics); Process (computing); Structuring; Coding (social sciences); Stochastic simulation; Data mining; Data science; Statistics","score_opus":0.6161079554313188,"score_gpt":0.658614947192893,"score_spread":0.04250699176157424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244187033","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.264202e-8,0.00030381719,0.056260712,0.08940719,0.0017987232,0.0026989316,0.8494598,0.000055729834,0.0000149623365],"genre_scores_gemma":[4.5111324e-7,0.00007863676,0.40433863,0.003060115,0.00035393072,0.00014267818,0.5919197,0.000036465222,0.00006933796],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98525274,0.0059214644,0.004626004,0.0011574148,0.0025366452,0.0005057577],"domain_scores_gemma":[0.9470153,0.029981565,0.0042611235,0.002423301,0.01550785,0.0008108951],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01125046,0.0007866825,0.0028528858,0.000380021,0.00026402748,0.00012428638,0.0017172587,0.0008650334,0.00059180945],"category_scores_gemma":[0.5846246,0.0005140416,0.0007904481,0.0028782827,0.00059518486,0.00022182203,0.0011912141,0.0014852629,0.00007676474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052604053,0.00033511082,6.1756407e-7,0.014399249,0.00047779558,4.4868347e-7,0.00016191047,0.0000043327987,0.0000026500895,0.0027644865,0.97394943,0.007851343],"study_design_scores_gemma":[0.00076051406,0.00024041146,0.00006900468,0.012760223,0.0011480581,0.000008250366,0.000050276347,0.0004988541,0.000021943335,0.013840481,0.9701286,0.0004733851],"about_ca_topic_score_codex":0.000014673186,"about_ca_topic_score_gemma":0.0000016018366,"teacher_disagreement_score":0.5733741,"about_ca_system_score_codex":0.00026747148,"about_ca_system_score_gemma":0.00063165196,"threshold_uncertainty_score":0.9997311},"labels":[],"label_agreement":null},{"id":"W4244736334","doi":"10.1002/9780471462422.eoct991","title":"Pharmacoepidemiology, Overview","year":2008,"lang":"en","type":"other","venue":"Wiley Encyclopedia of Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pharmacoepidemiology; Observational study; Confounding; Context (archaeology); Medicine; Medical prescription; Randomized controlled trial; Causality (physics); Intensive care medicine; Pharmacology; Internal medicine; Geography","score_opus":0.8426921910279196,"score_gpt":0.6895197365249248,"score_spread":0.15317245450299477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244736334","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010961928,0.011200759,0.0101986285,0.0004581873,0.01647867,0.0033152406,0.0019549998,0.00061183237,0.95577073],"genre_scores_gemma":[0.0000017192726,0.30982503,0.44916752,0.0006588214,0.012154651,0.00013420933,0.000019328023,0.0008008708,0.22723784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92326385,0.05178436,0.020888053,0.0018263442,0.0012780402,0.000959343],"domain_scores_gemma":[0.22639367,0.7530267,0.016716724,0.0026216416,0.0002719913,0.00096926955],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10207981,0.0010156585,0.016276922,0.00033456058,0.00004941413,0.000011165892,0.0014498971,0.003344588,0.03004824],"category_scores_gemma":[0.88667613,0.0007664272,0.0038445452,0.00042273506,0.0014570401,0.000043857915,0.0004336143,0.0020163795,0.00073684775],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026154285,0.00061642885,0.00041601883,0.00071220484,0.0010108174,0.00004225488,0.000008429661,1.06797906e-7,9.1092744e-7,0.015347236,0.8724515,0.10913259],"study_design_scores_gemma":[0.0028917398,0.00022419407,0.00005176359,0.0014645662,0.0010889146,0.000005099918,0.0000024863857,0.000005291828,0.0000054243333,0.3073308,0.6864115,0.0005182519],"about_ca_topic_score_codex":0.00008989435,"about_ca_topic_score_gemma":0.00001315239,"teacher_disagreement_score":0.7845963,"about_ca_system_score_codex":0.000027643668,"about_ca_system_score_gemma":0.00059047976,"threshold_uncertainty_score":0.9994787},"labels":[],"label_agreement":null},{"id":"W4245628571","doi":"10.1007/978-3-319-24612-3_13","title":"Caliper Profile","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Calipers; Mathematics; Geometry","score_opus":0.7563793037754692,"score_gpt":0.577214844005447,"score_spread":0.17916445977002227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245628571","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.522713e-8,0.000021258104,0.058074933,0.0007770719,0.0005722916,0.0005666832,0.000248541,0.00025633324,0.9394828],"genre_scores_gemma":[0.0000017903341,0.000010475455,0.49781266,0.0006029974,0.00061384396,0.000011035388,0.000003026315,0.00007481642,0.50086933],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978294,0.000092943,0.0009325479,0.0005127193,0.0004451166,0.00018729575],"domain_scores_gemma":[0.9718846,0.026999867,0.0002637064,0.000539248,0.00009392304,0.00021864494],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00073625817,0.0003392279,0.0010621925,0.000034176082,0.000029877323,0.000025883353,0.000293112,0.00060765084,0.056699444],"category_scores_gemma":[0.039079398,0.00025996298,0.000303764,0.000017095994,0.00014184932,0.000014744261,0.00019055945,0.0006700421,0.004528442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001556464,0.000010067071,1.6613885e-7,0.00012698807,0.00007387577,0.000028877514,0.0000067944147,4.1645296e-9,0.0000031231525,0.8178955,0.17472716,0.0071119373],"study_design_scores_gemma":[0.00017228861,0.00006650356,2.5479582e-7,0.00008556076,0.00013637696,0.000001983942,0.0000015567555,0.000014007533,0.000051581803,0.7814709,0.21774632,0.00025265728],"about_ca_topic_score_codex":0.0000014540385,"about_ca_topic_score_gemma":0.0000012445282,"teacher_disagreement_score":0.43973774,"about_ca_system_score_codex":0.000036925565,"about_ca_system_score_gemma":0.00006962178,"threshold_uncertainty_score":0.9999853},"labels":[],"label_agreement":null},{"id":"W4245761955","doi":"10.21203/rs.2.9437/v2","title":"Systematic review of basket trials, umbrella trials, and platform trials: A landscape analysis of master protocols","year":2019,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University","funders":"","keywords":"Clinical trial; Medicine; Interquartile range; Randomization; MEDLINE; Protocol (science); Randomized controlled trial; Medical physics; Alternative medicine; Internal medicine; Pathology","score_opus":0.8863518669458177,"score_gpt":0.7022952144570832,"score_spread":0.18405665248873448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245761955","genre_codex":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018205298,0.099767685,0.069727294,0.0013230832,0.0014236993,0.79419595,0.025287375,0.00024858004,0.006205771],"genre_scores_gemma":[0.011102424,0.13178231,0.6214102,0.0002826738,0.0027720265,0.22751997,0.00074840017,0.0008315066,0.0035504927],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.7987051,0.15932761,0.031417046,0.0022033209,0.0070275827,0.001319338],"domain_scores_gemma":[0.38806787,0.5931648,0.011829115,0.0037815336,0.0027558196,0.00040083643],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52856094,0.0007978368,0.035018194,0.0019728914,0.00007898872,0.00019857871,0.0015286932,0.0013291324,0.002656949],"category_scores_gemma":[0.9206074,0.0005035047,0.004836043,0.0022068997,0.0004102593,0.0000785898,0.0019185201,0.002204693,0.000029116914],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015203792,0.00046834518,0.00011866987,0.9723217,0.012274431,0.000009364988,0.00016295839,0.0000069878515,0.000043922857,0.007862286,0.004282844,0.0009281447],"study_design_scores_gemma":[0.0041449405,0.0008614357,0.000080005244,0.76616377,0.02976946,0.0000023237942,0.00030298086,0.0016534384,0.00031308053,0.19602956,0.00011166608,0.00056731707],"about_ca_topic_score_codex":0.000048215188,"about_ca_topic_score_gemma":0.000009219015,"teacher_disagreement_score":0.566676,"about_ca_system_score_codex":0.00015623667,"about_ca_system_score_gemma":0.0010342307,"threshold_uncertainty_score":0.99996734},"labels":[],"label_agreement":null},{"id":"W4246905884","doi":"10.1002/0470011815.b2a04003","title":"Bioequivalence","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Bioavailability; Nonparametric statistics; Econometrics; Mathematics; Pharmacology; Medicine","score_opus":0.25755174848982837,"score_gpt":0.5070750735515941,"score_spread":0.24952332506176572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246905884","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001185808,0.00042684324,0.15493807,0.00007361777,0.0016501603,0.0005230496,0.004266228,0.00024035333,0.8378805],"genre_scores_gemma":[0.0000030964786,0.0029868947,0.5941445,0.00004278687,0.0011014672,0.000013292784,0.00001213657,0.00043523492,0.40126058],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966943,0.0003610785,0.0013222452,0.00053892424,0.00066452706,0.00041891198],"domain_scores_gemma":[0.9765123,0.021068033,0.001206211,0.00091673114,0.000099892415,0.00019684173],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008365731,0.00047048673,0.0013214677,0.00025113107,0.000024162395,0.000012402748,0.00059144164,0.00064851047,0.020982647],"category_scores_gemma":[0.058606826,0.00042853167,0.00017397148,0.00024946884,0.0005253853,0.000017147195,0.00017100053,0.00042349027,0.00034964568],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015687207,0.00013715649,0.000021753802,0.0005797175,0.000089215224,0.000019768997,0.000025738487,5.4293462e-8,0.0000036029517,0.14963186,0.79194725,0.05752823],"study_design_scores_gemma":[0.00042880932,0.00010605617,0.000023294362,0.00042186255,0.0002885424,0.0000027585106,0.000010519595,0.00001095202,0.00003319754,0.30659497,0.69166684,0.00041218055],"about_ca_topic_score_codex":0.00004189475,"about_ca_topic_score_gemma":0.000034747296,"teacher_disagreement_score":0.43920645,"about_ca_system_score_codex":0.000036200796,"about_ca_system_score_gemma":0.00014263793,"threshold_uncertainty_score":0.99981666},"labels":[],"label_agreement":null},{"id":"W4246971544","doi":"10.7554/elife.25818.017","title":"Decision letter: Reverse translation of adverse event reports paves the way for de-risking preclinical off-targets","year":2017,"lang":"en","type":"peer-review","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Translation (biology); Computer science; Event (particle physics); Adverse effect; Medicine; Biology; Pharmacology; Genetics; Physics","score_opus":0.5740271156828191,"score_gpt":0.6019123597575924,"score_spread":0.02788524407477333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246971544","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033415738,0.009223067,0.93318325,0.033368744,0.011626556,0.007434492,0.0007943841,0.00010014779,0.0042359694],"genre_scores_gemma":[0.00009861184,0.0062771365,0.9718576,0.002144301,0.0015217292,0.00034133226,0.00006427461,0.00010918849,0.017585821],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99100024,0.0015518118,0.0049059987,0.0009324128,0.0011127819,0.000496731],"domain_scores_gemma":[0.82709163,0.16532488,0.004324092,0.0024951955,0.0005906867,0.00017351468],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029634954,0.0005251027,0.0025851813,0.00007618814,0.00021888035,0.000026302529,0.0008548619,0.00089793536,0.0008221576],"category_scores_gemma":[0.41015357,0.00032763917,0.0017412306,0.000084483916,0.00032225993,0.00008255763,0.00018535047,0.00083679747,0.000010580656],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014489467,0.00016099663,0.000011347344,0.004135729,0.00020033159,0.000021996717,0.000033670563,0.000002262486,0.0000054771917,0.0012437425,0.7272232,0.26681635],"study_design_scores_gemma":[0.0005471936,0.00012401509,0.000032928067,0.0073386785,0.0013277186,0.000014261669,0.0000041776243,0.00015717217,0.000085764295,0.4564895,0.5336207,0.00025787513],"about_ca_topic_score_codex":0.000027695016,"about_ca_topic_score_gemma":0.00009254908,"teacher_disagreement_score":0.45524576,"about_ca_system_score_codex":0.00008403388,"about_ca_system_score_gemma":0.0002767601,"threshold_uncertainty_score":0.99991757},"labels":[],"label_agreement":null},{"id":"W4247735967","doi":"10.1007/978-3-319-94153-0_9","title":"Efficiency","year":2018,"lang":"en","type":"book-chapter","venue":"Springer series in the data sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Mathematics; Sign test; Statistics; Test statistic; Wilcoxon signed-rank test; Statistic; Null hypothesis; Statistical hypothesis testing; Asymptotic distribution; Alternative hypothesis; Mann–Whitney U test","score_opus":0.725581839700009,"score_gpt":0.5610421790588936,"score_spread":0.16453966064111536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247735967","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010117773,0.0002876982,0.0050368807,0.0011278649,0.0028242504,0.00073473656,0.0010937748,0.00009399205,0.9886996],"genre_scores_gemma":[0.00020770122,0.00039598215,0.91864896,0.00051942404,0.0016417557,0.000019835887,0.00001940581,0.000059702645,0.078487255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99642646,0.0002882264,0.0008917352,0.0009567118,0.0010338454,0.00040300033],"domain_scores_gemma":[0.97548753,0.021163277,0.0004254175,0.002805509,0.00006166255,0.000056585628],"candidate_categories":["metaresearch","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015524263,0.00031443103,0.0006086499,0.00012578856,0.00026433446,0.00021925037,0.006811036,0.00024168234,0.0022967423],"category_scores_gemma":[0.045055877,0.00018868386,0.0000743328,0.00017216631,0.004171193,0.0002783535,0.0019415596,0.0005251279,0.00030815185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014705133,0.000024331972,0.000007229842,0.000055358378,0.000012360368,0.00001695122,0.0002189238,1.2979446e-7,0.0000015749428,0.9803754,0.016035786,0.0032372633],"study_design_scores_gemma":[0.00007236881,0.00014741873,0.000010837425,0.00019596017,0.000043870532,0.000010749089,0.00010163628,0.000028859053,0.000011887797,0.87416995,0.12497645,0.00023002346],"about_ca_topic_score_codex":0.000007931659,"about_ca_topic_score_gemma":0.0000624395,"teacher_disagreement_score":0.91361207,"about_ca_system_score_codex":0.000025222665,"about_ca_system_score_gemma":0.00014770239,"threshold_uncertainty_score":0.99861526},"labels":[],"label_agreement":null},{"id":"W4247852028","doi":"10.2165/11634080-000000000-00000","title":"Fundamentals of Population Pharmacokinetic Modelling","year":2012,"lang":"en","type":"review","venue":"Clinical Pharmacokinetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's & Women's Health Centre of British Columbia; University of British Columbia","funders":"","keywords":"Computer science; Usability; Population; Software; Context (archaeology); Variety (cybernetics); Data science; Risk analysis (engineering); Artificial intelligence; Medicine; Human–computer interaction; Biology","score_opus":0.9077627310124843,"score_gpt":0.7051695231200288,"score_spread":0.2025932078924555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247852028","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016985472,0.9554203,0.03465593,0.000020241507,0.0056159175,0.002370764,0.00052411587,0.00017893821,0.001196795],"genre_scores_gemma":[0.00005284596,0.7303368,0.26613507,0.00010755526,0.0027526452,0.00008674423,0.000060042385,0.00023499156,0.00023329911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.983573,0.0045163305,0.009006326,0.0010402087,0.000977359,0.0008867279],"domain_scores_gemma":[0.90653527,0.08730275,0.0039990395,0.0011544361,0.00033382318,0.00067468366],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0091296015,0.0010401479,0.0072859363,0.00028411552,0.00007790951,0.000037766687,0.0011527186,0.001190355,0.0020107583],"category_scores_gemma":[0.019878281,0.00086326833,0.002544611,0.00067882746,0.0005040525,0.00009986925,0.0005312286,0.0020866562,0.000208625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004322931,0.00096473657,0.00001847271,0.023812026,0.00072098087,0.000007811625,0.000009380868,0.000023827539,5.503449e-7,0.0034122304,0.0023963081,0.96859044],"study_design_scores_gemma":[0.0012978602,0.00017009668,0.0000028616328,0.0063244146,0.016638463,0.000013445707,0.0000028773193,0.0011234215,0.0000067378332,0.10517152,0.86831796,0.0009303692],"about_ca_topic_score_codex":0.0000062787562,"about_ca_topic_score_gemma":1.8802426e-7,"teacher_disagreement_score":0.96766007,"about_ca_system_score_codex":0.00012762232,"about_ca_system_score_gemma":0.00012250197,"threshold_uncertainty_score":0.9993818},"labels":[],"label_agreement":null},{"id":"W4248104173","doi":"10.1002/sim.3486","title":"Correction","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Inflation (cosmology); Sample size determination; Computer science; Statistics; Mathematics; Applied mathematics; Physics; Theoretical physics","score_opus":0.4513497466859385,"score_gpt":0.6047742542354313,"score_spread":0.15342450754949277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248104173","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000387168,0.000031150536,0.96260697,0.0013520622,0.0031978136,0.0002535539,0.000033647422,0.00007792044,0.032059737],"genre_scores_gemma":[0.031075671,0.000058885802,0.9659629,0.00090348016,0.0006032037,0.0000075822945,0.0000048110724,0.000015442996,0.0013680292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796355,0.00034222077,0.00081110105,0.0002475206,0.0003857774,0.00024981642],"domain_scores_gemma":[0.96447575,0.034891866,0.00015313269,0.00028234778,0.000093034934,0.00010386584],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026257958,0.00013803742,0.00052461453,0.00011637856,0.00003473858,0.000006479632,0.0001481196,0.0000966019,0.0009646682],"category_scores_gemma":[0.20617773,0.000109671215,0.000020263207,0.00029231637,0.00017535723,0.000022763074,0.000014876112,0.00037204562,0.000031239775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052117888,0.00009545128,0.00018589383,0.000019340036,0.000006106393,0.000054458866,0.0001536737,0.0000015296939,0.000082748855,0.63935256,0.21446794,0.14552815],"study_design_scores_gemma":[0.000989412,0.0004688373,0.0067631565,0.0001674776,0.000034174835,0.0000072230287,0.000062858046,0.0014379077,0.000052741678,0.9887634,0.0011395273,0.00011326562],"about_ca_topic_score_codex":0.00001713375,"about_ca_topic_score_gemma":0.000018012084,"teacher_disagreement_score":0.34941083,"about_ca_system_score_codex":0.0000652879,"about_ca_system_score_gemma":0.000026483827,"threshold_uncertainty_score":0.99994856},"labels":[],"label_agreement":null},{"id":"W4248702657","doi":"10.1002/9781118445112.stat07066","title":"Pharmacoepidemiology, Overview","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pharmacoepidemiology; Observational study; Confounding; Context (archaeology); Medicine; Medical prescription; Randomized controlled trial; Causality (physics); Intensive care medicine; Pharmacology; Internal medicine; Geography","score_opus":0.6925857855267518,"score_gpt":0.6141507203662222,"score_spread":0.07843506516052956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248702657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018954422,0.0023651894,0.79716426,0.00029446284,0.0025560209,0.0013296385,0.08705707,0.00096845103,0.10826303],"genre_scores_gemma":[0.000003928072,0.013514741,0.78920686,0.0011904138,0.0017621404,0.0000913092,0.0015317606,0.0012485458,0.19145028],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98977184,0.003476233,0.0028378894,0.0016162174,0.0010331655,0.0012646694],"domain_scores_gemma":[0.9401157,0.05458693,0.0023934953,0.0018623435,0.00033222744,0.0007093189],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.003610826,0.0013020964,0.0037220865,0.00040424583,0.000110139306,0.00006510081,0.0013448558,0.0013581472,0.03176803],"category_scores_gemma":[0.093637645,0.0011131229,0.00025739294,0.0003719464,0.00084206957,0.00003752919,0.0004738478,0.0020118887,0.0015249362],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041863386,0.0003100041,0.000019093193,0.0010150159,0.00025681828,0.000042793683,0.000008089511,4.908093e-7,0.0000056718904,0.31283578,0.6461163,0.039348084],"study_design_scores_gemma":[0.00082049373,0.00018136196,0.000015923106,0.0010507724,0.00043545078,0.0000068131644,0.000006502271,0.00030097683,0.0000028542165,0.50441885,0.4920532,0.0007067774],"about_ca_topic_score_codex":0.00023369881,"about_ca_topic_score_gemma":0.00045227126,"teacher_disagreement_score":0.1915831,"about_ca_system_score_codex":0.00015112107,"about_ca_system_score_gemma":0.00032677394,"threshold_uncertainty_score":0.99997306},"labels":[],"label_agreement":null},{"id":"W4249051753","doi":"10.1007/978-3-319-24612-3_1115","title":"Type B Behavior Pattern","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Type (biology); Geology; Paleontology","score_opus":0.7838106635775601,"score_gpt":0.5879229822764437,"score_spread":0.19588768130111645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249051753","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013056558,0.000028050226,0.05252201,0.0003442267,0.001227938,0.0005667659,0.00015968824,0.00024229093,0.9449077],"genre_scores_gemma":[0.000039441373,0.00003254035,0.47474632,0.0008313341,0.00077862485,0.000012736101,0.0000057927327,0.0001261709,0.52342707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980099,0.000075266806,0.000871783,0.00047041764,0.00040085908,0.00017173508],"domain_scores_gemma":[0.98223144,0.016614106,0.00027703834,0.000556258,0.00012162396,0.00019951236],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00050939934,0.00032975854,0.00094694324,0.00003574605,0.000024808625,0.000027794891,0.0003123099,0.0005638104,0.030733783],"category_scores_gemma":[0.018093456,0.00026973244,0.00024055174,0.000019032388,0.00009995594,0.000013063213,0.00019657759,0.00064693304,0.0035843863],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013947708,0.000023772058,0.000006724523,0.000091536596,0.00006714557,0.000107324704,0.0000061219284,2.7593192e-9,0.000004284432,0.88355947,0.0542316,0.06188808],"study_design_scores_gemma":[0.00018987943,0.00014330502,0.0000064818178,0.00008444204,0.00040401923,0.000003525507,0.0000010837878,0.0000038238004,0.000026070355,0.9160003,0.08283659,0.00030047444],"about_ca_topic_score_codex":0.0000026091086,"about_ca_topic_score_gemma":0.0000028037061,"teacher_disagreement_score":0.4222243,"about_ca_system_score_codex":0.000032765776,"about_ca_system_score_gemma":0.000050736064,"threshold_uncertainty_score":0.9999755},"labels":[],"label_agreement":null},{"id":"W4249082046","doi":"10.1093/humrep/deh021","title":"Reply","year":2003,"lang":"en","type":"article","venue":"Human Reproduction","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Gynecology","score_opus":0.690013135230439,"score_gpt":0.585945323489247,"score_spread":0.10406781174119195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249082046","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43179524,0.00020503292,0.22558722,0.0026132893,0.00964387,0.0020550299,0.000009840085,0.0016362531,0.32645422],"genre_scores_gemma":[0.11074938,0.000005767864,0.87878835,0.00018949434,0.0009874561,0.000033045024,6.482007e-7,0.00003553269,0.009210351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811304,0.0005668845,0.00047196652,0.0005050583,0.00019189692,0.000151176],"domain_scores_gemma":[0.99656427,0.0021810378,0.00015767048,0.00095433806,0.00009022069,0.000052444848],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00425321,0.000088831424,0.00022149534,0.00003798042,0.00011714619,0.000019808771,0.00007195171,0.000054935408,0.0008686613],"category_scores_gemma":[0.12406013,0.00008051315,0.000067054534,0.00012874206,0.000078964425,0.000033497476,0.0000149778325,0.00015520201,0.00009456873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009203542,0.00011236252,0.00018078259,0.00003252854,0.00001610935,0.0000029121834,0.000051514515,5.577061e-7,0.002127156,0.97560483,0.015297867,0.006564188],"study_design_scores_gemma":[0.00020502436,0.000056450834,0.000413482,0.000010520452,0.000025680572,0.000015065522,0.000020881453,7.581104e-7,0.014396048,0.95049393,0.034268294,0.0000938805],"about_ca_topic_score_codex":0.000003770617,"about_ca_topic_score_gemma":6.512999e-7,"teacher_disagreement_score":0.6532011,"about_ca_system_score_codex":0.000029629644,"about_ca_system_score_gemma":0.000011733665,"threshold_uncertainty_score":0.9511231},"labels":[],"label_agreement":null},{"id":"W4251203905","doi":"10.1177/2168479019841316","title":"Defining Efficacy Estimands in Clinical Trials: Examples Illustrating ICH E9(R1) Guidelines","year":2019,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Eli Lilly (Canada)","funders":"","keywords":"Pharmacy; Clinical trial; Computer science; Psychology; Outcomes research; Management science; Process (computing); Medicine; Alternative medicine; Family medicine; Economics","score_opus":0.8082886026921876,"score_gpt":0.6538258654569911,"score_spread":0.15446273723519655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251203905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92865986,0.00009335385,0.06519594,0.00066856144,0.0020623247,0.0010795705,0.0000087935405,0.00018218286,0.0020494312],"genre_scores_gemma":[0.58366406,0.0000061056658,0.41500396,0.00086269766,0.00025153492,0.000018599148,0.0000018092206,0.000028803677,0.00016245765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98862123,0.0024768072,0.0059240866,0.0010070824,0.0013090244,0.000661754],"domain_scores_gemma":[0.88153887,0.11122963,0.0030300054,0.0018771718,0.002123899,0.00020041286],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13372321,0.0003244051,0.0013782153,0.00059926626,0.00022308159,0.00017852234,0.00088623184,0.00028991888,0.0003490176],"category_scores_gemma":[0.2880754,0.00026364363,0.00016036985,0.0040810667,0.0011184879,0.0003958529,0.0001795224,0.00064317056,0.000105560175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017291964,0.00014345732,0.01286185,0.000040292838,0.000027105549,0.0000018226898,0.00015142404,0.00008289276,0.004631068,0.7487236,0.00012150907,0.23304206],"study_design_scores_gemma":[0.0037148918,0.00047979425,0.086575605,0.00044575514,0.00006774689,0.000009020736,0.00029717135,0.021637196,0.0019599684,0.8834071,0.0008009365,0.0006047894],"about_ca_topic_score_codex":0.000011456467,"about_ca_topic_score_gemma":0.000004540447,"teacher_disagreement_score":0.349808,"about_ca_system_score_codex":0.00013221819,"about_ca_system_score_gemma":0.0007863302,"threshold_uncertainty_score":0.9999816},"labels":[],"label_agreement":null},{"id":"W4251591017","doi":"10.3410/f.3856956.793455818","title":"Faculty Opinions recommendation of Mortality results from the Göteborg randomised population-based prostate-cancer screening trial.","year":2012,"lang":"en","type":"dataset","venue":"Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Prostate cancer; Medicine; Population; Prostate cancer screening; Family medicine; Gynecology; Cancer; Internal medicine; Prostate-specific antigen; Environmental health","score_opus":0.35940168104991405,"score_gpt":0.5414222484200644,"score_spread":0.18202056737015032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251591017","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002227583,0.00050243636,0.00081800093,0.13820545,0.0023288343,0.006180224,0.8518773,0.00006211617,0.000023433344],"genre_scores_gemma":[0.000009152433,0.00020999473,0.03752938,0.0036845608,0.0013568494,0.001176894,0.95573837,0.00005718938,0.00023763819],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98453045,0.0052484707,0.005790284,0.0010463106,0.0028190948,0.00056538003],"domain_scores_gemma":[0.94910085,0.03181098,0.0078893285,0.0037661016,0.0069216895,0.00051102985],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01452357,0.00081270485,0.0024436335,0.00020275565,0.00040565533,0.0001933049,0.0023834754,0.0011687982,0.0012766315],"category_scores_gemma":[0.3669855,0.000443632,0.0013818719,0.002002572,0.0005394033,0.00027524604,0.00051710155,0.0018598866,0.000025090278],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027607828,0.0006698069,0.000027826476,0.0033115689,0.00046860205,1.284882e-7,0.00008719953,3.9239274e-7,3.0301487e-7,0.00042545729,0.98810333,0.004144624],"study_design_scores_gemma":[0.031560663,0.00011138681,0.0028321042,0.0134947505,0.0012346761,0.0000011563194,0.000017998387,0.000028269453,0.000008956758,0.0025967793,0.9476639,0.00044936332],"about_ca_topic_score_codex":0.00058806647,"about_ca_topic_score_gemma":0.000027854565,"teacher_disagreement_score":0.35246193,"about_ca_system_score_codex":0.00015716848,"about_ca_system_score_gemma":0.00066719315,"threshold_uncertainty_score":0.9998015},"labels":[],"label_agreement":null},{"id":"W4251732303","doi":"10.21203/rs.2.9437/v1","title":"Systematic review of basket trials, umbrella trials, and platform trials: A landscape analysis of master protocols","year":2019,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University","funders":"","keywords":"Medicine; Interquartile range; Clinical trial; Sample size determination; Randomization; MEDLINE; Randomized controlled trial; Internal medicine; Statistics","score_opus":0.8863518669458177,"score_gpt":0.7022952144570832,"score_spread":0.18405665248873448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251732303","genre_codex":"protocol","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018205298,0.099767685,0.069727294,0.0013230832,0.0014236993,0.79419595,0.025287375,0.00024858004,0.006205771],"genre_scores_gemma":[0.011102424,0.13178231,0.6214102,0.0002826738,0.0027720265,0.22751997,0.00074840017,0.0008315066,0.0035504927],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.7987051,0.15932761,0.031417046,0.0022033209,0.0070275827,0.001319338],"domain_scores_gemma":[0.38806787,0.5931648,0.011829115,0.0037815336,0.0027558196,0.00040083643],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.52856094,0.0007978368,0.035018194,0.0019728914,0.00007898872,0.00019857871,0.0015286932,0.0013291324,0.002656949],"category_scores_gemma":[0.9206074,0.0005035047,0.004836043,0.0022068997,0.0004102593,0.0000785898,0.0019185201,0.002204693,0.000029116914],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015203792,0.00046834518,0.00011866987,0.9723217,0.012274431,0.000009364988,0.00016295839,0.0000069878515,0.000043922857,0.007862286,0.004282844,0.0009281447],"study_design_scores_gemma":[0.0041449405,0.0008614357,0.000080005244,0.76616377,0.02976946,0.0000023237942,0.00030298086,0.0016534384,0.00031308053,0.19602956,0.00011166608,0.00056731707],"about_ca_topic_score_codex":0.000048215188,"about_ca_topic_score_gemma":0.000009219015,"teacher_disagreement_score":0.566676,"about_ca_system_score_codex":0.00015623667,"about_ca_system_score_gemma":0.0010342307,"threshold_uncertainty_score":0.99996734},"labels":[],"label_agreement":null},{"id":"W4251738519","doi":"10.32920/ryerson.14664120","title":"Effective Multi-level Monte Carlo Methods for Stochastic Biochemical Kinetics","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Memorial University of Newfoundland","funders":"","keywords":"Monte Carlo method; Stochastic modelling; Stochastic simulation; Stochastic process; Computer science; Statistical physics; Kinetic Monte Carlo; Mathematical optimization; Applied mathematics; Mathematics; Physics; Statistics","score_opus":0.7206932361431452,"score_gpt":0.6524587646822684,"score_spread":0.0682344714608768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251738519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013794006,0.00035973298,0.98846596,0.00019841603,0.0033540246,0.0049776156,0.0008059194,0.00026140362,0.00019750053],"genre_scores_gemma":[0.0041740695,0.000015986156,0.99169356,0.00019138475,0.00076137745,0.0021888583,0.00002099881,0.00019810627,0.0007556818],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925141,0.0028165905,0.0019363256,0.0016068609,0.00042907047,0.0006970665],"domain_scores_gemma":[0.7985335,0.19840072,0.00058898854,0.0013341062,0.00081657525,0.00032613223],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0058836653,0.00081466924,0.0026846027,0.00012614448,0.0000689574,0.00015853679,0.00079530093,0.0016181108,0.00023441241],"category_scores_gemma":[0.44707802,0.0007100076,0.0010650568,0.00018748386,0.00031419657,0.000024522567,0.0019326989,0.0015619079,0.000008327925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016464771,0.007590835,0.00001658409,0.01652574,0.007252871,0.00007671753,0.0017384575,0.0016339634,0.052244067,0.08016651,0.016998114,0.8141097],"study_design_scores_gemma":[0.0028996246,0.00030242946,0.00008708996,0.0009094415,0.0016901548,0.000008680176,0.00013183132,0.06880131,0.044492424,0.87937874,0.000083834486,0.0012144732],"about_ca_topic_score_codex":0.000030251727,"about_ca_topic_score_gemma":0.000009344932,"teacher_disagreement_score":0.8128952,"about_ca_system_score_codex":0.0002519223,"about_ca_system_score_gemma":0.00018884886,"threshold_uncertainty_score":0.999678},"labels":[],"label_agreement":null},{"id":"W4251890067","doi":"10.1002/9781118445112.stat05890","title":"Loss Function","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Minimax; Frequentist inference; Decision theory; Bayesian probability; Function (biology); Expected utility hypothesis; Prospect theory; Computer science; Econometrics; Mathematics; Mathematical economics; Statistics; Bayesian inference; Artificial intelligence; Economics","score_opus":0.43340476732197836,"score_gpt":0.5261208180433039,"score_spread":0.09271605072132555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251890067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035590383,0.00023527678,0.84064233,0.000086397304,0.0023239183,0.0008551557,0.04650442,0.0007809352,0.108568035],"genre_scores_gemma":[0.000025089521,0.0011841021,0.73756,0.00032633194,0.00172809,0.00006230067,0.0015098059,0.0011515904,0.25645274],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99311185,0.0012503312,0.0019921178,0.0013652855,0.001312659,0.00096774695],"domain_scores_gemma":[0.97506773,0.020554675,0.0017108695,0.0017443147,0.00038584444,0.00053657056],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015783481,0.0010702914,0.0022779463,0.00041506227,0.000115045324,0.00010627284,0.0008669875,0.0012338136,0.022017661],"category_scores_gemma":[0.039943665,0.0009438619,0.00017821294,0.0003640123,0.00063773536,0.000041599338,0.00029134462,0.0015161639,0.0015642014],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009234667,0.00032821734,0.000020353102,0.00059224525,0.00021008382,0.00004030341,0.000008730405,5.3708214e-7,0.0000047386984,0.34239483,0.616125,0.04018263],"study_design_scores_gemma":[0.00081073545,0.00034696737,0.00003380349,0.0007234932,0.00041912583,0.000005291713,0.000011334578,0.00016597145,0.0000025294962,0.56986886,0.42693684,0.0006750374],"about_ca_topic_score_codex":0.00012355985,"about_ca_topic_score_gemma":0.0005395635,"teacher_disagreement_score":0.22747403,"about_ca_system_score_codex":0.00014553871,"about_ca_system_score_gemma":0.00028707852,"threshold_uncertainty_score":0.9993012},"labels":[],"label_agreement":null},{"id":"W4251986301","doi":"10.5351/kjas.2002.15.2.281","title":"Statistical consideration of assessing bioequivalence in the new KFDA regulation","year":2002,"lang":"en","type":"article","venue":"Korean Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Medicine; Confidence interval; Guideline; Equivalence (formal languages); Medical prescription; Food and drug administration; Statistics; Actuarial science; Econometrics; Pharmacology; Mathematics; Pharmacokinetics; Internal medicine; Economics","score_opus":0.4802062970807835,"score_gpt":0.5125779966137606,"score_spread":0.03237169953297708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251986301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00470148,0.000029644232,0.99096245,0.00037916747,0.00025006503,0.00028494492,0.00013383971,0.000008793468,0.0032495938],"genre_scores_gemma":[0.35599712,0.000030103538,0.64367074,0.000081378676,0.00018439027,0.0000015989795,0.0000021345495,0.00001616611,0.00001634387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958813,0.0006316625,0.0021643962,0.00018484495,0.00088405865,0.00025374675],"domain_scores_gemma":[0.9506878,0.04724642,0.0013708116,0.00029984178,0.0002678719,0.0001272332],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004065077,0.00018756927,0.00069452845,0.00014929635,0.000066182794,0.00008920125,0.00031787946,0.000119516306,0.0006364041],"category_scores_gemma":[0.032984186,0.00013472994,0.000064717206,0.0002956883,0.00031433292,0.00010771103,0.000031221258,0.0004974142,0.0000078097755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102686114,0.00022100672,0.00013836694,0.000106129904,0.0000373058,0.00005383829,0.00089851825,0.000073995136,0.000731122,0.9196201,0.027132358,0.05088455],"study_design_scores_gemma":[0.0012262543,0.00021464753,0.0024752691,0.00011472472,0.0001602886,0.00004866816,0.00038311855,0.0026995428,0.00085534295,0.991569,0.00011517318,0.00013800696],"about_ca_topic_score_codex":0.0000045928386,"about_ca_topic_score_gemma":0.000006059684,"teacher_disagreement_score":0.35129565,"about_ca_system_score_codex":0.00005957746,"about_ca_system_score_gemma":0.00011899169,"threshold_uncertainty_score":0.9751614},"labels":[],"label_agreement":null},{"id":"W4252029050","doi":"10.1002/sim.3909","title":"Construction of confidence limits about effect measures: A general approach—Reply","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Biostatistics; Epidemiology; Library science; Citation; Confidence interval; Medicine; History; Demography; Family medicine; Sociology; Computer science; Pathology","score_opus":0.29723315980429194,"score_gpt":0.5271650463082589,"score_spread":0.22993188650396695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252029050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020056635,0.00006622626,0.9700155,0.0001637144,0.0023067319,0.00077503436,0.00022921653,0.000054178876,0.0063327504],"genre_scores_gemma":[0.045084935,0.00008545792,0.95390105,0.00016441332,0.0005770487,0.00005108431,0.000009055275,0.000034739212,0.000092186994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99593455,0.00092505274,0.0015374377,0.00043635684,0.00082555047,0.00034105356],"domain_scores_gemma":[0.9493467,0.049035672,0.0005275797,0.0005974815,0.00031988125,0.0001726419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075377757,0.00025864973,0.0011836697,0.0001708126,0.00004627736,0.000010317403,0.00032440867,0.00020628146,0.0003679782],"category_scores_gemma":[0.28135228,0.00019737467,0.000054101376,0.00032563097,0.0015608694,0.00003473605,0.000045309233,0.00088407635,0.000007085677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019081637,0.000109794375,0.001945098,0.0005381455,0.00005424176,0.000025164163,0.00027520067,0.0000023482473,0.005816514,0.9357249,0.0039578914,0.05135986],"study_design_scores_gemma":[0.0025039518,0.0005715628,0.0023114237,0.00030243237,0.00017375464,0.000036845566,0.00007023711,0.0015314105,0.0022741123,0.98964596,0.00037535102,0.00020293774],"about_ca_topic_score_codex":0.000113674476,"about_ca_topic_score_gemma":0.000047229085,"teacher_disagreement_score":0.27381453,"about_ca_system_score_codex":0.00003091735,"about_ca_system_score_gemma":0.0000960438,"threshold_uncertainty_score":0.80487055},"labels":[],"label_agreement":null},{"id":"W4253174027","doi":"10.1200/jco.2007.25.18_suppl.6514","title":"The transition from phase II to phase III studies","year":2007,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Western University","funders":"","keywords":"Medicine; Clinical trial; Phase (matter); Phases of clinical research; Regimen; Randomized controlled trial; Internal medicine; Oncology","score_opus":0.8345654492440351,"score_gpt":0.75241606543189,"score_spread":0.0821493838121451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253174027","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5943551,0.00033757786,0.3753672,0.0195674,0.008484536,0.00044386633,0.00003723833,0.000025785528,0.0013812971],"genre_scores_gemma":[0.22141877,0.0007287387,0.76504904,0.005183435,0.0074014096,0.0000070933506,5.898732e-7,0.000031715732,0.00017923003],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9884247,0.0025424045,0.0076808645,0.00027289067,0.0006621286,0.00041696883],"domain_scores_gemma":[0.59343517,0.40163577,0.0029984722,0.0003777738,0.00091959833,0.00063318573],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05525371,0.00019429061,0.0024669962,0.00008006936,0.00024869232,0.00001829976,0.00051525974,0.00044930985,0.0002536615],"category_scores_gemma":[0.41026765,0.00011059622,0.0007189943,0.00021295097,0.0005444898,0.00008105365,0.000120828874,0.0013289589,0.000023720615],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020563245,0.0065566604,0.0000093798035,0.000010591507,0.000998619,0.00043796984,0.0010080647,0.0000019505521,0.00037064543,0.010966844,0.03398375,0.9250923],"study_design_scores_gemma":[0.029733589,0.029662963,0.0001076001,0.00008516446,0.0006939995,0.000026625808,0.0010380262,0.00004061416,0.0005671292,0.8376378,0.100252576,0.00015391018],"about_ca_topic_score_codex":0.00000452112,"about_ca_topic_score_gemma":0.000041771866,"teacher_disagreement_score":0.9249384,"about_ca_system_score_codex":0.00013138852,"about_ca_system_score_gemma":0.00037872247,"threshold_uncertainty_score":0.9728151},"labels":[],"label_agreement":null},{"id":"W4253422237","doi":"10.1002/9781118762516.index","title":"Index","year":2014,"lang":"en","type":"paratext","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Biostatistics; Index (typography); Library science; Citation; History; Medicine; Epidemiology; Computer science; World Wide Web; Internal medicine","score_opus":0.6816016167636747,"score_gpt":0.629782089966991,"score_spread":0.05181952679668367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253422237","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013150604,0.000018275286,0.4652174,0.00010479955,0.0036967015,0.0001992285,0.00005451433,0.00004686049,0.5306609],"genre_scores_gemma":[0.000030906605,0.000030600248,0.51148975,0.0004587296,0.0016592601,0.000025470272,0.000004179421,0.00005668926,0.4862444],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969424,0.00085915,0.0010110829,0.0004623394,0.000411234,0.0003137721],"domain_scores_gemma":[0.91176605,0.0868567,0.00035013777,0.0007804571,0.00010055696,0.00014607213],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023923768,0.00031309255,0.0012830938,0.0000731451,0.000035189707,0.00004550246,0.00046541888,0.0008970555,0.123571545],"category_scores_gemma":[0.09951827,0.00023186296,0.00024175752,0.00010191492,0.00012377334,0.000012008447,0.00016948784,0.0007209964,0.056535624],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011408467,0.000034337783,0.0000010788991,0.00021879401,0.00005259044,0.0000012683023,0.0000025068439,2.4651627e-7,9.515191e-7,0.124262266,0.867634,0.007780548],"study_design_scores_gemma":[0.00021122766,0.00003432289,0.0000019137992,0.000078242694,0.000042318283,9.471508e-7,0.0000012799685,0.00003609221,0.00003526422,0.59629446,0.40306762,0.000196321],"about_ca_topic_score_codex":0.000009892147,"about_ca_topic_score_gemma":0.0000022615923,"teacher_disagreement_score":0.4720322,"about_ca_system_score_codex":0.00003502144,"about_ca_system_score_gemma":0.00007295025,"threshold_uncertainty_score":0.9455097},"labels":[],"label_agreement":null},{"id":"W4253722978","doi":"10.1002/0471667196.ess7190","title":"Pharmacoepidemiology, Overview","year":2005,"lang":"en","type":"other","venue":"Encyclopedia of Statistical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Pharmacoepidemiology; Observational study; Confounding; Context (archaeology); Medical prescription; Medicine; Causality (physics); Randomized controlled trial; Intensive care medicine; Computer science; Pharmacology; Internal medicine; Geography","score_opus":0.4977696773901826,"score_gpt":0.5997718060092528,"score_spread":0.10200212861907026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253722978","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001858168,0.00162433,0.10712369,0.00033129344,0.0012655534,0.00048222384,0.0013070838,0.00017018132,0.88769376],"genre_scores_gemma":[0.0000072281146,0.0070368447,0.830417,0.00023616538,0.0012640095,0.000032655582,0.0000048442284,0.00016691143,0.16083437],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949053,0.001363762,0.0014817168,0.00080092665,0.0008348881,0.00061342085],"domain_scores_gemma":[0.9224489,0.07593344,0.00089283416,0.0003943142,0.0000468196,0.0002837171],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005221086,0.00041951108,0.0016919018,0.00019507365,0.000067583234,0.000016339176,0.00090724527,0.00044189204,0.071146496],"category_scores_gemma":[0.10786411,0.0003084665,0.00016964762,0.00040648718,0.0026335502,0.000038556736,0.0002193186,0.0004607218,0.0003091313],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055494415,0.000086182044,0.00005604804,0.00020765186,0.000033436634,0.000006077286,0.000007230626,1.7577761e-7,7.723707e-7,0.418617,0.53055114,0.050428737],"study_design_scores_gemma":[0.00020524322,0.00011311911,0.00007904543,0.00023293823,0.00013124893,0.0000021179096,0.0000069320945,0.00004024229,0.0000032029359,0.512854,0.4860838,0.00024814863],"about_ca_topic_score_codex":0.00014350105,"about_ca_topic_score_gemma":0.000045455894,"teacher_disagreement_score":0.7268594,"about_ca_system_score_codex":0.0000292836,"about_ca_system_score_gemma":0.00019254588,"threshold_uncertainty_score":0.99993676},"labels":[],"label_agreement":null},{"id":"W4253953616","doi":"10.1017/cbo9781139194648.019","title":"Epilogue","year":2013,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Variety (cybernetics); Simple (philosophy); Taste; Independence (probability theory); Computer science; Epistemology; Psychology; Mathematics; Artificial intelligence; Philosophy; Statistics","score_opus":0.4087568119758443,"score_gpt":0.407867141327465,"score_spread":0.0008896706483793038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253953616","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000092066075,0.000027411123,0.017199093,0.000025309262,0.0006484595,0.000833327,0.00064257556,0.00026368222,0.9803509],"genre_scores_gemma":[0.00001413238,0.000052013325,0.12337845,0.000086454274,0.00036207924,0.0000017210484,0.000008694259,0.00009554355,0.8760009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977081,0.00024607166,0.00056333106,0.0006871051,0.00041659025,0.00037884014],"domain_scores_gemma":[0.9859886,0.011849873,0.0005220626,0.0010539228,0.00026361074,0.00032193642],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058374746,0.00049869856,0.0011024378,0.00012961199,0.00012865457,0.00004571786,0.00076807186,0.00085533824,0.00020877727],"category_scores_gemma":[0.0035662246,0.000530417,0.00042042797,0.000006727517,0.00049451046,0.00004929341,0.0005801347,0.00090577855,0.0002957948],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044626628,0.000012425681,1.3971564e-7,0.0001311535,0.00016478942,0.00015373295,0.000006000211,3.911723e-8,0.0000064608657,0.78391844,0.21227251,0.0032896553],"study_design_scores_gemma":[0.0007163978,0.000083724015,0.0000024406204,0.00026813577,0.0005432127,0.000009157061,0.000006842838,0.000017690703,0.0001211286,0.10179107,0.8958383,0.0006018962],"about_ca_topic_score_codex":0.000041696745,"about_ca_topic_score_gemma":4.6554842e-7,"teacher_disagreement_score":0.6835658,"about_ca_system_score_codex":0.00017634135,"about_ca_system_score_gemma":0.000090064204,"threshold_uncertainty_score":0.99971473},"labels":[],"label_agreement":null},{"id":"W4255692848","doi":"10.1002/9781118445112.stat06900","title":"Collinearity","year":2014,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario","funders":"","keywords":"Citation; Encyclopedia; Library science; Collinearity; Computer science; Information retrieval; Operations research; Statistics; Mathematics","score_opus":0.5338410012981853,"score_gpt":0.5564268446970437,"score_spread":0.022585843398858385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255692848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000037389702,0.00023314137,0.76034945,0.000111800044,0.0015887708,0.0010935282,0.093371466,0.0008181628,0.14242992],"genre_scores_gemma":[0.000009121159,0.0012845368,0.72184736,0.0002898506,0.0013986614,0.000058900558,0.0013193601,0.0011165071,0.27267572],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992485,0.0014585999,0.0021784997,0.0014218976,0.001398686,0.001057308],"domain_scores_gemma":[0.96729386,0.02792482,0.0017454054,0.001947348,0.00043794702,0.0006506355],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019057005,0.0011288836,0.0027477674,0.00038333324,0.00012483945,0.00012235066,0.0011587121,0.0013420578,0.019847807],"category_scores_gemma":[0.066460505,0.0010046288,0.00018928487,0.0004095892,0.0007411403,0.000032995227,0.00038892694,0.0017575419,0.0012143976],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053242667,0.00044921515,0.000020022737,0.0006452742,0.0001851736,0.000050586546,0.000010950945,5.0160094e-7,0.0000043598766,0.29388604,0.6825112,0.022183456],"study_design_scores_gemma":[0.00084688544,0.00023842849,0.000019241425,0.00071675377,0.0003036645,0.000004818699,0.000010392524,0.00040845716,0.0000046133546,0.53285974,0.46384826,0.00073875295],"about_ca_topic_score_codex":0.00023317091,"about_ca_topic_score_gemma":0.0009926457,"teacher_disagreement_score":0.23897369,"about_ca_system_score_codex":0.00015701876,"about_ca_system_score_gemma":0.0004227436,"threshold_uncertainty_score":0.9999544},"labels":[],"label_agreement":null},{"id":"W4256045669","doi":"10.21203/rs.3.rs-15483/v2","title":"Explaining the variation in the attained power of a stepped-wedge trial with unequal cluster sizes","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Servier; Bayer Canada; Vancouver Coastal Health Research Institute; Biogen; Michael Smith Health Research BC; Compute Canada; Western Canada Research Grid; Heart and Stroke Foundation of Canada","keywords":"Wedge (geometry); Cluster (spacecraft); Variation (astronomy); Statistics; Econometrics; Mathematics; Computer science; Physics; Geometry; Astrophysics","score_opus":0.6774186248520271,"score_gpt":0.6187126014312694,"score_spread":0.0587060234207577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256045669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46244544,0.00030683048,0.422301,0.047657363,0.0023405124,0.050874732,0.0013452239,0.0002971153,0.012431798],"genre_scores_gemma":[0.8746406,0.00002576139,0.122853406,0.00015559538,0.00087999215,0.0012779855,0.000013001239,0.00007813404,0.00007554222],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97539055,0.018755987,0.0016028086,0.0007541412,0.002845842,0.00065066724],"domain_scores_gemma":[0.7699707,0.22735082,0.0005538563,0.0013969654,0.0006153747,0.00011226531],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035701483,0.00031755326,0.0010539112,0.00018968344,0.00017000748,0.00019359526,0.0014545086,0.0004691434,0.0002412729],"category_scores_gemma":[0.26163998,0.00015890725,0.00024082398,0.00080833473,0.00048172954,0.00004919046,0.00127508,0.0033787694,0.000018936706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17458089,0.0027441524,0.00042929818,0.006892549,0.0010304312,0.00024826272,0.090953685,0.0005364586,0.0001928284,0.69802356,0.01915969,0.0052082078],"study_design_scores_gemma":[0.025374167,0.0026928894,0.001400388,0.0013596597,0.000120201876,0.0000017958216,0.007259026,0.0024314423,0.00006624931,0.9587416,0.00022842578,0.0003241525],"about_ca_topic_score_codex":0.000099797624,"about_ca_topic_score_gemma":0.000045915247,"teacher_disagreement_score":0.41219515,"about_ca_system_score_codex":0.00013456326,"about_ca_system_score_gemma":0.0006222544,"threshold_uncertainty_score":0.9989205},"labels":[],"label_agreement":null},{"id":"W4256561221","doi":"10.22215/etd/2008-08057","title":"A statistical test for a parameter describing the association in correlated binary data","year":2008,"lang":"en","type":"dissertation","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Binary number; Test (biology); Statistics; Association (psychology); Mathematics; Computer science; Humanities; Arithmetic; Psychology; Art","score_opus":0.7393740798197711,"score_gpt":0.5644858879880205,"score_spread":0.17488819183175064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256561221","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039130352,0.00039724717,0.8822215,0.0017402276,0.0116626555,0.018597221,0.019845363,0.00084646384,0.025558967],"genre_scores_gemma":[0.0053448123,0.0001223011,0.98184204,0.00020815735,0.00027404734,0.00039137498,0.0025176038,0.00012603086,0.009173624],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955331,0.0008889197,0.0017114254,0.00075941056,0.00061601796,0.000491125],"domain_scores_gemma":[0.6624669,0.33583698,0.0006207749,0.0008147903,0.00019393094,0.000066640285],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005592304,0.0003536463,0.0010222959,0.00011477415,0.00014467713,0.00008431341,0.00083084864,0.00085943507,0.00028046285],"category_scores_gemma":[0.64832085,0.00024618517,0.00012631132,0.00031599146,0.00006127611,0.00009004111,0.00011981293,0.0009845267,0.000044577668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026451417,0.0035957065,0.009551481,0.0019116972,0.0011995634,0.00019132372,0.0022247387,0.000008896687,0.0002401159,0.19912013,0.6932095,0.086101696],"study_design_scores_gemma":[0.0024160363,0.0003511967,0.0065087075,0.0006528226,0.0008229183,0.0000056707195,0.0005518609,0.02589547,0.00007030949,0.96074253,0.001297695,0.0006847582],"about_ca_topic_score_codex":0.00007469915,"about_ca_topic_score_gemma":0.00038211688,"teacher_disagreement_score":0.7616224,"about_ca_system_score_codex":0.00026141686,"about_ca_system_score_gemma":0.0002538215,"threshold_uncertainty_score":0.99999905},"labels":[],"label_agreement":null},{"id":"W4280542190","doi":"10.1002/pst.2234","title":"Standard and reference‐based conditional mean imputation","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Missing data; Jackknife resampling; Frequentist inference; Imputation (statistics); Pooling; Computer science; Statistics; Inference; Bayesian probability; Econometrics; Bayesian inference; Mathematics; Estimator; Artificial intelligence","score_opus":0.6731853966455711,"score_gpt":0.6174407262752281,"score_spread":0.05574467037034303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280542190","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025812113,0.000037762136,0.9832269,0.00079589273,0.00037159424,0.00046198856,0.011187673,0.00012762703,0.0012093771],"genre_scores_gemma":[0.22387663,0.0000134119055,0.77456295,0.0011140183,0.00010134939,0.00010810935,0.0001196899,0.000035461086,0.00006839646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99635136,0.0011813228,0.00073198037,0.00041690958,0.00094268174,0.00037573566],"domain_scores_gemma":[0.9646532,0.03448611,0.00019051488,0.00018926727,0.00016483126,0.0003161095],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002377775,0.00020537393,0.00043934802,0.000072675706,0.0004041483,0.000055890552,0.00018628828,0.000061879626,0.007100018],"category_scores_gemma":[0.014729859,0.00020411133,0.00004577581,0.00019126381,0.0003269003,0.000042394528,0.00020608676,0.0006723935,0.000020455496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046352847,0.00019516518,0.00023072171,0.00012008679,0.000056175082,0.00005639077,0.000055712066,0.00007420139,0.00009741197,0.95832396,0.013394936,0.026931744],"study_design_scores_gemma":[0.0020169981,0.00032879738,0.00030306188,0.000006778095,0.0001713026,0.000014182257,0.000047501253,0.025863592,0.00028537342,0.9508915,0.019820236,0.0002506862],"about_ca_topic_score_codex":0.000004413636,"about_ca_topic_score_gemma":0.0000020183782,"teacher_disagreement_score":0.22129542,"about_ca_system_score_codex":0.00016274591,"about_ca_system_score_gemma":0.00013312462,"threshold_uncertainty_score":0.9938076},"labels":[],"label_agreement":null},{"id":"W4280546958","doi":"10.1038/s41433-022-02108-0","title":"Sensitivity analysis in clinical trials: three criteria for a valid sensitivity analysis","year":2022,"lang":"en","type":"letter","venue":"Eye","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; Impact","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Sensitivity (control systems); Medicine; Engineering","score_opus":0.7555676095515504,"score_gpt":0.6531789994994113,"score_spread":0.10238861005213917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280546958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028654176,0.000037163387,0.8654903,0.11481355,0.0029925937,0.0029368564,0.010262641,0.00023527163,0.00036620555],"genre_scores_gemma":[0.0035418503,0.000040547282,0.8495933,0.13078125,0.012974271,0.00067713216,0.0010663884,0.00027549025,0.0010497902],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9118049,0.0754687,0.0075998157,0.0025003343,0.001496229,0.0011300332],"domain_scores_gemma":[0.5130447,0.4817008,0.0026054208,0.00214077,0.00031404453,0.00019421466],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.20022503,0.00095553946,0.012428169,0.0017501905,0.00021653665,0.00020452717,0.00050922553,0.0023539066,0.0038158565],"category_scores_gemma":[0.6064276,0.0008786697,0.009362623,0.00428835,0.00039649248,0.000086013235,0.0006078937,0.004903093,0.000029469675],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017415382,0.0012355912,0.015460261,0.0009629354,0.060717132,0.0043213186,0.00014394733,0.00015994262,0.000025169235,0.0019113416,0.9007465,0.012574307],"study_design_scores_gemma":[0.0042723217,0.00054337195,0.014872716,0.00012097414,0.15715687,0.0000075356384,0.00004844539,0.051896196,0.000027321343,0.6820849,0.08658523,0.0023840773],"about_ca_topic_score_codex":0.00034583677,"about_ca_topic_score_gemma":0.0014590146,"teacher_disagreement_score":0.8141613,"about_ca_system_score_codex":0.00034881217,"about_ca_system_score_gemma":0.0002477885,"threshold_uncertainty_score":0.9993664},"labels":[],"label_agreement":null},{"id":"W4280562270","doi":"10.1002/pst.2231","title":"Two‐stage subgroup‐specific time‐to‐event (2S‐Sub‐TITE): An adaptive two‐stage time‐to‐toxicity design for subgroup‐specific dose finding in phase I oncology trials","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Subgroup analysis; Mathematics; Statistics; Sample size determination; Cluster analysis; Event (particle physics); Confidence interval","score_opus":0.7099022599683399,"score_gpt":0.6160788559671313,"score_spread":0.09382340400120859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280562270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010889496,0.0001231648,0.95303416,0.00063598884,0.0013918517,0.010253717,0.02258696,0.00032996648,0.000754697],"genre_scores_gemma":[0.019781778,0.000068199064,0.9722874,0.0016084488,0.0011821276,0.0027513343,0.00027058815,0.00038260565,0.0016675068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9715206,0.016084798,0.005470898,0.0024369778,0.0019590931,0.0025276546],"domain_scores_gemma":[0.8396204,0.1558236,0.0011809963,0.0011169421,0.0004082999,0.0018497613],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.037685916,0.0012213909,0.004061324,0.000751467,0.000832633,0.00027326652,0.0016345922,0.0003617206,0.028377214],"category_scores_gemma":[0.059848987,0.001267728,0.0005334694,0.0016751729,0.0004964345,0.00024560324,0.0010332417,0.0021549026,0.0016689894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05659872,0.018376958,0.000027584365,0.00046797935,0.0008105575,0.0016967733,0.0017392421,0.009113785,0.082508855,0.42236727,0.089315936,0.31697634],"study_design_scores_gemma":[0.04565733,0.013345435,0.000038149217,0.00015723148,0.00093921256,0.000041333988,0.00043736957,0.232789,0.02155168,0.47677666,0.20510033,0.0031662732],"about_ca_topic_score_codex":0.000024953035,"about_ca_topic_score_gemma":0.000014071256,"teacher_disagreement_score":0.31381005,"about_ca_system_score_codex":0.0025143481,"about_ca_system_score_gemma":0.00050662213,"threshold_uncertainty_score":0.9991083},"labels":[],"label_agreement":null},{"id":"W4280622755","doi":"10.1177/0272989x221099493","title":"Noninferiority Margin Size and Acceptance of Trial Results: Contingent Valuation Survey of Clinician Preferences for Noninferior Mortality","year":2022,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; McMaster University; McGill University; Children's Hospital of Eastern Ontario; Health Sciences Centre; BC Children's Hospital; University of Toronto; Sunnybrook Health Science Centre; University of British Columbia; Public Health Ontario; Université de Montréal; Hospital for Sick Children","funders":"","keywords":"Contingent valuation; Margin (machine learning); Actuarial science; Valuation (finance); Medicine; Psychology; Statistics; Economics; Willingness to pay; Computer science; Accounting; Mathematics; Microeconomics","score_opus":0.6880218127831303,"score_gpt":0.6223625294813742,"score_spread":0.06565928330175619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280622755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.702294,0.000041846015,0.29387492,0.000073756426,0.0013592832,0.0013241519,0.00084057054,0.000021474856,0.0001700067],"genre_scores_gemma":[0.6676353,0.00002437998,0.33203837,0.00006119332,0.00011605018,0.000094595685,0.0000052248993,0.000014323383,0.000010510206],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9899346,0.0034319996,0.0035411913,0.0005749297,0.0022338966,0.00028336947],"domain_scores_gemma":[0.61765873,0.3786548,0.002188679,0.0006875437,0.0006208394,0.00018939501],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054097705,0.0001818868,0.0013025338,0.00006905721,0.00015015862,0.00002344365,0.0005047542,0.00020336472,0.000888267],"category_scores_gemma":[0.72775537,0.0001531226,0.00018316568,0.00034392384,0.0003049912,0.0000510375,0.0005066586,0.0004095454,5.76282e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08355233,0.0012829398,0.026565915,0.00041235483,0.00022362308,0.0000090629155,0.00044387692,0.000018155617,0.00008274823,0.0124721015,0.0009163074,0.8740206],"study_design_scores_gemma":[0.029093456,0.0017398426,0.2438665,0.0004098894,0.00015916897,0.0000014154567,0.00010329118,0.0043857857,0.00010636941,0.71977085,0.00014887897,0.00021457172],"about_ca_topic_score_codex":0.00007213908,"about_ca_topic_score_gemma":0.00016657195,"teacher_disagreement_score":0.873806,"about_ca_system_score_codex":0.000052319912,"about_ca_system_score_gemma":0.00035752915,"threshold_uncertainty_score":0.97400546},"labels":[],"label_agreement":null},{"id":"W4280625667","doi":"10.1080/14737167.2022.2079497","title":"Examining the correlation between treatment effects in clinical trials and economic modeling","year":2022,"lang":"en","type":"article","venue":"Expert Review of Pharmacoeconomics & Outcomes Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; Centre for Addiction and Mental Health; University of Toronto; Public Health Ontario","funders":"","keywords":"Correlation; Clinical trial; Medicine; Covariance; Econometrics; Statistics; Intensive care medicine; Mathematics; Internal medicine","score_opus":0.7645576136209942,"score_gpt":0.7434989822412623,"score_spread":0.02105863137973185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280625667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83958584,0.10068226,0.020588739,0.01303009,0.0051191365,0.018223958,0.00045385494,0.00010464874,0.0022114853],"genre_scores_gemma":[0.480989,0.3172258,0.19080329,0.0035675564,0.00224134,0.0045472654,0.000032419597,0.00023342053,0.00035991997],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9683239,0.025544839,0.004603367,0.00065724994,0.0003941789,0.00047648748],"domain_scores_gemma":[0.718099,0.28037077,0.00072432536,0.0005886416,0.000054550594,0.00016267959],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10709914,0.0002435478,0.0026490656,0.00019065544,0.00022436699,0.000036102032,0.00047796225,0.0000859166,0.000622551],"category_scores_gemma":[0.067782335,0.00016689878,0.00040933714,0.00015128695,0.00019680052,0.00008499407,0.0005964571,0.00091779995,0.000019738425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036030603,0.000586627,0.05810446,0.002888597,0.0010428096,0.00002141544,0.0010894331,0.0007080906,0.000046762285,0.01910955,0.005586955,0.910455],"study_design_scores_gemma":[0.025453737,0.003392083,0.0100637805,0.004465634,0.0011982876,0.000024287052,0.0016262179,0.39684787,0.00038506486,0.5237319,0.03110689,0.0017042274],"about_ca_topic_score_codex":0.00013902488,"about_ca_topic_score_gemma":0.000005901987,"teacher_disagreement_score":0.9087508,"about_ca_system_score_codex":0.00060283236,"about_ca_system_score_gemma":0.00023918028,"threshold_uncertainty_score":0.94007015},"labels":[],"label_agreement":null},{"id":"W4281398380","doi":"10.1080/19466315.2022.2081602","title":"Accuracy and Safety of Novel Designs for Phase I Drug-Combination Oncology Trials","year":2022,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Seagen (Canada)","funders":"National Cancer Institute","keywords":"Biopharmaceutical; Computer science; Risk analysis (engineering); Clinical study design; Identification (biology); Clinical trial; Reliability engineering; Medicine; Engineering; Internal medicine","score_opus":0.9166994023925746,"score_gpt":0.7562379713766251,"score_spread":0.16046143101594956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281398380","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008614983,0.00021612077,0.973668,0.0018290202,0.0006969863,0.004981822,0.009247537,0.00003357685,0.0007120014],"genre_scores_gemma":[0.12827872,0.00036622194,0.8700414,0.000104744606,0.00011526412,0.0008622352,0.000032596658,0.000048674035,0.00015015155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98465455,0.009780506,0.0026376387,0.0006506209,0.0014487368,0.00082797906],"domain_scores_gemma":[0.52812386,0.47030473,0.00041050257,0.00032358489,0.0005694201,0.00026793487],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07995908,0.00020376242,0.0012711183,0.0004573119,0.00034375544,0.00003515962,0.000498726,0.00014437326,0.0009331973],"category_scores_gemma":[0.50419146,0.00019331489,0.00010669334,0.0007819131,0.00091079803,0.000052236486,0.000618249,0.0013367161,0.000002720586],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0062759947,0.0034490966,0.000029961995,0.00042372814,0.00007085541,0.000022530261,0.00028153867,0.00000647284,0.010312253,0.81611675,0.0039199167,0.15909089],"study_design_scores_gemma":[0.01987887,0.0016950909,0.000041821608,0.000038329752,0.000097046825,0.0000062809845,0.00045726198,0.021093154,0.005127016,0.94330776,0.008057781,0.00019958327],"about_ca_topic_score_codex":0.000019747084,"about_ca_topic_score_gemma":0.000005147048,"teacher_disagreement_score":0.46052423,"about_ca_system_score_codex":0.00044441636,"about_ca_system_score_gemma":0.00055034744,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W4281763071","doi":"10.1200/jco.2022.40.16_suppl.tps2078","title":"GBM AGILE: A global, phase 2/3 adaptive platform trial to evaluate multiple regimens in newly diagnosed and recurrent glioblastoma.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Agile software development; Clinical trial; Randomization; Biomarker; Glioblastoma; Oncology; Protocol (science); Internal medicine; Medical physics; Pathology; Cancer research; Alternative medicine; Computer science","score_opus":0.6883699714316404,"score_gpt":0.658131808954005,"score_spread":0.030238162477635333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281763071","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770418,0.00014899338,0.0067727086,0.0054423437,0.00783052,0.0019010582,0.00019140639,0.000027125292,0.00064408174],"genre_scores_gemma":[0.47831056,0.00020945238,0.5167531,0.00228332,0.0021520795,0.00017175497,9.929289e-7,0.00004641567,0.0000723277],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98422265,0.006615887,0.0069293254,0.0005497696,0.0011373156,0.0005450747],"domain_scores_gemma":[0.797241,0.19722919,0.0038278145,0.0004047411,0.00041975622,0.0008775262],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036307562,0.0002920204,0.003181439,0.0002029842,0.00011956078,0.000025383953,0.00058630964,0.00038971877,0.00048468],"category_scores_gemma":[0.42832506,0.00021668158,0.0005736419,0.0005733899,0.0002853245,0.00012080359,0.0005903315,0.0021765733,0.000013918611],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.4556655,0.010696743,0.00064581394,0.000024243867,0.0003414437,0.0015211751,0.0003009988,0.00008026112,0.000012403882,0.007000196,0.023801433,0.4999098],"study_design_scores_gemma":[0.3445121,0.17579667,0.00182966,0.00014523733,0.0005231844,0.00017110951,0.00063718995,0.0017810902,0.000013498378,0.44068253,0.03351871,0.00038902907],"about_ca_topic_score_codex":0.000019280804,"about_ca_topic_score_gemma":0.00019575388,"teacher_disagreement_score":0.5099804,"about_ca_system_score_codex":0.0006788786,"about_ca_system_score_gemma":0.001406097,"threshold_uncertainty_score":0.9923242},"labels":[],"label_agreement":null},{"id":"W4281921175","doi":"10.1093/ije/dyac123","title":"Sample size calculators for planning stepped-wedge cluster randomized trials: a review and comparison","year":2022,"lang":"en","type":"review","venue":"International Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Calculator; CRTS; Sample size determination; Computer science; Sample (material); Software; Set (abstract data type); Data mining; Statistics; Mathematics; Computer graphics (images)","score_opus":0.8888315450094642,"score_gpt":0.7192475098947496,"score_spread":0.16958403511471454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281921175","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.2053782e-7,0.73294806,0.26019722,0.0009595164,0.0028892376,0.0025349162,0.0004028473,0.0000115445955,0.00005630681],"genre_scores_gemma":[1.2587014e-7,0.59386426,0.40348512,0.001296514,0.0010093868,0.00025172444,0.0000148987365,0.00004065276,0.000037325382],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9342526,0.049233306,0.0150313685,0.00053925376,0.00051699026,0.00042643683],"domain_scores_gemma":[0.05722464,0.9270636,0.014699313,0.00031205066,0.00047036985,0.00023006852],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16261846,0.00050774304,0.022200722,0.00028036349,0.00007131242,0.000024760388,0.0010276296,0.00045855143,0.0013458101],"category_scores_gemma":[0.9695055,0.000325047,0.003828209,0.00011715106,0.00032417953,0.000059839418,0.0003416353,0.001334714,0.0000030801873],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010521585,0.00016420339,0.000013463245,0.019374747,0.007400809,0.000027789929,0.000036146255,0.0000046562436,1.43333265e-8,0.052845675,0.09190338,0.81770754],"study_design_scores_gemma":[0.018603288,0.00011183775,2.9069406e-7,0.011189743,0.007022483,0.00018871379,0.000005434596,0.000053704865,1.8829285e-8,0.37238482,0.5902653,0.00017435887],"about_ca_topic_score_codex":0.000007976134,"about_ca_topic_score_gemma":4.3837537e-7,"teacher_disagreement_score":0.87783027,"about_ca_system_score_codex":0.0002525971,"about_ca_system_score_gemma":0.00030431844,"threshold_uncertainty_score":0.9999201},"labels":[],"label_agreement":null},{"id":"W4282946278","doi":"10.1016/j.jid.2022.04.015","title":"Noninferiority Randomized Controlled Trials","year":2022,"lang":"en","type":"review","venue":"Journal of Investigative Dermatology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Women's College Hospital; University of Toronto; McMaster University; Population Health Research Institute","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada; Bayer; National Eczema Association; American Academy of Dermatology","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.7892367000881914,"score_gpt":0.6285021698156398,"score_spread":0.16073453027255158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282946278","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032756925,0.9809369,0.008537099,0.0005371839,0.0035215449,0.0047926176,0.00012847205,0.00003591662,0.0015070053],"genre_scores_gemma":[4.94861e-7,0.74803925,0.25050426,0.00022413052,0.000616462,0.00044751487,0.0000034902405,0.00007933939,0.000085049905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8379058,0.14015344,0.019914042,0.00043944997,0.0010877561,0.0004995102],"domain_scores_gemma":[0.14455114,0.8160287,0.03759057,0.00063454907,0.0006700509,0.00052499375],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.09618088,0.0009585474,0.082146995,0.00084078324,0.00016489699,0.00007428699,0.001169151,0.0009139772,0.0033468814],"category_scores_gemma":[0.91360044,0.00052630855,0.013033306,0.0005326077,0.0021379036,0.00010380741,0.00030867456,0.0034382564,0.000030118656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.053852424,0.0006576271,3.9173253e-7,0.024962785,0.03643352,0.002708994,0.00038969182,5.009871e-7,0.0000027929527,0.56233156,0.029670075,0.28898963],"study_design_scores_gemma":[0.11241578,0.00008984239,1.6329308e-8,0.002857401,0.01642707,0.0016719091,0.00002183417,0.000003770288,0.000013001831,0.5360161,0.33021295,0.00027033413],"about_ca_topic_score_codex":0.0000019212375,"about_ca_topic_score_gemma":4.5380236e-7,"teacher_disagreement_score":0.8174196,"about_ca_system_score_codex":0.00026622348,"about_ca_system_score_gemma":0.0024440268,"threshold_uncertainty_score":0.99971884},"labels":[],"label_agreement":null},{"id":"W4283779537","doi":"10.1007/s10985-022-09562-8","title":"Accounting for delayed entry into observational studies and clinical trials: length-biased sampling and restricted mean survival time","year":2022,"lang":"en","type":"article","venue":"Lifetime Data Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ottawa Hospital","funders":"National Eye Institute","keywords":"Observational study; Event (particle physics); Covariate; Inference; Population; Sampling (signal processing); Statistics; Outcome (game theory); Econometrics; Clinical trial; Parametric statistics; Medicine; Mathematics; Computer science; Artificial intelligence; Internal medicine","score_opus":0.85796020486516,"score_gpt":0.6510978969113885,"score_spread":0.20686230795377147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283779537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27352208,0.0019422617,0.693326,0.0033630051,0.001246981,0.0027374546,0.023439828,0.00034707555,0.00007528435],"genre_scores_gemma":[0.00861591,0.00034301652,0.9878832,0.00032651072,0.0007541993,0.00010319981,0.0017969405,0.000045940902,0.0001310447],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98811007,0.0063515287,0.003287759,0.0011594874,0.0007449287,0.00034621428],"domain_scores_gemma":[0.5144206,0.48174754,0.0016826452,0.0015368672,0.00036738935,0.00024494188],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04989527,0.00028567147,0.0024852785,0.00026087463,0.0006073227,0.00013965566,0.0006888444,0.0001502845,0.00047712258],"category_scores_gemma":[0.50311,0.00025552473,0.00036618905,0.0010786001,0.00023659611,0.0001968515,0.001781525,0.00044945307,0.000003827549],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016331183,0.004257516,0.21497953,0.0023355754,0.2328695,0.00010405948,0.0035865777,0.0007912361,0.0015480398,0.097976774,0.10371983,0.32150018],"study_design_scores_gemma":[0.0068431054,0.0005435386,0.015271843,0.00008037255,0.043275516,0.0000040577247,0.0021713772,0.27671662,0.000014231964,0.6491275,0.004901141,0.001050714],"about_ca_topic_score_codex":0.00007183959,"about_ca_topic_score_gemma":0.00004443867,"teacher_disagreement_score":0.55115074,"about_ca_system_score_codex":0.00005809786,"about_ca_system_score_gemma":0.00009854869,"threshold_uncertainty_score":0.9999897},"labels":[],"label_agreement":null},{"id":"W4283780334","doi":"10.1101/2022.06.28.22275821","title":"Assessing non-white ethnic participation in type 2 diabetes mellitus randomized clinical trials: A Meta-Analysis","year":2022,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"Canadian Institutes of Health Research; Health Canada; Government of Canada; World Health Organization; Hamilton Health Sciences; University of Toronto; McMaster University","keywords":"Ethnic group; Medicine; Randomized controlled trial; Meta-analysis; Clinical trial; Type 2 Diabetes Mellitus; Gerontology; MEDLINE; Government (linguistics); Family medicine; Demography; Diabetes mellitus; Internal medicine; Political science","score_opus":0.8768489736526639,"score_gpt":0.6899403624023523,"score_spread":0.18690861125031155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283780334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37911198,0.011318259,0.5819698,0.0026068753,0.010783322,0.010757709,0.00042433274,0.0004760127,0.0025517168],"genre_scores_gemma":[0.31345135,0.0011580476,0.6804617,0.00040635816,0.000707376,0.0032696237,0.00007782876,0.00015314163,0.0003145454],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80111074,0.17832273,0.01537422,0.0023409124,0.0018626271,0.0009887521],"domain_scores_gemma":[0.33358562,0.65688866,0.0060725627,0.0026475636,0.00042082512,0.0003847617],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.3642401,0.0007687509,0.019877551,0.0007530096,0.00010398119,0.00027920326,0.0010352781,0.0010576788,0.008492544],"category_scores_gemma":[0.7907049,0.0005637056,0.00995609,0.002033898,0.00042724982,0.000110935456,0.0013221605,0.0034340709,0.000040918825],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029633492,0.0052053654,0.034081805,0.0023413931,0.8549597,0.00018959958,0.001855549,0.006636572,0.000037657934,0.013580313,0.0009881513,0.050490387],"study_design_scores_gemma":[0.019443074,0.000056637644,0.0036685555,0.000040273782,0.39449993,9.183609e-8,0.00004489299,0.024099968,0.000035921697,0.5575197,0.000051189258,0.0005398117],"about_ca_topic_score_codex":0.000031862102,"about_ca_topic_score_gemma":0.00004630882,"teacher_disagreement_score":0.54393935,"about_ca_system_score_codex":0.00014667552,"about_ca_system_score_gemma":0.00033774498,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W4284892632","doi":"10.1002/sim.9516","title":"Adaptive response‐dependent two‐phase designs: Some results on robustness and efficiency","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Robustness (evolution); Computer science; Covariate; Biomarker; Statistics; Quantile; Data mining; Econometrics; Machine learning; Mathematics","score_opus":0.47951310210464493,"score_gpt":0.5641417443802038,"score_spread":0.08462864227555889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284892632","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020550413,0.00015878893,0.97024137,0.0021232413,0.0015481272,0.0013061285,0.0030590761,0.00008811114,0.0009247683],"genre_scores_gemma":[0.19403577,0.0000599021,0.8039847,0.00068261544,0.000407656,0.00019172473,0.000021406131,0.000066376444,0.00054984004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915539,0.004394959,0.0015577064,0.000729125,0.0012766104,0.00048771166],"domain_scores_gemma":[0.87082314,0.12793444,0.00039778292,0.00053742377,0.0001051975,0.00020202712],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.017854398,0.00030041908,0.000915795,0.00032937454,0.00025037577,0.000015156791,0.00037583153,0.00007854436,0.00049741234],"category_scores_gemma":[0.20920189,0.00025528733,0.000030446912,0.00041708344,0.0005827091,0.0000350045,0.00025980666,0.000950941,0.000006549994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028781122,0.0015192179,0.000016244787,0.00011123127,0.00006795173,0.0015960038,0.0016834853,0.0017582623,0.00041919973,0.9112333,0.017816674,0.03499732],"study_design_scores_gemma":[0.01752474,0.0069037527,0.00015609594,0.0001927243,0.000106958854,0.000026779991,0.0010484307,0.017749755,0.000103238795,0.9556704,0.0002004824,0.00031664674],"about_ca_topic_score_codex":0.000036916266,"about_ca_topic_score_gemma":0.000010173346,"teacher_disagreement_score":0.1913475,"about_ca_system_score_codex":0.00026842472,"about_ca_system_score_gemma":0.00013893182,"threshold_uncertainty_score":0.9999899},"labels":[],"label_agreement":null},{"id":"W4284899235","doi":"10.1002/sta4.487","title":"Bayesian group sequential designs for cluster‐randomized trials","year":2022,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Mitacs","keywords":"Randomized controlled trial; Cluster (spacecraft); Sample size determination; Interim; Cluster randomised controlled trial; Bayesian probability; Computer science; Statistics; Psychology; Medicine; Artificial intelligence; Mathematics; Surgery; Geography","score_opus":0.7519692633517723,"score_gpt":0.6057972438282709,"score_spread":0.14617201952350134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284899235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038950556,0.000041469928,0.9898792,0.0007031245,0.0023446812,0.0045640436,0.0009540534,0.0001375886,0.0009863342],"genre_scores_gemma":[0.011934755,0.000010353551,0.98361295,0.0005961732,0.00062293233,0.002344666,0.000021710122,0.00007241133,0.0007840443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9809944,0.015277031,0.0022054417,0.00047990165,0.0005760385,0.00046720856],"domain_scores_gemma":[0.6858251,0.31294665,0.0006301961,0.0003928237,0.000069463866,0.00013575036],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05353413,0.00022908922,0.0023012199,0.000091542,0.00032305447,0.000060244427,0.00036361115,0.000093672934,0.0035029731],"category_scores_gemma":[0.34621784,0.00018627875,0.0008863317,0.00016948648,0.000182011,0.00004685435,0.00022502695,0.00029681379,0.000011201667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12623027,0.00044089247,0.000003728498,0.00025298895,0.0006556351,0.000017077838,0.00041148847,0.000037901587,0.00071584614,0.7835327,0.06347994,0.024221571],"study_design_scores_gemma":[0.105765365,0.00030373986,3.5202316e-7,0.000012369447,0.0005015968,0.000004238676,0.00010771542,0.0029860358,0.00027298072,0.88613147,0.0037072725,0.00020687148],"about_ca_topic_score_codex":0.000011925569,"about_ca_topic_score_gemma":0.0000043630857,"teacher_disagreement_score":0.29766962,"about_ca_system_score_codex":0.000115579125,"about_ca_system_score_gemma":0.000085358915,"threshold_uncertainty_score":0.997408},"labels":[],"label_agreement":null},{"id":"W4285593666","doi":"10.1038/s43856-022-00155-y","title":"Hybrid-control arm construction using historical trial data for an early-phase, randomized controlled trial in metastatic colorectal cancer","year":2022,"lang":"en","type":"article","venue":"Communications Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"F. Hoffmann-La Roche; National Cancer Institute; Sanofi","keywords":"Medicine; Randomized controlled trial; Colorectal cancer; Frequentist inference; Oncology; Clinical endpoint; Internal medicine; Cancer; Bayesian probability; Artificial intelligence; Computer science; Bayesian inference","score_opus":0.6684205789792468,"score_gpt":0.6047035710687392,"score_spread":0.0637170079105076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285593666","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21132337,0.0028370721,0.6951907,0.010112161,0.012269791,0.06508209,0.002279733,0.0002710694,0.0006339654],"genre_scores_gemma":[0.26946062,0.00020912854,0.70956284,0.00028973533,0.0013007324,0.018692406,0.0002641837,0.00008862554,0.00013175116],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9824845,0.012607154,0.0033387647,0.0005574573,0.0006577566,0.00035435762],"domain_scores_gemma":[0.8438964,0.15165505,0.0013792844,0.002673324,0.00022634829,0.00016959655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02631805,0.00028626266,0.0038498994,0.0003173211,0.0005083653,0.000027007161,0.0020472647,0.00007452836,0.00052259193],"category_scores_gemma":[0.2118441,0.00022870833,0.00029918057,0.00038566889,0.00080052536,0.00014852303,0.0005251096,0.0007489179,6.983704e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.96773636,0.0022467966,0.0000027294143,0.000022782357,0.00043056766,0.0000023251773,0.00015932703,0.000020063007,0.00011475019,0.023398101,0.001134553,0.0047316374],"study_design_scores_gemma":[0.6988176,0.0018124469,3.4190225e-7,0.000034690253,0.0019189599,0.000006019819,0.000111289206,0.09317529,0.000003225464,0.20328237,0.00068259577,0.00015512983],"about_ca_topic_score_codex":0.00066997897,"about_ca_topic_score_gemma":0.00007897189,"teacher_disagreement_score":0.26891872,"about_ca_system_score_codex":0.000846797,"about_ca_system_score_gemma":0.00049103046,"threshold_uncertainty_score":0.93264556},"labels":[],"label_agreement":null},{"id":"W4285684531","doi":"10.14283/jpad.2022.48","title":"The Future of AD Clinical Trials with the Advent of Anti-Amyloid Therapies: An CTAD Task Force Report","year":2022,"lang":"en","type":"article","venue":"The Journal of Prevention of Alzheimer s Disease","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alzheimer Society of Canada","funders":"Avid Radiopharmaceuticals; National Institutes of Health; Genentech; Grifols; H. Lundbeck A/S; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; Novo Nordisk; Eisai; Prothena; Pfizer; Demensförbundet; Regeneron Pharmaceuticals; GHR Foundation; Danone; Biogen; AstraZeneca; Eli Lilly and Company; Amgen; Alzheimer's Drug Discovery Foundation; Sanofi; National Institute on Aging; Alzheimer's Association","keywords":"Clinical trial; Medicine; Dementia; Amyloid (mycology); Disease; Placebo; Task force; Cognitive decline; Oncology; Internal medicine; Pathology; Alternative medicine","score_opus":0.3964248221574626,"score_gpt":0.559941673221779,"score_spread":0.1635168510643164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285684531","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8786507,0.03326296,0.06443905,0.014394236,0.0037542554,0.0045884675,0.00066513824,0.000034773537,0.00021040525],"genre_scores_gemma":[0.97113717,0.001175978,0.026717564,0.00012820536,0.00061660516,0.000030306406,0.0000026240882,0.00004572622,0.00014582368],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97557145,0.017647922,0.0048802784,0.00019587681,0.0014932194,0.00021127192],"domain_scores_gemma":[0.94866437,0.038798396,0.01034566,0.0012643643,0.0007036423,0.00022357065],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.069040805,0.000203106,0.0013327706,0.00006210893,0.00025929004,0.000016257769,0.0010670812,0.00006719132,0.00040786894],"category_scores_gemma":[0.021021219,0.00008608442,0.001094771,0.00027357068,0.0006677056,0.000106260355,0.00019598233,0.00063981616,4.8324455e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11925062,0.029395077,0.006552753,0.0012704993,0.058940183,0.00044074704,0.009313361,0.0020232187,0.010094312,0.14921452,0.043047108,0.5704576],"study_design_scores_gemma":[0.005768456,0.0050382586,0.022060463,0.0003957091,0.017052345,0.00013855792,0.0068699447,0.00015641043,0.0017082705,0.936721,0.0037895795,0.00030096856],"about_ca_topic_score_codex":0.000002616513,"about_ca_topic_score_gemma":0.0000024552915,"teacher_disagreement_score":0.7875065,"about_ca_system_score_codex":0.000016310254,"about_ca_system_score_gemma":0.00047118106,"threshold_uncertainty_score":0.9872251},"labels":[],"label_agreement":null},{"id":"W4285821763","doi":"10.1007/978-3-319-52636-2_118","title":"Essential Statistical Tests","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Ontario Institute for Cancer Research","funders":"","keywords":"Statistical hypothesis testing; Wilcoxon signed-rank test; Parametric statistics; Statistics; Categorical variable; Nonparametric statistics; Exact test; Mathematics; Statistical analysis; Analysis of variance; Mann–Whitney U test","score_opus":0.561293042833734,"score_gpt":0.5727593470750534,"score_spread":0.011466304241319336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285821763","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.545167e-7,0.000021818665,0.13526145,0.00019078358,0.0013884277,0.0005069524,0.001108608,0.00023870925,0.8612825],"genre_scores_gemma":[0.000009745563,0.000030579547,0.52995574,0.00014704118,0.0005392314,0.000024541438,0.000020590887,0.00011597652,0.46915653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99619275,0.00028179144,0.0013855058,0.0007404221,0.0010325738,0.0003669797],"domain_scores_gemma":[0.9057165,0.09279817,0.00037662234,0.0007816136,0.00009220109,0.00023489958],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001866813,0.0004629356,0.0012771762,0.00010303886,0.00011685414,0.000046166093,0.00046777687,0.00046941751,0.33812943],"category_scores_gemma":[0.05193067,0.000412977,0.00028586242,0.000029242065,0.00032283625,0.000026861157,0.000532492,0.0012352996,0.0009030024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043415024,0.00005542571,0.0000011588179,0.00010462782,0.00012663621,0.00011575708,0.000006069997,7.1621145e-8,0.000002682486,0.8992188,0.092352815,0.0079725245],"study_design_scores_gemma":[0.00030995443,0.00013060677,0.000004261237,0.000034815046,0.00027065576,0.000012482013,0.000001734257,0.000012001646,0.0000068333816,0.7704206,0.22842535,0.000370678],"about_ca_topic_score_codex":0.000006932134,"about_ca_topic_score_gemma":0.0000064904757,"teacher_disagreement_score":0.39469433,"about_ca_system_score_codex":0.00011847078,"about_ca_system_score_gemma":0.00015312286,"threshold_uncertainty_score":0.9998749},"labels":[],"label_agreement":null},{"id":"W4286247398","doi":"10.1080/19466315.2022.2081601","title":"Clinical and Statistical Perspectives on the ICH E9(R1) Estimand Framework Implementation","year":2022,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Addendum; Clinical trial; Political science; Medicine","score_opus":0.8326010788102322,"score_gpt":0.7522871790303445,"score_spread":0.08031389977988768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286247398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11993586,0.00066931185,0.83725405,0.017888354,0.0022738718,0.0067493133,0.009636471,0.00021766848,0.005375123],"genre_scores_gemma":[0.40122345,0.00045458158,0.59675753,0.00056791486,0.0003199302,0.00047446505,0.000013064689,0.00006917495,0.00011985853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.980617,0.01279625,0.00165878,0.0011459137,0.002605317,0.0011767263],"domain_scores_gemma":[0.70519334,0.2933373,0.00014434116,0.00061066396,0.00029599053,0.0004183676],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03437999,0.00032265068,0.00072026433,0.00030170838,0.0009708706,0.00018502188,0.00076078257,0.00018869183,0.008672514],"category_scores_gemma":[0.21106628,0.00024988537,0.000081932805,0.0009978524,0.0029529352,0.000046665336,0.0011632527,0.0054029445,0.000079138495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077731727,0.0007116278,0.0040127165,0.00006708635,0.000068729336,0.0001747268,0.0006499442,0.0000028341942,0.000022778604,0.939903,0.0133684315,0.040240813],"study_design_scores_gemma":[0.0015120886,0.0010322337,0.007909426,0.000037046866,0.000052716005,0.000010466167,0.005566417,0.0036320896,0.000048360227,0.97710484,0.0028140743,0.00028026671],"about_ca_topic_score_codex":0.000042478012,"about_ca_topic_score_gemma":0.000013106717,"teacher_disagreement_score":0.28128758,"about_ca_system_score_codex":0.00031314467,"about_ca_system_score_gemma":0.00030490544,"threshold_uncertainty_score":0.99999535},"labels":[],"label_agreement":null},{"id":"W4287832036","doi":"10.18433/jpps33093","title":"Erratum to 'Piecing Together Human Adult Comparative Pharmacokinetic Trials and Rodent Studies: What Happens to Drug Clearance in Obesity?'","year":2022,"lang":"en","type":"erratum","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Pharmacokinetics; Human obesity; Pharmacology; Drug; Rodent; Medicine; Rodent model; Obesity; Psychology; Internal medicine; Biology","score_opus":0.7273250630193224,"score_gpt":0.6632658467853536,"score_spread":0.06405921623396882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287832036","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5028003,0.100663505,0.004099468,0.08722135,0.26704758,0.017999142,0.0006683964,0.00035205446,0.01914824],"genre_scores_gemma":[0.31140277,0.116058074,0.4188399,0.076898195,0.03582356,0.0012168303,0.000013459936,0.00081522984,0.038931977],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9807476,0.007549492,0.0056111845,0.0013848062,0.0033574575,0.0013495036],"domain_scores_gemma":[0.95160913,0.04251795,0.002784316,0.000438339,0.0009945929,0.0016556407],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03805908,0.0009823475,0.0052822013,0.0010648243,0.0006730793,0.0006712542,0.002253963,0.00018551754,0.0020828843],"category_scores_gemma":[0.04739925,0.0007581645,0.00066774874,0.0020439997,0.0010296126,0.00081242283,0.0013039898,0.004461686,0.00003838831],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025564323,0.0015412228,0.00028430574,0.0011161454,0.001090603,0.0006098994,0.014350029,0.00042083085,0.0040429006,0.0030208845,0.93894666,0.032020085],"study_design_scores_gemma":[0.012157715,0.002089757,0.0002341164,0.00753843,0.0030433594,0.00021447151,0.017292628,0.0020057892,0.00882114,0.13496989,0.8090136,0.0026190765],"about_ca_topic_score_codex":0.000045113447,"about_ca_topic_score_gemma":0.000050630104,"teacher_disagreement_score":0.4147404,"about_ca_system_score_codex":0.0006478214,"about_ca_system_score_gemma":0.0005388794,"threshold_uncertainty_score":0.9994869},"labels":[],"label_agreement":null},{"id":"W4287996197","doi":"10.5281/zenodo.3566771","title":"Null hypothesis significance testing interpreted and calibrated by estimating probabilities of sign errors: A Bayes-frequentist continuum","year":2019,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Frequentist inference; Null hypothesis; Sign (mathematics); Statistical hypothesis testing; Bayes factor; Statistics; Bayes' theorem; Alternative hypothesis; Econometrics; Null (SQL); Bayesian probability; Mathematics; Computer science; Bayesian inference; Data mining; Mathematical analysis","score_opus":0.3165564284266273,"score_gpt":0.44395340145644646,"score_spread":0.12739697302981917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287996197","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5409758,0.00005984608,0.442449,0.00021288329,0.0004818274,0.0023315882,0.00028314954,0.0004264451,0.012779448],"genre_scores_gemma":[0.29674494,7.400224e-7,0.7023257,0.000058605612,0.00003220895,0.000040596857,8.873756e-7,0.00004014103,0.0007561789],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99653006,0.00082256674,0.0014382213,0.0005411314,0.00030862473,0.00035938818],"domain_scores_gemma":[0.8865956,0.11195943,0.00061169814,0.00047009057,0.00023548155,0.00012767721],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024598248,0.00027997178,0.0010106517,0.000056007484,0.000046797322,0.00007061586,0.00027282807,0.00017057802,0.00069852016],"category_scores_gemma":[0.17942534,0.0002299575,0.00008793876,0.00028030132,0.00039092774,0.00013835412,0.00012805294,0.00024246958,0.000015903941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011463062,0.0017765425,0.063367076,0.013274538,0.0011435397,0.000035878318,0.003009364,0.000047351597,0.6049939,0.14415826,0.029951626,0.13709562],"study_design_scores_gemma":[0.0011579874,0.00048523795,0.00039995415,0.0009246908,0.00011473126,0.0000066289335,0.0003431296,0.028622292,0.03474486,0.93273956,0.000023792365,0.00043714707],"about_ca_topic_score_codex":0.00012772129,"about_ca_topic_score_gemma":0.000010644358,"teacher_disagreement_score":0.7885813,"about_ca_system_score_codex":0.000038001228,"about_ca_system_score_gemma":0.000063547195,"threshold_uncertainty_score":0.93773943},"labels":[],"label_agreement":null},{"id":"W4288033295","doi":"10.1093/aje/kwac131","title":"Nondifferential Treatment Misclassification Biases Toward the Null? Not a Safe Bet for Active Comparator Studies","year":2022,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of North Carolina at Chapel Hill; National Institute of Child Health and Human Development; McGill University","keywords":"Comparator; Statistics; Econometrics; Medicine; Pharmacoepidemiology; Null hypothesis; Null (SQL); Meta-analysis; Polytomous Rasch model; Mathematics; Internal medicine; Computer science; Data mining; Pharmacology; Item response theory; Psychometrics","score_opus":0.877682074488842,"score_gpt":0.6555413949705122,"score_spread":0.22214067951832972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288033295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5260982,0.0007844214,0.39644247,0.07023716,0.0035985617,0.001702436,0.0010021382,0.000039402785,0.00009519443],"genre_scores_gemma":[0.5430047,0.00029316358,0.4536585,0.0018909888,0.00078486436,0.00027465998,0.000004438127,0.000026715441,0.00006200652],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.989353,0.00795728,0.0018548092,0.00027172174,0.0002100772,0.00035308956],"domain_scores_gemma":[0.6604443,0.33602113,0.002859627,0.00030304625,0.00025068506,0.00012123847],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075119934,0.00021037305,0.0019863474,0.000094115574,0.0002514652,0.0000058428295,0.0004067155,0.000039317023,0.00017218744],"category_scores_gemma":[0.18945798,0.00011739323,0.00049301976,0.00017767538,0.00093113456,0.0000280478,0.00010143951,0.0003651969,0.0000030301114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021540962,0.003236611,0.005215864,0.00012469133,0.010486206,0.000049299073,0.01179573,0.00067705684,0.0015708059,0.24761274,0.10795722,0.5897328],"study_design_scores_gemma":[0.0030607202,0.014317848,0.0046572904,0.00005002587,0.0013124136,0.00016180155,0.01466755,0.00081087975,0.00078020495,0.94209546,0.017777976,0.0003078171],"about_ca_topic_score_codex":0.00002224345,"about_ca_topic_score_gemma":0.0000041659982,"teacher_disagreement_score":0.69448274,"about_ca_system_score_codex":0.0003450601,"about_ca_system_score_gemma":0.00013974145,"threshold_uncertainty_score":0.8173696},"labels":[],"label_agreement":null},{"id":"W4292616279","doi":"10.1093/oncolo/oyac130","title":"The Effect of Biomarker Use on the Speed and Duration of Clinical Trials for Cancer Drugs","year":2022,"lang":"en","type":"article","venue":"The Oncologist","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Medicine; Clinical trial; Biomarker; Oncology; Breast cancer; Cancer; Colorectal cancer; Lung cancer; Internal medicine; Timeline; Randomized controlled trial","score_opus":0.857347171000808,"score_gpt":0.6903379268061591,"score_spread":0.1670092441946489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292616279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9654118,0.0001724757,0.003959206,0.01848498,0.0029839016,0.006987078,0.00082838826,0.000037763584,0.0011344174],"genre_scores_gemma":[0.97419006,0.00026162178,0.022469461,0.0005883457,0.00054358575,0.0009591984,0.0000025658194,0.00004078519,0.0009443914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9764141,0.020690676,0.0021337187,0.00021479822,0.00037694085,0.00016980118],"domain_scores_gemma":[0.41222408,0.58598065,0.0012893146,0.00041487964,0.000065594984,0.00002543446],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.105237454,0.00011991741,0.0009665699,0.00001590251,0.000343216,0.000025245236,0.00040163382,0.00008678642,0.00013584041],"category_scores_gemma":[0.5295992,0.00004438887,0.0003148253,0.00013317473,0.0009399996,0.000015498603,0.00019328018,0.00028969676,8.8525786e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.033833556,0.00058461603,0.0029832139,0.0002842513,0.0012221321,0.0000023918335,0.00054937805,0.00003873514,0.0023355817,0.43635604,0.076287195,0.4455229],"study_design_scores_gemma":[0.0077559827,0.0076189954,0.00787139,0.00008944571,0.0014071723,0.000002238458,0.00062589056,0.0034766777,0.00876667,0.9428698,0.019288763,0.00022697967],"about_ca_topic_score_codex":0.000063996515,"about_ca_topic_score_gemma":0.00002007519,"teacher_disagreement_score":0.56529,"about_ca_system_score_codex":0.000042264648,"about_ca_system_score_gemma":0.000073919495,"threshold_uncertainty_score":0.92134637},"labels":[],"label_agreement":null},{"id":"W4293222009","doi":"10.1038/s41416-022-01926-z","title":"Evaluation of the patient experience of symptomatic adverse events on Phase I clinical trials using PRO-CTCAE","year":2022,"lang":"en","type":"article","venue":"British Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Medicine; Adverse effect; Clinical trial; MEDLINE; Dermatology; Surgery; Internal medicine","score_opus":0.7884720102891636,"score_gpt":0.6858444371946468,"score_spread":0.10262757309451676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293222009","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930824,0.00050012424,0.0025788618,0.00005305638,0.0025604775,0.0009628327,0.00019126486,0.0000035517066,0.000067442845],"genre_scores_gemma":[0.95585984,0.00010531895,0.043598957,0.0000983881,0.00024156833,0.000065980144,1.8762465e-7,0.00002077324,0.000008989542],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9790474,0.013538307,0.004254724,0.00017424492,0.0028261933,0.00015911687],"domain_scores_gemma":[0.97481704,0.018350916,0.0054591415,0.0002768975,0.0010031662,0.000092845716],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04448237,0.00011039778,0.0011120668,0.000060546972,0.00010780533,0.0000065504155,0.00039535764,0.000066198045,0.0014099507],"category_scores_gemma":[0.21701151,0.00008896015,0.00057843054,0.00025576953,0.00016428252,0.0000720868,0.0001297482,0.0004528674,2.6265724e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014934011,0.003706861,0.0019127642,0.00019316324,0.000672002,0.00002859101,0.0010696169,0.0032160343,0.0015708247,0.0006667555,0.0008955915,0.9845744],"study_design_scores_gemma":[0.048331235,0.0067700096,0.013129037,0.0110028675,0.008086581,0.00055619545,0.0032543354,0.026592245,0.02230436,0.8585125,0.0006995564,0.0007610601],"about_ca_topic_score_codex":0.00003330054,"about_ca_topic_score_gemma":0.0000060881434,"teacher_disagreement_score":0.98381335,"about_ca_system_score_codex":0.00026372282,"about_ca_system_score_gemma":0.00070771744,"threshold_uncertainty_score":0.9995029},"labels":[],"label_agreement":null},{"id":"W4294233607","doi":"10.15626/mp.2021.2720","title":"Z-curve 2.0: Estimating Replication Rates and Discovery Rates","year":2022,"lang":"en","type":"article","venue":"Meta-Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Replication (statistics); Confidence interval; False discovery rate; Statistics; Selection (genetic algorithm); False positive paradox; Multiple comparisons problem; Computer science; Range (aeronautics); Extension (predicate logic); Statistical power; Econometrics; Mathematics; Artificial intelligence; Biology; Engineering","score_opus":0.7276317683307449,"score_gpt":0.64387429511749,"score_spread":0.083757473213255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294233607","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06307341,0.0007893696,0.9164829,0.011457492,0.002408108,0.0011095864,0.000275743,0.00024594093,0.0041574053],"genre_scores_gemma":[0.051939037,0.00002354443,0.9439685,0.0024910863,0.00022301392,0.0005782188,0.000010888531,0.00004708385,0.0007186732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951055,0.0026026706,0.0009406981,0.00079952495,0.00025420057,0.00029741292],"domain_scores_gemma":[0.9731434,0.025206797,0.00045622478,0.0010559376,0.00005755076,0.00008010906],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007435662,0.0002077712,0.0008794412,0.00008822545,0.00024692246,0.000053718173,0.0003175724,0.00009464981,0.0013654961],"category_scores_gemma":[0.06030139,0.0001702773,0.00016392922,0.000266899,0.00021237647,0.000099410674,0.00029144812,0.00043430118,0.000022454076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092316774,0.0018143227,0.008078642,0.0003717468,0.004676923,0.00011548242,0.0011167035,0.00007334703,0.0095647955,0.7168034,0.10273095,0.15373056],"study_design_scores_gemma":[0.0006487608,0.00023095231,0.002684729,0.000003819187,0.0007278182,0.000045088378,0.000029889849,0.0006837421,0.0003296986,0.9889766,0.0054431427,0.00019574638],"about_ca_topic_score_codex":0.000008719313,"about_ca_topic_score_gemma":0.000001840573,"teacher_disagreement_score":0.27217326,"about_ca_system_score_codex":0.000023151057,"about_ca_system_score_gemma":0.000020624444,"threshold_uncertainty_score":0.99954736},"labels":[],"label_agreement":null},{"id":"W4294647301","doi":"10.1186/s13063-022-06689-9","title":"Overestimation of benefit when clinical trials stop early: a simulation study","year":2022,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Relative risk; Medicine; Early stopping; Interim analysis; Interim; Sprint; Clinical trial; Randomized controlled trial; Confidence interval; Physical therapy; Internal medicine; Computer science","score_opus":0.930647252010631,"score_gpt":0.7294744882088581,"score_spread":0.20117276380177296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294647301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7595259,0.00007689002,0.22083814,0.00031522106,0.004401142,0.01249092,0.0011024397,0.00026202245,0.0009873622],"genre_scores_gemma":[0.73701555,0.0000046909317,0.2612608,0.00008054027,0.000842644,0.00038201784,0.000006944744,0.00005328617,0.00035349632],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.897939,0.08084183,0.017316114,0.0010567363,0.0023306925,0.0005155831],"domain_scores_gemma":[0.3290457,0.6628486,0.006365505,0.0012008671,0.0003377184,0.00020161238],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24180485,0.00027174212,0.004353459,0.00018936441,0.00019109179,0.000051355302,0.00049723976,0.00018769175,0.0049985372],"category_scores_gemma":[0.7702074,0.00022778435,0.0008808915,0.00032481604,0.00010032307,0.000103711616,0.0003590203,0.00053710904,0.000029344106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03577219,0.0246005,0.02716882,0.0005349742,0.005049829,0.000068747766,0.010420498,0.019135209,0.0013148596,0.35876995,0.013126316,0.5040381],"study_design_scores_gemma":[0.009587346,0.0022246349,0.005032802,0.00003125659,0.0011469364,7.006247e-7,0.00039015693,0.0038332825,0.00013382733,0.97708786,0.00028386465,0.00024736355],"about_ca_topic_score_codex":0.000055217362,"about_ca_topic_score_gemma":0.0000028585353,"teacher_disagreement_score":0.61831784,"about_ca_system_score_codex":0.00009338888,"about_ca_system_score_gemma":0.0001251993,"threshold_uncertainty_score":0.995911},"labels":[],"label_agreement":null},{"id":"W4294686035","doi":"10.1093/neuonc/noac174.254","title":"P11.65.B GBM AGILE: A global, phase 2/3 adaptive platform trial to evaluate multiple treatment regimens in newly diagnosed and recurrent glioblastoma","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Agile software development; Medicine; Randomization; Protocol (science); Clinical trial; Biomarker; Medical physics; Oncology; Computer science; Internal medicine; Software engineering; Pathology; Alternative medicine","score_opus":0.4195986878733863,"score_gpt":0.5471289144013946,"score_spread":0.12753022652800827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294686035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9818053,0.0000820595,0.0023625537,0.002906879,0.0041042278,0.006611842,0.0010056746,0.00016480601,0.0009566334],"genre_scores_gemma":[0.622617,0.00024280397,0.3641671,0.0033426885,0.0012782865,0.008042364,0.00001935794,0.00017607641,0.000114343435],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99292237,0.0033444222,0.0014265585,0.00101246,0.0005874796,0.0007067226],"domain_scores_gemma":[0.9353366,0.063084684,0.00048695595,0.00057321537,0.00008990722,0.00042863734],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002771517,0.00042682674,0.0014475707,0.00017864963,0.00020597113,0.00003058867,0.0003485036,0.00021748689,0.00047916637],"category_scores_gemma":[0.058481935,0.00035579145,0.00019276195,0.0006037269,0.0001680183,0.00006270564,0.00055335445,0.0005712962,0.000038407583],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.29182628,0.01202008,0.00015642833,0.00003995194,0.00022491578,0.0024534718,0.0021149213,0.00013121606,0.0025174087,0.011761877,0.016158776,0.66059464],"study_design_scores_gemma":[0.42869678,0.21275645,0.00015156351,0.00006240162,0.000605855,0.00019243041,0.0011122902,0.006304479,0.0014300254,0.23502202,0.11275366,0.00091205054],"about_ca_topic_score_codex":0.00007931793,"about_ca_topic_score_gemma":0.0005384018,"teacher_disagreement_score":0.65968263,"about_ca_system_score_codex":0.0017629787,"about_ca_system_score_gemma":0.00046295245,"threshold_uncertainty_score":0.99988943},"labels":[],"label_agreement":null},{"id":"W4296092041","doi":"10.18433/jpps32892","title":"Critical Remarks on Reference-Scaled Average Bioequivalence","year":2022,"lang":"en","type":"article","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bioequivalence; Type I and type II errors; Econometrics; Medicine; Set (abstract data type); Statistics; Computer science; Mathematics; Pharmacology","score_opus":0.7160800627062461,"score_gpt":0.6501009608732287,"score_spread":0.06597910183301747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296092041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57388043,0.003847312,0.13560271,0.09780524,0.03376098,0.003282371,0.0008754496,0.0006157627,0.15032977],"genre_scores_gemma":[0.83504164,0.00028993416,0.16040066,0.0032735206,0.0008038822,0.000021324813,2.7419173e-7,0.000027579359,0.00014117463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990536,0.0031959233,0.0019346467,0.0005572428,0.0029560723,0.0008201344],"domain_scores_gemma":[0.94375116,0.054154605,0.0006764351,0.0002836927,0.00034954946,0.0007845891],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016355231,0.00032134753,0.0008412873,0.00029848007,0.0008383395,0.00015065774,0.0017575213,0.00006253452,0.014936941],"category_scores_gemma":[0.054488268,0.000241339,0.00038041454,0.000985449,0.0014473362,0.00036544286,0.00052717363,0.0022015986,0.00004799851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048892912,0.0048398105,0.002092081,0.00036004785,0.000261393,0.0016424335,0.000405837,0.0004868369,0.0300015,0.68617064,0.035921402,0.23292875],"study_design_scores_gemma":[0.004615986,0.0025152725,0.00015886515,0.00014035059,0.00043481158,0.00062004715,0.00025856867,0.008666005,0.01823605,0.7976267,0.16605999,0.0006673991],"about_ca_topic_score_codex":0.0000037311222,"about_ca_topic_score_gemma":2.383742e-7,"teacher_disagreement_score":0.26116124,"about_ca_system_score_codex":0.00021921397,"about_ca_system_score_gemma":0.0003650123,"threshold_uncertainty_score":0.9859635},"labels":[],"label_agreement":null},{"id":"W4296266806","doi":"10.1177/17407745221118366","title":"A Bayesian adaptive design for clinical trials of rare efficacy outcomes with multiple definitions","year":2022,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; Impact; Institute for Clinical Evaluative Sciences; McGill University","funders":"Bill and Melinda Gates Foundation","keywords":"Flexibility (engineering); Computer science; Outcome (game theory); Bayesian probability; Early stopping; Set (abstract data type); Clinical trial; Risk analysis (engineering); Clinical study design; Rare events; Variety (cybernetics); Machine learning; Data mining; Artificial intelligence; Statistics; Medicine; Mathematics","score_opus":0.9518411116323391,"score_gpt":0.6939768661821792,"score_spread":0.25786424545015985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296266806","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003924312,0.00013291524,0.9734517,0.0015196502,0.0035583924,0.011463646,0.0053372993,0.00025272474,0.00035938833],"genre_scores_gemma":[0.07694277,0.00015967242,0.9179482,0.0008118248,0.0014274262,0.0023003244,0.00003712135,0.00016788815,0.00020477921],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.80615795,0.16116785,0.028103488,0.0019659863,0.0015771926,0.0010275487],"domain_scores_gemma":[0.04091936,0.94670975,0.009244892,0.00174844,0.0006641488,0.0007134319],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3912285,0.0006686525,0.012027363,0.00023451538,0.0004869964,0.00006529978,0.001168233,0.0006797961,0.0018274208],"category_scores_gemma":[0.9550707,0.00046854265,0.0051255245,0.0006411103,0.001047699,0.00009721781,0.00047498857,0.0016032727,0.000022037915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14327343,0.032415424,0.03295576,0.00065963285,0.015362582,0.0001661351,0.00050326553,0.00053140684,0.00009637974,0.3701095,0.16315004,0.24077643],"study_design_scores_gemma":[0.046954364,0.009831704,0.002296597,0.00020654131,0.003912785,0.000008466665,0.0004152765,0.0020114903,0.00017916522,0.9298239,0.0035630325,0.0007967071],"about_ca_topic_score_codex":0.000007996819,"about_ca_topic_score_gemma":0.000005070905,"teacher_disagreement_score":0.7855419,"about_ca_system_score_codex":0.000087429384,"about_ca_system_score_gemma":0.0008795818,"threshold_uncertainty_score":0.9997766},"labels":[],"label_agreement":null},{"id":"W4296371025","doi":"10.6000/1929-6029.2022.11.11","title":"Comprehensive Evaluation of Reference Values of Parametric and Non-Parametric Effect Size Methods for Two Independent Groups","year":2022,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Parametric statistics; Skewness; Mathematics; Statistics; Parametric model; Measure (data warehouse); Nonparametric statistics; Value (mathematics); Significant difference; Computer science; Data mining","score_opus":0.6426058132913987,"score_gpt":0.7105112017097936,"score_spread":0.067905388418395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296371025","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3158052,0.00041197854,0.6807405,0.0002497122,0.0011528771,0.0009975,0.00042365683,0.0000032174385,0.00021540631],"genre_scores_gemma":[0.49433476,0.00016779042,0.5053108,0.000018961677,0.000090660986,0.00005391912,0.0000029988332,0.000013327364,0.0000067827477],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9721021,0.013323961,0.0029534942,0.00036512257,0.010868865,0.00038644273],"domain_scores_gemma":[0.5453072,0.4474495,0.0011046114,0.00021404738,0.005704133,0.00022051603],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09934775,0.0001502589,0.0009705245,0.0013153255,0.00006906387,0.000028885008,0.0010831106,0.00013122022,0.00083111244],"category_scores_gemma":[0.69239056,0.00012656015,0.00011747342,0.0010469108,0.0005900145,0.00006009021,0.00059793075,0.0016188895,5.9459865e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035150773,0.0013811899,0.0034863553,0.0006601679,0.00070089806,0.000118859876,0.00039179367,0.00043579267,0.0010208288,0.12013678,0.0012416965,0.8669106],"study_design_scores_gemma":[0.0061558583,0.0022647255,0.00840741,0.00024878842,0.00012957302,0.000051890333,0.00027518912,0.045898426,0.0012709555,0.93511283,0.00008222451,0.00010213309],"about_ca_topic_score_codex":0.00006519016,"about_ca_topic_score_gemma":0.00000411116,"teacher_disagreement_score":0.8668084,"about_ca_system_score_codex":0.00043488937,"about_ca_system_score_gemma":0.0008147772,"threshold_uncertainty_score":0.927411},"labels":[],"label_agreement":null},{"id":"W4297333613","doi":"10.1214/22-aoas1600","title":"Bayesian hierarchical random-effects meta-analysis and design of phase I clinical trials","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Meta-analysis; Random effects model; Computer science; Bayesian probability; Parametric statistics; Clinical study design; Statistics; Clinical trial; Data mining; Artificial intelligence; Mathematics; Medicine","score_opus":0.8487982915840147,"score_gpt":0.6507765650971692,"score_spread":0.19802172648684546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297333613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005404325,0.00022199508,0.9931199,0.00052334595,0.00013046135,0.002052602,0.0030990867,0.000027868928,0.00028430484],"genre_scores_gemma":[0.1327813,0.00017256154,0.8659258,0.0005824588,0.00009444062,0.0003348166,0.000014346949,0.000042626514,0.00005167913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97383726,0.019141141,0.0048631025,0.0005736763,0.0011702421,0.0004146061],"domain_scores_gemma":[0.58672816,0.41003245,0.0020356309,0.00082668924,0.000184106,0.00019297682],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08113342,0.00032990563,0.005871309,0.00021641643,0.00021350342,0.000025648935,0.00064381794,0.0001334861,0.0011976423],"category_scores_gemma":[0.14842562,0.00021133371,0.0013435851,0.0007714313,0.00092078623,0.00001884968,0.00038404512,0.00071768905,0.0000020043035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011269355,0.0021357422,0.000006429858,0.00033221723,0.1243932,0.000023065564,0.0004913687,0.0006351654,0.0005221032,0.8004571,0.0104572475,0.04927695],"study_design_scores_gemma":[0.0040500886,0.00088625704,0.000018853747,0.0000025124696,0.11489191,0.000001305729,0.00006219816,0.007649299,0.0015580802,0.87058365,0.00011077578,0.00018504856],"about_ca_topic_score_codex":0.000008131169,"about_ca_topic_score_gemma":0.0000011579832,"teacher_disagreement_score":0.3908913,"about_ca_system_score_codex":0.000007691122,"about_ca_system_score_gemma":0.00011318978,"threshold_uncertainty_score":0.9997154},"labels":[],"label_agreement":null},{"id":"W4297811834","doi":"10.1002/pst.2336","title":"Evaluating hybrid controls methodology in early‐phase oncology trials: A simulation study based on the <scp>MORPHEUS‐UC</scp> trial","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Roche (Canada)","funders":"F. Hoffmann-La Roche","keywords":"Frequentist inference; Bayesian probability; Sample size determination; Prior probability; Statistics; Clinical trial; Computer science; Econometrics; Medicine; Oncology; Bayesian inference; Mathematics; Internal medicine","score_opus":0.9531832501912486,"score_gpt":0.7584745799826099,"score_spread":0.1947086702086387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297811834","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22425951,0.000015087485,0.7627189,0.0006380573,0.0022228386,0.008394783,0.0011691374,0.00028889487,0.000292755],"genre_scores_gemma":[0.44046867,0.000015811669,0.555485,0.0013716947,0.0010322556,0.0013770355,0.000029589657,0.00012653635,0.00009341635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.92940533,0.061639618,0.0046659242,0.0011667038,0.0017896268,0.0013328242],"domain_scores_gemma":[0.42053577,0.57748175,0.00083326414,0.000575019,0.0002721116,0.00030206927],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10514563,0.00059492793,0.002818358,0.0003708984,0.0003013822,0.00013757091,0.0006977348,0.0003222419,0.0007320004],"category_scores_gemma":[0.8400598,0.0004281533,0.0003307745,0.0010917835,0.00044645526,0.00006453421,0.0002427964,0.0017458445,0.0003367996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10846021,0.030546246,0.000974042,0.00052066887,0.0019351591,0.0024075496,0.0032492338,0.055436853,0.0020595994,0.21644688,0.01850704,0.5594565],"study_design_scores_gemma":[0.08352025,0.0050169127,0.00015470201,0.00003311015,0.00071289064,0.0000013875717,0.00020490878,0.56161875,0.00017097648,0.3475836,0.0008484786,0.000134048],"about_ca_topic_score_codex":0.00002670312,"about_ca_topic_score_gemma":0.000010102523,"teacher_disagreement_score":0.7349142,"about_ca_system_score_codex":0.0003248276,"about_ca_system_score_gemma":0.00037338008,"threshold_uncertainty_score":0.999817},"labels":[],"label_agreement":null},{"id":"W4298007568","doi":"10.1016/j.annonc.2022.09.158","title":"Oncology phase I trial design and conduct: time for a change - MDICT Guidelines 2022","year":2022,"lang":"en","type":"review","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":97,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Queen's University","funders":"European Society for Medical Oncology; National Institute for Health and Care Research","keywords":"Medicine; Clinical trial; Clinical endpoint; Protocol (science); Randomization; Center of excellence; Clinical study design; Oncology; Medical physics; Phases of clinical research; Internal medicine; Alternative medicine; Pathology","score_opus":0.9812556986171592,"score_gpt":0.7770008680159786,"score_spread":0.20425483060118066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298007568","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016979882,0.96824366,0.013065699,0.0017433378,0.0026612536,0.011476295,0.0018209433,0.00007055567,0.00091654254],"genre_scores_gemma":[1.19674155e-8,0.6244099,0.36938405,0.00073406496,0.0013890162,0.0036354202,0.000046540856,0.00008136405,0.00031962016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.985186,0.008816279,0.0041195233,0.0008781712,0.00036919987,0.00063085277],"domain_scores_gemma":[0.7675969,0.22845262,0.0027693934,0.0005839238,0.00037567646,0.00022151365],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023233186,0.0005940061,0.0081566395,0.00033458014,0.00012932696,0.000014057602,0.0007068315,0.0012714766,0.0035407238],"category_scores_gemma":[0.20784964,0.00048483405,0.0010258633,0.0003368041,0.00048808206,0.00005515272,0.0004646919,0.00076386955,0.000024200835],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071516447,0.0011632775,3.2261824e-9,0.004170976,0.0005292455,0.00004642265,0.000045588207,3.012856e-8,9.575465e-7,0.0057349526,0.13694723,0.8442097],"study_design_scores_gemma":[0.01845959,0.026950361,2.5199647e-9,0.0005585913,0.0017796756,0.00005269588,0.000012094892,0.000036542628,0.0000026638954,0.19483836,0.75700045,0.00030895977],"about_ca_topic_score_codex":0.00000800082,"about_ca_topic_score_gemma":0.0000013295446,"teacher_disagreement_score":0.84390074,"about_ca_system_score_codex":0.00013602308,"about_ca_system_score_gemma":0.0014878268,"threshold_uncertainty_score":0.9997603},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4298139633","doi":"10.1200/jco.2022.40.28_suppl.040","title":"Comparing chair time required for systemic agent drug reaction (DR) management to allocated chair time for systemic protocol.","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Island Health; BC Cancer Agency","funders":"","keywords":"Medicine; Regimen; Surgery","score_opus":0.6319275583430035,"score_gpt":0.6184079064705147,"score_spread":0.013519651872488825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298139633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07359836,0.00008021361,0.5569289,0.027090337,0.011729466,0.32576677,0.00018551628,0.0004891729,0.0041312855],"genre_scores_gemma":[0.032021888,0.000013358776,0.8678697,0.0022761193,0.003766722,0.087597474,0.000011251876,0.00019342109,0.006250073],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985158,0.0042110807,0.00849175,0.00062320195,0.0008974061,0.00061854126],"domain_scores_gemma":[0.9253084,0.066858426,0.005952804,0.00055932347,0.00079716515,0.0005238564],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045288615,0.00034385337,0.003699431,0.0002753189,0.00025657096,0.000034904322,0.0009320525,0.00036001543,0.0001729567],"category_scores_gemma":[0.053439096,0.00029020116,0.001096639,0.00031487903,0.000112569716,0.00010293871,0.00035370776,0.0009774377,0.00008977693],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09083619,0.013180248,0.000360527,0.008683664,0.0065301647,0.0010929019,0.00090632046,0.0015886571,0.010677453,0.06178827,0.72681576,0.07753985],"study_design_scores_gemma":[0.05903693,0.040911987,0.00047772215,0.0030950736,0.0033948752,0.002403825,0.0011497826,0.019772163,0.0003441935,0.5311067,0.3368072,0.0014995363],"about_ca_topic_score_codex":0.0000034664479,"about_ca_topic_score_gemma":0.000001343812,"teacher_disagreement_score":0.46931845,"about_ca_system_score_codex":0.0011457846,"about_ca_system_score_gemma":0.0005231231,"threshold_uncertainty_score":0.999955},"labels":[],"label_agreement":null},{"id":"W4299846041","doi":"10.5772/intechopen.106352","title":"Optimal N-of-1 Clinical Trials for Individualized Patient Care and Aggregated N-of-1 Designs","year":2022,"lang":"en","type":"book-chapter","venue":"IntechOpen eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Ontario Medical Association","funders":"","keywords":"Clinical trial; Medicine; Crossover; Clinical study design; Disease; Crossover study; Construct (python library); Precision medicine; Psychological intervention; Intensive care medicine; Alternative medicine; Medical physics; Computer science; Artificial intelligence; Placebo; Internal medicine; Pathology","score_opus":0.8258476800656984,"score_gpt":0.6233321059364946,"score_spread":0.20251557412920385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299846041","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016866813,0.0015139258,0.113031246,0.00006319004,0.004773414,0.021316512,0.016623171,0.00028059926,0.84071124],"genre_scores_gemma":[0.0012864544,0.00012671495,0.9811103,0.00008825123,0.00028135526,0.00049211114,0.000050213643,0.0002352304,0.016329415],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9873553,0.0026696173,0.007886895,0.0009178485,0.0008197175,0.00035064423],"domain_scores_gemma":[0.83259284,0.16028973,0.0053974376,0.00087862305,0.0006243599,0.00021699876],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018645836,0.0006156994,0.005524432,0.00026235092,0.000100686266,0.00003675453,0.0007411722,0.0011248499,0.0016698255],"category_scores_gemma":[0.20254722,0.000525502,0.0014900794,0.000030596206,0.0007964853,0.00002918931,0.0008409269,0.0011810281,0.0000041867997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002527256,0.00008359145,0.0000036595438,0.00091818825,0.0011914333,0.0000253249,0.0006849022,6.718789e-7,0.000052451313,0.4090517,0.0017697156,0.5836911],"study_design_scores_gemma":[0.004939784,0.004935029,6.887592e-7,0.0014546756,0.0020783101,0.000010573818,0.00025928335,0.000015479905,0.0036118594,0.86857605,0.11347123,0.0006470657],"about_ca_topic_score_codex":0.000013785183,"about_ca_topic_score_gemma":0.0000037481825,"teacher_disagreement_score":0.868079,"about_ca_system_score_codex":0.00006845538,"about_ca_system_score_gemma":0.00043240443,"threshold_uncertainty_score":0.9997197},"labels":[],"label_agreement":null},{"id":"W4301600257","doi":"10.1007/s11523-022-00920-y","title":"Do Early Phase Oncology Trials Predict Clinical Efficacy in Subsequent Biomarker-Enriched Phase III Randomized Trials?","year":2022,"lang":"en","type":"article","venue":"Targeted Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Princess Margaret Cancer Centre; University Health Network; University of Toronto; Canadian Centre for Applied Research in Cancer Control; Sunnybrook Hospital","funders":"","keywords":"Medicine; Randomized controlled trial; Clinical endpoint; Clinical trial; Internal medicine; Confidence interval; Biomarker; Surrogate endpoint; Phases of clinical research; Oncology","score_opus":0.7138172971596959,"score_gpt":0.6583019463492661,"score_spread":0.0555153508104298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301600257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7979239,0.0017160987,0.13681535,0.0053460887,0.022489922,0.026270224,0.0018176845,0.0009110622,0.0067096464],"genre_scores_gemma":[0.6089014,0.00059559854,0.38054144,0.0015987752,0.0024915314,0.00506606,0.0001799728,0.00024178751,0.00038344171],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.69062465,0.27943224,0.024142286,0.002319152,0.0015844451,0.0018972415],"domain_scores_gemma":[0.26853192,0.7212972,0.0075009963,0.0014727048,0.0003475185,0.0008496629],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.34753045,0.0008539583,0.0192384,0.000851528,0.00035372822,0.00006998505,0.0014264197,0.0014635035,0.015455894],"category_scores_gemma":[0.7929523,0.00069326395,0.0030946853,0.0014469849,0.0014868496,0.00012353215,0.00084651285,0.0030899118,0.000085846936],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6523542,0.032410882,0.00003855601,0.00005757272,0.0023671642,0.0013007799,0.00088236795,0.000016268643,0.003575805,0.034486793,0.02069665,0.25181296],"study_design_scores_gemma":[0.62963325,0.00883469,0.000046394012,0.000025036965,0.0020574513,0.000041057916,0.0002188465,0.0012669559,0.00018659087,0.33972114,0.017436888,0.0005316752],"about_ca_topic_score_codex":0.000109384986,"about_ca_topic_score_gemma":0.000017254746,"teacher_disagreement_score":0.44542184,"about_ca_system_score_codex":0.0014515669,"about_ca_system_score_gemma":0.0020932122,"threshold_uncertainty_score":0.9998328},"labels":[],"label_agreement":null},{"id":"W4304695372","doi":"10.1136/bmjopen-2022-063436","title":"Dose optimisation and scarce resource allocation: two sides of the same coin","year":2022,"lang":"en","type":"review","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Heart, Lung, and Blood Institute","keywords":"Scarcity; Medicine; Pandemic; Repurposing; Resource allocation; Coronavirus disease 2019 (COVID-19); Clinical trial; Resource (disambiguation); Health care; Risk analysis (engineering); Disease; Computer science; Economic growth; Microeconomics; Economics","score_opus":0.8255357170646623,"score_gpt":0.6661719584624166,"score_spread":0.15936375860224572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304695372","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006051254,0.9014292,0.0038427,0.0013125975,0.0009496689,0.052352436,0.0006161807,0.00007522318,0.039415978],"genre_scores_gemma":[6.904095e-7,0.53500724,0.46024925,0.0001791187,0.00022936774,0.0021550783,0.000015174563,0.000070763715,0.0020932907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.992351,0.0049194563,0.0016166997,0.00042336708,0.00053080154,0.00015870556],"domain_scores_gemma":[0.9318037,0.065338105,0.0014979965,0.001235389,0.00005291152,0.0000719031],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011028787,0.0002530067,0.0019413612,0.000045556102,0.0001310421,0.00009704142,0.0013586275,0.00016326566,0.0010161891],"category_scores_gemma":[0.09689264,0.00016437777,0.00026447442,0.0003257209,0.0002131699,0.00004801185,0.0021383315,0.00043712178,0.000009460038],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035198085,0.000060619182,0.0000018431338,0.009674448,0.00012335555,0.0000025387787,0.00010601098,0.000001789878,2.1872363e-7,0.050986912,0.0031488962,0.9358582],"study_design_scores_gemma":[0.00045298444,0.00005453307,0.0000057440698,0.00660578,0.00076823356,0.00002459015,0.00006374925,0.000019020512,0.0000024271233,0.24679759,0.74498236,0.00022301292],"about_ca_topic_score_codex":0.000044495533,"about_ca_topic_score_gemma":0.000008755905,"teacher_disagreement_score":0.93563515,"about_ca_system_score_codex":0.0000804636,"about_ca_system_score_gemma":0.0003631423,"threshold_uncertainty_score":0.999897},"labels":[],"label_agreement":null},{"id":"W4306318633","doi":"10.1016/j.cct.2022.106963","title":"Machine learning for detecting centre-level irregularities in randomized controlled trials: A pilot study","year":2022,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; University of Toronto; Hamilton Health Sciences; Public Health Ontario; McMaster University; Population Health Research Institute","funders":"Canadian Institutes of Health Research","keywords":"Machine learning; Artificial intelligence; Medicine; Support vector machine; Unsupervised learning; Clinical trial; Computer science","score_opus":0.8906204871631688,"score_gpt":0.6318866838975108,"score_spread":0.258733803265658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306318633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12216117,0.015156404,0.5016852,0.010894435,0.039411023,0.2964841,0.004105708,0.0023959205,0.0077060307],"genre_scores_gemma":[0.8757641,0.000118433716,0.11049624,0.0004760229,0.0018716315,0.008769692,0.000027825738,0.00017837048,0.002297726],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.39747706,0.54904145,0.047668934,0.002375074,0.0021419087,0.0012955939],"domain_scores_gemma":[0.041310526,0.94620615,0.010763448,0.00096035097,0.00036915185,0.00039038245],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7181996,0.0008054834,0.034651313,0.0005189091,0.0006009883,0.00020940306,0.00095332245,0.00027585743,0.0012622765],"category_scores_gemma":[0.98140186,0.00057398574,0.0057539404,0.0005569402,0.00041734488,0.00015201228,0.0006708414,0.0023779126,0.000009451086],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9447795,0.007652635,0.0028366388,0.00017150558,0.0042569246,0.000090162226,0.00046670294,0.000045380068,0.00004432965,0.019614277,0.0019596212,0.018082326],"study_design_scores_gemma":[0.5701227,0.0041946652,0.000038895996,0.000114401155,0.0014033443,0.0000018761353,0.0014580064,0.0038735855,0.000013751995,0.41752177,0.0008108495,0.00044612252],"about_ca_topic_score_codex":0.0001477957,"about_ca_topic_score_gemma":0.00004360402,"teacher_disagreement_score":0.75360286,"about_ca_system_score_codex":0.0001502758,"about_ca_system_score_gemma":0.00063895894,"threshold_uncertainty_score":0.99992365},"labels":[],"label_agreement":null},{"id":"W4306795924","doi":"10.1093/epirev/mxac010","title":"Randomized Trials With Repeatedly Measured Outcomes: Handling Irregular and Potentially Informative Assessment Times","year":2022,"lang":"en","type":"review","venue":"Epidemiologic Reviews","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Hospital for Sick Children; National Institute of Mental Health; University of Toronto","keywords":"Outcome (game theory); Medicine; Randomized controlled trial; Randomization; Missing data; Machine learning; Computer science; Surgery; Mathematics","score_opus":0.8764469627589582,"score_gpt":0.6564248351818112,"score_spread":0.220022127577147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306795924","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.4232528e-7,0.84310573,0.13824716,0.00017666836,0.0006738815,0.014998403,0.00013675966,0.00015786588,0.0025033748],"genre_scores_gemma":[1.919614e-8,0.5415545,0.45437104,0.00027564363,0.00013697056,0.0032465027,0.000045658744,0.00006114283,0.00030851868],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7822326,0.19368967,0.020387512,0.0016676475,0.0010760492,0.000946517],"domain_scores_gemma":[0.2303174,0.7467321,0.019943245,0.0023323495,0.00021800646,0.00045687266],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.35919437,0.0016276302,0.05375172,0.00028528032,0.0003530056,0.00012458327,0.0009896177,0.00082210853,0.0020675694],"category_scores_gemma":[0.85428256,0.00074088253,0.005156625,0.00056078506,0.00066615804,0.00014344226,0.0005907787,0.002141232,0.000055566343],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014530909,0.00008663432,0.0000042144934,0.019939927,0.002603206,0.000024558149,0.00004014803,8.7441447e-7,1.6617422e-8,0.022639202,0.004720602,0.9484875],"study_design_scores_gemma":[0.019984003,0.00022662012,0.0000012929747,0.012458412,0.010823116,0.000042436484,0.000014984945,0.000015240438,2.8071334e-8,0.22227116,0.7334607,0.0007020146],"about_ca_topic_score_codex":0.000010290915,"about_ca_topic_score_gemma":9.811424e-7,"teacher_disagreement_score":0.9477855,"about_ca_system_score_codex":0.0002904673,"about_ca_system_score_gemma":0.00046745923,"threshold_uncertainty_score":0.99964714},"labels":[],"label_agreement":null},{"id":"W4306936867","doi":"10.5539/ijsp.v11n6p12","title":"Combining Correlated P-values From Primary Data Analyses","year":2022,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Statistics; Independent and identically distributed random variables; Bayesian probability; Test statistic; Statistic; Statistical hypothesis testing; Random variable","score_opus":0.6046218179486453,"score_gpt":0.5719758431237235,"score_spread":0.03264597482492182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306936867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15666483,0.00038044841,0.82069427,0.0010287307,0.004116383,0.00029263372,0.016082538,0.000028759463,0.00071142556],"genre_scores_gemma":[0.13691743,0.00007537432,0.8624532,0.00019579112,0.00021690567,0.0000031610637,0.00009591504,0.000013542508,0.000028629429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964448,0.0009243487,0.0012834269,0.00026394258,0.00096379983,0.000119680895],"domain_scores_gemma":[0.9680659,0.029982328,0.0009458465,0.00035709768,0.00054465694,0.00010416204],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044919276,0.000121902034,0.00048377833,0.0000749906,0.000112541755,0.000075068194,0.0009117908,0.000041472198,0.00094296254],"category_scores_gemma":[0.04053292,0.00010490072,0.00005825227,0.00008707141,0.00018163073,0.00011902526,0.0008817592,0.000521997,0.000001216997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005348915,0.004256132,0.047404043,0.00025655286,0.0056809876,0.0011229437,0.0022486805,0.0006722612,0.0016010778,0.4927144,0.081823215,0.35687077],"study_design_scores_gemma":[0.0009826202,0.00020043956,0.0076246997,0.000032634165,0.0001875883,0.000043302727,0.00007503336,0.0035127136,0.000024078641,0.98621684,0.0009924246,0.00010764815],"about_ca_topic_score_codex":0.000055484434,"about_ca_topic_score_gemma":0.000003808787,"teacher_disagreement_score":0.4935024,"about_ca_system_score_codex":0.0001222799,"about_ca_system_score_gemma":0.00015988381,"threshold_uncertainty_score":0.9999703},"labels":[],"label_agreement":null},{"id":"W4307130839","doi":"10.9734/ajpas/2022/v20i3428","title":"A Simulation Study Using a Mixed Model Framework to Analyze the Impact of Sample Size and Variability on Type I Error","year":2022,"lang":"en","type":"article","venue":"Asian Journal of Probability and Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Johnson & Johnson (Canada)","funders":"","keywords":"Mixed model; Generalized linear mixed model; Normality; Type I and type II errors; Statistics; Sample size determination; Standard error; Random effects model; Statistical inference; Econometrics; Monte Carlo method; Estimator; Variance (accounting); Mathematics; Inference; Computer science; Medicine; Meta-analysis","score_opus":0.46572605646419624,"score_gpt":0.5610340482888468,"score_spread":0.0953079918246506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307130839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41671938,0.0000029837026,0.5821517,0.00011093692,0.00007916722,0.00048485538,0.00044120353,0.000003043156,0.00000670829],"genre_scores_gemma":[0.50599444,4.1376197e-7,0.49395674,0.000016688678,0.000020817997,0.0000025541383,1.6188633e-7,0.000007342745,8.54771e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99520916,0.0027059906,0.0011881525,0.00023319577,0.0004897259,0.00017375428],"domain_scores_gemma":[0.88820684,0.10989896,0.0007731609,0.00043932488,0.0004910556,0.0001906577],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009363183,0.0001581784,0.0006715215,0.00005433758,0.00020581757,0.00003455522,0.0001907786,0.00005831983,0.000118535165],"category_scores_gemma":[0.32418323,0.00010591644,0.00009333478,0.0003189216,0.00020258666,0.000040041472,0.00015263938,0.0005495812,1.0229073e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005926722,0.0050869607,0.045112323,0.00034915068,0.0008146256,0.000022232722,0.014697095,0.6856285,0.00006590743,0.22010648,0.00014927432,0.022040742],"study_design_scores_gemma":[0.0004213046,0.0026075288,0.015929664,0.000022537528,0.00019575025,0.000004242085,0.0005667262,0.1722106,0.0000014224631,0.80795723,7.333725e-7,0.00008227942],"about_ca_topic_score_codex":0.000023269913,"about_ca_topic_score_gemma":0.0000060059833,"teacher_disagreement_score":0.58785075,"about_ca_system_score_codex":0.00014349312,"about_ca_system_score_gemma":0.00021177273,"threshold_uncertainty_score":0.68150944},"labels":[],"label_agreement":null},{"id":"W4308003681","doi":"10.54846/jshap/1295","title":"Maximizing value and minimizing waste in clinical trial research in swine: Selecting interventions to build an evidence base","year":2022,"lang":"en","type":"article","venue":"Journal of Swine Health and Production","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"University of Guelph","keywords":"Psychological intervention; Intervention (counseling); Clinical trial; Baseline (sea); Medicine; Replication (statistics); Placebo; Equivalence (formal languages); Randomized controlled trial; Physical therapy; Intensive care medicine; Computer science; Alternative medicine; Mathematics; Surgery; Nursing; Internal medicine; Pathology","score_opus":0.8853342306265641,"score_gpt":0.7093134579139678,"score_spread":0.1760207727125963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308003681","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96579003,0.0011050847,0.0035168899,0.026669083,0.0018493527,0.0010521058,0.0000028875843,0.000008689788,0.000005878196],"genre_scores_gemma":[0.45247197,0.00087089045,0.54353017,0.0003498078,0.00267275,0.000048702765,4.4555193e-7,0.000026140071,0.000029112605],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9870046,0.00850454,0.0030601313,0.00043056498,0.00061422243,0.00038593376],"domain_scores_gemma":[0.9771105,0.0209387,0.0009375275,0.00025752364,0.00027056018,0.00048520596],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09081885,0.00010593101,0.0006702781,0.00065538485,0.00027382077,0.000046925845,0.00014840579,0.00006232173,0.000017371696],"category_scores_gemma":[0.18044446,0.000098440076,0.0000878528,0.0009147216,0.00006185147,0.0002575202,0.00018198934,0.001760203,2.7994824e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.08961195,0.004302138,0.017271819,0.005503083,0.00007120768,0.00015548762,0.006784207,0.0009807174,0.0010253806,0.0046459814,0.0038499243,0.8657981],"study_design_scores_gemma":[0.05443402,0.059570286,0.009808496,0.014047245,0.0001407274,0.0010116694,0.01911368,0.0036455847,0.00045773017,0.83607,0.000944238,0.0007563174],"about_ca_topic_score_codex":0.00008660198,"about_ca_topic_score_gemma":0.00004062524,"teacher_disagreement_score":0.8650418,"about_ca_system_score_codex":0.00022407887,"about_ca_system_score_gemma":0.00039584714,"threshold_uncertainty_score":0.93619335},"labels":[],"label_agreement":null},{"id":"W4308393630","doi":"10.1111/stan.12283","title":"Prior effective sample size in phase II clinical trials with mixed binary and continuous responses","year":2022,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Sample size determination; Binary number; Phase (matter); Statistics; Mathematics; Binary data; Set (abstract data type); Sample (material); Coronavirus disease 2019 (COVID-19); Clinical trial; Continuous phase modulation; Computer science; Medicine; Internal medicine; Physics; Chemistry; Chromatography","score_opus":0.38248530851437895,"score_gpt":0.5807419879171977,"score_spread":0.19825667940281871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308393630","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78247625,0.00018390341,0.19718933,0.0013958294,0.001228498,0.0061603975,0.01058222,0.00026788638,0.00051567325],"genre_scores_gemma":[0.34659436,0.000037976002,0.65187484,0.00024553845,0.0001680688,0.00076162687,0.00001629831,0.00007109925,0.00023018524],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97594666,0.018941881,0.0027937533,0.0009201959,0.00077933405,0.0006181822],"domain_scores_gemma":[0.44077367,0.557544,0.0007791862,0.00049285596,0.00008053851,0.00032977076],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032018363,0.00038936362,0.0025811628,0.00019309521,0.00046640926,0.000058389367,0.00031894684,0.00016861914,0.0020098847],"category_scores_gemma":[0.6381495,0.00030441466,0.00016700737,0.0004766608,0.00066244253,0.00005325333,0.00046567252,0.0010632514,0.000006989204],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.107104346,0.0119040115,0.014181141,0.00062513223,0.001361369,0.0031272622,0.0024303014,0.0000073079555,0.0008455359,0.20918119,0.038454846,0.61077756],"study_design_scores_gemma":[0.03538241,0.02223528,0.020917138,0.00014357876,0.00067124557,0.00007170075,0.00060993875,0.0007250637,0.00007971937,0.9136038,0.004838759,0.0007214121],"about_ca_topic_score_codex":0.00006370456,"about_ca_topic_score_gemma":0.000025332489,"teacher_disagreement_score":0.7044226,"about_ca_system_score_codex":0.0001065167,"about_ca_system_score_gemma":0.00025500022,"threshold_uncertainty_score":0.9999408},"labels":[],"label_agreement":null},{"id":"W4308976590","doi":"10.1093/neuonc/noac209.303","title":"CTNI-38. UPDATE ON GBM AGILE: A GLOBAL, PHASE 2/3 ADAPTIVE PLATFORM TRIAL TO EVALUATE MULTIPLE REGIMENS IN NEWLY DIAGNOSED AND RECURRENT GLIOBLASTOMA","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Agile software development; Randomization; Biomarker; Clinical trial; Oncology; Glioblastoma; Protocol (science); Internal medicine; Computer science; Pathology; Cancer research; Alternative medicine; Biology; Software engineering","score_opus":0.3613912606678735,"score_gpt":0.5353546190290961,"score_spread":0.17396335836122256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308976590","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9770293,0.000043271066,0.003141267,0.005117933,0.0057810564,0.0060104653,0.0011221921,0.00019549599,0.001559015],"genre_scores_gemma":[0.65526384,0.00016700335,0.32766667,0.010446857,0.001453907,0.004704456,0.000021758835,0.00020902063,0.00006646272],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99220836,0.0037718767,0.0014805313,0.0010681383,0.0007385229,0.00073257444],"domain_scores_gemma":[0.9330764,0.065235905,0.0005443251,0.00062591775,0.00009990834,0.00041756273],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0043540373,0.0004105273,0.0013575461,0.0002165588,0.00020829466,0.000034428263,0.00047868618,0.00024020353,0.0006218968],"category_scores_gemma":[0.09804448,0.00036233637,0.0001646336,0.0007051951,0.00018800999,0.000068213616,0.0007528257,0.0010482981,0.00007708651],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.46607643,0.009493909,0.000078608005,0.0000623623,0.000168896,0.0026023432,0.0013566519,0.0002960309,0.0022712944,0.04264629,0.064148165,0.41079903],"study_design_scores_gemma":[0.32283664,0.12776853,0.00011767055,0.0000958827,0.00032136004,0.00013101863,0.00073989463,0.007908179,0.0012098713,0.4039788,0.13391405,0.0009781077],"about_ca_topic_score_codex":0.000024828227,"about_ca_topic_score_gemma":0.00020190647,"teacher_disagreement_score":0.4098209,"about_ca_system_score_codex":0.0008917407,"about_ca_system_score_gemma":0.00034995543,"threshold_uncertainty_score":0.9998829},"labels":[],"label_agreement":null},{"id":"W4309515696","doi":"10.1002/sim.9608","title":"Double robust estimation of optimal partially adaptive treatment strategies: An application to breast cancer treatment using hormonal therapy","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; McGill University; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Breast cancer; Covariate; Computer science; Robustness (evolution); Ordinary least squares; Confounding; Estimation; Econometrics; Statistics; Machine learning; Cancer; Medicine; Mathematics; Internal medicine","score_opus":0.49093574846171567,"score_gpt":0.5630733962666775,"score_spread":0.07213764780496185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309515696","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05428284,0.00006395499,0.9413937,0.00026069683,0.00023265333,0.0014746889,0.0021489977,0.00003094326,0.00011156199],"genre_scores_gemma":[0.2638878,0.00008577951,0.73499894,0.00004624073,0.00019166034,0.0006789896,0.000052978514,0.00003410027,0.000023525812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714124,0.0005094956,0.0010239594,0.00043894627,0.00059579336,0.00029053574],"domain_scores_gemma":[0.9944042,0.0044678976,0.00040551336,0.00039597778,0.00016045714,0.00016594787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012533945,0.00026479614,0.00077513396,0.00015250187,0.0001279392,0.000013227942,0.0001886311,0.000060538463,0.00077922887],"category_scores_gemma":[0.00057722395,0.00020809405,0.000040241932,0.00037522538,0.00018271265,0.00006483473,0.00004369058,0.00014422277,0.0000013755965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040630577,0.0017809811,0.00024481176,0.000044599903,0.00021170087,0.000028998948,0.004400384,0.5283531,0.0014419648,0.2326953,0.00016795512,0.22656713],"study_design_scores_gemma":[0.00972643,0.0097067375,0.0020828699,0.000100890924,0.00033102863,0.00001810611,0.0033816008,0.5561154,0.0005555306,0.4174855,0.00011850849,0.00037742328],"about_ca_topic_score_codex":0.00261504,"about_ca_topic_score_gemma":0.00034172006,"teacher_disagreement_score":0.22618972,"about_ca_system_score_codex":0.00091856404,"about_ca_system_score_gemma":0.00038299663,"threshold_uncertainty_score":0.8532009},"labels":[],"label_agreement":null},{"id":"W4309915763","doi":"10.1002/sim.9606","title":"Adjusting for treatment selection in phase II/III clinical trials with time to event data","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Novartis Pharma; Medical Research Council Canada","keywords":"Estimator; Statistics; Selection (genetic algorithm); Stage (stratigraphy); U-statistic; Selection bias; Mean squared error; Variance (accounting); Clinical trial; Efficiency; Mathematics; Computer science; Econometrics; Medicine; Internal medicine; Artificial intelligence","score_opus":0.7994143033413676,"score_gpt":0.7010730436421652,"score_spread":0.09834125969920249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309915763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004870047,0.00004050052,0.984468,0.0015367627,0.0006722309,0.0038790165,0.0041894712,0.000052955096,0.00029102463],"genre_scores_gemma":[0.0065692863,0.000027742499,0.98986155,0.00041781648,0.00086632505,0.0007584002,0.00026025067,0.00005903432,0.0011795816],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99000746,0.0041332887,0.003801552,0.0008694791,0.0007044677,0.0004837702],"domain_scores_gemma":[0.8385807,0.15973525,0.0007392354,0.0006085682,0.000116553274,0.00021968907],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047501598,0.00027477366,0.002209684,0.0002515072,0.00018042649,0.000010203353,0.0004653473,0.000090498084,0.0027829483],"category_scores_gemma":[0.35633132,0.000202912,0.000054481632,0.0006145911,0.00014351522,0.000034950597,0.0003247148,0.00039679176,0.000007432436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013149278,0.0064427773,0.00040859173,0.00021911928,0.00036429404,0.00020457627,0.0013435886,0.000437915,0.00028878884,0.040687636,0.16381422,0.7726392],"study_design_scores_gemma":[0.073405504,0.04793291,0.0002624679,0.0005798244,0.0012770395,0.000027203883,0.0008743675,0.113228515,0.000052076306,0.7361036,0.0255865,0.0006700129],"about_ca_topic_score_codex":0.000107045904,"about_ca_topic_score_gemma":0.00019296714,"teacher_disagreement_score":0.7719692,"about_ca_system_score_codex":0.00041115782,"about_ca_system_score_gemma":0.00026967115,"threshold_uncertainty_score":0.99812865},"labels":[],"label_agreement":null},{"id":"W4309975183","doi":"10.32942/x27g6w","title":"Describing posterior distributions of variance components: Problems and the use of null distributions to aid interpretation","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"University of Edinburgh; Natural Sciences and Engineering Research Council of Canada; Norges Forskningsråd; Fonds de recherche du Québec – Nature et technologies; Deutsche Forschungsgemeinschaft; National Science Foundation","keywords":"Variance (accounting); Posterior probability; Statistics; Markov chain Monte Carlo; Mathematics; Econometrics; Contrast (vision); Null (SQL); Null hypothesis; Bayesian probability; Computer science; Data mining; Artificial intelligence","score_opus":0.6216908457498204,"score_gpt":0.4913225778001523,"score_spread":0.13036826794966805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309975183","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029520893,0.000038131042,0.9563611,0.0013931519,0.0005520911,0.0023093882,0.009641835,0.00005083984,0.00013254964],"genre_scores_gemma":[0.26905042,0.000030190668,0.7301993,0.000077206874,0.000030115927,0.00037360174,0.00014594347,0.000024074045,0.00006915604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99515855,0.0018105614,0.0019094286,0.00047594702,0.0004181774,0.00022734012],"domain_scores_gemma":[0.95531166,0.042339824,0.00095564616,0.000892238,0.0003691207,0.00013151552],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029267224,0.000262564,0.0011154156,0.00007401516,0.00014033826,0.0000784929,0.00047477058,0.00017115535,0.00042439552],"category_scores_gemma":[0.10720878,0.00019173398,0.00025413904,0.0002564948,0.00052594853,0.00006742601,0.0020557446,0.0006216029,0.0000017487322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012379788,0.0007141198,0.0004162366,0.0013790058,0.0005606078,0.0000022855963,0.001503144,0.00068938755,0.0014305726,0.98399174,0.0010149034,0.007060031],"study_design_scores_gemma":[0.0015478435,0.0001676234,0.0010103338,0.0014414857,0.0006407794,0.0000058221412,0.00012247033,0.008622965,0.000624346,0.98493665,0.0005632005,0.00031649365],"about_ca_topic_score_codex":0.00027775668,"about_ca_topic_score_gemma":0.000018590288,"teacher_disagreement_score":0.23952954,"about_ca_system_score_codex":0.00012424368,"about_ca_system_score_gemma":0.00008694631,"threshold_uncertainty_score":0.9003116},"labels":[],"label_agreement":null},{"id":"W4310022099","doi":"10.1002/sim.9594","title":"Practical implementation of the partial ordering continual reassessment method in a Phase I combination‐schedule dose‐finding trial","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council Canada; Department of Health and Social Care; Merck KGaA; Medical Research Council; National Institute for Health and Care Research","keywords":"Computer science; Dosing; Maximum tolerated dose; Schedule; Scheduling (production processes); A priori and a posteriori; Operations research; Medical physics; Clinical trial; Risk analysis (engineering); Management science; Medicine; Mathematical optimization; Mathematics","score_opus":0.5226493986877256,"score_gpt":0.6801128053508417,"score_spread":0.1574634066631161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310022099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060858168,0.000010399538,0.93093526,0.0027153024,0.0022289276,0.0023616913,0.00047538689,0.000022013815,0.00039284307],"genre_scores_gemma":[0.3067176,0.0000051728402,0.69267106,0.00010757657,0.0001464739,0.00028619394,0.000017067254,0.00002268563,0.00002615538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99185556,0.0041313353,0.002147627,0.00036531276,0.0011549343,0.0003452045],"domain_scores_gemma":[0.9529894,0.04561841,0.0008477711,0.00035611406,0.00011490174,0.00007338851],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014838845,0.00017878032,0.0008287188,0.00018241891,0.00012435629,0.000011190436,0.0002744354,0.00006381106,0.0017777642],"category_scores_gemma":[0.08419108,0.00014218003,0.00005133248,0.00066347694,0.00020845018,0.000049438277,0.00028151774,0.0007814003,6.985808e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051807794,0.0017388735,0.0012223278,0.00014073377,0.000068397574,0.0000664651,0.0019641244,0.000028080538,0.00047931046,0.9476533,0.0037025942,0.03775505],"study_design_scores_gemma":[0.11769586,0.002377749,0.0017965706,0.00011154986,0.00020393687,0.0000111157615,0.00603362,0.0058824075,0.00058112195,0.8646617,0.0004416514,0.0002027034],"about_ca_topic_score_codex":0.00020167751,"about_ca_topic_score_gemma":0.00013730723,"teacher_disagreement_score":0.24585943,"about_ca_system_score_codex":0.00028803034,"about_ca_system_score_gemma":0.00029845024,"threshold_uncertainty_score":0.9991347},"labels":[],"label_agreement":null},{"id":"W4310370496","doi":"10.1016/j.eclinm.2022.101753","title":"Objective response rate of placebo in randomized controlled trials of anticancer medicines","year":2022,"lang":"en","type":"article","venue":"EClinicalMedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Ontario Institute for Cancer Research","keywords":"Medicine; Placebo; Internal medicine; Randomized controlled trial; Cancer; Clinical trial; Response Evaluation Criteria in Solid Tumors; Cohort; Oncology; Surgery; Phases of clinical research; Pathology; Alternative medicine","score_opus":0.46788988723664343,"score_gpt":0.6053944571943353,"score_spread":0.13750456995769184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310370496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8504397,0.0035743609,0.06339538,0.03499287,0.009509198,0.029528905,0.0007496732,0.00020177825,0.0076080994],"genre_scores_gemma":[0.8827884,0.00042487672,0.112910196,0.0012882582,0.000586999,0.0013138069,0.000004253641,0.00006211552,0.0006210731],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.79096407,0.18009704,0.025070991,0.0010303706,0.0021382999,0.00069920416],"domain_scores_gemma":[0.13030687,0.8633925,0.005128006,0.00069150474,0.00032853117,0.00015264483],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.447303,0.0003128384,0.017699344,0.0004711733,0.000050799026,0.0000031519446,0.00046011785,0.00016940673,0.004772041],"category_scores_gemma":[0.9623503,0.00019131473,0.0014649814,0.0007516392,0.0014319711,0.000028221448,0.00023722238,0.0008021855,0.0000026104906],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9734912,0.00074750604,0.00031621917,0.00014020572,0.00089788414,0.000039482005,0.00050838967,0.000023473667,0.0013474866,0.019313857,0.0022066245,0.0009676928],"study_design_scores_gemma":[0.52198625,0.0011327502,0.0005257598,0.000368302,0.0011530895,0.0000026948853,0.00043651488,0.0006048786,0.00051756453,0.47306043,0.000084385014,0.00012738944],"about_ca_topic_score_codex":0.00004476119,"about_ca_topic_score_gemma":0.000005030514,"teacher_disagreement_score":0.6832954,"about_ca_system_score_codex":0.00007729069,"about_ca_system_score_gemma":0.0004550173,"threshold_uncertainty_score":0.9968839},"labels":[],"label_agreement":null},{"id":"W4310462658","doi":"10.1002/sim.9618","title":"A nonparametric simultaneous confidence band for biomarker effect on the restricted mean survival time","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Cancer Society; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biomarker; Censoring (clinical trials); Confidence interval; Statistics; Proportional hazards model; Breast cancer; Nonparametric statistics; Survival analysis; Oncology; Smoothing; Sample size determination; Medicine; Econometrics; Mathematics; Internal medicine; Cancer; Biology","score_opus":0.2991692867616709,"score_gpt":0.5212572817545618,"score_spread":0.22208799499289084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310462658","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018372145,0.00011968297,0.95870656,0.0029144706,0.0035111024,0.0059297597,0.0041027153,0.00016955317,0.0061739995],"genre_scores_gemma":[0.4147325,0.00004041961,0.5796731,0.0015001354,0.0006174221,0.0010978075,0.000092067035,0.00016983617,0.0020767371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99319726,0.0034427026,0.0011717849,0.0005290807,0.0011815826,0.00047759854],"domain_scores_gemma":[0.578089,0.42097047,0.00026794936,0.00045996305,0.00012007306,0.000092562586],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011730382,0.00029265773,0.0010015428,0.0002760601,0.00027296945,0.000020311696,0.00058599946,0.00009331149,0.002396707],"category_scores_gemma":[0.5590194,0.00018942221,0.000068743975,0.0012000784,0.00047391633,0.000012042155,0.00012204959,0.0007146594,0.000026658305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004391609,0.00059066084,0.00020285606,0.00044801825,0.00028712148,0.0006338484,0.00065847836,0.00019538125,0.001550429,0.8196012,0.12672426,0.044716135],"study_design_scores_gemma":[0.0037462479,0.0041419007,0.00025134062,0.00013001463,0.0002107788,0.000010875125,0.0001372412,0.026325416,0.00012675408,0.9631118,0.0015437185,0.00026388955],"about_ca_topic_score_codex":0.000052570867,"about_ca_topic_score_gemma":0.00001254544,"teacher_disagreement_score":0.547289,"about_ca_system_score_codex":0.00017974817,"about_ca_system_score_gemma":0.00007984268,"threshold_uncertainty_score":0.99851525},"labels":[],"label_agreement":null},{"id":"W4310482382","doi":"10.1080/03610926.2022.2150062","title":"A fortune cookie problem: A test for nominal data whether two samples are from the same population of equally likely elements","year":2022,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Greenfield Research (Canada)","funders":"National Cancer Institute","keywords":"Test (biology); Statistics; Population; Mathematics; Econometrics; Biology; Demography; Sociology","score_opus":0.6434253497905342,"score_gpt":0.6133464733381453,"score_spread":0.030078876452388936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310482382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021756715,0.00053280615,0.9800825,0.00036426738,0.00012570398,0.0013392044,0.015239671,0.000025145191,0.00011502457],"genre_scores_gemma":[0.029995134,0.00010088314,0.9684632,0.00026261876,0.000047508278,0.0004847564,0.0005096205,0.000041401974,0.000094874784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98420745,0.013269968,0.0015690817,0.00042411577,0.00028694473,0.00024244821],"domain_scores_gemma":[0.71477413,0.28233624,0.001046837,0.0016513446,0.00013655513,0.000054896547],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033735625,0.00019513257,0.0006441177,0.0000537668,0.00038118157,0.000042587617,0.0013459902,0.0000668929,0.00026461823],"category_scores_gemma":[0.12763284,0.00016231867,0.000050694136,0.00019721611,0.00032858635,0.00008896096,0.0012907692,0.0004187259,5.1321626e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060180057,0.00033696232,0.004828953,0.00012550026,0.00008365549,4.5578372e-7,0.0010196145,0.000010756495,0.00033248225,0.848439,0.0009270777,0.14329378],"study_design_scores_gemma":[0.0015387043,0.00015037063,0.0070927725,0.00012787826,0.00022634373,0.0000015303202,0.0010833066,0.0031310676,0.000057904697,0.9846872,0.0017259617,0.00017694366],"about_ca_topic_score_codex":0.0003035562,"about_ca_topic_score_gemma":0.00024819846,"teacher_disagreement_score":0.26943332,"about_ca_system_score_codex":0.00006090482,"about_ca_system_score_gemma":0.00006786731,"threshold_uncertainty_score":0.9949725},"labels":[],"label_agreement":null},{"id":"W4310566398","doi":"10.1002/sim.9605","title":"Point estimation for adaptive trial designs I: A methodological review","year":2022,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research; Medical Research Council Canada; Department of Health and Social Care; Cancer Research UK; Health and Care Research Wales","keywords":"Estimator; Computer science; Estimation; Type I and type II errors; Point estimation; Point (geometry); Contrast (vision); Set (abstract data type); Econometrics; Statistics; Artificial intelligence; Mathematics","score_opus":0.9563494966257471,"score_gpt":0.7322871607745378,"score_spread":0.22406233585120927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310566398","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0958632e-9,0.48299348,0.5069911,0.000099774115,0.0012302574,0.007038091,0.0012783484,0.000043404325,0.0003255577],"genre_scores_gemma":[1.5075861e-9,0.4989441,0.4967474,0.00023479915,0.00046098902,0.003247237,0.00017936868,0.00007606356,0.0001100399],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97788954,0.013765913,0.005443167,0.001123923,0.0011301286,0.00064734236],"domain_scores_gemma":[0.5717872,0.42524847,0.0018967566,0.00073647196,0.00014252464,0.00018859073],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04316554,0.00081176154,0.009406961,0.00033608204,0.00013118256,0.000014350118,0.00079817243,0.00050462235,0.0052671293],"category_scores_gemma":[0.75426865,0.00056774676,0.00054484955,0.000814416,0.00048389158,0.000032567008,0.00024580187,0.0017048809,0.000018694029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012181841,0.000131013,4.397882e-9,0.051359635,0.00012385815,0.000049852777,0.000019826084,2.7359877e-7,6.346444e-9,0.2590469,0.042817567,0.64523286],"study_design_scores_gemma":[0.0068177297,0.0023312839,2.1030896e-8,0.03373432,0.0032682014,0.00001667119,0.000014563743,0.00016939583,1.8429853e-8,0.57573503,0.3775855,0.00032727738],"about_ca_topic_score_codex":0.000010210643,"about_ca_topic_score_gemma":0.000003994642,"teacher_disagreement_score":0.7111031,"about_ca_system_score_codex":0.0005504522,"about_ca_system_score_gemma":0.0005204607,"threshold_uncertainty_score":0.9996774},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4310723854","doi":"10.31234/osf.io/u5p84","title":"A Computational Model to Characterize the Time-Course of Response to Rapid Antidepressant Therapies","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Dalhousie University","funders":"Research Nova Scotia; Dalhousie University; Dalhousie Medical Research Foundation","keywords":"Magnitude (astronomy); Antidepressant; Computer science; Noise (video); Computational model; Linear model; Statistics; Mathematics; Algorithm; Artificial intelligence; Machine learning; Medicine; Physics; Internal medicine","score_opus":0.46749694397977726,"score_gpt":0.534374369352142,"score_spread":0.06687742537236474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310723854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17195119,0.000043478387,0.80204433,0.016662069,0.000719753,0.0032804913,0.003811867,0.000184848,0.0013019922],"genre_scores_gemma":[0.028465547,0.000012073321,0.96664184,0.0024158277,0.00011254744,0.00048757158,0.000016347483,0.00008038856,0.0017678314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99325174,0.0033046235,0.0015201332,0.0006984929,0.00090370636,0.00032130524],"domain_scores_gemma":[0.9117806,0.085844494,0.00051235716,0.0013122099,0.0003675815,0.00018273115],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010794462,0.000385496,0.0012742666,0.00014318121,0.000119946184,0.000068699344,0.0012283258,0.00020179004,0.0048778877],"category_scores_gemma":[0.05306309,0.0002552286,0.0003310549,0.00028126463,0.00015630708,0.000022592003,0.002474586,0.00073901814,0.00005746953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.046123326,0.005878259,0.00023701119,0.0017794307,0.0053180386,0.00007633175,0.031109085,0.27617195,0.031118495,0.30941314,0.20541401,0.08736093],"study_design_scores_gemma":[0.00048030887,0.0002718199,0.002080062,0.00014259324,0.00013329583,0.0000021617275,0.00015241397,0.060890466,0.00038827502,0.9345362,0.0005448909,0.0003774972],"about_ca_topic_score_codex":0.000011630301,"about_ca_topic_score_gemma":6.4007895e-7,"teacher_disagreement_score":0.6251231,"about_ca_system_score_codex":0.00006294694,"about_ca_system_score_gemma":0.00041760434,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W4311683938","doi":"10.21203/rs.3.rs-2163946/v1","title":"A scoping review on two-stage randomized preference trial in mental health","year":2022,"lang":"en","type":"review","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Randomized controlled trial; Blinding; Mental health; Preference; Medicine; Psychological intervention; Generalizability theory; Population; Clinical psychology; Physical therapy; Psychology; Psychiatry; Surgery; Environmental health","score_opus":0.9358554349528032,"score_gpt":0.7671878181029377,"score_spread":0.16866761684986553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311683938","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5353838e-7,0.94047177,0.00022626047,0.00030492668,0.0006086122,0.055096097,0.0005756649,0.00007017766,0.0026463273],"genre_scores_gemma":[4.1688835e-8,0.9576218,0.02766815,0.00013769076,0.00036567333,0.013398987,0.00008203343,0.00012773227,0.00059790356],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.8880348,0.10012012,0.005393378,0.0014356178,0.0036385395,0.0013775275],"domain_scores_gemma":[0.6836575,0.31335828,0.0011778583,0.0013386373,0.00010431898,0.00036339287],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.124894604,0.00061903923,0.0113152,0.0006891364,0.0003206748,0.00009910787,0.0012299218,0.0002797933,0.0077848895],"category_scores_gemma":[0.46966818,0.00044501634,0.0014805138,0.001725192,0.00036017015,0.000050008926,0.00092613,0.0043137707,0.00016710901],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03001017,0.00036546166,1.43263925e-8,0.44643638,0.00007118353,0.000026932355,0.000038708065,3.8217227e-8,1.5836746e-9,0.019817978,0.0018402224,0.5013929],"study_design_scores_gemma":[0.15883707,0.0006779745,3.8191965e-9,0.5930773,0.00008624453,0.0000022029083,0.000014576261,0.0000036898673,3.2691787e-8,0.03092484,0.21611296,0.00026310477],"about_ca_topic_score_codex":0.000070007016,"about_ca_topic_score_gemma":0.000034682907,"teacher_disagreement_score":0.5011298,"about_ca_system_score_codex":0.0014044225,"about_ca_system_score_gemma":0.0034429133,"threshold_uncertainty_score":0.99980015},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4311934119","doi":"10.1002/psp4.12907","title":"Regulatory utility of physiologically‐based pharmacokinetic modeling to support alternative bioequivalence approaches and risk assessment: A workshop summary report","year":2022,"lang":"en","type":"review","venue":"CPT Pharmacometrics & Systems Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"","keywords":"Physiologically based pharmacokinetic modelling; Bioequivalence; Session (web analytics); Regulatory science; Computer science; Food and drug administration; Management science; Pharmaceutical industry; Risk analysis (engineering); Medicine; Pharmacology; Pharmacokinetics; Engineering","score_opus":0.801231966031526,"score_gpt":0.6141261854069908,"score_spread":0.1871057806245352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311934119","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084725575,0.83454734,0.13790391,0.000041817246,0.010971412,0.010760536,0.0033112175,0.00037721588,0.0012392842],"genre_scores_gemma":[0.003156987,0.9237322,0.06801426,0.00014105054,0.001137332,0.0032057327,0.00012947634,0.000278909,0.00020404717],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9725128,0.01443871,0.0068507716,0.002908924,0.0019164945,0.0013722959],"domain_scores_gemma":[0.904436,0.087071,0.0056279874,0.0013764214,0.00050197204,0.000986629],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.022885162,0.0016193176,0.008375788,0.0025805961,0.00037479808,0.000099382916,0.0023746635,0.0008028851,0.0023941435],"category_scores_gemma":[0.025670607,0.0014188989,0.001318559,0.005094449,0.0006768975,0.00017592455,0.0021327517,0.0036037539,0.000014939046],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053661107,0.0030114632,0.000130781,0.07959385,0.0056610005,0.0012757588,0.00011440861,0.0021699308,0.000114175564,0.0009287789,0.014869336,0.89159393],"study_design_scores_gemma":[0.007173502,0.001531231,0.000014848017,0.0049744067,0.03469258,0.0005338221,0.00015949816,0.24597238,0.00014148344,0.011340761,0.6893357,0.004129807],"about_ca_topic_score_codex":0.0000368313,"about_ca_topic_score_gemma":2.348086e-7,"teacher_disagreement_score":0.8874641,"about_ca_system_score_codex":0.00067448686,"about_ca_system_score_gemma":0.0010789294,"threshold_uncertainty_score":0.9996554},"labels":[],"label_agreement":null},{"id":"W4312086030","doi":"10.1002/alz.069243","title":"Biological variation of Alzheimer’s disease plasma biomarkers in healthy individuals","year":2022,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Biomarker; Medicine; Coefficient of variation; Neurodegeneration; Disease; Oncology; Internal medicine; Alzheimer's disease; Pathology; Biology; Statistics; Genetics","score_opus":0.40672154942758415,"score_gpt":0.48476781906323846,"score_spread":0.07804626963565431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312086030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8130943,0.09884111,0.041444764,0.011569736,0.010779129,0.013375434,0.0052364264,0.0009055673,0.0047534932],"genre_scores_gemma":[0.7450202,0.000036611775,0.25425488,0.00033673283,0.000058516434,0.00024094676,0.000024048306,0.00002747106,5.868377e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944382,0.002403853,0.0015448332,0.0005427961,0.00063464866,0.0004356741],"domain_scores_gemma":[0.9882627,0.010314755,0.0006377952,0.0005094926,0.000056725625,0.00021849817],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051449314,0.00023062911,0.00063971017,0.0002114815,0.00014868694,0.000017229813,0.00043451102,0.00010549689,0.002418466],"category_scores_gemma":[0.008121381,0.00021908201,0.00017925931,0.0005371227,0.00016085773,0.00006965869,0.0004773216,0.00031983567,0.000020523861],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006431247,0.008837528,0.13242769,0.00012391467,0.0723713,0.00017168684,0.0017415652,0.00019194525,0.0012798643,0.56326264,0.017386504,0.19577414],"study_design_scores_gemma":[0.0034515208,0.00089916773,0.11116914,0.000027641767,0.012521993,0.0000033368342,0.00014714424,0.0007645169,0.0006406816,0.86796504,0.0018816112,0.00052818074],"about_ca_topic_score_codex":0.000056080535,"about_ca_topic_score_gemma":0.000004091196,"teacher_disagreement_score":0.30470246,"about_ca_system_score_codex":0.000016593805,"about_ca_system_score_gemma":0.00013832383,"threshold_uncertainty_score":0.99849343},"labels":[],"label_agreement":null},{"id":"W4312118888","doi":"10.1002/sim.9632","title":"Power analyses for stepped wedge designs with multivariate continuous outcomes","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging","keywords":"Multivariate statistics; Univariate; Statistics; Multivariate analysis; Estimator; Sample size determination; Multivariate normal distribution; Computer science; Linear model; Econometrics; Mathematics","score_opus":0.6093308194721376,"score_gpt":0.6148700768653204,"score_spread":0.005539257393182728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312118888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018423229,0.000040560113,0.9917019,0.00072034635,0.0008802857,0.0016538429,0.0016867286,0.00007133446,0.0014027001],"genre_scores_gemma":[0.059853703,0.000005403467,0.9375214,0.0005865249,0.00010557887,0.00048187698,0.00003040109,0.00007130974,0.001343794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99588156,0.0011006737,0.001278966,0.00048709018,0.0007701073,0.0004815875],"domain_scores_gemma":[0.9012395,0.09749831,0.00044109364,0.00047002634,0.00020590649,0.0001451221],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047632405,0.0002987371,0.0014187661,0.00021292732,0.00018588228,0.000014376648,0.00037046484,0.000070345435,0.0022982806],"category_scores_gemma":[0.11262077,0.0002091385,0.00006414561,0.00040247195,0.00036315052,0.000026325342,0.00013066636,0.0004869053,0.000004909634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024630378,0.001011924,0.0073954635,0.00035047712,0.0006958051,0.00042086776,0.002336048,0.00011453378,0.0007626586,0.9140432,0.06377,0.006636009],"study_design_scores_gemma":[0.009952517,0.0021672715,0.0040215,0.00008936273,0.00038565724,0.000009001601,0.0015108917,0.0013740329,0.000057318197,0.9784821,0.001604317,0.00034601917],"about_ca_topic_score_codex":0.00008324609,"about_ca_topic_score_gemma":0.000035722944,"teacher_disagreement_score":0.107857525,"about_ca_system_score_codex":0.00013570636,"about_ca_system_score_gemma":0.000101848,"threshold_uncertainty_score":0.9986138},"labels":[],"label_agreement":null},{"id":"W4312418468","doi":"10.1007/978-3-031-08329-7_15","title":"A Selective Overview of Statistical Methods for Identification of the Treatment-Sensitive Subsets of Patients","year":2012,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Categorical variable; Covariate; Identification (biology); Clinical trial; Outcome (game theory); Medicine; Computer science; Data science; Machine learning; Internal medicine; Mathematics; Biology","score_opus":0.3969927116591078,"score_gpt":0.5521006210478049,"score_spread":0.15510790938869706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312418468","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000059301412,0.00081663625,0.9177332,0.000016417638,0.0010599338,0.0037922643,0.07000657,0.000018846647,0.0064968634],"genre_scores_gemma":[0.00070690387,0.0022597532,0.98689884,0.000022633532,0.00008450197,0.000114138486,0.00017906819,0.00013879198,0.009595391],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940963,0.001039863,0.0034490724,0.00048546467,0.0005665617,0.00036278187],"domain_scores_gemma":[0.9304455,0.06380187,0.0034220985,0.00084202376,0.001394679,0.00009383835],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002353939,0.00053325505,0.0023221564,0.00015520405,0.00005476062,0.00000971579,0.000364346,0.0005286745,0.00023611856],"category_scores_gemma":[0.038876977,0.00042338992,0.00032354917,0.000113551796,0.001311996,0.00010046546,0.00013586781,0.00034230968,0.00000243768],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006220724,0.00047336158,0.00011058132,0.0020782952,0.0004371166,9.655714e-7,0.0006979337,0.0000013939359,0.00008816989,0.9476649,0.00066583074,0.04715934],"study_design_scores_gemma":[0.0012186901,0.00084464456,0.0013880903,0.0005459145,0.0012481749,9.797418e-7,0.000032054744,0.00008603255,0.0077008735,0.9804601,0.0061317463,0.00034266355],"about_ca_topic_score_codex":0.000019317917,"about_ca_topic_score_gemma":0.000044707427,"teacher_disagreement_score":0.069827504,"about_ca_system_score_codex":0.0002880914,"about_ca_system_score_gemma":0.00026706158,"threshold_uncertainty_score":0.9998218},"labels":[],"label_agreement":null},{"id":"W4316495941","doi":"10.1016/j.cct.2023.107085","title":"A rank-based approach to design and analysis of pretest-posttest randomized trials, with application to COVID-19 ordinal scale data","year":2023,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Chongqing Municipal Education Commission","keywords":"Categorical variable; Covariate; Ordinal data; Randomized controlled trial; Medicine; Ordinal Scale; Analysis of covariance; Sample size determination; Research design; Statistics; Sample (material); Scale (ratio); Mathematics","score_opus":0.9017466379471525,"score_gpt":0.6591598961225824,"score_spread":0.24258674182457007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316495941","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022929476,0.00009670128,0.97354245,0.0044051236,0.00027582725,0.016565932,0.0021909273,0.0003244303,0.00030567555],"genre_scores_gemma":[0.09306343,0.00005230604,0.90166783,0.002381252,0.00045090367,0.0018169978,0.0003842995,0.00008830238,0.00009466872],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8969936,0.08433956,0.014127978,0.0025674147,0.0013525091,0.0006189488],"domain_scores_gemma":[0.17483725,0.81586987,0.004010034,0.003212516,0.00047277592,0.0015975438],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3881864,0.0005685201,0.013689977,0.0009077838,0.00014212151,0.00013300288,0.0014339199,0.00052552123,0.000082626735],"category_scores_gemma":[0.91317207,0.00038280303,0.0012871595,0.0043034144,0.0007510527,0.00014797528,0.00055569794,0.00045209573,0.000034983987],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.83367646,0.0029246632,0.00539084,0.0010928346,0.014855926,0.000034160632,0.000372576,0.0038160768,0.0004758096,0.012626991,0.0910137,0.033719976],"study_design_scores_gemma":[0.42207026,0.0030890573,0.0010454053,0.00046617378,0.031818174,0.000003339032,0.00021196686,0.22075072,0.00040367714,0.3139081,0.0044822805,0.001750828],"about_ca_topic_score_codex":0.00007602082,"about_ca_topic_score_gemma":0.000006192581,"teacher_disagreement_score":0.7315303,"about_ca_system_score_codex":0.00004774963,"about_ca_system_score_gemma":0.0011569895,"threshold_uncertainty_score":0.9998624},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"randomized_trial","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4316814331","doi":"10.1186/s13063-023-07092-8","title":"Minimum important difference is minimally important in sample size calculations","year":2023,"lang":"en","type":"letter","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sample size determination; Null hypothesis; Sample (material); Set (abstract data type); Value (mathematics); Statistics; Statistical power; Power (physics); Econometrics; Computer science; Mathematics; Physics","score_opus":0.6995163840529842,"score_gpt":0.580853928960117,"score_spread":0.11866245509286721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316814331","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073043765,0.00054912997,0.013729597,0.90487677,0.01540075,0.016375754,0.038595166,0.0016068337,0.001561596],"genre_scores_gemma":[0.000076640164,0.00043285455,0.7566757,0.22346932,0.010777644,0.0010682263,0.00016275649,0.0004826948,0.0068541705],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9791876,0.005425518,0.010970945,0.0015923923,0.0015530002,0.0012705231],"domain_scores_gemma":[0.40972662,0.58433753,0.0037476406,0.0017522251,0.0002159472,0.00022003594],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.023897203,0.0009574545,0.0058714785,0.00037517614,0.00010758757,0.00016672652,0.001053533,0.0023963484,0.004272935],"category_scores_gemma":[0.77234393,0.0007808084,0.0012100495,0.00082589814,0.0002758769,0.00004904869,0.00032539145,0.0026224481,0.00022135778],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018449563,0.00014256297,0.0007403659,0.0005112452,0.00035422642,0.0008323956,0.00018124352,1.5244545e-7,0.00018886063,0.0029512614,0.99308467,0.00082854857],"study_design_scores_gemma":[0.002191868,0.00016227305,0.0010829526,0.0005489597,0.0006968111,0.0000059583335,0.00002245793,0.00010079898,0.00013385956,0.9412305,0.05293799,0.0008855981],"about_ca_topic_score_codex":0.000332705,"about_ca_topic_score_gemma":0.00012696053,"teacher_disagreement_score":0.9401466,"about_ca_system_score_codex":0.00021304116,"about_ca_system_score_gemma":0.00056157645,"threshold_uncertainty_score":0.99967855},"labels":[],"label_agreement":null},{"id":"W4317597455","doi":"10.1016/j.adro.2023.101178","title":"Ensuring Superior Reporting of Radiation Therapy Noninferiority Trials: A Systematic Review","year":2023,"lang":"en","type":"review","venue":"Advances in Radiation Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Princess Margaret Cancer Centre; Sunnybrook Health Science Centre; Cancer Care Ontario","funders":"Ontario Institute for Cancer Research; AstraZeneca","keywords":"Medicine; Interquartile range; Sample size determination; Clinical endpoint; Randomized controlled trial; Radiation therapy; Clinical trial; Confidence interval; Margin (machine learning); Meta-analysis; Medical physics; Surgery; Internal medicine; Statistics","score_opus":0.7632949404090885,"score_gpt":0.6951879868199576,"score_spread":0.06810695358913088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317597455","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018571886,0.98658323,0.0025421025,0.00004170399,0.0020013463,0.008277041,0.00010234505,0.00012943929,0.00032094514],"genre_scores_gemma":[0.0000011408882,0.95428497,0.04273333,0.000064871914,0.0004352583,0.0023030252,0.000029629377,0.00010687331,0.000040907347],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9581073,0.017673537,0.022372387,0.0007886376,0.0005960521,0.0004620674],"domain_scores_gemma":[0.6825544,0.27969813,0.03629354,0.0011095841,0.0002150206,0.00012930414],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06763957,0.0005751979,0.01925025,0.00047694787,0.00006179391,0.000020942161,0.0005247299,0.0007979621,0.00010801562],"category_scores_gemma":[0.7365258,0.00043696832,0.0012943662,0.0012916757,0.00014280535,0.00020662692,0.00009569984,0.0007961439,0.000035390996],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009776284,0.00006546015,0.0000044450558,0.47376737,0.00014013474,0.000020317093,0.00003632689,0.0000013950593,9.7542845e-8,0.0019966452,0.000031092794,0.5239269],"study_design_scores_gemma":[0.0012844102,0.00036374983,0.0000052968157,0.6841756,0.0035418512,0.0000526353,0.000028226745,0.000038186117,0.0000046576592,0.07943516,0.23044746,0.00062277226],"about_ca_topic_score_codex":0.0000090256235,"about_ca_topic_score_gemma":0.000012587749,"teacher_disagreement_score":0.6688862,"about_ca_system_score_codex":0.0007639435,"about_ca_system_score_gemma":0.0008626693,"threshold_uncertainty_score":0.9998082},"labels":[],"label_agreement":null},{"id":"W4318455086","doi":"10.1002/psp4.12931","title":"Establishing the suitability of <scp>model‐integrated</scp> evidence to demonstrate bioequivalence for <scp>long‐acting</scp> injectable and implantable drug products: Summary of workshop","year":2023,"lang":"en","type":"review","venue":"CPT Pharmacometrics & Systems Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"U.S. Food and Drug Administration; Teva Pharmaceutical Industries","keywords":"Bioequivalence; Food and drug administration; Computer science; Management science; Medicine; Risk analysis (engineering); Engineering; Pharmacology; Pharmacokinetics","score_opus":0.6228652721554956,"score_gpt":0.5726171040619016,"score_spread":0.050248168093594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318455086","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026109917,0.92714804,0.0396609,0.00007524246,0.009521468,0.015784452,0.004603561,0.00034524171,0.00025010778],"genre_scores_gemma":[0.00060273,0.9396607,0.052898932,0.00009749751,0.001245434,0.0028114924,0.000042698466,0.00037827075,0.0022622326],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798191,0.0072261756,0.0070093684,0.0023987328,0.0014279324,0.0021186613],"domain_scores_gemma":[0.5155687,0.47573516,0.0048035933,0.0012681505,0.0019799292,0.00064452336],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.043119684,0.0014884347,0.007995106,0.002278781,0.0004124926,0.00030590748,0.003399685,0.0009513044,0.000014050982],"category_scores_gemma":[0.40691793,0.0011082871,0.0009032288,0.011981218,0.00087438704,0.0005928091,0.0016143163,0.0025546928,0.000018263901],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014906372,0.0012711072,0.00038920162,0.45252624,0.0044491333,0.00006543638,0.0013336429,0.00046897528,0.00208589,0.0020391133,0.35492522,0.18029697],"study_design_scores_gemma":[0.0067603644,0.0015863958,0.000013754291,0.10259247,0.04862647,0.00050517777,0.004589998,0.014092607,0.018703924,0.029249286,0.77116525,0.0021143048],"about_ca_topic_score_codex":0.00018077022,"about_ca_topic_score_gemma":0.000007932867,"teacher_disagreement_score":0.46850896,"about_ca_system_score_codex":0.00059567305,"about_ca_system_score_gemma":0.0019055508,"threshold_uncertainty_score":0.9997865},"labels":[],"label_agreement":null},{"id":"W4318823732","doi":"10.3329/jsr.v56i1.63944","title":"Three influential design quantities on the power of Wald-type tests for treatment comparisons in clinical trials","year":2023,"lang":"en","type":"article","venue":"Journal of Statistical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Type I and type II errors; Wald test; Statistical power; Randomization; Econometrics; Statistics; Inference; Statistical inference; Clinical trial; Statistical hypothesis testing; Mathematics; Power (physics); Computer science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.9681519983893333,"score_gpt":0.7682835522666835,"score_spread":0.19986844612264976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318823732","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095825076,0.00008174854,0.89509773,0.003858771,0.0013804894,0.002911306,0.00053421693,0.000025098961,0.0002855853],"genre_scores_gemma":[0.3213769,0.0002835792,0.677518,0.000058167072,0.0005261599,0.000075544755,0.0000020051164,0.000054424156,0.00010523202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97898084,0.0129798995,0.005117385,0.00032296425,0.0018920733,0.000706862],"domain_scores_gemma":[0.29924506,0.698025,0.00086471025,0.00042785337,0.0011768248,0.00026056875],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12867819,0.00020610963,0.0020892592,0.00045513661,0.00012835779,0.00007585147,0.0005905592,0.00024083703,0.0004888694],"category_scores_gemma":[0.7905198,0.000112995105,0.00041841812,0.0006894247,0.00090890616,0.000048678743,0.000118108605,0.00090628094,0.000057672813],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017214173,0.002296749,0.00202284,0.00016648043,0.0006169872,0.00018152475,0.00026176588,0.00006842611,0.0003779884,0.77463883,0.17942989,0.022724332],"study_design_scores_gemma":[0.0033587418,0.0086365305,0.014803234,0.0002906308,0.00013046691,0.000003934436,0.00029062247,0.0024389299,0.0005387626,0.9686535,0.0007394906,0.000115165036],"about_ca_topic_score_codex":0.000018957357,"about_ca_topic_score_gemma":0.000031109255,"teacher_disagreement_score":0.68504506,"about_ca_system_score_codex":0.00014812911,"about_ca_system_score_gemma":0.00071515376,"threshold_uncertainty_score":0.89720917},"labels":[],"label_agreement":null},{"id":"W4318917969","doi":"10.1177/09622802231151210","title":"Revisiting sample size planning for receiver operating characteristic studies: A confidence interval approach with precision and assurance","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Sample size determination; Calculator; Variance (accounting); Computer science; Confidence interval; Coverage probability; Sample (material); Statistics; Range (aeronautics); Estimator; Central limit theorem; Function (biology); Limit (mathematics); Receiver operating characteristic; Mathematics","score_opus":0.7934405002011646,"score_gpt":0.7264650259137247,"score_spread":0.06697547428743988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318917969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050296015,0.00018073987,0.99103296,0.0010431103,0.00025251173,0.0016579923,0.00022493994,0.000115783056,0.00046236377],"genre_scores_gemma":[0.008024334,0.00034607697,0.98996633,0.00014779238,0.00044019023,0.0008819553,0.000007666762,0.00007840393,0.00010723955],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9791504,0.013431642,0.0020027538,0.001405719,0.00256931,0.0014401713],"domain_scores_gemma":[0.14649652,0.8513118,0.00022394679,0.00052847795,0.0007926174,0.0006466584],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10077014,0.00034975173,0.0016382152,0.00027234136,0.00039107792,0.0001631809,0.0006334004,0.00035081466,0.0003571777],"category_scores_gemma":[0.96032304,0.00025487348,0.00006930045,0.0013607104,0.001738659,0.00011308977,0.0006804861,0.0020510866,0.000009054152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012605848,0.00017053081,0.0012940349,0.004717961,0.00018423024,0.00035958068,0.0021656377,0.000008107262,0.0003137811,0.18406464,0.0018114981,0.8036494],"study_design_scores_gemma":[0.0018089102,0.0006638144,0.00471697,0.0043142685,0.00004726375,0.000025489962,0.0024842024,0.06323023,0.00007596901,0.92196935,0.000311319,0.00035223545],"about_ca_topic_score_codex":0.00002780053,"about_ca_topic_score_gemma":0.0000039292945,"teacher_disagreement_score":0.85955286,"about_ca_system_score_codex":0.00015417478,"about_ca_system_score_gemma":0.00034004386,"threshold_uncertainty_score":0.99999034},"labels":[],"label_agreement":null},{"id":"W4319063464","doi":"10.1002/sim.9677","title":"Conditional concordance‐assisted learning under matched case‐control design for combining biomarkers for population screening","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"University of Texas Health Science Center at Houston; National Center for Advancing Translational Sciences; University of Texas at Austin; National Institute of Diabetes and Digestive and Kidney Diseases; Center for Clinical and Translational Sciences, University of Texas Health Science Center at Houston; National Cancer Institute; National Institutes of Health; Cancer Prevention and Research Institute of Texas","keywords":"Concordance; Confounding; Logistic regression; Biomarker; Population; Discriminative model; Prostate cancer; Computer science; Medicine; Case-control study; Oncology; Machine learning; Statistics; Cancer; Internal medicine; Mathematics; Environmental health; Biology","score_opus":0.530148671326099,"score_gpt":0.5642905653385226,"score_spread":0.034141894012423624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319063464","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012358204,0.00001980863,0.99373114,0.00066260336,0.0007231455,0.0020328138,0.0013608629,0.00018092165,0.000052906693],"genre_scores_gemma":[0.19742548,0.000005745872,0.801045,0.00021342708,0.00030961793,0.00044582796,0.000364388,0.00006996942,0.00012052801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961304,0.000980591,0.0014631383,0.00046512554,0.00043848858,0.00052227266],"domain_scores_gemma":[0.8091722,0.18981977,0.00045467663,0.00017715772,0.00025423235,0.000121960315],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009850793,0.00026359007,0.0010003584,0.0002798527,0.00027100526,0.0000257717,0.00014558145,0.00018613873,0.00018623326],"category_scores_gemma":[0.17255142,0.00024434144,0.000077956596,0.00046111303,0.00027812447,0.000050452545,0.00003026897,0.00031023138,0.0000046987507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021600567,0.0001248682,0.0020609358,0.0010447705,0.0006773513,0.00046708094,0.00039887158,0.0061572436,0.0005857436,0.8945986,0.028308569,0.06341589],"study_design_scores_gemma":[0.008610307,0.0005134684,0.00443037,0.00028909682,0.0002708624,0.000039329236,0.000917208,0.21529908,0.000012640051,0.7693537,0.000048284033,0.00021569253],"about_ca_topic_score_codex":0.00006917219,"about_ca_topic_score_gemma":0.000044019453,"teacher_disagreement_score":0.20914184,"about_ca_system_score_codex":0.000102430386,"about_ca_system_score_gemma":0.00006059226,"threshold_uncertainty_score":0.9963955},"labels":[],"label_agreement":null},{"id":"W4319295079","doi":"10.1186/s12874-023-01857-0","title":"The empirical estimate of the survival and variance using a weighted composite endpoint","year":2023,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; Alberta Health; University of Alberta; Alberta Health Services","funders":"","keywords":"Confidence interval; Statistics; Variance (accounting); Estimator; Sample size determination; Medicine; Event (particle physics); Clinical endpoint; Survival analysis; Point estimation; Treatment effect; Delta method; Proportional hazards model; Clinical trial; Mathematics; Econometrics; Internal medicine","score_opus":0.9708732306564802,"score_gpt":0.7604618313884888,"score_spread":0.21041139926799146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319295079","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16823545,0.00015366173,0.82220864,0.0066461167,0.0013226193,0.0007428986,0.000034244007,0.00008243121,0.00057394843],"genre_scores_gemma":[0.0068236035,0.00023112915,0.9922109,0.00009487886,0.0003259696,0.000051298965,6.518591e-7,0.00003684752,0.0002246748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9039505,0.09013951,0.0014327919,0.00059224904,0.0028267356,0.0010581759],"domain_scores_gemma":[0.32571745,0.672659,0.0002052191,0.0007393601,0.0003174675,0.0003614952],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16124527,0.0001763382,0.00093803176,0.00012338332,0.00051599863,0.00003772916,0.0011355747,0.00044820568,0.00023160534],"category_scores_gemma":[0.83763784,0.000088812114,0.00016863825,0.0012975839,0.004029886,0.000024031679,0.0017054159,0.0016379332,0.000020584344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016215269,0.00023689169,0.012352036,0.00089113583,0.0002609105,0.00011043684,0.0006798725,0.000008954174,0.0038554464,0.9103391,0.00456429,0.06507937],"study_design_scores_gemma":[0.00074431166,0.000107878055,0.012482116,0.00015823291,0.00004049398,0.000025114876,0.00026296437,0.0301245,0.0007322822,0.95451665,0.00070844655,0.00009698262],"about_ca_topic_score_codex":0.000073152834,"about_ca_topic_score_gemma":0.000080621256,"teacher_disagreement_score":0.67639256,"about_ca_system_score_codex":0.000051461593,"about_ca_system_score_gemma":0.00082622626,"threshold_uncertainty_score":0.9986806},"labels":[],"label_agreement":null},{"id":"W4319657136","doi":"10.1002/pst.2292","title":"Bayesian single‐to‐double arm transition design using both short‐term and long‐term endpoints","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Clinical endpoint; Frequentist inference; Sample size determination; Bayesian probability; Computer science; Statistics; Randomized controlled trial; Bayesian inference; Medicine; Mathematics; Internal medicine","score_opus":0.7559694574546456,"score_gpt":0.6006447139559284,"score_spread":0.15532474349871717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319657136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017564705,0.000027510634,0.9788319,0.0002973548,0.00066438894,0.0012689073,0.0007541717,0.00034818953,0.00024289849],"genre_scores_gemma":[0.18093574,0.00007909397,0.8178675,0.00050686195,0.00035553353,0.000050891515,0.000021268948,0.00011952224,0.00006354108],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99540246,0.0008772906,0.0012115489,0.00077684666,0.0007620723,0.00096975703],"domain_scores_gemma":[0.9748948,0.023481311,0.00013012024,0.00040114156,0.00013992088,0.00095270335],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002895735,0.0004520865,0.0008463656,0.00019757172,0.00024455186,0.00018763891,0.00028878276,0.00022921959,0.0007105401],"category_scores_gemma":[0.009231768,0.00044252173,0.00010088567,0.00059330446,0.00034861223,0.00011525302,0.00017771132,0.00053362176,0.00010657077],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0075706067,0.0050592166,0.0038413787,0.0051770573,0.001381293,0.0040457807,0.004151059,0.0009931362,0.082844146,0.2672783,0.013837809,0.6038202],"study_design_scores_gemma":[0.004815439,0.0009201237,0.0032354568,0.00045292597,0.00140921,0.00011117668,0.00006446616,0.12437548,0.023483839,0.8394352,0.00023941239,0.001457244],"about_ca_topic_score_codex":0.000003847049,"about_ca_topic_score_gemma":0.000003262448,"teacher_disagreement_score":0.60236293,"about_ca_system_score_codex":0.0001629612,"about_ca_system_score_gemma":0.00006988644,"threshold_uncertainty_score":0.99980265},"labels":[],"label_agreement":null},{"id":"W4319841983","doi":"10.1080/19466315.2023.2166099","title":"Designing Dose-Optimization Studies in Cancer Drug Development: Discussions with Regulators","year":2023,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Drug development; Center of excellence; Biopharmaceutical; Medicine; Excellence; Cancer drugs; Drug; Regulatory science; Oncology; Food and drug administration; Pharmacology; Medical education; Medical physics; Political science; Biotechnology; Pathology","score_opus":0.8741899254027933,"score_gpt":0.7166264774546857,"score_spread":0.15756344794810762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319841983","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11773066,0.0009972852,0.85868907,0.006190034,0.0020531511,0.01025392,0.001002874,0.0008449619,0.0022380676],"genre_scores_gemma":[0.052609663,0.0010300664,0.9442911,0.00004672538,0.00010898944,0.0009384749,0.0000109558505,0.00008188319,0.0008821491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99266577,0.0026316429,0.0012050625,0.00071547274,0.0015674673,0.0012145708],"domain_scores_gemma":[0.92189074,0.07689165,0.00010958961,0.00033522694,0.00046125468,0.00031151966],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0136683695,0.00027610164,0.000674433,0.0008446651,0.00027371448,0.00006625569,0.00040935865,0.00015353983,0.0003250396],"category_scores_gemma":[0.0843822,0.00019948673,0.000030292302,0.0035117117,0.0011335615,0.00008778101,0.0004360219,0.0013374089,0.000070409864],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041022915,0.0024632968,0.032122504,0.0055582817,0.0007321305,0.0035181723,0.017173585,0.020202909,0.001823782,0.70489514,0.03926143,0.16814646],"study_design_scores_gemma":[0.0041679167,0.0001573627,0.005422183,0.0023449215,0.00005262055,0.0000036039175,0.0034525157,0.05080544,0.0044624764,0.9276637,0.0007478481,0.0007194352],"about_ca_topic_score_codex":0.000026852904,"about_ca_topic_score_gemma":0.0001794275,"teacher_disagreement_score":0.22276853,"about_ca_system_score_codex":0.000569842,"about_ca_system_score_gemma":0.0004257003,"threshold_uncertainty_score":0.9233304},"labels":[],"label_agreement":null},{"id":"W4320035412","doi":"10.1002/cjs.11760","title":"Tests of linear hypotheses using indirect information","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test statistic; Statistics; Statistic; Mathematics; Null distribution; Sample size determination; Statistical hypothesis testing; F-test; Z-test; Null hypothesis; Asymptotic distribution; Type I and type II errors; Test (biology); One- and two-tailed tests","score_opus":0.6289948457109944,"score_gpt":0.5167737091779451,"score_spread":0.11222113653304933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320035412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20436972,0.000050666087,0.7871287,0.00018808126,0.0023245504,0.00036022102,0.0044462145,0.000034104305,0.0010977441],"genre_scores_gemma":[0.09019955,0.000020370475,0.90948063,0.00006544175,0.00017611167,7.0024777e-7,0.0000032605549,0.000020239266,0.000033663902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978251,0.00022360624,0.0012932323,0.000060372473,0.00032941674,0.0002683139],"domain_scores_gemma":[0.9794445,0.018417427,0.0009017809,0.00016290424,0.0006567328,0.0004166331],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022347216,0.00011182898,0.0005021377,0.00048911845,0.00007960246,0.00003164086,0.00022583352,0.00010137321,0.00020035577],"category_scores_gemma":[0.14991482,0.00010073587,0.00007292358,0.0004919823,0.00017681875,0.00014922449,0.000015697637,0.00024367029,0.000026405098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002808713,0.00015554336,0.031719223,0.0025430745,0.0010782377,0.0015090567,0.007285244,0.00211514,0.0011329073,0.51949614,0.16207533,0.27060923],"study_design_scores_gemma":[0.0006123303,0.00024355363,0.008115055,0.00031552566,0.0001764855,0.00006164807,0.0003078016,0.0027349936,0.00058736297,0.98420686,0.002453975,0.00018442384],"about_ca_topic_score_codex":0.00037715991,"about_ca_topic_score_gemma":0.0007233285,"teacher_disagreement_score":0.46471068,"about_ca_system_score_codex":0.00009849437,"about_ca_system_score_gemma":0.0011824865,"threshold_uncertainty_score":0.8572458},"labels":[],"label_agreement":null},{"id":"W4321011930","doi":"10.1093/icvts/ivac293","title":"Is there a need of providing at least 3 decimal <i>P</i>-value to avoid type 1 error in a clinical research?","year":2023,"lang":"en","type":"letter","venue":"Interdisciplinary CardioVascular and Thoracic Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Decimal; Value (mathematics); Arithmetic; Type (biology); Type I and type II errors; Computer science; Statistics; Mathematics","score_opus":0.6559350541418375,"score_gpt":0.5974741195362981,"score_spread":0.05846093460553936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321011930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61377877,0.015250013,0.011218967,0.31481665,0.022564754,0.011533176,0.0023122567,0.000965983,0.007559441],"genre_scores_gemma":[0.39972726,0.0062722713,0.35683855,0.13683227,0.06594402,0.004284353,0.0005907527,0.00604549,0.023465024],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9794616,0.011627293,0.0035141686,0.0018932285,0.00224313,0.0012605567],"domain_scores_gemma":[0.8841639,0.11235999,0.00046618347,0.0021593417,0.0005379589,0.000312595],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.049070634,0.00074096053,0.0047705094,0.0012129622,0.00023976629,0.00009420193,0.0007769274,0.0018303432,0.00013922743],"category_scores_gemma":[0.073779285,0.0006418381,0.003574389,0.0018139408,0.0007991869,0.00010422572,0.004490423,0.0042327326,0.00028407297],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019335174,0.00022500404,0.0029710375,0.0049591623,0.003646938,0.005584832,0.0010005498,0.000012219409,0.000018184037,0.00009217487,0.9454618,0.0340946],"study_design_scores_gemma":[0.0023373987,0.0019031916,0.010652326,0.03239294,0.0042234235,0.000745758,0.0027095955,0.0005549496,0.0010836882,0.7209605,0.2176504,0.0047858534],"about_ca_topic_score_codex":0.00005471034,"about_ca_topic_score_gemma":0.000018341623,"teacher_disagreement_score":0.7278114,"about_ca_system_score_codex":0.0002856069,"about_ca_system_score_gemma":0.00039973448,"threshold_uncertainty_score":0.9996033},"labels":[],"label_agreement":null},{"id":"W4322500107","doi":"10.1002/bimj.202100384","title":"Comparison of cohort and nested case‐control designs for estimating the effect of time‐varying drug exposure on the risk of adverse event in the presence of ties","year":2023,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Nested case-control study; Hazard ratio; Estimator; Confounding; Medicine; Propensity score matching; Statistics; Pharmacoepidemiology; Cohort; Proportional hazards model; Cohort study; Adverse effect; Breast cancer; Econometrics; Internal medicine; Confidence interval; Mathematics; Cancer; Pharmacology","score_opus":0.3681908664452839,"score_gpt":0.5328397207256098,"score_spread":0.16464885428032588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322500107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9018562,0.0001290778,0.09629747,0.00020375973,0.00013489224,0.0012530375,0.00010152561,0.000006341001,0.00001772008],"genre_scores_gemma":[0.9291151,0.000016073132,0.07076836,0.000005500629,0.00005810431,0.000021298823,2.3931543e-7,0.000010883611,0.0000043977325],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.992937,0.004565771,0.0015202162,0.00013233974,0.00065209117,0.0001925778],"domain_scores_gemma":[0.68893284,0.30961367,0.0010746717,0.00021846317,0.00012306357,0.000037279715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021791572,0.00013237074,0.0008499805,0.00035306608,0.000115456925,0.000010890329,0.000376742,0.000082399485,0.000014643885],"category_scores_gemma":[0.24837083,0.000056125107,0.00022858096,0.0016921698,0.00033333706,0.000027791968,0.00006507119,0.00038188096,4.966485e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006743346,0.0020029952,0.8111411,0.0036280693,0.0033288673,0.00018517506,0.008511828,0.02040335,0.010235747,0.005702045,0.005990677,0.12212681],"study_design_scores_gemma":[0.00958567,0.009157074,0.11416688,0.0019452437,0.0033339064,0.00027008326,0.002645433,0.68017614,0.033537503,0.14479037,0.0000069427397,0.0003847489],"about_ca_topic_score_codex":0.00002109951,"about_ca_topic_score_gemma":6.0209584e-7,"teacher_disagreement_score":0.6969742,"about_ca_system_score_codex":0.000017605746,"about_ca_system_score_gemma":0.00002953544,"threshold_uncertainty_score":0.75796044},"labels":[],"label_agreement":null},{"id":"W4322722649","doi":"10.54846/jshap/1313","title":"Maximizing value and minimizing waste in clinical trial research in swine: Design features to minimize bias","year":2023,"lang":"en","type":"article","venue":"Journal of Swine Health and Production","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"University of Guelph","keywords":"Blinding; Protocol (science); Clinical study design; Medicine; Computer science; Outcome (game theory); Research design; Clinical trial; Preference; A priori and a posteriori; Statistics; Placebo; Mathematics; Alternative medicine; Internal medicine; Pathology","score_opus":0.9028891415252518,"score_gpt":0.6820067925674281,"score_spread":0.22088234895782366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322722649","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9046216,0.0011591256,0.0077689067,0.07942317,0.0045438455,0.0024094547,0.0000047476283,0.000032290063,0.000036882855],"genre_scores_gemma":[0.034454677,0.0043861982,0.9555908,0.00046250405,0.004906649,0.000031937067,6.2442285e-7,0.00004180809,0.00012484573],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98931587,0.0061613303,0.002887463,0.00044761997,0.00065254053,0.000535169],"domain_scores_gemma":[0.95784724,0.040392436,0.0007155682,0.00025366296,0.0002563317,0.000534786],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07833802,0.0001493117,0.0009891462,0.0009204628,0.00011382629,0.000054988624,0.00013129937,0.00018319103,0.0000041766607],"category_scores_gemma":[0.22153738,0.00011961407,0.000075795506,0.0012361235,0.0001072945,0.00012841349,0.00009940784,0.0012751827,0.0000025365175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12676348,0.0011759255,0.004391939,0.0022958224,0.00010034917,0.00025765807,0.004572105,0.00046422088,0.0005178509,0.0030638655,0.04829986,0.80809695],"study_design_scores_gemma":[0.0542435,0.010914759,0.020755196,0.0038379943,0.00006021881,0.00027031158,0.004387095,0.0008522789,0.0006366055,0.90208614,0.0014850243,0.0004708584],"about_ca_topic_score_codex":0.00003229436,"about_ca_topic_score_gemma":0.000007705988,"teacher_disagreement_score":0.94782186,"about_ca_system_score_codex":0.00009815849,"about_ca_system_score_gemma":0.00041204787,"threshold_uncertainty_score":0.94904494},"labels":[],"label_agreement":null},{"id":"W4322758210","doi":"10.1111/ajo.13656","title":"Subgroup effects should be examined using both relative and absolute effect measures","year":2023,"lang":"en","type":"article","venue":"Australian and New Zealand Journal of Obstetrics and Gynaecology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"","keywords":"Relative risk; Absolute risk reduction; Medicine; Absolute (philosophy); Subgroup analysis; Scale (ratio); Odds ratio; Statistics; Demography; Internal medicine; Confidence interval; Mathematics","score_opus":0.4495699960674924,"score_gpt":0.4788952897863761,"score_spread":0.029325293718883705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322758210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941279,0.000635921,0.0013099919,0.00085533684,0.0025847983,0.00033017376,0.000015868101,0.00002405448,0.00011593897],"genre_scores_gemma":[0.91681045,0.0016491355,0.0778974,0.00021475554,0.0002965146,0.0000037774903,0.0000013970273,0.000056476274,0.0030700993],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99767995,0.0007047391,0.00074478413,0.0002466968,0.00026354255,0.0003603049],"domain_scores_gemma":[0.91268563,0.08630222,0.00043833398,0.00011268535,0.00007630005,0.00038484714],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027955677,0.00022299285,0.0009060089,0.0003129332,0.00011048099,0.00006740473,0.000102439466,0.00032204864,0.000049330214],"category_scores_gemma":[0.068705216,0.00016169857,0.000089064255,0.00039984242,0.00019593623,0.00010921573,0.00008171522,0.0004902085,0.0000011241295],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006150362,0.00036907848,0.16223124,0.0013621276,0.0019071965,0.0044789156,0.0021793412,0.000013675374,0.0019590894,0.023608042,0.03105568,0.7702206],"study_design_scores_gemma":[0.009808698,0.0050391685,0.6011549,0.00010813079,0.00095654366,0.00026319394,0.00008744561,0.00019320521,0.00045849537,0.3777863,0.003716144,0.0004277105],"about_ca_topic_score_codex":0.000015931542,"about_ca_topic_score_gemma":0.00000364703,"teacher_disagreement_score":0.76979285,"about_ca_system_score_codex":0.000044550714,"about_ca_system_score_gemma":0.000052462932,"threshold_uncertainty_score":0.9391395},"labels":[],"label_agreement":null},{"id":"W4323542543","doi":"10.1136/bmjebm-2022-112100","title":"Proposed triggers for retiring a living systematic review","year":2023,"lang":"en","type":"article","venue":"BMJ evidence-based medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Construct (python library); Computer science; Certainty; Actuarial science; Risk analysis (engineering); Business","score_opus":0.8168270424800806,"score_gpt":0.6492158980082676,"score_spread":0.16761114447181302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323542543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007034876,0.031929586,0.81172496,0.096880935,0.0036847922,0.051973984,0.0000602215,0.0022379218,0.00080413313],"genre_scores_gemma":[0.0064296466,0.009068269,0.95867336,0.01251451,0.0028120603,0.007239824,0.000009766056,0.0002659906,0.002986588],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9923989,0.0023178216,0.002875955,0.00061576185,0.0011948231,0.0005967488],"domain_scores_gemma":[0.67636704,0.3209464,0.0009504853,0.0010399802,0.0004232047,0.00027289696],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045198187,0.00035163906,0.0025772073,0.00023442434,0.00013670388,0.000023669767,0.00054823887,0.00016092758,0.00038924426],"category_scores_gemma":[0.8755799,0.00023113948,0.00034098767,0.0012014502,0.00027240068,0.00010769152,0.00007889716,0.0002872524,0.00012413082],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013007801,0.000055978795,0.000025719963,0.93642116,0.00011050589,0.00006770914,0.00010326137,0.0000023516395,0.0002719453,0.010199597,0.051352415,0.0012592617],"study_design_scores_gemma":[0.0009989426,0.0006070661,0.000021055195,0.86160856,0.0017509517,0.000009526775,0.00010986224,0.0018875307,0.00021926625,0.13241112,0.0000876646,0.000288415],"about_ca_topic_score_codex":0.0000070948495,"about_ca_topic_score_gemma":0.0000015834838,"teacher_disagreement_score":0.8303817,"about_ca_system_score_codex":0.0001427996,"about_ca_system_score_gemma":0.00029231503,"threshold_uncertainty_score":0.9831694},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4323568000","doi":"10.1016/j.jclinepi.2023.02.010","title":"Methodology and design of platform trials: a meta-epidemiological study","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Juravinski Hospital; Dalhousie University; SickKids Foundation; Public Health Ontario; Hospital for Sick Children; University of British Columbia; Sinai Health System; McMaster University; Toronto General Hospital; Western University; University of Toronto; University Health Network; Institute for Clinical Evaluative Sciences; University of Ottawa; University of Calgary","funders":"McMaster University","keywords":"Epidemiology; Research design; Meta-analysis; Medicine; Environmental health; Statistics; Internal medicine; Mathematics","score_opus":0.9970151318499682,"score_gpt":0.8266353721958252,"score_spread":0.17037975965414298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323568000","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008819914,0.6278362,0.3661446,0.0002665324,0.0031125962,0.0024854841,0.00008667146,0.000040537798,0.000018532844],"genre_scores_gemma":[4.821847e-7,0.5130639,0.4851026,0.00017345771,0.0014563276,0.000087325105,9.021789e-7,0.00007326723,0.00004176109],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.16752541,0.720143,0.10800839,0.0019348859,0.00095926726,0.0014290002],"domain_scores_gemma":[0.016896077,0.9159472,0.064351305,0.0012450652,0.00069605093,0.0008642878],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.8216716,0.0013708717,0.1377189,0.00071649905,0.00007568372,0.000012665246,0.0018092416,0.004368186,0.00038674875],"category_scores_gemma":[0.9950824,0.0006646689,0.016235678,0.0006774596,0.0018076483,0.00008712089,0.00081334333,0.006391147,0.00003130078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013587823,0.00137686,0.0001470453,0.008728,0.046422265,0.00026824808,0.000033520348,0.000013311028,4.594071e-8,0.05701667,0.0072742905,0.87736094],"study_design_scores_gemma":[0.0019777415,0.0071860813,0.00005870518,0.0028067988,0.07468951,0.00028708339,0.000053896587,0.000039152477,6.268984e-8,0.87154037,0.040941074,0.00041953308],"about_ca_topic_score_codex":0.000012495602,"about_ca_topic_score_gemma":0.0000027600704,"teacher_disagreement_score":0.87694144,"about_ca_system_score_codex":0.00006507904,"about_ca_system_score_gemma":0.0009365477,"threshold_uncertainty_score":0.9999042},"labels":[],"label_agreement":null},{"id":"W4324344210","doi":"10.1016/j.cjca.2023.03.010","title":"The Impact of COVID-19 Research on the Development of Scalable Frameworks for Efficient Clinical Trials in Cardiovascular Medicine","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of Manitoba; CancerCare Manitoba; University of Toronto","funders":"Canadian Institutes of Health Research; Novo Nordisk; Research Manitoba; AstraZeneca; CancerCare Manitoba Foundation; Heart and Stroke Foundation of Canada; Amgen","keywords":"Medicine; Clinical trial; Timeline; Pandemic; Protocol (science); Intensive care medicine; Coronavirus disease 2019 (COVID-19); Clinical study design; Randomized controlled trial; Disease; Medical physics; Alternative medicine; Pathology; Infectious disease (medical specialty)","score_opus":0.8578234025578151,"score_gpt":0.6899900819911525,"score_spread":0.16783332056666256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324344210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29534847,0.0030469557,0.6661935,0.02102391,0.0059824586,0.005100371,0.00032744533,0.000018178298,0.002958727],"genre_scores_gemma":[0.9704809,0.00019523852,0.027497945,0.000102539,0.0015923262,0.00006454192,0.0000012584428,0.00003511464,0.000030137842],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9736248,0.020783754,0.004127755,0.00022170464,0.0006366315,0.0006053213],"domain_scores_gemma":[0.57723004,0.42016822,0.0007891374,0.00055095693,0.00072279014,0.0005388889],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33467796,0.00014671242,0.002800318,0.00050468894,0.00021568683,0.000012196214,0.0007768372,0.00049431756,0.000037628353],"category_scores_gemma":[0.81465214,0.000068953465,0.001419883,0.0008187555,0.0014407784,0.000008676482,0.000050354985,0.0014030709,0.0000034686195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005135798,0.00009300193,0.014052963,0.0006123625,0.015112396,0.00028634752,0.004135127,0.12656122,0.0001194225,0.22486745,0.45342958,0.15559435],"study_design_scores_gemma":[0.0040391223,0.0019311606,0.015552864,0.00052777585,0.00032111487,0.000026451815,0.0020198538,0.00060941867,0.00010351734,0.9452571,0.029445145,0.00016644325],"about_ca_topic_score_codex":0.00031210846,"about_ca_topic_score_gemma":0.00029367305,"teacher_disagreement_score":0.72038966,"about_ca_system_score_codex":0.00039264283,"about_ca_system_score_gemma":0.0056519085,"threshold_uncertainty_score":0.9999851},"labels":[],"label_agreement":null},{"id":"W4327519997","doi":"10.2139/ssrn.4381439","title":"ADSP: An Adaptive Sample Pooling Strategy for Diagnostic Testing","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"","keywords":"Pooling; Sample (material); Econometrics; Computer science; Business; Artificial intelligence; Economics","score_opus":0.6191996054516808,"score_gpt":0.5531897188962673,"score_spread":0.06600988655541351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327519997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04587552,0.00015985059,0.95209575,0.00019573758,0.00047112713,0.00061232963,0.00009441799,0.00025847025,0.00023680556],"genre_scores_gemma":[0.36553437,0.0003368684,0.63181216,0.00006902372,0.0018335807,0.000080302954,0.000005857705,0.00010976228,0.00021808711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99507236,0.0005929258,0.00088312605,0.00035930733,0.00036487522,0.0027273877],"domain_scores_gemma":[0.808487,0.19029982,0.00040616264,0.0002741524,0.00031023874,0.00022259606],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01256146,0.00023013158,0.0005160357,0.00014712643,0.0003517284,0.000098124736,0.00039731505,0.00015066969,0.00004115302],"category_scores_gemma":[0.3400448,0.00020109126,0.0001741213,0.0005361,0.000073425195,0.0001564033,0.000057324065,0.0016506047,0.000031797583],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014747454,0.00010488796,0.00027855823,0.000029932966,0.00016695115,0.000010303587,0.0000615135,0.000298817,0.00011359085,0.8521468,0.0002034871,0.14643767],"study_design_scores_gemma":[0.00095644384,0.0020003344,0.00022988263,0.00007647661,0.00014342433,0.000072626,0.0011241827,0.0071675624,0.0000674905,0.98786944,0.000052998228,0.00023914319],"about_ca_topic_score_codex":0.000037376747,"about_ca_topic_score_gemma":0.00015001027,"teacher_disagreement_score":0.32748333,"about_ca_system_score_codex":0.00038600047,"about_ca_system_score_gemma":0.0014135821,"threshold_uncertainty_score":0.82002634},"labels":[],"label_agreement":null},{"id":"W4327856879","doi":"10.1017/9781108917919.006","title":"Clinical Trial Simulations","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Adaptive design; Computer science; Medical physics; Quality (philosophy); Clinical study design; Medicine; Internal medicine","score_opus":0.6617060423124212,"score_gpt":0.5112509063982514,"score_spread":0.1504551359141698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327856879","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047847858,0.000005771024,0.012183843,0.000025491303,0.0028978589,0.0015707372,0.0017682826,0.0005655394,0.9809346],"genre_scores_gemma":[0.00003591492,0.00005198608,0.047480673,0.00005532155,0.0014499038,0.0000015667501,0.00002341496,0.00014630226,0.95075494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962284,0.0006244761,0.0013036678,0.00089133816,0.0005714738,0.00038065208],"domain_scores_gemma":[0.9427448,0.054689493,0.0007791786,0.001169047,0.00027371463,0.00034376528],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018679444,0.000474876,0.0014729772,0.00018558787,0.00019443587,0.000047889276,0.00076715136,0.0012598084,0.000050288956],"category_scores_gemma":[0.019373488,0.00052521884,0.00086712086,0.000018083738,0.0006002575,0.000040734714,0.00068222155,0.0013168177,0.00014211467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036632076,0.000041489955,5.247725e-7,0.00008112299,0.00033918352,0.00021723782,0.000005234999,8.3772807e-7,5.5212183e-7,0.91542554,0.07718688,0.0030382015],"study_design_scores_gemma":[0.025358712,0.00041795522,0.0000047902504,0.00031780615,0.0014865104,0.0000024241997,0.0000074466534,0.00017513537,0.000007694795,0.11896001,0.85247093,0.00079059193],"about_ca_topic_score_codex":0.000012572085,"about_ca_topic_score_gemma":0.0000017764614,"teacher_disagreement_score":0.7964655,"about_ca_system_score_codex":0.00012860118,"about_ca_system_score_gemma":0.0001987326,"threshold_uncertainty_score":0.9997199},"labels":[],"label_agreement":null},{"id":"W4327856893","doi":"10.1017/9781108917919.002","title":"Introduction to Clinical Trial Research","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Sample size determination; Protocol (science); Research design; Psychological intervention; Medicine; Clinical study design; Type I and type II errors; Sample (material); Medical physics; Computer science; Statistics; Mathematics; Alternative medicine; Internal medicine; Pathology","score_opus":0.7729106141329445,"score_gpt":0.564773166484077,"score_spread":0.20813744764886744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327856893","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000617812,0.000004552692,0.006514202,0.0004641674,0.006438197,0.0027505811,0.00046220105,0.00044405914,0.98286027],"genre_scores_gemma":[0.0000044639346,0.000064704225,0.047570575,0.000050991384,0.012114664,0.0000066911302,0.000011099307,0.00014892744,0.9400279],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936502,0.0018249383,0.0012703664,0.0014372937,0.001194997,0.00062219094],"domain_scores_gemma":[0.9529431,0.04363523,0.0004171246,0.0016467525,0.0007853098,0.0005724854],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011430364,0.0004257062,0.0014120156,0.00047810999,0.00027352132,0.000078631165,0.0010580774,0.0012208429,0.000056264045],"category_scores_gemma":[0.06038853,0.00046880014,0.0005868597,0.000052799554,0.00074786175,0.000041352727,0.0013809103,0.0025083881,0.0006758937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0073799156,0.00003049468,8.362246e-8,0.00006434168,0.00013871302,0.00013097716,0.0000081185235,1.0650966e-7,0.000001585502,0.5701892,0.41799054,0.0040659327],"study_design_scores_gemma":[0.0093753375,0.0008827359,0.0000023302937,0.0001857463,0.00032312918,0.00000290188,0.00002001596,0.0000071486415,0.000032862285,0.0500572,0.9386524,0.00045819968],"about_ca_topic_score_codex":0.000028745342,"about_ca_topic_score_gemma":0.0000021539513,"teacher_disagreement_score":0.5206619,"about_ca_system_score_codex":0.00031309837,"about_ca_system_score_gemma":0.00025378284,"threshold_uncertainty_score":0.9997929},"labels":[],"label_agreement":null},{"id":"W4327856904","doi":"10.1017/9781108917919.004","title":"Characteristics and Principles of Adaptive Trial Designs","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Adaptive design; Interim; Interim analysis; Computer science; Clinical trial; Research design; Risk analysis (engineering); Medicine; Mathematics; Statistics; Political science; Law","score_opus":0.6014118872243567,"score_gpt":0.4202319524751986,"score_spread":0.18117993474915806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327856904","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002373414,0.000010884928,0.01867008,0.0000067745045,0.0006471555,0.0014109137,0.0022891944,0.00016457493,0.9765631],"genre_scores_gemma":[0.00010965102,0.00014759395,0.06270209,0.000009846888,0.0002828047,0.0000021263656,0.000008377113,0.000089671754,0.93664783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978089,0.00028798293,0.0007389686,0.0005318693,0.00038379733,0.00024851356],"domain_scores_gemma":[0.9800604,0.018025419,0.0009036214,0.0005715521,0.00024835896,0.00019065342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009983584,0.0003804034,0.0012939557,0.00015460486,0.000086815875,0.000020273648,0.00039138875,0.0006076302,0.000007922464],"category_scores_gemma":[0.006434524,0.0004088166,0.00025848424,0.000011032325,0.0006476064,0.000028436443,0.00058160094,0.0005427578,0.0000066564426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007379854,0.000022887672,5.6058076e-7,0.00028551582,0.00029123676,0.00014557989,0.000026014222,4.951271e-8,0.000011222322,0.98826396,0.001967969,0.0016051183],"study_design_scores_gemma":[0.08473216,0.006292391,0.0001915983,0.005676708,0.010514933,0.000036190377,0.00020539374,0.0006218914,0.0016493603,0.23445657,0.65090495,0.0047178264],"about_ca_topic_score_codex":0.0000135478,"about_ca_topic_score_gemma":6.2526277e-7,"teacher_disagreement_score":0.7538074,"about_ca_system_score_codex":0.00007721155,"about_ca_system_score_gemma":0.00012811185,"threshold_uncertainty_score":0.9998364},"labels":[],"label_agreement":null},{"id":"W4327860460","doi":"10.1017/9781108917919.010","title":"Case Studies of Adaptive Trial Designs","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Adaptive design; Presentation (obstetrics); Computer science; Comprehension; Complement (music); Clinical trial; Research design; Management science; Psychology; Medicine; Engineering; Sociology; Social science; Pathology; Programming language","score_opus":0.7657468682068368,"score_gpt":0.4871234175456831,"score_spread":0.2786234506611537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860460","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011907023,0.000041462325,0.013648951,0.0000060541693,0.0012977746,0.0018340332,0.001715584,0.00024333816,0.9810937],"genre_scores_gemma":[0.000120388504,0.00010359766,0.0700164,0.000011364028,0.00034530467,0.0000036022575,0.0000027150618,0.000100507874,0.92929614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972479,0.0005212765,0.00084823824,0.0006211296,0.00045993307,0.0003015594],"domain_scores_gemma":[0.9558833,0.041778337,0.0008940048,0.00076279504,0.00050913624,0.00017242787],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014699083,0.0004626257,0.0017426448,0.00020822619,0.00014014498,0.0000122325255,0.0004462443,0.00060997513,0.0000089949135],"category_scores_gemma":[0.012011998,0.0004774005,0.000541377,0.000018212357,0.0009144734,0.000033130502,0.0006616511,0.00064653374,0.000016144582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008496492,0.000028426173,2.3606438e-8,0.000333621,0.0012126578,0.009155651,0.00007266302,3.4353167e-7,0.0000046446066,0.9541135,0.025456466,0.0011255076],"study_design_scores_gemma":[0.10731314,0.007817333,5.906341e-7,0.0045270068,0.017831668,0.0009433075,0.0020404595,0.00017495538,0.0020164754,0.71479636,0.13798355,0.004555174],"about_ca_topic_score_codex":0.000025991401,"about_ca_topic_score_gemma":0.0000021387646,"teacher_disagreement_score":0.23931716,"about_ca_system_score_codex":0.00017072845,"about_ca_system_score_gemma":0.0001429343,"threshold_uncertainty_score":0.9997678},"labels":[],"label_agreement":null},{"id":"W4327860477","doi":"10.1017/9781108917919.011","title":"Case Studies of Platform Trials","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Computer science; Coronavirus disease 2019 (COVID-19); Medicine; Medical physics; Pathology; Disease","score_opus":0.7793433779194361,"score_gpt":0.5108029219179084,"score_spread":0.26854045600152765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860477","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012255792,0.000073085444,0.0030947307,0.000009204497,0.0011870115,0.0011804615,0.0027398379,0.00026047337,0.99133265],"genre_scores_gemma":[0.00006116628,0.0002823765,0.042662002,0.000015725742,0.00030904575,0.0000021520148,0.00000524176,0.00010286808,0.9565594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966698,0.0004752207,0.0014748418,0.00058399426,0.00048767022,0.00030844592],"domain_scores_gemma":[0.91378963,0.083255924,0.0014802302,0.00084247784,0.00045714714,0.00017460395],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0046912627,0.00048431917,0.0030277013,0.00024947803,0.00013495152,0.00001635821,0.00047280034,0.0006845993,0.0000155278],"category_scores_gemma":[0.044692736,0.00046293845,0.0007952355,0.00001727175,0.00075062254,0.00004120215,0.00074067997,0.0006288431,0.000020209589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026154573,0.0000151632075,9.642407e-8,0.00085875957,0.0014776882,0.007898332,0.00006575558,2.027978e-7,0.000008935296,0.94033855,0.046099607,0.0029753484],"study_design_scores_gemma":[0.007303171,0.0008014833,8.8300453e-7,0.003551485,0.012415154,0.00095239066,0.0009423093,0.000049430313,0.0023803364,0.62353265,0.3456394,0.0024313214],"about_ca_topic_score_codex":0.00002363969,"about_ca_topic_score_gemma":0.0000019982076,"teacher_disagreement_score":0.31680593,"about_ca_system_score_codex":0.0001530173,"about_ca_system_score_gemma":0.00011221247,"threshold_uncertainty_score":0.9997822},"labels":[],"label_agreement":null},{"id":"W4327860480","doi":"10.1017/9781108917919.007","title":"Characteristics and Principles of Master Protocols","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Protocol (science); Computer science; Clinical trial; Medical physics; Medicine; Alternative medicine","score_opus":0.5522377976103402,"score_gpt":0.4323905452384725,"score_spread":0.11984725237186772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860480","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000648405,0.0000030071767,0.0038912313,0.000010337668,0.00015693015,0.0068844412,0.0017059033,0.00014703616,0.98713624],"genre_scores_gemma":[0.000012320276,0.000034064316,0.044569124,0.000014455859,0.00014571342,0.000036362406,0.0000067924184,0.00008877031,0.9550924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806726,0.00016440124,0.0006952046,0.00048663322,0.00035244966,0.00023404554],"domain_scores_gemma":[0.9904152,0.007727135,0.00079654873,0.00066881435,0.00022345707,0.00016884299],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074968254,0.0003501575,0.0011037318,0.00013108324,0.00006411712,0.000026677459,0.0003976454,0.00051835866,0.0000115425255],"category_scores_gemma":[0.0036372088,0.00036554236,0.00019266021,0.000008642578,0.00052598974,0.000028354114,0.00072134787,0.00047719973,0.000009500484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018064523,0.000015451233,0.000010602073,0.0012676026,0.00015932169,0.00012920538,0.00002065662,2.5054229e-8,0.00001907773,0.9936437,0.0024989753,0.0020547514],"study_design_scores_gemma":[0.0020030807,0.00035849927,0.00032262312,0.003344703,0.0010566179,0.000013464123,0.000021609825,0.000085669955,0.0005637402,0.035136957,0.95605737,0.0010356366],"about_ca_topic_score_codex":0.0000053924055,"about_ca_topic_score_gemma":3.425587e-7,"teacher_disagreement_score":0.9585067,"about_ca_system_score_codex":0.00005148256,"about_ca_system_score_gemma":0.000075471085,"threshold_uncertainty_score":0.99987966},"labels":[],"label_agreement":null},{"id":"W4327860511","doi":"10.1017/9781108917919.005","title":"Common Types of Adaptive Trial Designs","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Adaptive design; Sample size determination; Interim; Interim analysis; Flexibility (engineering); Computer science; Research design; Type I and type II errors; Clinical study design; Clinical trial; Reliability engineering; Statistics; Engineering; Medicine; Mathematics","score_opus":0.5965747815827512,"score_gpt":0.44150170741398703,"score_spread":0.1550730741687642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860511","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003655228,0.000013533839,0.0157716,0.000007097187,0.000817861,0.0012512961,0.0012594423,0.00020413192,0.9806385],"genre_scores_gemma":[0.0001305151,0.00004171036,0.048977315,0.000011867766,0.0002920007,0.000001970118,0.000007779723,0.000101051046,0.9504358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976327,0.0004282508,0.0007005523,0.0005029826,0.00046720947,0.00026830667],"domain_scores_gemma":[0.9746406,0.023422068,0.00077558914,0.00075114955,0.00024467282,0.00016589092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010062327,0.00038275134,0.001409523,0.00017386186,0.00008382037,0.000014177902,0.00063400075,0.0007012995,0.000021268395],"category_scores_gemma":[0.0037245594,0.0004104647,0.0004678706,0.000016201366,0.0005310503,0.000027902986,0.00047767386,0.0006554651,0.000031584328],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010443425,0.00003076176,9.635313e-8,0.000164306,0.00042102532,0.00015796533,0.000017373228,5.520668e-7,0.000009154476,0.9654909,0.021210691,0.0020537807],"study_design_scores_gemma":[0.05718697,0.005587929,0.0000062830422,0.0027260599,0.0066457097,0.000011110533,0.00012628648,0.00023730338,0.002263984,0.5942745,0.32830465,0.002629191],"about_ca_topic_score_codex":0.000042498068,"about_ca_topic_score_gemma":0.0000023820762,"teacher_disagreement_score":0.37121633,"about_ca_system_score_codex":0.00011427813,"about_ca_system_score_gemma":0.00013566673,"threshold_uncertainty_score":0.9998347},"labels":[],"label_agreement":null},{"id":"W4327860516","doi":"10.1017/9781108917919.008","title":"Platform Trials","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Medical physics; Psychological intervention; Medicine; Clinical study design; Adaptive design; Computer science; Pathology; Nursing","score_opus":0.6805199866615016,"score_gpt":0.47091225172732953,"score_spread":0.20960773493417206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860516","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000055958917,0.000016780547,0.0112378085,0.00002355492,0.0014751806,0.0011600644,0.0020041482,0.0006379787,0.9834389],"genre_scores_gemma":[0.000004566233,0.00012309139,0.04716687,0.000052573527,0.000685202,0.0000024370447,0.000017653465,0.0001683355,0.95177925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964205,0.00044862888,0.0012311335,0.00079329073,0.0006537154,0.00045275182],"domain_scores_gemma":[0.9400194,0.05731757,0.0010642563,0.0010529765,0.00022605354,0.00031973125],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004415519,0.0005849344,0.0023900075,0.0002487113,0.0001699877,0.00005926338,0.00084734097,0.0011062894,0.0000624719],"category_scores_gemma":[0.02797699,0.0005930194,0.0009291468,0.00001563739,0.0004030616,0.000052015308,0.00070009416,0.0010163337,0.00019710138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021482715,0.000010631465,8.159629e-8,0.0002039282,0.00042625924,0.00038491955,0.000011026108,1.0130137e-7,0.000006199886,0.83573496,0.15842505,0.00458202],"study_design_scores_gemma":[0.0015566219,0.00010524341,0.0000013919284,0.0005192303,0.0014310492,0.0000073619626,0.000018156015,0.000019246427,0.00018374073,0.20783529,0.78759515,0.0007274968],"about_ca_topic_score_codex":0.000023219949,"about_ca_topic_score_gemma":0.0000011199678,"teacher_disagreement_score":0.6291701,"about_ca_system_score_codex":0.0002127111,"about_ca_system_score_gemma":0.0001561157,"threshold_uncertainty_score":0.99965215},"labels":[],"label_agreement":null},{"id":"W4327860535","doi":"10.1017/9781108917919.014","title":"Common Misconceptions of Adaptive Trial Designs and Master Protocols","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Field (mathematics); Field trial; Clinical trial; Computer science; Protocol (science); Adaptive design; Medical physics; Medical education; Psychology; Medicine; Alternative medicine; Mathematics; Pathology; Biology","score_opus":0.6988894581241069,"score_gpt":0.46925039188590384,"score_spread":0.22963906623820302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860535","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000045824836,0.000004806141,0.01907553,0.000011167575,0.00020275178,0.017667664,0.0015305732,0.0001433834,0.9613183],"genre_scores_gemma":[0.000042228112,0.00001215557,0.06353967,0.000014483569,0.00020110756,0.00012501536,0.00000568008,0.00008146723,0.9359782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99773157,0.0004441939,0.000695577,0.00051801075,0.00036781334,0.0002428329],"domain_scores_gemma":[0.98462117,0.013661041,0.0007075811,0.000632918,0.00019570148,0.0001815868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083119265,0.0003644592,0.0012154793,0.00014498846,0.00010352619,0.000024807794,0.00040375668,0.0005830854,0.000019390207],"category_scores_gemma":[0.0018238694,0.00038306526,0.00029212507,0.000012804914,0.00079730514,0.000038863458,0.00047287162,0.0005817918,0.000009444301],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0081319455,0.0000334882,4.5237684e-7,0.00027212867,0.00024878484,0.00007869646,0.0000412918,2.0527457e-7,0.000017591756,0.9801889,0.009416565,0.0015699667],"study_design_scores_gemma":[0.111535825,0.007962746,0.000032631273,0.008021813,0.005503628,0.00002599254,0.0003980497,0.0003069817,0.0015397974,0.47885853,0.38234207,0.0034719359],"about_ca_topic_score_codex":0.000022234412,"about_ca_topic_score_gemma":0.0000021569972,"teacher_disagreement_score":0.5013304,"about_ca_system_score_codex":0.00007627119,"about_ca_system_score_gemma":0.00010465461,"threshold_uncertainty_score":0.99986213},"labels":[],"label_agreement":null},{"id":"W4327860560","doi":"10.1017/9781108917919.013","title":"Standards and Guidelines for Adaptive Trial Designs and Master Protocols","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Rigour; Adaptive design; Clinical trial; Protocol (science); Computer science; Research design; Clinical study design; Medical physics; Risk analysis (engineering); Management science; Medicine; Alternative medicine; Engineering","score_opus":0.7911254429652516,"score_gpt":0.5253933955109477,"score_spread":0.2657320474543039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860560","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000110833325,0.000028803279,0.24570936,0.00008029667,0.00040295007,0.04563199,0.008758739,0.0002764031,0.6991004],"genre_scores_gemma":[0.0000010277098,0.000037329653,0.23607865,0.000049463823,0.0004382482,0.00028113442,0.000004813007,0.00009573632,0.7630136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99758905,0.00022628119,0.0006982963,0.00071964867,0.00046581464,0.00030092854],"domain_scores_gemma":[0.9827725,0.015063437,0.00048966845,0.0004518343,0.0009926687,0.00022984737],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002238629,0.00044107417,0.0011459914,0.0001290116,0.00016791951,0.00007443657,0.0002716087,0.0006022513,0.000005682945],"category_scores_gemma":[0.013780507,0.00043301028,0.00021804737,0.000008173275,0.0004803128,0.000046808975,0.000462048,0.00037429784,0.0000013615618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018412553,0.000010054463,1.0473554e-7,0.0004187582,0.00023687472,0.000052059113,0.000019085073,7.905043e-8,0.000004342798,0.9045704,0.07001954,0.006256132],"study_design_scores_gemma":[0.041418612,0.0023979007,0.0000011232419,0.00197697,0.0013234281,0.000008344044,0.00006781368,0.00025459728,0.00012067025,0.18007967,0.77134603,0.0010048581],"about_ca_topic_score_codex":0.000008271897,"about_ca_topic_score_gemma":0.000001570168,"teacher_disagreement_score":0.72449076,"about_ca_system_score_codex":0.00010880054,"about_ca_system_score_gemma":0.0001978292,"threshold_uncertainty_score":0.9998122},"labels":[],"label_agreement":null},{"id":"W4327860586","doi":"10.1017/9781108917919.009","title":"Basket Trials and Umbrella Trials","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Medicine; Biomarker; Clinical study design; Research design; Sample size determination; Intensive care medicine; Medical physics; Internal medicine; Biology","score_opus":0.705493394791692,"score_gpt":0.48928603022412687,"score_spread":0.21620736456756517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327860586","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013610855,0.0001089002,0.00939259,0.00006680139,0.0015037396,0.0020139085,0.0035343862,0.00046619916,0.98289984],"genre_scores_gemma":[0.00000811681,0.00076924893,0.0445122,0.00007506193,0.00087466626,0.0000041235653,0.000017487844,0.00017782081,0.95356125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99197483,0.0034873097,0.0022575385,0.0011052836,0.0006863284,0.00048872334],"domain_scores_gemma":[0.84298116,0.15355743,0.0018315562,0.0009825223,0.00023987284,0.00040746224],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019271985,0.0007337276,0.005063583,0.00031431252,0.00020330561,0.000110715584,0.0006686781,0.0012957366,0.00006681105],"category_scores_gemma":[0.11002486,0.00070677215,0.0010670541,0.000020141264,0.0006078988,0.000048189977,0.0008324939,0.000995981,0.00006534835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045226005,0.000013202475,2.2511533e-7,0.00038829085,0.0007311363,0.00029871537,0.000016714906,7.4861134e-8,0.0000238982,0.84937346,0.14086229,0.0078397095],"study_design_scores_gemma":[0.003891705,0.00018823026,0.0000038599323,0.0010095888,0.004256575,0.000014982636,0.000031691285,0.0000274233,0.00029804048,0.1828432,0.8063723,0.0010624486],"about_ca_topic_score_codex":0.000036706202,"about_ca_topic_score_gemma":0.0000013164872,"teacher_disagreement_score":0.6665303,"about_ca_system_score_codex":0.0001333399,"about_ca_system_score_gemma":0.00017202982,"threshold_uncertainty_score":0.99953836},"labels":[],"label_agreement":null},{"id":"W4327862509","doi":"10.1017/9781108917919","title":"Introduction to Adaptive Trial Designs and Master Protocols","year":2023,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Adaptive design; Protocol (science); Resource (disambiguation); Computer science; Clinical study design; Clinical Practice; Medical research; Research design; Medical physics; Alternative medicine; Engineering ethics; Medicine; Engineering; Nursing; Sociology; Pathology; Social science","score_opus":0.5740663308523115,"score_gpt":0.4556085735928875,"score_spread":0.11845775725942403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327862509","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021397896,0.0000027472497,0.115212716,0.00014260628,0.0010900722,0.04470876,0.00082415005,0.0004483165,0.8375492],"genre_scores_gemma":[5.0098015e-7,0.0000029574428,0.10674376,0.000042711825,0.0028009715,0.0003829618,0.0000067337855,0.00009113393,0.8899283],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99682766,0.0008535947,0.0005688247,0.00093423435,0.00044397786,0.000371686],"domain_scores_gemma":[0.9882542,0.010033376,0.0004006507,0.00075313926,0.00023673914,0.0003219065],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014728532,0.00042146532,0.001055263,0.0002235062,0.0001396872,0.00007229076,0.00043387184,0.0005982494,0.000013114185],"category_scores_gemma":[0.0086307805,0.00045015605,0.00019969938,0.00003730699,0.00028162455,0.00005394978,0.00063765846,0.00068337296,0.0000549021],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014086366,0.000025728035,5.369389e-8,0.000197124,0.00014061964,0.000074015596,0.000030727424,3.5422258e-7,0.000010098978,0.5142276,0.46935013,0.0018571849],"study_design_scores_gemma":[0.017102042,0.0019248512,0.0000027531362,0.0005971247,0.00069383625,0.0000068652917,0.000050240455,0.000039005696,0.0002128769,0.023581728,0.9549836,0.000805091],"about_ca_topic_score_codex":0.0000085258525,"about_ca_topic_score_gemma":9.112657e-7,"teacher_disagreement_score":0.4906459,"about_ca_system_score_codex":0.00032798777,"about_ca_system_score_gemma":0.00024083008,"threshold_uncertainty_score":0.999795},"labels":[],"label_agreement":null},{"id":"W4327877209","doi":"10.1017/9781108917919.015","title":"Practical Considerations for Adaptive Trial Designs and Master Protocols","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Firewall (physics); Plan (archaeology); Key (lock); Risk analysis (engineering); Clinical trial; Process management; Engineering management; Engineering; Computer security; Medicine; Business","score_opus":0.8215124172747243,"score_gpt":0.5145899958078205,"score_spread":0.30692242146690385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327877209","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017282199,0.0000015782357,0.22926258,0.00012216771,0.0003080945,0.038484532,0.0017666059,0.00022758506,0.72982514],"genre_scores_gemma":[0.0000033914187,0.0000038596822,0.37082216,0.000048836548,0.00031744558,0.00046446887,0.0000041504086,0.00007740577,0.6282583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975767,0.00041013432,0.00063880195,0.00071353983,0.00033643076,0.00032439435],"domain_scores_gemma":[0.9315571,0.06685048,0.00050738995,0.0005054402,0.00034160787,0.00023796424],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001265431,0.00040839746,0.0010205049,0.0001261741,0.0002457038,0.00009513918,0.00014452312,0.0007097334,0.000019307901],"category_scores_gemma":[0.021433031,0.00043043468,0.00028921562,0.000007775643,0.00052192976,0.00006888002,0.00032466833,0.0006243768,0.000012148648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010410218,0.00003123981,3.6279665e-8,0.0001879627,0.00027288997,0.00019194561,0.000018480867,8.529519e-8,0.0000041844337,0.8982229,0.09040453,0.00025550945],"study_design_scores_gemma":[0.040943824,0.00246839,8.379561e-7,0.0008075356,0.0020586161,0.00004085701,0.0000637181,0.00031176812,0.00018410065,0.65651053,0.29548588,0.0011239003],"about_ca_topic_score_codex":0.0000047536746,"about_ca_topic_score_gemma":0.0000016480232,"teacher_disagreement_score":0.24171236,"about_ca_system_score_codex":0.00010198868,"about_ca_system_score_gemma":0.00030231944,"threshold_uncertainty_score":0.99981475},"labels":[],"label_agreement":null},{"id":"W4327877221","doi":"10.1017/9781108917919.012","title":"Case Studies of Basket Trials and Umbrella Trials","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Clinical trial; Medicine; Internal medicine","score_opus":0.7949948364774804,"score_gpt":0.526504689734919,"score_spread":0.26849014674256133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327877221","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026913578,0.00050001213,0.0037720741,0.00003616527,0.001657591,0.002679137,0.0061739325,0.00028457062,0.98462737],"genre_scores_gemma":[0.00008148836,0.0015639897,0.04142381,0.000025134914,0.00043996368,0.0000036944346,0.000005872057,0.000118272495,0.95633775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992495,0.003312076,0.0025302302,0.00080964714,0.0005164557,0.00033658522],"domain_scores_gemma":[0.8022262,0.1939962,0.0023298105,0.0007825749,0.00044154093,0.00022366621],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.018693862,0.0006013725,0.0059567844,0.00030542185,0.00016081659,0.000032480635,0.00038985786,0.0008110758,0.000018117094],"category_scores_gemma":[0.15128988,0.00055025,0.00090910034,0.000021125586,0.0010227835,0.00003748814,0.0008462744,0.0006264117,0.000008581079],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005312014,0.000017959324,2.3699975e-7,0.001360333,0.0022209347,0.004771216,0.00007945366,1.386071e-7,0.00003048334,0.9360409,0.04989176,0.0050553996],"study_design_scores_gemma":[0.017464677,0.001312362,0.000002640158,0.006268546,0.032695018,0.0013027429,0.0012263181,0.00006722876,0.0033247839,0.55078673,0.38200867,0.003540273],"about_ca_topic_score_codex":0.000035290268,"about_ca_topic_score_gemma":0.000002130062,"teacher_disagreement_score":0.38525414,"about_ca_system_score_codex":0.0000990649,"about_ca_system_score_gemma":0.00012430441,"threshold_uncertainty_score":0.9996949},"labels":[],"label_agreement":null},{"id":"W4360977532","doi":"10.2139/ssrn.4399146","title":"Assessing the Reporting Quality of Early Phase Dose-Finding Trial Protocols: A Methodological Study","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"","keywords":"Quality (philosophy); Phase (matter); Medical physics; Medicine; Psychology; Epistemology; Chemistry; Philosophy","score_opus":0.9540272095614603,"score_gpt":0.7637354314740533,"score_spread":0.19029177808740694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360977532","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5527427,0.00004545883,0.4205854,0.00029531875,0.0013754297,0.024646344,0.000016033764,0.00015861214,0.00013465725],"genre_scores_gemma":[0.47812757,0.000081691134,0.50946146,0.000025884598,0.0037732653,0.0080112545,0.0000022440995,0.00020972839,0.0003069082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92921084,0.04427327,0.017902663,0.0015507335,0.0029837822,0.0040787156],"domain_scores_gemma":[0.7942433,0.17374578,0.029179534,0.0018850468,0.0007171025,0.00022927314],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.37196115,0.00062354346,0.0035250636,0.00022128005,0.0004996426,0.00057747087,0.0016790873,0.00073260564,0.00005063191],"category_scores_gemma":[0.6792603,0.00039021918,0.0013328162,0.0005077371,0.00029865606,0.00014014237,0.001263702,0.014884899,0.0000054359352],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07457551,0.016631028,0.009583433,0.0020435199,0.011419976,0.0004001569,0.0046141394,0.00009435081,0.0013934732,0.5788645,0.00018118293,0.30019867],"study_design_scores_gemma":[0.025914805,0.003548668,0.0013322006,0.00049125106,0.00059516076,0.000052827585,0.0036136094,0.00005658531,0.000060797418,0.9639384,0.000004790618,0.00039087553],"about_ca_topic_score_codex":0.00012505065,"about_ca_topic_score_gemma":0.00006529961,"teacher_disagreement_score":0.3850739,"about_ca_system_score_codex":0.0010003,"about_ca_system_score_gemma":0.005479775,"threshold_uncertainty_score":0.999855},"labels":[],"label_agreement":null},{"id":"W4361269722","doi":"10.1080/19466315.2023.2197402","title":"Application of Group Sequential Methods to the 2-in-1 Design and Its Extensions for Interim Monitoring","year":2023,"lang":"en","type":"article","venue":"Statistics in Biopharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Interim; Interim analysis; Group (periodic table); Adaptive design; Research design; Computer science; Reliability engineering; Medicine; Statistics; Risk analysis (engineering); Medical physics; Mathematics; Randomized controlled trial; Clinical trial; Engineering; Internal medicine; Political science; Chemistry","score_opus":0.9038046754759503,"score_gpt":0.7565153356159264,"score_spread":0.1472893398600239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361269722","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044273078,0.0000781246,0.9912073,0.0008124437,0.00038633306,0.0027513595,0.00027360022,0.000031298747,0.00003221376],"genre_scores_gemma":[0.10129122,0.0002203465,0.8973579,0.000027611493,0.00015234742,0.0008679338,0.0000028040777,0.000036921807,0.000042909054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933337,0.003794703,0.0009987764,0.0005119043,0.0006583885,0.0007025245],"domain_scores_gemma":[0.82175845,0.17729194,0.00007193394,0.0003100073,0.0003607041,0.0002069862],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032681674,0.00015104728,0.00046078273,0.0004129857,0.00011977694,0.000039890438,0.00043521775,0.00014479758,0.00002455295],"category_scores_gemma":[0.18266703,0.000117922566,0.000041573025,0.0014296448,0.0003058817,0.00003101149,0.00048404347,0.0007097338,0.000023710025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092510734,0.00022134992,0.00021529027,0.00056988554,0.0000347141,0.000023405235,0.00039930956,0.000092146045,0.08954758,0.70973223,0.00096383074,0.19727516],"study_design_scores_gemma":[0.00078745844,0.00023458489,0.001231418,0.000114760165,0.000023934537,0.0000013019927,0.00015281886,0.14290987,0.023709456,0.83013415,0.0005752034,0.00012505808],"about_ca_topic_score_codex":0.000017868619,"about_ca_topic_score_gemma":0.0000059385925,"teacher_disagreement_score":0.1971501,"about_ca_system_score_codex":0.00010678108,"about_ca_system_score_gemma":0.00007079803,"threshold_uncertainty_score":0.99605775},"labels":[],"label_agreement":null},{"id":"W4361270669","doi":"10.5539/ijsp.v12n2p42","title":"The Importance of Type II Error in Hypothesis Testing","year":2023,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Null hypothesis; Type I and type II errors; Alternative hypothesis; Null (SQL); Statistical hypothesis testing; Sample size determination; Statistical power; Statistics; Mathematics; p-value; Nominal level; Inference; Statistical significance; Sample (material); Type (biology); Econometrics; Statistical inference; Computer science; Confidence interval; Artificial intelligence; Data mining","score_opus":0.5385117902769211,"score_gpt":0.5303622478039222,"score_spread":0.008149542472998927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361270669","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97948617,0.00007313526,0.016156724,0.0018942432,0.0012048724,0.0002581204,0.0003400969,0.00001376319,0.0005728788],"genre_scores_gemma":[0.28622743,0.00008874083,0.7135249,0.00002758941,0.00009360641,0.0000021678882,3.1133928e-7,0.00000755859,0.000027735567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798775,0.00023609567,0.0011390866,0.000102224294,0.00042089896,0.000113953975],"domain_scores_gemma":[0.92968374,0.068599544,0.0006520352,0.00011779128,0.00090024166,0.000046667075],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005409947,0.00007217747,0.0002726829,0.000059601894,0.000047937356,0.000022192844,0.00027215434,0.000041187533,0.00003821169],"category_scores_gemma":[0.27179602,0.00004758309,0.000036764726,0.00020433709,0.0001962169,0.000035718156,0.00011005169,0.00018550243,0.0000010490118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008722408,0.0004026877,0.21133819,0.00022351234,0.00027825648,0.000129892,0.00052667136,0.00009369684,0.0003821825,0.5080719,0.0041533397,0.27352744],"study_design_scores_gemma":[0.00030586877,0.00015301401,0.06796438,0.000071770366,0.000016140704,0.0000102705035,0.000032252065,0.0010651777,0.000048509355,0.9301614,0.00012788139,0.00004330899],"about_ca_topic_score_codex":0.000008014166,"about_ca_topic_score_gemma":0.000029226052,"teacher_disagreement_score":0.69736814,"about_ca_system_score_codex":0.00004005663,"about_ca_system_score_gemma":0.00009797075,"threshold_uncertainty_score":0.734338},"labels":[],"label_agreement":null},{"id":"W4361293897","doi":"10.1136/bmjopen-2022-068173","title":"SPIRIT and CONSORT extensions for early phase dose-finding clinical trials: the DEFINE (DosE-FIndiNg Extensions) study protocol","year":2023,"lang":"en","type":"article","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; University of Toronto; Institute of Cancer Research","funders":"National Center for Advancing Translational Sciences; Medical Research Council; National Institute for Health and Care Research; Cancer Research UK; National Institutes of Health; UK Research and Innovation","keywords":"Consolidated Standards of Reporting Trials; Medicine; Protocol (science); Clinical trial; Delphi method; Transparency (behavior); Psychological intervention; Alternative medicine; Research ethics; Checklist; Citation; Multidisciplinary approach; Family medicine; Medical education; Medical physics; Pathology; Nursing; Library science; Psychology; Computer science","score_opus":0.9555482932110939,"score_gpt":0.7833121367096345,"score_spread":0.1722361565014594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361293897","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081657626,0.000006661837,0.012994008,0.0040235054,0.0013742067,0.898163,0.00031364532,0.00033870604,0.0011286216],"genre_scores_gemma":[0.01195807,0.0000064285787,0.35569048,0.00069526344,0.0012695444,0.6283261,0.00000705412,0.00017872037,0.0018683294],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9815181,0.010090916,0.005483144,0.0012637558,0.00083070446,0.00081338023],"domain_scores_gemma":[0.7146706,0.2815418,0.0015366275,0.0015238776,0.0003402351,0.00038686412],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13135765,0.0004512812,0.0026603155,0.00016650473,0.0008729726,0.00059404713,0.0011537364,0.00033082304,0.00032373684],"category_scores_gemma":[0.5956945,0.00028392058,0.00048129683,0.00071710703,0.00040387476,0.00019467201,0.001690975,0.0006500806,0.00013394104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042768035,0.014357458,0.034549836,0.001677094,0.003178174,0.001135331,0.0032130766,0.00000974677,0.0012698295,0.25828874,0.27604353,0.36350912],"study_design_scores_gemma":[0.06779463,0.0059066247,0.030821845,0.0011663021,0.0015082195,0.00004844286,0.002482463,0.0024544606,0.00011453263,0.8722168,0.0143886935,0.0010969376],"about_ca_topic_score_codex":0.000032291533,"about_ca_topic_score_gemma":0.000032289005,"teacher_disagreement_score":0.6139281,"about_ca_system_score_codex":0.00003164411,"about_ca_system_score_gemma":0.00032623,"threshold_uncertainty_score":0.9999613},"labels":[],"label_agreement":null},{"id":"W4362455928","doi":"10.1002/sim.9709","title":"New late‐emphasis and combination tests based on infimum and supremum logrank statistics with application in oncology trials","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ligue Contre le Cancer","keywords":"Infimum and supremum; Statistics; Log-rank test; Medicine; Clinical trial; Hazard; Survival analysis; Statistical hypothesis testing; Rank (graph theory); Computer science; Mathematics; Internal medicine","score_opus":0.36581877912489835,"score_gpt":0.575420074643495,"score_spread":0.20960129551859663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362455928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006754394,0.000033897504,0.9877119,0.0023998276,0.00035652437,0.0015036563,0.0006026272,0.00008543146,0.0005517373],"genre_scores_gemma":[0.04873318,0.0003094432,0.9498528,0.00045193057,0.00019963001,0.00012911977,0.00013712634,0.00005660196,0.00013013008],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952948,0.0015606455,0.001624921,0.00054804515,0.00058810634,0.00038349128],"domain_scores_gemma":[0.86313915,0.13575688,0.00045137617,0.00031648,0.0001355762,0.0002005342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0099542,0.0002889867,0.0014276998,0.00055454765,0.000056899113,0.000022690358,0.0001438955,0.00024072245,0.0001045245],"category_scores_gemma":[0.14537239,0.00022472668,0.000015658918,0.000862808,0.0004539839,0.000037385707,0.00005394918,0.00046459903,0.000009283803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013747901,0.00040385284,0.017827386,0.0006528243,0.000060735274,0.00025157645,0.0009676529,0.000120706536,0.00021223625,0.47212937,0.024074802,0.48192406],"study_design_scores_gemma":[0.010513413,0.0020320667,0.0372665,0.00037713724,0.00015066474,0.0000039753068,0.00012742216,0.03281161,0.00002187314,0.9158426,0.0006174169,0.0002353248],"about_ca_topic_score_codex":0.00026155685,"about_ca_topic_score_gemma":0.0007797392,"teacher_disagreement_score":0.48168874,"about_ca_system_score_codex":0.0001334833,"about_ca_system_score_gemma":0.0001789963,"threshold_uncertainty_score":0.9164088},"labels":[],"label_agreement":null},{"id":"W4362474550","doi":"10.3390/curroncol30040300","title":"Borrowing Concurrent Information from Non-Concurrent Control to Enhance Statistical Efficiency in Platform Trials","year":2023,"lang":"en","type":"article","venue":"Current Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Medicine; Protocol (science); Hazard ratio; Hazard; Clinical trial; Truncation (statistics); Statistics; Computer science; Confidence interval; Machine learning; Alternative medicine; Internal medicine; Mathematics; Pathology; Nursing","score_opus":0.6378450707136968,"score_gpt":0.6475387607399151,"score_spread":0.009693690026218338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362474550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049272783,0.0000965995,0.9325101,0.0007388095,0.012010792,0.002661772,0.0016888445,0.00023242127,0.0007879234],"genre_scores_gemma":[0.86449915,0.00023829352,0.1308365,0.0006437902,0.0017663362,0.001616669,0.00029036612,0.00007845416,0.000030422689],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99201626,0.0018527427,0.003805334,0.0006427274,0.0007332796,0.00094963727],"domain_scores_gemma":[0.884531,0.11366114,0.00076424907,0.00042962003,0.00019595756,0.00041799407],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012219506,0.00040756603,0.002262185,0.00044419445,0.00010166223,0.00007840372,0.00054393336,0.00033437856,0.0007249406],"category_scores_gemma":[0.20439568,0.00035350377,0.00022739265,0.0008508007,0.00018997077,0.00025033846,0.00025869053,0.0008556853,0.0017366202],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032812418,0.0006488082,0.00065819867,0.00019702585,0.00006001025,0.000023034461,0.0012756139,0.000059820373,0.00016815774,0.039997738,0.02891812,0.92766535],"study_design_scores_gemma":[0.019315174,0.0025000535,0.008171682,0.001278498,0.00057288975,0.0000050774606,0.0010502212,0.06147734,0.0015754019,0.73567814,0.16667071,0.0017048068],"about_ca_topic_score_codex":0.000028480703,"about_ca_topic_score_gemma":0.000024561956,"teacher_disagreement_score":0.92596054,"about_ca_system_score_codex":0.0005318268,"about_ca_system_score_gemma":0.00036175313,"threshold_uncertainty_score":0.9998917},"labels":[],"label_agreement":null},{"id":"W4362507535","doi":"10.1002/sim.9733","title":"Online error rate control for platform trials","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Innovative Medicines Initiative; Medical Research Council Canada; European Commission; Department of Health and Social Care; National Institute for Health and Care Research; Springworks Therapeutics; Medical Research Council; European Federation of Pharmaceutical Industries and Associations","keywords":"False discovery rate; Bonferroni correction; Word error rate; Computer science; Multiple comparisons problem; Type I and type II errors; Null hypothesis; Statistical hypothesis testing; Protocol (science); Control (management); Error detection and correction; Statistics; Artificial intelligence; Algorithm; Mathematics; Medicine","score_opus":0.7550225175797985,"score_gpt":0.6523072582200737,"score_spread":0.10271525935972481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362507535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013659557,0.000037909118,0.98219603,0.003179685,0.0025336677,0.002207299,0.007804569,0.0002010067,0.00047387287],"genre_scores_gemma":[0.0075113378,0.00013394094,0.98771113,0.0010945131,0.0017302596,0.0003044123,0.00020422666,0.00008998373,0.0012202109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941457,0.0012422103,0.0029552411,0.00048467887,0.00053597044,0.0006361849],"domain_scores_gemma":[0.70201445,0.2967349,0.0005039951,0.00037333957,0.00020924714,0.00016404485],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03278321,0.00030005156,0.0022935697,0.00030580332,0.00007933337,0.000014894248,0.00033438706,0.00021238835,0.0007267047],"category_scores_gemma":[0.7079838,0.000218111,0.000114584116,0.0005935699,0.00037069662,0.00003579993,0.000054103726,0.00040588502,0.000054789194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082206796,0.0002043928,0.00010096869,0.00048035503,0.00015089368,0.000096922726,0.00025210445,0.00001991175,0.00026992522,0.7780565,0.18616891,0.03337707],"study_design_scores_gemma":[0.011192204,0.0005902082,0.0010136005,0.00028045935,0.0002932817,0.0000018356685,0.00029406085,0.0139477635,0.000037715832,0.9687779,0.003347157,0.00022381007],"about_ca_topic_score_codex":0.000022106255,"about_ca_topic_score_gemma":0.00007929522,"teacher_disagreement_score":0.6752006,"about_ca_system_score_codex":0.00008824127,"about_ca_system_score_gemma":0.000098661076,"threshold_uncertainty_score":0.9959532},"labels":[],"label_agreement":null},{"id":"W4362640931","doi":"10.1016/j.jclinepi.2023.03.028","title":"Bypassing phase 2 in cancer drug development erodes the risk/benefit balance in phase 3 trials","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Clinical trial; Medicine; Randomized controlled trial; Clinical study design; Balance (ability); Intensive care medicine; Internal medicine; Physical therapy","score_opus":0.9540781456989651,"score_gpt":0.7867139564248123,"score_spread":0.16736418927415275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362640931","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009949291,0.9707039,0.016630396,0.001849212,0.007532366,0.0019211208,0.00027870806,0.000035413545,0.000053926397],"genre_scores_gemma":[0.000006729234,0.7738873,0.22242583,0.000405486,0.0028876713,0.00016636799,0.0000035636672,0.000094818184,0.00012222542],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.74491996,0.17685406,0.07432547,0.0014064522,0.0009326501,0.0015614198],"domain_scores_gemma":[0.08923134,0.87260914,0.0365141,0.00087156624,0.00029589015,0.00047796906],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.49476877,0.00084731716,0.035540003,0.00055746344,0.00010523293,0.00003403874,0.0017759319,0.0016789088,0.00030294512],"category_scores_gemma":[0.95222086,0.000447981,0.0038292918,0.0009857,0.00067016884,0.000090957175,0.00035253473,0.0076360065,0.000057768186],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060248846,0.0012810996,0.00082068273,0.0033769612,0.00088435825,0.0001616049,0.000058010613,0.000019690202,3.5746776e-8,0.003320369,0.0051368945,0.9843378],"study_design_scores_gemma":[0.009065119,0.00037784784,0.00027981348,0.031683188,0.0018051785,0.000029969084,0.000023327464,0.0002041627,3.5438015e-7,0.56116986,0.3948958,0.00046539612],"about_ca_topic_score_codex":0.000068597255,"about_ca_topic_score_gemma":0.00023549065,"teacher_disagreement_score":0.9838724,"about_ca_system_score_codex":0.00043126798,"about_ca_system_score_gemma":0.0023237956,"threshold_uncertainty_score":0.99979717},"labels":[],"label_agreement":null},{"id":"W4362658038","doi":"10.1002/sim.9734","title":"Point estimation for adaptive trial designs <scp>II</scp>: Practical considerations and guidance","year":2023,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research; Medical Research Council Canada; Department of Health and Social Care; Cancer Research UK; Health and Care Research Wales","keywords":"Estimation; Computer science; Point estimation; Point (geometry); Econometrics; Statistics; Mathematical optimization; Mathematics; Economics","score_opus":0.8358348090652867,"score_gpt":0.6690181020821543,"score_spread":0.16681670698313245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362658038","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9204883e-7,0.16793142,0.8216316,0.00025013014,0.0014499744,0.006058553,0.002288972,0.000099041885,0.0002901156],"genre_scores_gemma":[2.3284187e-7,0.37712643,0.6204691,0.00007244316,0.00071622734,0.001119161,0.00007811776,0.00010195403,0.0003163387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918244,0.0022871972,0.0037140287,0.000894611,0.0007150955,0.0005647039],"domain_scores_gemma":[0.6038005,0.39418584,0.0011149897,0.00041793648,0.00028421517,0.00019654333],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011382448,0.00063440925,0.0042334506,0.00036219548,0.00023441656,0.000049766713,0.00016156197,0.00063382846,0.000061962804],"category_scores_gemma":[0.81541,0.0004997159,0.00016139273,0.0004485203,0.00080034084,0.00007026196,0.00017669139,0.0010502394,0.000024402814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022791242,0.00013807043,6.011793e-8,0.009090702,0.00020919488,0.00011580333,0.00019012617,0.0000011002439,9.678866e-8,0.80224645,0.09175807,0.096022405],"study_design_scores_gemma":[0.009957608,0.0020683387,5.1193825e-7,0.012217984,0.0024049713,0.000047758036,0.00011063611,0.0023281476,4.590624e-7,0.9318815,0.038782205,0.00019990024],"about_ca_topic_score_codex":0.000013121862,"about_ca_topic_score_gemma":0.000036285353,"teacher_disagreement_score":0.80402756,"about_ca_system_score_codex":0.0002124077,"about_ca_system_score_gemma":0.0007533566,"threshold_uncertainty_score":0.9997454},"labels":[],"label_agreement":null},{"id":"W4366140941","doi":"10.1007/s43441-023-00520-6","title":"The Data Monitoring Committee: A Collective or a Collection?","year":2023,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"","keywords":"Session (web analytics); Unitary state; Pharmacy; Process (computing); Data collection; Psychology; Political science; Computer science; Public relations; Medical education; Operations research; Medicine; Family medicine; Law; Sociology; Engineering; World Wide Web","score_opus":0.7390566231936863,"score_gpt":0.5887758607498497,"score_spread":0.1502807624438366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366140941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78951395,0.00015028981,0.15980503,0.012892579,0.017129071,0.005667116,0.00015909613,0.0028047217,0.011878129],"genre_scores_gemma":[0.7774194,0.000052100084,0.20082742,0.00058158004,0.0008215603,0.00023193884,0.000004167295,0.00007759532,0.019984242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964438,0.0004749642,0.0008593544,0.0005789875,0.001143359,0.00049954664],"domain_scores_gemma":[0.9703255,0.026510028,0.00041288618,0.001774598,0.00090985827,0.000067099565],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.018929565,0.0001698422,0.00028270314,0.00036617392,0.0020207635,0.00025313563,0.0016814957,0.00008664482,0.000051490566],"category_scores_gemma":[0.04661053,0.000108079745,0.000027688839,0.015198844,0.001524518,0.0003287286,0.00048358217,0.00029280156,0.00006010398],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046631446,0.00012906762,0.0023695508,0.000043363063,0.00013901092,0.000007546246,0.001244961,0.00001197468,0.011002143,0.8399101,0.018291721,0.12638429],"study_design_scores_gemma":[0.00055950775,0.00011557626,0.02968325,0.00004632483,0.000030722713,0.0000074807435,0.0006734529,0.0053449096,0.0033700848,0.9561601,0.003805423,0.00020313248],"about_ca_topic_score_codex":0.000004612117,"about_ca_topic_score_gemma":0.0000048442384,"teacher_disagreement_score":0.12618116,"about_ca_system_score_codex":0.0002731273,"about_ca_system_score_gemma":0.0012035957,"threshold_uncertainty_score":0.9992785},"labels":[],"label_agreement":null},{"id":"W4366333690","doi":"10.7759/cureus.37799","title":"The Upper Limits of Risk Ratios and Recommendations for Reporting Risk Ratios, Odds Ratios, and Rate Ratios","year":2023,"lang":"en","type":"article","venue":"Cureus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Relative risk; Medicine; Confidence interval; Incidence (geometry); Odds ratio; Population; Risk factor; Statistics; Absolute risk reduction; Demography; Internal medicine; Mathematics; Environmental health","score_opus":0.5255270047310163,"score_gpt":0.555790130182481,"score_spread":0.0302631254514647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366333690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28757054,0.0011995606,0.6810924,0.014633864,0.0039102077,0.0070954137,0.0023946061,0.0006057565,0.0014976637],"genre_scores_gemma":[0.1260193,0.0060162316,0.86480117,0.0002427031,0.00086110574,0.0006557398,0.00006645006,0.00012559576,0.0012117025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948057,0.0014710502,0.0026215583,0.0004907832,0.00025152668,0.0003593604],"domain_scores_gemma":[0.8988637,0.09748579,0.002555225,0.00060943485,0.00035547907,0.00013039469],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012999051,0.00024981037,0.00068257836,0.00006451259,0.0007929807,0.00016513014,0.00019293839,0.00018976719,0.00006576189],"category_scores_gemma":[0.42785558,0.0001838083,0.00013880945,0.0003189077,0.00025159257,0.0001752331,0.00013010713,0.0003370417,0.000009027481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005973549,0.0003834371,0.027082838,0.00071066734,0.0012011536,0.000014153814,0.0060421657,0.00006203149,0.0040324978,0.59299135,0.15958172,0.2073006],"study_design_scores_gemma":[0.0014984851,0.00023210478,0.0060165357,0.000110863286,0.00046829702,0.000005840576,0.0010835974,0.0074235615,0.0038116556,0.9726581,0.006373973,0.00031701475],"about_ca_topic_score_codex":0.00002580267,"about_ca_topic_score_gemma":0.00015042143,"teacher_disagreement_score":0.41485652,"about_ca_system_score_codex":0.000029600209,"about_ca_system_score_gemma":0.00009886643,"threshold_uncertainty_score":0.7495485},"labels":[],"label_agreement":null},{"id":"W4366404590","doi":"10.28924/2291-8639-21-2023-36","title":"A Comparison of Nonparametric Statistics and Bootstrap Methods for Testing Two Independent Populations with Unequal Variance","year":2023,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Kasetsart University","keywords":"Nonparametric statistics; Statistics; Mathematics; Parametric statistics; Goldfeld–Quandt test; Statistical hypothesis testing; Sample size determination; Type I and type II errors; F-test of equality of variances; Normality; Variance (accounting); Econometrics; Z-test; Test statistic","score_opus":0.6456795734692238,"score_gpt":0.6713076971864439,"score_spread":0.02562812371722012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366404590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014985822,0.000044297885,0.984195,0.00019729011,0.000056455916,0.0002111041,0.00024903475,0.000010077012,0.000050917206],"genre_scores_gemma":[0.28886405,0.000019645307,0.71095747,0.000009717982,0.00008882825,0.000027317732,0.000007829182,0.000007644755,0.000017510372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980845,0.00017641563,0.0011178635,0.00016613772,0.0003524409,0.000102681675],"domain_scores_gemma":[0.97263855,0.02491184,0.0011451785,0.000128264,0.0010868082,0.000089359244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022626962,0.00009741756,0.0005619216,0.00055789156,0.00007373808,0.000055468023,0.00019922701,0.000044357548,0.00001350259],"category_scores_gemma":[0.010656248,0.000077357785,0.000096292664,0.0012221114,0.000105520616,0.000055867957,0.000049482704,0.000117198026,3.668201e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001399563,0.0004309384,0.07762757,0.00007492466,0.003004695,0.0000032266087,0.00017405458,0.004152058,0.0010383202,0.58910453,0.0001650048,0.3240847],"study_design_scores_gemma":[0.0010190352,0.00021443701,0.049520787,0.00004707248,0.0023139855,0.000010546367,0.00018668042,0.096750244,0.0003389684,0.8492526,0.00021720827,0.00012844765],"about_ca_topic_score_codex":0.0000192708,"about_ca_topic_score_gemma":0.000016740478,"teacher_disagreement_score":0.32395625,"about_ca_system_score_codex":0.000022404503,"about_ca_system_score_gemma":0.000050018018,"threshold_uncertainty_score":0.9976774},"labels":[],"label_agreement":null},{"id":"W4366422437","doi":"10.1002/cjs.11771","title":"Finite sample and asymptotic distributions of a statistic for sufficient follow‐up in cure models","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Censoring (clinical trials); Statistic; Test statistic; Asymptotic distribution; Mathematics; Statistics; Sample (material); Population; Asymptotic analysis; Kaplan–Meier estimator; Null distribution; Sample size determination; Null hypothesis; Applied mathematics; Statistical hypothesis testing; Estimator; Medicine; Physics","score_opus":0.4727748261641168,"score_gpt":0.47982800150954663,"score_spread":0.0070531753454298185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366422437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008993835,0.000049344922,0.95471394,0.00023412208,0.0006169245,0.00034941483,0.035007317,0.000006236041,0.000028879997],"genre_scores_gemma":[0.26813856,0.000050015955,0.7315852,0.00002878096,0.00006171439,0.000011356743,0.000043074266,0.000028893646,0.00005241876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99706066,0.0002999134,0.001683918,0.00018844112,0.0003083099,0.0004587866],"domain_scores_gemma":[0.9124004,0.08562819,0.00062923186,0.00020985784,0.00059397664,0.0005383221],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031041577,0.0001705676,0.0007980662,0.00040718433,0.000097821016,0.000044762965,0.00023115368,0.00011392617,0.00009155407],"category_scores_gemma":[0.19650838,0.0001595642,0.000099054225,0.00050107506,0.00027696596,0.000059953512,0.000024030118,0.0002784755,0.0000023553227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007965051,0.00005351902,0.0016372637,0.00038524432,0.000088798166,0.00011406783,0.0008496527,0.0018002666,0.000008947781,0.9720672,0.01794639,0.0049690492],"study_design_scores_gemma":[0.0014011381,0.00033243804,0.0018007944,0.0001998365,0.00014368384,0.000008395348,0.00027171124,0.043295737,0.00001353593,0.9519869,0.00039895723,0.00014684831],"about_ca_topic_score_codex":0.0006327847,"about_ca_topic_score_gemma":0.0066906903,"teacher_disagreement_score":0.25914472,"about_ca_system_score_codex":0.0001453702,"about_ca_system_score_gemma":0.0010392879,"threshold_uncertainty_score":0.81025976},"labels":[],"label_agreement":null},{"id":"W4366463553","doi":"10.1177/09622802231163332","title":"Design and analysis of factorial clinical trials: The impact of one treatment's effectiveness on the statistical power and required sample size of the other","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Statistics; Statistical power; Factorial; Factorial experiment; Multiplicative function; Mathematics; Odds ratio; Outcome (game theory); Treatment effect; Type I and type II errors; Treatment and control groups; Power (physics); Sample (material); Econometrics; Medicine; Physics","score_opus":0.8881970642432903,"score_gpt":0.7718697113697441,"score_spread":0.11632735287354612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366463553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041610353,0.000055821896,0.9524916,0.00083061267,0.00033065764,0.0024815637,0.0020229856,0.000017927014,0.00015850525],"genre_scores_gemma":[0.26371467,0.00023789344,0.7356285,0.000030588773,0.0001266123,0.00019354188,0.000003138878,0.000049475126,0.000015599764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.77940005,0.21116237,0.0042582927,0.0009101261,0.0033684017,0.0009007379],"domain_scores_gemma":[0.09020383,0.90724814,0.0006342615,0.001094748,0.00040958915,0.00040941397],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.273307,0.00033802478,0.0033079986,0.00032360328,0.00016552207,0.00003938275,0.0008460236,0.0005214373,0.0022678254],"category_scores_gemma":[0.95122373,0.00014124655,0.00052343105,0.0029093034,0.006916928,0.000027336131,0.00050962163,0.0014805964,0.0000023582465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0088712545,0.0018511943,0.008257153,0.0003128464,0.005007685,0.000022898575,0.000768054,0.000022149441,0.001319182,0.6459989,0.00082161947,0.3267471],"study_design_scores_gemma":[0.0021789984,0.0024988374,0.13359167,0.00022870467,0.0008022616,7.045298e-7,0.00014091215,0.011251961,0.0007402705,0.8484177,0.000022036227,0.00012596075],"about_ca_topic_score_codex":0.00080026954,"about_ca_topic_score_gemma":0.000022876,"teacher_disagreement_score":0.6960858,"about_ca_system_score_codex":0.0001250269,"about_ca_system_score_gemma":0.00065052963,"threshold_uncertainty_score":0.99864423},"labels":[],"label_agreement":null},{"id":"W4375947893","doi":"10.1016/j.annepidem.2023.05.004","title":"The application of lag times in cancer pharmacoepidemiology: a narrative review","year":2023,"lang":"en","type":"review","venue":"Annals of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; McGill University Health Centre","funders":"","keywords":"Medicine; Pharmacoepidemiology; Narrative review; Narrative; Lag; Internal medicine; Intensive care medicine; Pharmacology; Linguistics","score_opus":0.9266390608503267,"score_gpt":0.766301925030867,"score_spread":0.16033713581945963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375947893","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.8153936e-7,0.98954004,0.0021222671,0.0047570504,0.00038843663,0.0024466275,0.00032051472,0.000032614822,0.0003919665],"genre_scores_gemma":[2.3733335e-7,0.968983,0.027493602,0.0011962717,0.00022712434,0.0018359239,0.000019535599,0.000058397334,0.00018591151],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9540447,0.03459521,0.009447074,0.00087056856,0.00020290239,0.0008395172],"domain_scores_gemma":[0.45890358,0.5340376,0.0057362467,0.0009158084,0.0003026448,0.000104117054],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07857783,0.0004675454,0.0104396725,0.00015676032,0.000052265605,0.0000011758679,0.0009982641,0.0007294703,0.00014243803],"category_scores_gemma":[0.67920506,0.00027112677,0.0011600287,0.0008260906,0.0009243392,0.000023268889,0.00025924138,0.0009470234,0.000042330666],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021833324,0.00005945824,0.000020653843,0.05843894,0.0004920349,0.0000016113954,0.000021606053,9.860968e-7,9.920143e-8,0.1420343,0.09484254,0.7040659],"study_design_scores_gemma":[0.00006761595,0.000053882202,0.000004772798,0.027806342,0.00041616548,0.0000020680345,0.0000058235123,0.00002299605,6.8625076e-7,0.5187729,0.45271656,0.00013018897],"about_ca_topic_score_codex":0.00017291935,"about_ca_topic_score_gemma":0.000041263433,"teacher_disagreement_score":0.70393574,"about_ca_system_score_codex":0.000036229005,"about_ca_system_score_gemma":0.0002844365,"threshold_uncertainty_score":0.9999741},"labels":[],"label_agreement":null},{"id":"W4377862454","doi":"10.5539/ijsp.v12n3p1","title":"The Just-About-Right Pilot Sample Size to Control the Error Margin","year":2023,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sample size determination; Sample (material); Margin (machine learning); Control (management); Statistics; Minimal clinically important difference; Computer science; Mathematics; Randomized controlled trial; Medicine; Artificial intelligence; Machine learning; Surgery","score_opus":0.3441206393443927,"score_gpt":0.5175251064445082,"score_spread":0.17340446710011553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377862454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040857427,0.00006818028,0.9127334,0.037088703,0.0043457244,0.0010000868,0.003493548,0.000039616676,0.00037334274],"genre_scores_gemma":[0.25762567,0.0001522032,0.7402779,0.00089529145,0.00076189643,0.000032407614,0.0000015442656,0.00002342729,0.00022966471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968199,0.00073234644,0.0011993593,0.00018179574,0.0008292972,0.00023726902],"domain_scores_gemma":[0.81901175,0.17919579,0.00046753837,0.00023193966,0.0009487534,0.0001442449],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008583785,0.00014295532,0.00035673694,0.000041204912,0.0002067424,0.00019417657,0.00068371854,0.00004663693,0.00023351978],"category_scores_gemma":[0.2624391,0.00007340876,0.000090599744,0.00015139677,0.0003191526,0.00004622576,0.00014749379,0.00035378995,0.00001663786],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001334541,0.00019414761,0.0016788798,0.00005518151,0.00041637995,0.00005003643,0.0003199689,0.000061619554,0.000067829154,0.9073483,0.039140742,0.04933241],"study_design_scores_gemma":[0.00089332374,0.00031512426,0.020918082,0.000043707376,0.000070198155,0.000017399772,0.000055327546,0.0007108171,0.000024512832,0.96813756,0.008726024,0.00008793699],"about_ca_topic_score_codex":0.000023810453,"about_ca_topic_score_gemma":0.00005580953,"teacher_disagreement_score":0.25385532,"about_ca_system_score_codex":0.000072769435,"about_ca_system_score_gemma":0.00011152694,"threshold_uncertainty_score":0.7437737},"labels":[],"label_agreement":null},{"id":"W4379386960","doi":"10.1080/00949655.2023.2219359","title":"Confidence intervals for the cross product ratio under the special case of direct-inverse sampling scheme and its applications","year":2023,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Regina","funders":"","keywords":"Mathematics; Confidence interval; Statistics; Estimator; Sampling (signal processing); Inverse; Credible interval; Coverage probability; Computer science","score_opus":0.5526817099489584,"score_gpt":0.5964679837013607,"score_spread":0.043786273752402294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379386960","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024481047,0.000048827478,0.9737831,0.00060615136,0.00023442616,0.0007016823,0.000106830375,0.000012224147,0.000025733394],"genre_scores_gemma":[0.74029064,0.000031252166,0.25897518,0.00006648082,0.0005862245,0.000015401263,0.0000026951116,0.000010926727,0.000021198604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982089,0.00030840284,0.00097127474,0.00015183631,0.00024478513,0.00011479405],"domain_scores_gemma":[0.89833236,0.10032574,0.00054734957,0.00008863644,0.00064167613,0.00006424188],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033192073,0.00009875658,0.0003128084,0.00006055572,0.00025014984,0.00009383819,0.00008212087,0.0000478419,0.00002722216],"category_scores_gemma":[0.030035932,0.00006001481,0.000055830118,0.00019917572,0.00023098689,0.00009961686,0.000041740375,0.00016552792,0.0000016417814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003509271,0.000079008714,0.00007702364,0.00033000865,0.00014032613,0.000011815928,0.00071513816,0.10770044,0.00021121309,0.8480903,0.00058758864,0.041706234],"study_design_scores_gemma":[0.0004780342,0.00007633492,0.0009986563,0.000029245615,0.00008536706,0.000027763957,0.00020480946,0.48015627,0.000045818862,0.5177666,0.000084490166,0.00004662339],"about_ca_topic_score_codex":0.0000021889632,"about_ca_topic_score_gemma":0.000004166402,"teacher_disagreement_score":0.7158096,"about_ca_system_score_codex":0.000018863459,"about_ca_system_score_gemma":0.000045716475,"threshold_uncertainty_score":0.9781345},"labels":[],"label_agreement":null},{"id":"W4379509156","doi":"10.1177/09622802231176034","title":"qTPI: A quasi-toxicity probability interval design for phase I trials with multiple-grade toxicities","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Science Foundation of Shanghai","keywords":"Toxicity; Dosing; Confidence interval; Interval (graph theory); Computer science; Common Terminology Criteria for Adverse Events; Clinical study design; Medicine; Clinical trial; Statistics; Mathematics; Internal medicine","score_opus":0.9107704970381562,"score_gpt":0.7548613736585712,"score_spread":0.15590912337958496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379509156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034513804,0.000037289647,0.9846308,0.0032707718,0.00058307935,0.0063640885,0.0010031057,0.0003332169,0.00032622693],"genre_scores_gemma":[0.0067111473,0.00007325126,0.9882736,0.0001834309,0.00059903256,0.0037761016,0.000022817323,0.00013917558,0.0002214086],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8825397,0.101149954,0.0052938764,0.00216584,0.0057947473,0.0030559006],"domain_scores_gemma":[0.14068578,0.8553674,0.0003923842,0.0011609754,0.00086994516,0.0015234771],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33759516,0.0005944681,0.003563443,0.0007524549,0.0003531394,0.00017340072,0.0014535974,0.00088898325,0.0026265902],"category_scores_gemma":[0.96562254,0.00041416116,0.00035395043,0.0025742573,0.0038883945,0.00011841761,0.0006479181,0.003119671,0.00006261634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008949317,0.0034374513,0.000105028455,0.0015617061,0.00022647285,0.0003951189,0.00052041974,0.0000070497586,0.00078238687,0.375492,0.011115981,0.59740704],"study_design_scores_gemma":[0.008948881,0.004460663,0.000160718,0.0006012379,0.000089411864,0.000011276276,0.00047341865,0.06562958,0.003564207,0.9147259,0.00088893395,0.00044578],"about_ca_topic_score_codex":0.000065506836,"about_ca_topic_score_gemma":0.00007895413,"teacher_disagreement_score":0.7542175,"about_ca_system_score_codex":0.00040371247,"about_ca_system_score_gemma":0.0013038144,"threshold_uncertainty_score":0.999831},"labels":[],"label_agreement":null},{"id":"W4380577504","doi":"10.1017/cts.2023.542","title":"Concurrent dose-finding of a novel cancer drug with and without a second agent","year":2023,"lang":"en","type":"article","venue":"Journal of Clinical and Translational Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute; American Society of Clinical Oncology; American Association for Cancer Research","keywords":"Medicine; Clinical trial; Flexibility (engineering); Maximum tolerated dose; Clinical Oncology; Cancer; Medical physics; Research design; Clinical study design; Oncology; Computer science; Internal medicine; Mathematics","score_opus":0.700391225347021,"score_gpt":0.6334065225304991,"score_spread":0.06698470281652191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380577504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97687674,0.00009386342,0.020950481,0.0012525856,0.00042981384,0.00013523313,0.000049643375,0.0000066240664,0.00020503342],"genre_scores_gemma":[0.8465486,0.00010633899,0.15308203,0.000051848787,0.00015779243,0.0000019693,8.723757e-8,0.000005239276,0.000046099743],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974134,0.00012734723,0.0013499744,0.00020240057,0.0007466573,0.00016020381],"domain_scores_gemma":[0.98401934,0.01471345,0.0006689611,0.0000711053,0.00028853642,0.00023861023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008729467,0.00009104858,0.00056089036,0.00010027289,0.000084791245,0.000029492388,0.00016253923,0.00004663892,0.00006714598],"category_scores_gemma":[0.0079789655,0.000055650602,0.00008631728,0.00040443154,0.0013222487,0.00015376201,0.000032254058,0.0002805283,4.4134444e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008840601,0.0007900912,0.6199038,0.0005297347,0.00027595222,0.000019800304,0.0014212673,0.00009951816,0.0020326131,0.17213689,0.0002548444,0.2016514],"study_design_scores_gemma":[0.0061084386,0.00042393457,0.69998384,0.00054260524,0.00018446129,0.00004131197,0.000084804255,0.0046325456,0.00027349836,0.28711644,0.00043022714,0.00017791503],"about_ca_topic_score_codex":0.000003197629,"about_ca_topic_score_gemma":0.000015770624,"teacher_disagreement_score":0.20147347,"about_ca_system_score_codex":0.000004526396,"about_ca_system_score_gemma":0.00032915012,"threshold_uncertainty_score":0.9552143},"labels":[],"label_agreement":null},{"id":"W4380589797","doi":"10.1002/sim.9811","title":"Sample size considerations for assessing treatment effect heterogeneity in randomized trials with heterogeneous intracluster correlations and variances","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Patient-Centered Outcomes Research Institute","keywords":"Sample size determination; Univariate; Randomized controlled trial; Statistics; Context (archaeology); Cluster (spacecraft); Multivariate statistics; Sample (material); Outcome (game theory); Econometrics; Mathematics; Computer science; Medicine; Internal medicine","score_opus":0.48912071704197413,"score_gpt":0.5797179367516512,"score_spread":0.09059721970967705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380589797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032732632,0.00007929681,0.9603394,0.0009900852,0.00058648386,0.004120388,0.0010016423,0.00007193446,0.000078083205],"genre_scores_gemma":[0.16136117,0.00015877165,0.83718294,0.000118184274,0.0001979451,0.0008960073,0.00002388906,0.000035325,0.000025745625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992157,0.00472121,0.00200772,0.00045454202,0.0003034814,0.00035604756],"domain_scores_gemma":[0.3944357,0.6048154,0.00036996463,0.00020418505,0.00008654202,0.000088193876],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018010145,0.00029798457,0.002973555,0.00020985708,0.00013063647,0.000056994664,0.0000662473,0.0001373914,0.0001595589],"category_scores_gemma":[0.732293,0.00018149734,0.00008602524,0.00031665046,0.00055260066,0.000050469942,0.000030428982,0.00018762004,0.0000020311895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07525103,0.0013254489,0.020760683,0.0027422078,0.0028445153,0.0010638288,0.0074488437,0.003714794,0.0004810227,0.765307,0.006209493,0.112851106],"study_design_scores_gemma":[0.09769481,0.00068148883,0.0008639222,0.00032546735,0.0005762226,0.000013671185,0.00007065996,0.022574648,0.00008626549,0.8769284,0.000015464506,0.00016899749],"about_ca_topic_score_codex":0.00013110008,"about_ca_topic_score_gemma":0.0006604456,"teacher_disagreement_score":0.7142829,"about_ca_system_score_codex":0.00010616913,"about_ca_system_score_gemma":0.000098790755,"threshold_uncertainty_score":0.74012464},"labels":[],"label_agreement":null},{"id":"W4380728286","doi":"10.1002/pst.2318","title":"Alone, together: On the benefits of Bayesian borrowing in a meta‐analytic setting","year":2023,"lang":"en","type":"review","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Veterinarians of British Columbia; NeuroDevNet","funders":"","keywords":"Bayes' theorem; Bayesian probability; Randomized controlled trial; Inference; Sample size determination; Bayesian inference; Econometrics; Fraction (chemistry); Bayesian hierarchical modeling; Randomized response; Meta-analysis; Bayes factor; Statistics; Computer science; Mathematics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.8273449729662699,"score_gpt":0.6381815326863675,"score_spread":0.1891634402799024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380728286","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012514819,0.893301,0.09223382,0.00047611995,0.00091505883,0.0036780797,0.007871975,0.00020038588,0.0013222703],"genre_scores_gemma":[0.00000683319,0.72847843,0.2703133,0.000249664,0.000261946,0.0003229724,0.000020968302,0.00022939444,0.00011649335],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878164,0.0050267903,0.004016462,0.0009343748,0.001233049,0.00097290735],"domain_scores_gemma":[0.72298086,0.27490532,0.0009625757,0.0007749011,0.00012328984,0.00025302323],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011753892,0.00092188007,0.006034459,0.00032161962,0.00012102135,0.00007383463,0.0011030494,0.00052773725,0.0009799164],"category_scores_gemma":[0.16679256,0.0005680187,0.0010978057,0.001349339,0.00040087852,0.00003513862,0.00040033928,0.002301235,0.00020446033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029840274,0.00023302535,0.0000017860012,0.02040976,0.0034457105,0.00008473839,0.000048127473,0.000011232887,1.1859821e-7,0.48420757,0.0019665454,0.48956153],"study_design_scores_gemma":[0.0006519111,0.00013379221,0.0000022240306,0.012193061,0.035306584,0.000012089826,0.000025825528,0.0023539762,0.000014734296,0.8498337,0.098603904,0.00086816587],"about_ca_topic_score_codex":0.000020443742,"about_ca_topic_score_gemma":0.000017117802,"teacher_disagreement_score":0.4886934,"about_ca_system_score_codex":0.00018947628,"about_ca_system_score_gemma":0.00025890407,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W4380994339","doi":"10.48550/arxiv.2306.09151","title":"Estimating the Sampling Distribution of Posterior Decision Summaries in Bayesian Clinical Trials","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Posterior probability; Bayesian probability; Sample size determination; Statistics; Bayesian linear regression; Computer science; Sampling (signal processing); Bayesian statistics; Prior probability; Bayes factor; Statistical inference; Bayesian hierarchical modeling; Sampling distribution; Posterior predictive distribution; Parametric statistics; Statistical hypothesis testing; Econometrics; Bayesian inference; Mathematics","score_opus":0.8372758867953959,"score_gpt":0.5268001536986172,"score_spread":0.31047573309677867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380994339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30889577,0.000011350516,0.68774086,0.0001070694,0.0018147625,0.00080033665,0.0005067222,0.00008619335,0.000036905032],"genre_scores_gemma":[0.69561857,0.00006940231,0.30382746,0.0000196573,0.00031242167,0.000003853825,0.000036561436,0.000043460554,0.000068613124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886796,0.006394333,0.003279548,0.0010208115,0.00023484361,0.00039086505],"domain_scores_gemma":[0.69671035,0.29902986,0.0023930008,0.0014259799,0.0002796841,0.00016111504],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036842473,0.00035653758,0.0021541244,0.00015183877,0.00012667489,0.00007294241,0.0010321385,0.0006637456,0.000063452426],"category_scores_gemma":[0.4373286,0.00028682104,0.00077944953,0.0006101387,0.00050269207,0.000070785805,0.001687966,0.0013703489,0.000020021096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053956527,0.0013264954,0.08217474,0.002622991,0.001324166,0.0006326962,0.0005165153,0.12583195,0.00004350634,0.68038,0.0020467266,0.09770461],"study_design_scores_gemma":[0.000969138,0.00006996499,0.0070402427,0.0011588684,0.00038237913,0.0000010637823,0.00010404531,0.11537108,0.00001895459,0.8746291,0.000014382505,0.0002407959],"about_ca_topic_score_codex":0.00012191394,"about_ca_topic_score_gemma":0.000100414,"teacher_disagreement_score":0.4004861,"about_ca_system_score_codex":0.00016880211,"about_ca_system_score_gemma":0.00022839649,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W4381309562","doi":"10.1177/09622802231181220","title":"Two-stage multivariate Mendelian randomization on multiple outcomes with mixed distributions","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre; Queen's University; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Mendelian randomization; Multivariate statistics; Univariate; Confounding; Causal inference; Instrumental variable; Multivariate analysis; Statistics; Outcome (game theory); Computer science; Econometrics; Randomized controlled trial; Medicine; Mathematics; Genetic variants; Internal medicine; Biology","score_opus":0.7000715705924438,"score_gpt":0.7152868082466625,"score_spread":0.015215237654218616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381309562","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025629313,0.0000063723082,0.9869063,0.0034684278,0.0005976027,0.0016559244,0.00096964167,0.0002962673,0.0035365364],"genre_scores_gemma":[0.028121937,0.000044722565,0.96986175,0.00015499756,0.00018367259,0.00072607404,0.00007336051,0.000099765915,0.0007337004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9633978,0.027149428,0.0020037435,0.0012281645,0.0044489778,0.0017718739],"domain_scores_gemma":[0.4865016,0.51128376,0.0001473543,0.00075455947,0.0003976696,0.00091508543],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07379348,0.00043359393,0.0015823734,0.0007372818,0.0003778396,0.000111007736,0.0008707349,0.00048115835,0.003619515],"category_scores_gemma":[0.8807,0.00029619047,0.00014835907,0.0031144342,0.0016453629,0.00007753533,0.00050506566,0.0028962153,0.0003115191],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022045497,0.00073059206,0.0017809899,0.00018785975,0.00012088695,0.0006161622,0.00010763949,0.00003416848,0.00016152106,0.81842536,0.0026966417,0.17293361],"study_design_scores_gemma":[0.014973892,0.00051460275,0.012005628,0.00034330558,0.00004356121,0.0000036448428,0.00028790176,0.054240763,0.000622378,0.9153537,0.001212612,0.00039798053],"about_ca_topic_score_codex":0.00022715113,"about_ca_topic_score_gemma":0.00018849419,"teacher_disagreement_score":0.8069065,"about_ca_system_score_codex":0.00029865777,"about_ca_system_score_gemma":0.00047543304,"threshold_uncertainty_score":0.99994904},"labels":[],"label_agreement":null},{"id":"W4381434989","doi":"10.3390/curroncol30060443","title":"Characteristics of Phase IV Clinical Trials in Oncology: An Analysis Using the ClinicalTrials.gov Registry Data","year":2023,"lang":"en","type":"article","venue":"Current Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Clinical trial; Adverse effect; Psychological intervention; Internal medicine; Clinical Oncology; Sample size determination; Oncology; Cancer; Intensive care medicine","score_opus":0.9697628496947025,"score_gpt":0.7983529685784945,"score_spread":0.17140988111620803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381434989","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8710501,0.00017290212,0.10714469,0.0018665516,0.013258201,0.0024300113,0.003661054,0.00019030787,0.000226153],"genre_scores_gemma":[0.34693283,0.0066244705,0.6310409,0.0006918375,0.012857243,0.00026780198,0.0012589125,0.00022069272,0.000105358195],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9175575,0.06490339,0.014317077,0.0015891925,0.0007637049,0.0008691529],"domain_scores_gemma":[0.35952663,0.6268635,0.007915604,0.0047292453,0.00046362568,0.0005014273],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2159605,0.0003697231,0.0066868616,0.00046083482,0.000116195806,0.000041448224,0.00235764,0.0009947495,0.00039575994],"category_scores_gemma":[0.7470762,0.0002596784,0.00091473473,0.0022246,0.0012867245,0.00012835697,0.0011720607,0.0016834792,0.000034988192],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004331924,0.01278039,0.047371082,0.00030426835,0.0019226259,0.00017535119,0.00040517355,0.000016739252,0.00016976155,0.01391463,0.012182715,0.90642536],"study_design_scores_gemma":[0.037484977,0.0065743546,0.031169811,0.000449962,0.024657112,0.000023700642,0.0016967165,0.24375243,0.00006795089,0.5316304,0.12109158,0.0014010363],"about_ca_topic_score_codex":0.00002242553,"about_ca_topic_score_gemma":0.00008541604,"teacher_disagreement_score":0.9050243,"about_ca_system_score_codex":0.00022526197,"about_ca_system_score_gemma":0.0011553126,"threshold_uncertainty_score":0.9999855},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4381469694","doi":"10.1002/sim.9831","title":"Permutation‐based multiple testing corrections for P$$ P $$‐values and confidence intervals for cluster randomized trials","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research","keywords":"Confidence interval; Statistics; Permutation (music); Resampling; Bonferroni correction; Multiple comparisons problem; Mathematics; Inference; Standard error; Type I and type II errors; Confidence distribution; Statistical hypothesis testing; Computer science; Artificial intelligence","score_opus":0.7094685578629825,"score_gpt":0.6281742164474525,"score_spread":0.08129434141552994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381469694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008237105,0.00004244618,0.98890656,0.0016038677,0.0017246035,0.005177015,0.0014596793,0.00013574316,0.00012637072],"genre_scores_gemma":[0.012789611,0.00003256614,0.98378086,0.00050660205,0.00045696888,0.0018983958,0.00007549651,0.00005463664,0.00040488216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937644,0.0025096014,0.0025527664,0.00045486566,0.0003467974,0.00037158583],"domain_scores_gemma":[0.43456146,0.56422627,0.0005107617,0.00017982545,0.0004317337,0.000089976806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042812202,0.00024339193,0.0023702106,0.00029416967,0.00015767927,0.000034016528,0.00015822751,0.00013708688,0.000090021094],"category_scores_gemma":[0.94493717,0.00018276766,0.00012856987,0.00041058895,0.0007015463,0.000037845773,0.000045349894,0.00020171357,0.0000041619437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06825701,0.00035328345,0.0014640912,0.0050335946,0.0006135629,0.000027052865,0.004239385,0.0005699809,0.0012007643,0.62494135,0.18076773,0.1125322],"study_design_scores_gemma":[0.0805058,0.00023945096,0.000091211645,0.00049808196,0.0003328769,0.0000010298849,0.0002660627,0.26453942,0.00006186183,0.65327513,0.000060489325,0.0001285688],"about_ca_topic_score_codex":0.000053983706,"about_ca_topic_score_gemma":0.000054989112,"teacher_disagreement_score":0.902125,"about_ca_system_score_codex":0.000053683205,"about_ca_system_score_gemma":0.00008906563,"threshold_uncertainty_score":0.9856263},"labels":[],"label_agreement":null},{"id":"W4381852553","doi":"10.1101/2023.06.18.23291542","title":"An explainable machine learning-based phenomapping strategy for adaptive predictive enrichment in randomized controlled trials","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Center of Excellence in Regulatory Science and Innovation; Janssen Research and Development; National Institutes of Health; HLS Therapeutics; Idorsia Pharmaceuticals; Eisai; Moderna; Shenzhen Center for Health Information; St. Jude Medical; Regeneron Pharmaceuticals; Eli Lilly and Company; CSL Behring; Sanofi; Novo Nordisk; Medicines Company; Boston Scientific Corporation; MyoKardia; Yale University; Ironwood Pharmaceuticals, Incorporated; National Heart, Lung, and Blood Institute; Pfizer; Advanced Micro Devices","keywords":"Randomized controlled trial; Medicine; Hazard ratio; Sprint; Blood pressure; Internal medicine; Physical therapy; Confidence interval","score_opus":0.5634698805662555,"score_gpt":0.5387562044959715,"score_spread":0.024713676070283963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381852553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005667992,0.0003197197,0.96596456,0.0003046876,0.0017834586,0.024232324,0.00056952017,0.0004554789,0.00070226274],"genre_scores_gemma":[0.33447093,0.00018245656,0.6291931,0.0000973264,0.0012500975,0.032723077,0.00015947701,0.0002920531,0.0016314287],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95294964,0.03662681,0.0070780385,0.0015630695,0.00092150323,0.0008609306],"domain_scores_gemma":[0.59551555,0.39992458,0.0032052428,0.0007234825,0.00040300994,0.00022816219],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13812338,0.00090408494,0.016043296,0.00059387507,0.00015020029,0.00017353758,0.00076145155,0.00087355677,0.00047852797],"category_scores_gemma":[0.66326576,0.00065505627,0.002431647,0.000294355,0.00028061421,0.00006417232,0.00028371916,0.0017373877,0.000027419035],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8125229,0.0018053966,0.00042157367,0.0019802656,0.005095832,0.000110658846,0.00088666537,0.12533519,0.00013447393,0.049562067,0.00027898842,0.001865986],"study_design_scores_gemma":[0.21742155,0.00046019905,0.000027003096,0.00048398488,0.0010689833,1.545227e-7,0.00015716342,0.30176374,0.00009951011,0.47818303,0.000013461674,0.00032122672],"about_ca_topic_score_codex":0.00011585787,"about_ca_topic_score_gemma":0.000036101752,"teacher_disagreement_score":0.59510136,"about_ca_system_score_codex":0.00031191672,"about_ca_system_score_gemma":0.000594409,"threshold_uncertainty_score":0.99959004},"labels":[],"label_agreement":null},{"id":"W4382182859","doi":"10.1002/sim.9818","title":"Handling misclassified stratification variables in the analysis of randomised trials with continuous outcomes","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Health and Medical Research Council; Medical Research Council Canada; Medical Research Council; University of Adelaide","keywords":"Covariate; Stratification (seeds); Statistics; Econometrics; Medicine; Mathematics","score_opus":0.5420455474370366,"score_gpt":0.5745915147372646,"score_spread":0.03254596730022796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382182859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030195503,0.000034748853,0.9635227,0.0015241866,0.00034996544,0.0019822791,0.0007572112,0.000052285173,0.0015811744],"genre_scores_gemma":[0.33838233,0.00010460594,0.6606981,0.00015176478,0.00010895611,0.00021635466,0.00012445905,0.0000293057,0.00018408052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99212146,0.0036353203,0.0028212944,0.0003336512,0.0008056912,0.00028256286],"domain_scores_gemma":[0.7332164,0.2653943,0.00076087855,0.00044038938,0.00014499587,0.000043063923],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036390387,0.00020039373,0.0026082206,0.00062819815,0.00004061828,0.000018364899,0.00032649343,0.00011432586,0.00025703968],"category_scores_gemma":[0.3725915,0.00010450652,0.0000969228,0.00255764,0.00037210816,0.00002211725,0.000021280393,0.00030138926,0.0000023247503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040360726,0.00046526428,0.030581288,0.00048624555,0.0025797698,0.00015427722,0.0060227634,0.0006327259,0.0008378331,0.9355928,0.005401803,0.013209208],"study_design_scores_gemma":[0.019550549,0.00019505838,0.06655961,0.00026121654,0.003048991,6.0185124e-7,0.0026088802,0.00939053,0.000062640225,0.8981459,0.000019937064,0.00015606874],"about_ca_topic_score_codex":0.00012328856,"about_ca_topic_score_gemma":0.0003818702,"teacher_disagreement_score":0.3362011,"about_ca_system_score_codex":0.000031465086,"about_ca_system_score_gemma":0.00007256868,"threshold_uncertainty_score":0.9922389},"labels":[],"label_agreement":null},{"id":"W4382239692","doi":"10.7554/elife.76300.sa2","title":"Author response: A systematic assessment of preclinical multilaboratory studies and a comparison to single laboratory studies","year":2022,"lang":"en","type":"peer-review","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medical physics; Medicine","score_opus":0.8253662570831656,"score_gpt":0.7053014019992164,"score_spread":0.12006485508394915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382239692","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011398377,0.83967316,0.013975207,0.0883325,0.02040594,0.027066853,0.008080193,0.0007656686,0.0005606185],"genre_scores_gemma":[0.00017263398,0.005155716,0.95247644,0.0025403136,0.00031196914,0.0032167966,0.000008707506,0.0001777685,0.03593965],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9658377,0.022140503,0.0076391897,0.00145822,0.0023429673,0.0005813914],"domain_scores_gemma":[0.51055855,0.47835523,0.004221639,0.0023600282,0.004021779,0.00048274966],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051385023,0.0008936836,0.0106505165,0.0003362208,0.00019479108,0.000043979682,0.00075868185,0.00045547434,0.0004826199],"category_scores_gemma":[0.70674497,0.00066631095,0.00040971942,0.0010182002,0.00066203444,0.000053216452,0.0018768611,0.001379436,0.000012783581],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021030528,0.00057056703,0.000018773175,0.33980125,0.0022481908,0.000020197675,0.0004917486,0.0000012365108,0.00002301255,0.0019005026,0.6544476,0.0002665736],"study_design_scores_gemma":[0.0032833514,0.007917119,0.00012723153,0.59569573,0.017954575,0.0000119047445,0.013311819,0.00017505433,0.00015305486,0.073740095,0.2847266,0.0029034782],"about_ca_topic_score_codex":0.0000034387547,"about_ca_topic_score_gemma":0.000027625942,"teacher_disagreement_score":0.93850124,"about_ca_system_score_codex":0.0006608963,"about_ca_system_score_gemma":0.00082734163,"threshold_uncertainty_score":0.99957883},"labels":[],"label_agreement":null},{"id":"W4383340853","doi":"10.1016/j.jclinepi.2023.06.022","title":"Noninferiority margins exceed superiority effect estimates for mortality in cardiovascular trials in high-impact journals","year":2023,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Interquartile range; Medicine; Clinical trial; MEDLINE; Sample size determination; Guideline; Relative risk; Emergency medicine; Confidence interval; Internal medicine; Statistics","score_opus":0.9328234368721308,"score_gpt":0.7624042600171351,"score_spread":0.17041917685499564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383340853","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053280653,0.9414306,0.037866496,0.00024503632,0.009078824,0.005201507,0.00077315985,0.000056480552,0.000019808695],"genre_scores_gemma":[0.000062881496,0.789308,0.20575336,0.00006745306,0.00442404,0.00019777768,0.000010825884,0.00016703,0.000008605645],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6475059,0.2729521,0.07438421,0.0017622056,0.0012994948,0.0020960877],"domain_scores_gemma":[0.050098963,0.92207694,0.024547314,0.0016224551,0.00063629675,0.0010180115],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"category_scores_codex":[0.7395143,0.0014140132,0.113592744,0.0011833259,0.00008003793,0.0000680063,0.0017495438,0.0045402357,0.0001927017],"category_scores_gemma":[0.98679507,0.0008746926,0.03036405,0.00119887,0.0007137425,0.00019467577,0.00038865057,0.007734035,0.00003341947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017910018,0.0011281467,0.14243089,0.04082409,0.017763654,0.001060985,0.000019772016,0.00013813899,1.793202e-7,0.004798367,0.0014351443,0.7886096],"study_design_scores_gemma":[0.008175476,0.0028235626,0.08639856,0.033172816,0.016249552,0.00019191578,0.000005699272,0.00015174785,2.9438218e-7,0.83022594,0.021695266,0.00090919435],"about_ca_topic_score_codex":0.00026020894,"about_ca_topic_score_gemma":0.00007190728,"teacher_disagreement_score":0.82542753,"about_ca_system_score_codex":0.00065438886,"about_ca_system_score_gemma":0.0020103308,"threshold_uncertainty_score":0.999861},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"meta_analysis","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4383551038","doi":"10.1038/s41416-023-02307-w","title":"A tailored phase I-specific patient-reported outcome (PRO) survey to capture the patient experience of symptomatic adverse events","year":2023,"lang":"en","type":"article","venue":"British Journal of Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute","keywords":"Tolerability; Clinical trial; Medicine; Adverse effect; Medical physics; Intensive care medicine; Internal medicine","score_opus":0.42334773358831657,"score_gpt":0.5319927219761352,"score_spread":0.10864498838781866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383551038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99082124,0.0004060088,0.005508949,0.00018102417,0.0019328609,0.0007463873,0.00032309088,0.000028910137,0.000051526575],"genre_scores_gemma":[0.9666187,0.00027096426,0.032472916,0.00024705444,0.00014843294,0.000095405776,0.000002190865,0.000048009828,0.00009633795],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99428236,0.0010795138,0.0028184087,0.00025686008,0.0012014405,0.0003614277],"domain_scores_gemma":[0.98799294,0.008649303,0.0018648009,0.00039183887,0.0008422942,0.00025884123],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031477653,0.00019514794,0.0009055568,0.00014542814,0.00009735894,0.000027048847,0.0004639925,0.00010874071,0.00052196975],"category_scores_gemma":[0.04593473,0.00015349229,0.00029070728,0.0009557604,0.0001413551,0.00010877867,0.00013209385,0.0003888439,0.000011210867],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038275113,0.0032460927,0.08340465,0.00071753544,0.0016953645,0.0034378867,0.019128544,0.0007019907,0.0026216076,0.00091316784,0.06710666,0.813199],"study_design_scores_gemma":[0.030814132,0.005570455,0.6897764,0.012783119,0.0014357123,0.0021541794,0.013903935,0.0008923741,0.00956765,0.21507859,0.015205565,0.0028178466],"about_ca_topic_score_codex":0.00022894933,"about_ca_topic_score_gemma":0.00013449338,"teacher_disagreement_score":0.8103811,"about_ca_system_score_codex":0.000117505144,"about_ca_system_score_gemma":0.00013230596,"threshold_uncertainty_score":0.96210176},"labels":[],"label_agreement":null},{"id":"W4384205504","doi":"10.1007/s00180-023-01384-y","title":"Semiparametric Bayesian approach to assess non-inferiority with assay sensitivity in a three-arm trial with normally distributed endpoints","year":2023,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Key Research and Development Program of China; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Prior probability; Bayesian probability; Frequentist inference; Markov chain Monte Carlo; Posterior probability; Parametric statistics; Computer science; Bayesian inference; Placebo; Statistics; Clinical trial; Econometrics; Mathematics; Artificial intelligence; Medicine; Internal medicine","score_opus":0.34298443982420707,"score_gpt":0.47626012327663997,"score_spread":0.1332756834524329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384205504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033736724,0.0000010147098,0.9600143,0.00011340851,0.000240093,0.0019362011,0.0031363543,0.00019236605,0.0006295437],"genre_scores_gemma":[0.31958765,7.8884267e-7,0.6797084,0.00007426608,0.00013235245,0.00013299315,0.00029120911,0.000052781696,0.00001955548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948033,0.0011725774,0.0011552662,0.00080204225,0.0013823698,0.0006844551],"domain_scores_gemma":[0.9262621,0.07201743,0.0003809824,0.00040274576,0.0005647731,0.00037201194],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0064195963,0.00043831542,0.0011048996,0.00039605208,0.00016874784,0.00016160638,0.00027671506,0.00019486355,0.000038769973],"category_scores_gemma":[0.041510146,0.0003626135,0.00007053598,0.002945604,0.0002257213,0.00010529063,0.0001847427,0.0006205096,0.00005688663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04138657,0.0067221913,0.04568868,0.0012628292,0.00085746596,0.0020386425,0.0007253501,0.2654388,0.000019680314,0.59809047,0.009151505,0.02861784],"study_design_scores_gemma":[0.014649758,0.0009399475,0.07516743,0.000111148576,0.00011538469,0.000028711642,0.000053240594,0.3793618,0.000013752652,0.5289819,0.000022313368,0.000554554],"about_ca_topic_score_codex":0.000057475427,"about_ca_topic_score_gemma":0.0002448217,"teacher_disagreement_score":0.2858509,"about_ca_system_score_codex":0.00025119694,"about_ca_system_score_gemma":0.0004663012,"threshold_uncertainty_score":0.9998826},"labels":[],"label_agreement":null},{"id":"W4384698675","doi":"10.1080/02331888.2023.2232912","title":"Fiducialize statistical significance: transforming<i>p</i>-values into conservative posterior probabilities and Bayes factors","year":2023,"lang":"en","type":"article","venue":"Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Bayes' theorem; Statistics; Posterior probability; Statistical significance; Bayes factor; Bayesian probability; Bayesian hierarchical modeling; Econometrics","score_opus":0.38717664603646634,"score_gpt":0.5233458211079679,"score_spread":0.13616917507150156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384698675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23932971,0.000046083536,0.74244785,0.00062567677,0.0011619201,0.0019190991,0.013100566,0.00063933275,0.00072974927],"genre_scores_gemma":[0.052919593,0.00010330839,0.9454402,0.00016794863,0.00018320186,0.00014739347,0.000092271715,0.00009891083,0.00084721076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957199,0.0009557238,0.0013036414,0.00070117804,0.0006610974,0.00065842987],"domain_scores_gemma":[0.9089969,0.089798674,0.00024084996,0.00038317556,0.00028097778,0.00029945094],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021819484,0.00044302532,0.0010457368,0.000102808626,0.0003037121,0.00013272694,0.00026144888,0.00022091214,0.00028055214],"category_scores_gemma":[0.09834288,0.00037717327,0.00007780333,0.00039991847,0.0014223802,0.000120761004,0.00013259804,0.00038054836,0.000041654333],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025953393,0.00014040734,0.0037817955,0.0015725186,0.00017679128,0.000088151035,0.008396145,0.0000013569661,0.00053765974,0.93943876,0.020112764,0.025494106],"study_design_scores_gemma":[0.0007280221,0.00044772922,0.0053647985,0.00011019,0.00016839686,0.000004349237,0.0021691706,0.0004539565,0.00094646285,0.9883024,0.0008428221,0.0004616884],"about_ca_topic_score_codex":0.00014040458,"about_ca_topic_score_gemma":0.00010262985,"teacher_disagreement_score":0.2029923,"about_ca_system_score_codex":0.00007989005,"about_ca_system_score_gemma":0.00022118766,"threshold_uncertainty_score":0.99986804},"labels":[],"label_agreement":null},{"id":"W4385265605","doi":"10.18203/2349-3259.ijct20232191","title":"How big is a big hazard ratio in clinical trials?","year":2023,"lang":"en","type":"article","venue":"International Journal of Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Hazard ratio; Event (particle physics); Statistics; Proportional hazards model; Categorical variable; Confidence interval; Hazard; Medicine; Odds ratio; Event data; Mathematics; Internal medicine; Physics","score_opus":0.9351277403998367,"score_gpt":0.7398338795503866,"score_spread":0.1952938608494501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385265605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26501364,0.0004928284,0.34891567,0.16311271,0.21368527,0.0042558415,0.001303455,0.0004004111,0.002820183],"genre_scores_gemma":[0.4052577,0.009017251,0.4469155,0.0084025785,0.124442294,0.00012614796,0.000021294029,0.00031338964,0.0055038403],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86567026,0.080611065,0.04692685,0.0012553395,0.004600315,0.00093616324],"domain_scores_gemma":[0.18267317,0.79554904,0.017488644,0.0009051368,0.0024897645,0.0008942448],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45550787,0.000487697,0.008224204,0.00095203024,0.00005884352,0.000514596,0.0020631496,0.0010983961,0.0005936835],"category_scores_gemma":[0.96079594,0.00034687668,0.005285865,0.00087423867,0.00050247624,0.0002869364,0.00040881304,0.0025269631,0.00021553774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070824088,0.0014986674,0.010645662,0.000049039943,0.0027485464,0.00090152235,0.000111491,0.000009808577,0.00014701611,0.0230655,0.09012229,0.8636181],"study_design_scores_gemma":[0.021433312,0.0009968295,0.009893914,0.000686962,0.00058225944,0.00004802428,0.00015953272,0.00067100866,0.0004472858,0.92006904,0.04456975,0.00044207604],"about_ca_topic_score_codex":0.0000068282143,"about_ca_topic_score_gemma":0.00001822841,"teacher_disagreement_score":0.89700353,"about_ca_system_score_codex":0.00011545214,"about_ca_system_score_gemma":0.0010454953,"threshold_uncertainty_score":0.9998983},"labels":[],"label_agreement":null},{"id":"W4385684876","doi":"10.1177/13524585231189673","title":"Assessing heterogeneity of treatment effect in multiple sclerosis trials","year":2023,"lang":"en","type":"review","venue":"Multiple Sclerosis Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"European Committee for Treatment and Research in Multiple Sclerosis; National Multiple Sclerosis Society","keywords":"Covariate; Multiple sclerosis; Clinical trial; Treatment effect; Medicine; Random effects model; Set (abstract data type); Statistics; Computer science; Meta-analysis; Mathematics; Internal medicine","score_opus":0.9378935239878043,"score_gpt":0.6287405873391883,"score_spread":0.3091529366486161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385684876","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062502627,0.972103,0.008881298,0.000032094285,0.004599496,0.006467671,0.0013557047,0.0002579434,0.000052507738],"genre_scores_gemma":[0.00053203496,0.8273719,0.17029478,0.0000096312115,0.0010203538,0.00043983196,0.000014676906,0.0002951875,0.000021624606],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.96283877,0.023932869,0.009831165,0.0011253238,0.0011231827,0.0011486885],"domain_scores_gemma":[0.7023052,0.29056495,0.0054730796,0.0009984501,0.00020282879,0.00045548455],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.039481897,0.0014151604,0.01520371,0.0010149179,0.0003111521,0.0004998581,0.0010533999,0.0012595957,0.00016432915],"category_scores_gemma":[0.3692261,0.00092806184,0.0050811768,0.0012894014,0.00030274742,0.00027149133,0.0003381534,0.0016796177,0.000098721015],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001274769,0.00058921915,0.00058545166,0.0095008025,0.0014358369,0.000033608572,0.00005305367,0.0000109016455,0.00012252448,0.00003358726,0.00022665595,0.9872809],"study_design_scores_gemma":[0.06428151,0.007796612,0.005563014,0.741777,0.039306104,0.00025837627,0.00026563124,0.0015530186,0.0043906667,0.07262892,0.054297846,0.007881305],"about_ca_topic_score_codex":0.00008987378,"about_ca_topic_score_gemma":0.00010268855,"teacher_disagreement_score":0.97939956,"about_ca_system_score_codex":0.0015346785,"about_ca_system_score_gemma":0.0006208895,"threshold_uncertainty_score":0.99985987},"labels":[],"label_agreement":null},{"id":"W4385840831","doi":"10.1016/j.ejps.2023.106566","title":"The Global Bioequivalence Harmonisation Initiative (GBHI): Report of the fifth international EUFEPS/AAPS conference","year":2023,"lang":"en","type":"review","venue":"European Journal of Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"U.S. Food and Drug Administration","keywords":"Bioequivalence; Context (archaeology); Political science; Operations research; Pharmacology; Management science; Medicine; Computer science; Mathematics; Engineering; Pharmacokinetics","score_opus":0.911852360600215,"score_gpt":0.6840624049793826,"score_spread":0.22778995562083237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385840831","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000107223575,0.85107183,0.0504258,0.010835378,0.027786518,0.0025644514,0.0008108487,0.00012550871,0.05627242],"genre_scores_gemma":[0.0003162489,0.96048087,0.037958644,0.00011575932,0.0009101854,0.0000041883613,7.7306936e-7,0.000031874177,0.00018148348],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9862413,0.007512364,0.0034868217,0.00040131848,0.0019696478,0.00038859082],"domain_scores_gemma":[0.9590118,0.03510572,0.0046294723,0.0003842123,0.00064206414,0.00022672673],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02925801,0.00032736818,0.0012002983,0.00008090612,0.00033008662,0.00023999467,0.0034794086,0.00008132504,0.00018542487],"category_scores_gemma":[0.12310447,0.00015014896,0.0007698016,0.0010255808,0.0028669836,0.0001576797,0.00076368276,0.000999103,0.0000589532],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004330142,0.00013274589,0.00004628028,0.0013883115,0.0004796099,0.00045815457,0.00012766694,0.0000021417297,0.000003056504,0.087250166,0.0038081307,0.90626043],"study_design_scores_gemma":[0.00037883216,0.00021253408,0.00009751051,0.008558867,0.0010479082,0.0006663704,0.00011255447,0.000099622564,0.000021417267,0.20470716,0.78383064,0.00026655785],"about_ca_topic_score_codex":0.000001046916,"about_ca_topic_score_gemma":7.191322e-7,"teacher_disagreement_score":0.9059939,"about_ca_system_score_codex":0.00015470257,"about_ca_system_score_gemma":0.00084911956,"threshold_uncertainty_score":0.99984664},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4385980772","doi":"10.1016/b978-0-323-91259-4.00027-8","title":"Time-to-event outcomes and survival analysis","year":2023,"lang":"en","type":"book-chapter","venue":"Translational Sports Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Censoring (clinical trials); Survival analysis; Proportional hazards model; Event (particle physics); Event data; Survival function; Hazard; Outcome (game theory); Computer science; Kaplan–Meier estimator; Focus (optics); Accelerated failure time model; Econometrics; Statistics; Data mining; Mathematics","score_opus":0.37848999648510795,"score_gpt":0.5130668214234215,"score_spread":0.13457682493831358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385980772","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002046875,0.0003129976,0.1358994,0.029595494,0.0022015146,0.002606441,0.0015823653,0.0007182799,0.82687885],"genre_scores_gemma":[0.00046332553,0.00013068588,0.10930213,0.0004861467,0.0010229258,0.000020901734,0.00019751434,0.00016731187,0.88820904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959654,0.00007748209,0.0015434715,0.0006205013,0.001553173,0.00023996693],"domain_scores_gemma":[0.97344667,0.025285764,0.0003594575,0.00042632894,0.0001505981,0.00033117898],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034335656,0.00042929512,0.002098799,0.00049311813,0.00005990434,0.000007769974,0.00016704762,0.00034954917,0.022675388],"category_scores_gemma":[0.005765328,0.00032592478,0.0003513939,0.00020965755,0.00031879504,0.000019689582,0.000037595666,0.00037524718,0.0002681024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014646047,0.000049027312,0.0011568782,0.00020949863,0.0034465245,0.0001656321,0.00021582202,0.000051848783,0.000002436057,0.94610167,0.00688905,0.04156513],"study_design_scores_gemma":[0.00068131596,0.00006604023,0.02080776,0.0003239129,0.004399194,0.0000016125983,0.0000040711548,0.00012049316,2.7486993e-7,0.95941556,0.013847095,0.00033268135],"about_ca_topic_score_codex":0.000007371883,"about_ca_topic_score_gemma":0.00001452499,"teacher_disagreement_score":0.061330225,"about_ca_system_score_codex":0.000023264658,"about_ca_system_score_gemma":0.000051775598,"threshold_uncertainty_score":0.9999193},"labels":[],"label_agreement":null},{"id":"W4386116424","doi":"10.1002/sim.9867","title":"A comparison of Bayesian information borrowing methods in basket trials and a novel proposal of modified exchangeability‐nonexchangeability method","year":2023,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Bayesian probability; Type I and type II errors; Sample size determination; Computer science; Econometrics; Homogeneity (statistics); Statistics; Bayesian inference; Generalization; Contrast (vision); Bayesian hierarchical modeling; Machine learning; Artificial intelligence; Mathematics","score_opus":0.7989345094425112,"score_gpt":0.7116990724016434,"score_spread":0.08723543704086778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386116424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014908209,0.1249162,0.86697435,0.000063263535,0.00064727373,0.0043146037,0.0028908837,0.00003873976,0.00015320975],"genre_scores_gemma":[0.00000442778,0.2461243,0.7532302,0.00001112925,0.00012791481,0.0003365137,0.00009417321,0.00006261706,0.000008744603],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95791537,0.022239182,0.01672221,0.0009820109,0.001414939,0.00072627456],"domain_scores_gemma":[0.68872756,0.30565354,0.004268568,0.0008334675,0.00034747325,0.00016941024],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11154485,0.00071961764,0.0148992045,0.0013529717,0.00003399218,0.00001599664,0.00054428,0.0008673798,0.00015764555],"category_scores_gemma":[0.64935654,0.0005406122,0.0003033233,0.001814123,0.0008226094,0.00011099372,0.0003624025,0.001346668,0.0000013179393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013458636,0.00030755633,0.000028685661,0.11980686,0.0001853286,0.000004363717,0.0018074049,0.0000032052315,0.000006855548,0.097429745,0.00024311947,0.7800423],"study_design_scores_gemma":[0.003107708,0.0006654857,0.00006141906,0.03466898,0.0022446353,0.0000052776663,0.00072649785,0.007466149,0.000019454204,0.9473505,0.0031717173,0.00051218295],"about_ca_topic_score_codex":0.00036068435,"about_ca_topic_score_gemma":0.00016463992,"teacher_disagreement_score":0.84992075,"about_ca_system_score_codex":0.00025939845,"about_ca_system_score_gemma":0.0005370804,"threshold_uncertainty_score":0.99972564},"labels":[],"label_agreement":null},{"id":"W4386194115","doi":"10.1007/978-3-031-32614-1_8","title":"Approaches to Generating Virtual Patient Cohorts with Applications in Oncology","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Leverage (statistics); Virtual patient; Population; Clinical trial; Computer science; Precision medicine; Drug development; Computational biology; Medicine; Data science; Drug; Medical physics; Machine learning; Bioinformatics; Biology; Pharmacology","score_opus":0.7648892132621216,"score_gpt":0.5151650713464321,"score_spread":0.24972414191568948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386194115","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006683516,0.0000063627526,0.41990942,0.0003037755,0.00020811618,0.0028550732,0.00012910143,0.00020805541,0.57631326],"genre_scores_gemma":[0.0000986901,0.00000811217,0.8553875,0.00025847385,0.00027102345,0.00082547625,0.000017233968,0.00013649398,0.14299698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970913,0.00018615709,0.0012709048,0.00072964566,0.00042049252,0.0003015152],"domain_scores_gemma":[0.96465236,0.034117762,0.00035707306,0.0006071125,0.000072382565,0.00019333477],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001413638,0.00036723856,0.0012061971,0.00019285851,0.00006000042,0.000027270564,0.00023908906,0.00054516416,0.0003801113],"category_scores_gemma":[0.006881376,0.00027556595,0.000100137535,0.000106046435,0.00012907598,0.000016034024,0.00024372105,0.00058170146,0.00022236812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030741765,0.00007730575,0.000009449359,0.000045492787,0.000072534225,0.000022739561,0.00013674305,0.00006126248,0.0000024195867,0.9340732,0.0014566758,0.06401143],"study_design_scores_gemma":[0.0003019346,0.000732118,0.000006396375,0.00016168988,0.000110382985,0.0000036576384,0.000118621174,0.0001974079,0.00003346395,0.9804254,0.017487278,0.00042166092],"about_ca_topic_score_codex":0.000009433271,"about_ca_topic_score_gemma":0.00024044282,"teacher_disagreement_score":0.4354781,"about_ca_system_score_codex":0.00018895834,"about_ca_system_score_gemma":0.00015368438,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W4386258640","doi":"10.1016/j.cct.2023.107327","title":"Extending the vision of adaptive point-of-care platform trials to improve targeted use of drug therapy regimens: An agile approach in the learning healthcare system toolkit","year":2023,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Center for Bioenergy Innovation; School of Public Health, University of California Berkeley; Massachusetts Institute of Technology; AbbVie; Bristol-Myers Squibb","keywords":"Medicine; Health care; Agile software development; Medical physics; Healthcare system; Point of care; Precision medicine; Intensive care medicine; Nursing; Software engineering; Pathology","score_opus":0.8586186157186623,"score_gpt":0.6280046643658966,"score_spread":0.23061395135276563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386258640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87539816,0.005628972,0.05174552,0.0047804117,0.0074307416,0.049064633,0.0034405112,0.0007554059,0.0017556443],"genre_scores_gemma":[0.92360526,0.00037120297,0.07452413,0.00023663972,0.00067869225,0.00038490116,0.00004076434,0.00009280541,0.00006557166],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8852199,0.09379907,0.017328938,0.0013048567,0.0016495896,0.0006976664],"domain_scores_gemma":[0.4945627,0.49613005,0.0066986885,0.0016723906,0.000692549,0.00024363634],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24779755,0.0004992751,0.006483648,0.00033589822,0.00016671978,0.00008136086,0.001283041,0.00058433926,0.000025734402],"category_scores_gemma":[0.51282316,0.0002680904,0.0015342988,0.001416477,0.0004741171,0.00036511244,0.00033032472,0.0012191309,0.000007763412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09633401,0.0045143324,0.007618713,0.0071232575,0.003238256,0.00012390655,0.03747399,0.000561097,0.0069388933,0.38516998,0.021524657,0.4293789],"study_design_scores_gemma":[0.06753411,0.04045223,0.011902201,0.014312519,0.0015979372,0.000013177151,0.22237097,0.013691973,0.017576573,0.60234505,0.0051699425,0.0030333288],"about_ca_topic_score_codex":0.00018829996,"about_ca_topic_score_gemma":0.0000065448703,"teacher_disagreement_score":0.4263456,"about_ca_system_score_codex":0.0000757952,"about_ca_system_score_gemma":0.00043404938,"threshold_uncertainty_score":0.9999771},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W4386294098","doi":"10.21203/rs.3.rs-3280124/v1","title":"Risks and rates, and the mathematical link between them","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Link (geometry); Computer science; Computer network","score_opus":0.9068669818093833,"score_gpt":0.6960497609284334,"score_spread":0.2108172208809499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386294098","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21192573,0.0060799904,0.44423136,0.21606283,0.0034543078,0.052382138,0.008137253,0.003467389,0.05425902],"genre_scores_gemma":[0.16940284,0.0052810544,0.81301093,0.000089767964,0.005827504,0.0017969114,0.000033815046,0.0004307825,0.004126398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9875857,0.007744676,0.0012478407,0.0009546816,0.0016598385,0.00080725516],"domain_scores_gemma":[0.6991846,0.29889086,0.00019259413,0.0010983802,0.00034093283,0.00029264644],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041935906,0.00037792552,0.0015364137,0.00015785001,0.00036377122,0.00046109324,0.00079436385,0.0008278505,0.00029778376],"category_scores_gemma":[0.3305924,0.00022345001,0.00021250294,0.0003297351,0.0024491863,0.00002960999,0.004741502,0.004225854,0.00028396028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028785877,0.00006783613,0.002282797,0.007290287,0.00048028032,0.00007581665,0.0009926887,7.438626e-7,0.0000020893863,0.9212378,0.0058026756,0.06147909],"study_design_scores_gemma":[0.0012562557,0.00007300508,0.003150659,0.0013532388,0.0001477443,0.00000542531,0.00025169403,0.0007675572,0.000032037216,0.9923555,0.00037146045,0.00023541064],"about_ca_topic_score_codex":0.00008007146,"about_ca_topic_score_gemma":0.0000051750085,"teacher_disagreement_score":0.36877957,"about_ca_system_score_codex":0.00006565238,"about_ca_system_score_gemma":0.00017247308,"threshold_uncertainty_score":0.99807143},"labels":[],"label_agreement":null},{"id":"W4386346081","doi":"10.5281/zenodo.8306240","title":"Drug interactions and pharmacogenetic factors contribute to variation in apixaban concentration in atrial fibrillation patients in routine care","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Ontario Ministry of Research, Innovation and Science","keywords":"Apixaban; Atrial fibrillation; Pharmacogenetics; Drug; Medicine; Internal medicine; Pharmacology; Cardiology; Warfarin; Rivaroxaban; Genotype; Chemistry","score_opus":0.15415533075673818,"score_gpt":0.42450228291754233,"score_spread":0.2703469521608042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386346081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938823,0.000018038385,0.002585446,0.00018262888,0.0002676538,0.001466924,0.00021485421,0.00008141009,0.0013007699],"genre_scores_gemma":[0.995992,0.000028740813,0.0033409721,0.000030079125,0.00009227828,8.930924e-8,0.00025725816,0.00022801147,0.00003056533],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99736625,0.001129544,0.0006206357,0.00036575447,0.00026816074,0.0002496747],"domain_scores_gemma":[0.9979245,0.0013497814,0.0001547708,0.00018537419,0.00028268824,0.00010285042],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011730752,0.0001226463,0.00026081133,0.00024336996,0.00014717132,0.00016988779,0.00019566914,0.00005187899,0.0013403944],"category_scores_gemma":[0.015292219,0.00013089685,0.00003452523,0.00054759096,0.000029763312,0.00018225779,0.0002596741,0.00023012931,0.00025186],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060012434,0.0013436531,0.3867116,0.0015220348,0.00025541228,0.000034446955,0.09659153,0.009169571,0.02207187,0.040650856,0.011182117,0.42446566],"study_design_scores_gemma":[0.018544832,0.00076152384,0.9006094,0.0005587446,0.00007190075,0.0000059815234,0.0020275933,0.010426114,0.0015818488,0.020542923,0.044007104,0.0008620735],"about_ca_topic_score_codex":0.00007651617,"about_ca_topic_score_gemma":0.0000175872,"teacher_disagreement_score":0.5138978,"about_ca_system_score_codex":0.00036154376,"about_ca_system_score_gemma":0.0000053740355,"threshold_uncertainty_score":0.9995725},"labels":[],"label_agreement":null},{"id":"W4386401250","doi":"10.1101/2023.08.31.23294918","title":"Benefit-Risk Assessment of Medical Products Using Bayesian Multi-Criteria Augmented Decision Analysis for Clinical Development","year":2023,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Bayesian probability; Risk analysis (engineering); Computer science; Business; Artificial intelligence","score_opus":0.7750856687358957,"score_gpt":0.6690172628057338,"score_spread":0.10606840593016187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386401250","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26452318,0.000033257787,0.7295113,0.00028886524,0.0033375048,0.0017114013,0.00044844352,0.000138437,0.0000075702633],"genre_scores_gemma":[0.046171565,0.00032488297,0.95225376,0.000042678454,0.00063009537,0.00028305608,0.0000734686,0.00014692055,0.00007359451],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9855302,0.0024246725,0.006718898,0.0019760567,0.0026882936,0.0006618536],"domain_scores_gemma":[0.9109748,0.08236668,0.0029104222,0.0020740884,0.001126879,0.000547111],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047852065,0.00065639766,0.003736355,0.0006194297,0.00016332582,0.000094782066,0.001535627,0.0014335783,0.00038289634],"category_scores_gemma":[0.35147837,0.00055537437,0.0011516566,0.0010338603,0.00030559735,0.000038810558,0.002353664,0.0014933028,0.0000073809297],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010361385,0.007998721,0.78821766,0.008203235,0.027420357,0.00015666438,0.0007793642,0.001276475,0.00020465114,0.0077450112,0.0023081158,0.15465361],"study_design_scores_gemma":[0.003516492,0.00018720266,0.23110008,0.002184214,0.006824986,0.0000016574702,0.00005600764,0.3785262,0.00060051994,0.375787,0.00026777314,0.00094788114],"about_ca_topic_score_codex":0.000041309522,"about_ca_topic_score_gemma":0.00009911626,"teacher_disagreement_score":0.5571176,"about_ca_system_score_codex":0.00023178187,"about_ca_system_score_gemma":0.0011907596,"threshold_uncertainty_score":0.9998628},"labels":[],"label_agreement":null},{"id":"W4386562232","doi":"10.1080/00031305.2023.2257237","title":"Statistical Challenges in Online Controlled Experiments: A Review of A/B Testing Methodology","year":2023,"lang":"en","type":"review","venue":"The American Statistician","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data science; The Internet; Computer science; Scale (ratio); Big data; World Wide Web; Marketing; Business; Data mining; Geography","score_opus":0.9449757609267309,"score_gpt":0.7096567412494859,"score_spread":0.235319019677245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386562232","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.186626e-7,0.94729453,0.044542827,0.00021875736,0.00035512156,0.0036226804,0.003222942,0.00011250455,0.00063013274],"genre_scores_gemma":[9.6089614e-8,0.5375277,0.46142006,0.00016645058,0.00016851594,0.00053314265,0.000025942045,0.00012658254,0.000031495143],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9696804,0.021822803,0.00579107,0.0009955093,0.0008417498,0.00086841],"domain_scores_gemma":[0.58023256,0.41439053,0.00394371,0.0010657244,0.0002143029,0.00015314687],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.016219392,0.0008837228,0.014849555,0.00035611694,0.00006813382,0.000017980543,0.0012532093,0.00020534128,0.00021501347],"category_scores_gemma":[0.5453734,0.0005533636,0.00059390656,0.0016300702,0.0016269524,0.000023812418,0.00042971232,0.0012439693,0.000079214275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095569754,0.00024422852,4.792701e-7,0.094039395,0.00050664286,0.00009889769,0.00005465731,6.5205455e-8,2.0837531e-7,0.079221934,0.00091112655,0.8248268],"study_design_scores_gemma":[0.0021516774,0.0013002865,0.000035863864,0.26741457,0.0066743265,0.000056074226,0.0006784787,0.00006328825,2.979798e-7,0.67049015,0.050021518,0.0011134798],"about_ca_topic_score_codex":0.00022390766,"about_ca_topic_score_gemma":0.00006504169,"teacher_disagreement_score":0.8237133,"about_ca_system_score_codex":0.00018565531,"about_ca_system_score_gemma":0.0005422517,"threshold_uncertainty_score":0.999776},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4386765575","doi":"10.2139/ssrn.4565730","title":"A Promising Biomarker Adaptive Phase 2/3 Design – Explained and Expanded","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Biomarker; Adaptive design; Phase (matter); Computer science; Biology; Chemistry; Bioinformatics","score_opus":0.6612258785281305,"score_gpt":0.5615395806061236,"score_spread":0.0996862979220069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386765575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011237897,0.0008343648,0.98454756,0.00061046,0.0010396319,0.0013301864,0.000048329926,0.00021280302,0.00013880098],"genre_scores_gemma":[0.084092125,0.004373601,0.90844464,0.000057402656,0.0011238204,0.00014129649,0.0000047904596,0.00026830938,0.0014940056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99155855,0.0027235625,0.0015476269,0.0008105343,0.00065291324,0.002706832],"domain_scores_gemma":[0.97059965,0.027218156,0.0011060586,0.0005438263,0.00023818454,0.00029411045],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02369348,0.00056993373,0.0013372327,0.00029138307,0.00024098503,0.00021931205,0.0005463889,0.00062241114,0.000060694107],"category_scores_gemma":[0.053681448,0.0004803376,0.00033760126,0.00022080058,0.00021229603,0.000084879706,0.0005631307,0.0059480844,0.000025038198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0074045616,0.0013532533,0.000043769905,0.00054779224,0.0061742985,0.00034701594,0.001298265,0.000038240596,0.0017865604,0.6776683,0.003180753,0.30015722],"study_design_scores_gemma":[0.003947114,0.0008283403,0.000013364169,0.000532247,0.0004927571,0.00026803385,0.00069294125,0.0028679592,0.00022193552,0.98962045,0.000016740374,0.0004980929],"about_ca_topic_score_codex":0.000014897445,"about_ca_topic_score_gemma":0.00003328419,"teacher_disagreement_score":0.3119522,"about_ca_system_score_codex":0.00097237126,"about_ca_system_score_gemma":0.0032982721,"threshold_uncertainty_score":0.99976486},"labels":[],"label_agreement":null},{"id":"W4386793875","doi":"10.1093/biomet/asad057","title":"<i>E</i>-values as unnormalized weights in multiple testing","year":2023,"lang":"en","type":"article","venue":"Biometrika","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Normalization (sociology); Statistics; Statistical hypothesis testing; Multiple comparisons problem","score_opus":0.7188583237540784,"score_gpt":0.5729042471527536,"score_spread":0.14595407660132487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386793875","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9755667,0.00012586713,0.0072338423,0.00040999218,0.0017935551,0.0010612592,0.00011305962,0.0012311911,0.012464562],"genre_scores_gemma":[0.1368351,0.000037985606,0.86161387,0.00012726385,0.00029672403,0.00006127603,0.0000045005036,0.000054125492,0.0009691264],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969677,0.00061149814,0.00097161403,0.00042212976,0.0005112895,0.0005157683],"domain_scores_gemma":[0.8691643,0.12991288,0.00020631946,0.00044645244,0.00011268618,0.00015738717],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052308943,0.00019774788,0.0006063039,0.0011669627,0.000087115244,0.00004886244,0.00034278497,0.00019219848,0.00023755149],"category_scores_gemma":[0.4471984,0.00016725821,0.00011135262,0.00830516,0.00013486716,0.0000702713,0.0002012191,0.00022550984,0.00080004544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088775315,0.002066408,0.1824758,0.0013937803,0.000392185,0.0012217192,0.0014776732,0.000012698875,0.036172677,0.1664677,0.031129817,0.5763018],"study_design_scores_gemma":[0.002075131,0.00013057094,0.011950026,0.00013817774,0.000027227645,0.0000048862726,0.000056668585,0.0014455728,0.004430844,0.9750994,0.004360463,0.00028106486],"about_ca_topic_score_codex":0.0000874603,"about_ca_topic_score_gemma":0.0000060663956,"teacher_disagreement_score":0.8543801,"about_ca_system_score_codex":0.000061087296,"about_ca_system_score_gemma":0.000055312074,"threshold_uncertainty_score":0.99997795},"labels":[],"label_agreement":null},{"id":"W4386810972","doi":"10.1002/pst.2338","title":"A marginalized two‐part joint model for a longitudinal biomarker and a terminal event with application to advanced head and neck cancers","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut National Du Cancer","keywords":"Biomarker; Covariate; Medicine; Oncology; Head and neck cancer; Clinical trial; Event (particle physics); Statistics; Internal medicine; Cancer; Mathematics; Biology","score_opus":0.5750052390768035,"score_gpt":0.5987650466759101,"score_spread":0.023759807599106675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386810972","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028698446,0.000038265924,0.9661779,0.0010609587,0.00011430815,0.0020465816,0.0016841715,0.00012446956,0.00005490657],"genre_scores_gemma":[0.06579154,0.00010065402,0.93218714,0.00042315485,0.00009613832,0.0010857255,0.000021087259,0.000064754335,0.00022981274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740523,0.00017196791,0.00073357014,0.00069470133,0.00040433666,0.0005901936],"domain_scores_gemma":[0.9892689,0.009518442,0.00016893372,0.00026896474,0.00018658182,0.0005881876],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001448051,0.0003057349,0.00065826223,0.000095833,0.00015882165,0.000062545885,0.00012011724,0.00007534843,0.00004577811],"category_scores_gemma":[0.007882001,0.00025566068,0.000047571157,0.00031628212,0.00027333447,0.000053734457,0.00014710485,0.00020600809,0.000013598827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012595537,0.00054114044,0.0016336717,0.003107641,0.0005450329,0.00015453956,0.0006215404,0.0019814149,0.002902566,0.4020708,0.018079426,0.5557667],"study_design_scores_gemma":[0.0042961156,0.00026708498,0.0010038291,0.00013391394,0.00030037935,0.00002120658,0.000017659502,0.63802385,0.0001526121,0.35298133,0.0024909931,0.00031104204],"about_ca_topic_score_codex":0.000015399377,"about_ca_topic_score_gemma":0.00005344619,"teacher_disagreement_score":0.6360424,"about_ca_system_score_codex":0.000128025,"about_ca_system_score_gemma":0.00010451814,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W4386818390","doi":"10.15537/1658-3175.8235","title":"Robust analysis challenges theory that depression and anxiety increase cancer risk","year":2023,"lang":"en","type":"article","venue":"Saudi Medical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Depression (economics); Anxiety; Psychiatry","score_opus":0.4402531614101,"score_gpt":0.5236097453599208,"score_spread":0.08335658394982076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386818390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4226636,0.0154180825,0.54068136,0.012097235,0.0031446887,0.00063599297,0.00032140905,0.0005863564,0.0044513107],"genre_scores_gemma":[0.3748238,0.33535355,0.28476727,0.00087251404,0.003564253,0.00007381684,0.000004375811,0.00010975646,0.000430667],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936907,0.0032423623,0.0007743519,0.0004078993,0.0014263146,0.00045836862],"domain_scores_gemma":[0.9548185,0.04330021,0.00046184132,0.00033511015,0.00010960166,0.00097471813],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019808266,0.0002151409,0.0008099661,0.00023626475,0.00028221786,0.000058215795,0.00036281365,0.00035778293,0.0036132843],"category_scores_gemma":[0.15379792,0.00014140483,0.0002986263,0.00057739136,0.00032986165,0.000077345685,0.00028360815,0.0012956684,0.000024043742],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029195112,0.0001475054,0.047557548,0.00013296101,0.0018231296,0.00029209402,0.0003655907,0.000029044122,0.0000103131015,0.007835337,0.0071587265,0.9343558],"study_design_scores_gemma":[0.001225198,0.000045581728,0.07341245,0.00030237102,0.0019705743,0.000079039724,0.00034183633,0.0029180185,0.000041016996,0.91859865,0.0008449887,0.0002202721],"about_ca_topic_score_codex":0.000025526726,"about_ca_topic_score_gemma":0.000054416018,"teacher_disagreement_score":0.93413556,"about_ca_system_score_codex":0.00004511486,"about_ca_system_score_gemma":0.00013092993,"threshold_uncertainty_score":0.9972975},"labels":[],"label_agreement":null},{"id":"W4386943803","doi":"","title":"Using a Discrete-Choice Experiment in a Decision Aid to Nudge Patients Towards Value-Concordant Treatment Choices in Rheumatoid Arthritis: A Proof-of-Concept Study","year":2020,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rheumatoid arthritis; Value (mathematics); Proof of concept; Medicine; Physical therapy; Nudge theory; Computer science; Psychology; Immunology; Social psychology; Machine learning","score_opus":0.7267299249265989,"score_gpt":0.6857658372684308,"score_spread":0.04096408765816817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386943803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795529,0.002890157,0.011795567,0.00009551936,0.00051966537,0.0047616484,0.00013533077,0.0000263492,0.00022283263],"genre_scores_gemma":[0.8850263,0.000621928,0.113593824,0.00020005876,0.000097326636,0.00036651146,0.000002039438,0.00008643538,0.0000056200274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9910739,0.002123779,0.0038303637,0.00096777687,0.0014223647,0.0005818263],"domain_scores_gemma":[0.98419625,0.012698667,0.0015931742,0.0006725847,0.00028498584,0.00055433065],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032257568,0.00057758385,0.0027350453,0.00064133387,0.0001035706,0.0004584185,0.0020174917,0.00015168481,0.001472761],"category_scores_gemma":[0.04121251,0.00047512355,0.00029108662,0.0015791553,0.00013448637,0.00091087417,0.0013633783,0.00043366087,0.0000036449028],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037603276,0.010679261,0.74186766,0.00020127668,0.00045925513,0.0001712064,0.009755431,0.0010195434,0.0044313264,0.00022730367,0.00072843954,0.22669895],"study_design_scores_gemma":[0.0460878,0.0034376835,0.5160328,0.01223989,0.00037303744,0.000009758346,0.004014418,0.0028489148,0.18675628,0.22418696,0.0010763584,0.0029360796],"about_ca_topic_score_codex":0.0024951196,"about_ca_topic_score_gemma":0.0002602871,"teacher_disagreement_score":0.22583486,"about_ca_system_score_codex":0.0004701951,"about_ca_system_score_gemma":0.00027550425,"threshold_uncertainty_score":0.99977005},"labels":[],"label_agreement":null},{"id":"W4386947832","doi":"10.1016/j.neuchi.2023.101492","title":"Understanding the role of randomization in clinical research and practice","year":2023,"lang":"en","type":"review","venue":"Neurochirurgie","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta Hospital; Health Sciences Centre; Centre Hospitalier de l’Université de Montréal","funders":"","keywords":"Randomization; Argument (complex analysis); Randomized controlled trial; Perspective (graphical); Medical research; Best practice; Research design; Clinical trial; Psychology; Medicine; Medical education; Management science; Computer science; Sociology; Artificial intelligence; Political science; Law; Social science","score_opus":0.9591975132280013,"score_gpt":0.7243400137130938,"score_spread":0.23485749951490753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386947832","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000022380877,0.9764781,0.009991775,0.000260844,0.00084310124,0.0035129264,0.000051942476,0.00007474825,0.008784328],"genre_scores_gemma":[0.0000053580834,0.9780173,0.021401677,0.000021664328,0.00029253104,0.000095319694,0.0000018831946,0.00008512072,0.00007916219],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9754105,0.019939981,0.0029531643,0.00057819026,0.00075805443,0.0003600822],"domain_scores_gemma":[0.44609532,0.55247265,0.00074876053,0.0005038624,0.0001117179,0.00006769315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04725783,0.00023339712,0.0023985114,0.00027910873,0.0000944868,0.00005883895,0.00046035176,0.0004394911,0.00002197364],"category_scores_gemma":[0.6607586,0.00014696032,0.00028625963,0.0011302881,0.0005711016,0.00005499026,0.00041057507,0.0018481482,0.000024639803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048903195,0.00024899826,0.000003968725,0.008365936,0.00016609904,0.00004198176,0.00008031054,4.5384698e-7,1.5188402e-7,0.487505,0.00083413854,0.5022639],"study_design_scores_gemma":[0.0010198784,0.00011419748,0.0000015244757,0.004746028,0.0003861773,0.000011883385,0.00016107025,0.000036832167,1.2664589e-7,0.84135574,0.15205915,0.00010738701],"about_ca_topic_score_codex":0.0000058449173,"about_ca_topic_score_gemma":0.0000061732653,"teacher_disagreement_score":0.61350083,"about_ca_system_score_codex":0.00007450477,"about_ca_system_score_gemma":0.00024973263,"threshold_uncertainty_score":0.9810486},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4387344941","doi":"10.1007/s12630-023-02557-5","title":"Interpreting frequentist hypothesis tests: insights from Bayesian inference","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"University of Auckland","keywords":"Frequentist inference; Bayes factor; Bayesian probability; Frequentist probability; Statistical hypothesis testing; Statistical inference; Credible interval; Inference; Confidence interval; Randomized controlled trial; Bayesian inference; Econometrics; Bayes' theorem; Outcome (game theory); Prior probability; Bayesian statistics; Statistics; Mathematics; Computer science; Medicine; Artificial intelligence; Internal medicine","score_opus":0.1598509748472757,"score_gpt":0.3903339045655515,"score_spread":0.2304829297182758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387344941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98516285,0.00049187965,0.004406678,0.005742251,0.0019428805,0.0003513533,0.000099725694,0.00009217715,0.0017102133],"genre_scores_gemma":[0.8774879,0.000085380976,0.120052636,0.00022523761,0.001672095,0.000006994236,0.000003882029,0.00015114703,0.0003147016],"study_design_codex":"case_report","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99340546,0.0012660535,0.0026396124,0.00045865536,0.00094310654,0.0012871263],"domain_scores_gemma":[0.9672145,0.024916047,0.0019872836,0.000661866,0.001040819,0.004179445],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0041566556,0.0005633234,0.0014876393,0.0013763668,0.0006611865,0.00060916075,0.0016443579,0.00045069994,0.0009754595],"category_scores_gemma":[0.07484001,0.00049384445,0.0005683809,0.0012817341,0.0005100538,0.00049346435,0.000035170717,0.0017114258,0.00012593012],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017872137,0.00008511458,0.008591147,0.0001090329,0.00054860814,0.9179657,0.0030690157,0.00008535542,0.00030874033,0.021245904,0.023543205,0.024269415],"study_design_scores_gemma":[0.00087926723,0.0005481353,0.0072375224,0.0010529283,0.00027644858,0.25742048,0.00093342125,0.00013246645,0.00013633777,0.72703665,0.0037019085,0.00064444344],"about_ca_topic_score_codex":0.005136735,"about_ca_topic_score_gemma":0.015850661,"teacher_disagreement_score":0.70579076,"about_ca_system_score_codex":0.00096992776,"about_ca_system_score_gemma":0.0038397978,"threshold_uncertainty_score":0.9999378},"labels":[],"label_agreement":null},{"id":"W4387473849","doi":"10.3233/jad-230660","title":"Landscape of Phase II Trials in Alzheimer’s Disease","year":2023,"lang":"en","type":"review","venue":"Journal of Alzheimer s Disease","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Dementia Research Alliance; Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Randomization; Sample size determination; Randomized controlled trial; Research design; Adaptive design; Clinical trial; Drug development; Medicine; Multinomial logistic regression; Clinical study design; Computer science; Statistics; Drug; Internal medicine; Pharmacology; Machine learning; Mathematics","score_opus":0.7912605651815485,"score_gpt":0.6414366354857995,"score_spread":0.14982392969574898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387473849","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031014435,0.9928784,0.00042310773,0.00018484643,0.002034363,0.002049832,0.002267228,0.00004680595,0.000084444226],"genre_scores_gemma":[0.000044642173,0.9660242,0.031700235,0.00005336156,0.0017601963,0.00010909415,0.000027224844,0.0002432273,0.00003782717],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9766913,0.008265317,0.012191538,0.0006371786,0.0015763965,0.000638282],"domain_scores_gemma":[0.8919422,0.09254215,0.011580931,0.0013348538,0.0005395406,0.0020603072],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024449196,0.00092076004,0.012276312,0.0012166844,0.00008053658,0.00006473688,0.0012342761,0.00046083803,0.0011582879],"category_scores_gemma":[0.26856408,0.000645599,0.0052274405,0.0011530035,0.00026480915,0.00019048726,0.00041219304,0.0013261655,0.000067470995],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022234174,0.0052265786,0.000015621976,0.012071286,0.01019108,0.002259952,0.00005759734,0.0000032013882,2.851273e-7,0.004372947,0.02621423,0.9373638],"study_design_scores_gemma":[0.01084263,0.001372893,0.00005008638,0.06820992,0.21578977,0.000029735733,0.000038819067,0.00006137777,0.0000048183842,0.47880918,0.22329153,0.0014992686],"about_ca_topic_score_codex":0.0000026861942,"about_ca_topic_score_gemma":7.942707e-7,"teacher_disagreement_score":0.9358645,"about_ca_system_score_codex":0.00005911024,"about_ca_system_score_gemma":0.0024080712,"threshold_uncertainty_score":0.9997548},"labels":[],"label_agreement":null},{"id":"W4387506154","doi":"10.2196/48925","title":"Drug Repurposing for Cancers With Limited Survival: Protocol for a Retrospective Cohort Study","year":2023,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Cohort; Retrospective cohort study; Cancer; Informatics; Population; Repurposing; Cohort study; Oncology; Internal medicine; Intensive care medicine; Emergency medicine; Environmental health","score_opus":0.8666310653555355,"score_gpt":0.75055173358801,"score_spread":0.1160793317675255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387506154","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002964911,4.6363695e-8,0.010755932,0.00025477028,0.000022840024,0.9870636,0.0001796568,0.0004976278,0.00092905463],"genre_scores_gemma":[0.00004175289,3.9892623e-8,0.17682111,0.000014041795,0.0003916431,0.8204711,0.0000034962322,0.00016323193,0.002093587],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9910567,0.0029323734,0.0012068088,0.0012978617,0.0021353327,0.0013709373],"domain_scores_gemma":[0.9352916,0.060625803,0.00038194197,0.0012247532,0.0021760107,0.0002999307],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03364229,0.00035670077,0.0011592489,0.00035473544,0.00061578635,0.0002923909,0.00076572143,0.00018563718,0.00009839358],"category_scores_gemma":[0.10299281,0.00026468025,0.00019678033,0.0019160294,0.0004062017,0.00013905442,0.00031403266,0.00082415075,0.000022327902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07313329,0.010288752,0.24702899,0.017754048,0.0017719507,0.00016303358,0.0038958697,0.000027196877,0.0007258694,0.10865411,0.5154851,0.021071762],"study_design_scores_gemma":[0.026330464,0.017176695,0.02072022,0.004119688,0.00004028404,0.0000018221126,0.0011537252,0.001204458,0.001720582,0.8551878,0.07156744,0.0007768206],"about_ca_topic_score_codex":0.000050870327,"about_ca_topic_score_gemma":0.0001609474,"teacher_disagreement_score":0.7465337,"about_ca_system_score_codex":0.00078647415,"about_ca_system_score_gemma":0.0006948808,"threshold_uncertainty_score":0.99998057},"labels":[],"label_agreement":null},{"id":"W4387789727","doi":"10.1007/978-3-031-40055-1_2","title":"MANOVA for Large Number of Treatments","year":2023,"lang":"en","type":"book-chapter","venue":"Contributions to statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Multivariate analysis of variance; Statistics; Univariate; Homoscedasticity; Statistic; Mathematics; Sample size determination; Normality; Test statistic; Heteroscedasticity; Econometrics; Multivariate statistics; Statistical hypothesis testing","score_opus":0.4464529949305117,"score_gpt":0.5891110466878909,"score_spread":0.14265805175737922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387789727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.667401e-7,0.000009314587,0.6794033,0.00012333442,0.0006485002,0.0015500197,0.27623987,0.0000984673,0.04192664],"genre_scores_gemma":[0.000012874002,0.000032689877,0.60529006,0.000050969524,0.00026775576,0.00017444069,0.0004879368,0.00012299008,0.3935603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99668795,0.000106694926,0.0016712194,0.0005328877,0.00046728854,0.000533958],"domain_scores_gemma":[0.9386689,0.058246482,0.0006619727,0.00073361234,0.0014347119,0.00025431544],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015549834,0.00044499838,0.0015546713,0.00013721337,0.0001442185,0.000026642669,0.00031775053,0.0005580108,0.002338767],"category_scores_gemma":[0.11371885,0.0004356606,0.0003163195,0.0000955553,0.00012468899,0.000017823571,0.00018394223,0.00031134152,0.001667629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008125631,0.000104422914,0.0000032531693,0.00022024778,0.00048821463,0.00001635985,0.000015026822,3.1088152e-7,0.0000028855904,0.82904667,0.16657242,0.0034489313],"study_design_scores_gemma":[0.0015226204,0.00019610887,0.0000129057335,0.0002761613,0.0011640065,0.0000025539068,0.000003700923,0.00007075942,0.000040901272,0.87946707,0.11690452,0.00033871143],"about_ca_topic_score_codex":0.000003586958,"about_ca_topic_score_gemma":0.000014838361,"teacher_disagreement_score":0.35163364,"about_ca_system_score_codex":0.0002465508,"about_ca_system_score_gemma":0.00020943092,"threshold_uncertainty_score":0.9998095},"labels":[],"label_agreement":null},{"id":"W4387807507","doi":"10.1136/bmj-2023-076386","title":"Enhancing quality and impact of early phase dose-finding clinical trial protocols: SPIRIT Dose-finding Extension (SPIRIT-DEFINE) guidance","year":2023,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Robarts Clinical Trials; Women's College Hospital; University of Toronto","funders":"Medical Research Council; National Institute for Health and Care Research; NIHR Imperial Biomedical Research Centre; National Heart Foundation of Australia; Cancer Research UK","keywords":"Protocol (science); Guideline; Clinical trial; Medical physics; Medicine; Transparency (behavior); Alternative medicine; Computer science; Pathology","score_opus":0.830895637081085,"score_gpt":0.712227277059108,"score_spread":0.118668360021977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387807507","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.959743,0.000021119964,0.017240303,0.0005666678,0.00089619384,0.020646278,0.00014973946,0.00030512214,0.0004315827],"genre_scores_gemma":[0.31594732,0.000029342375,0.6762652,0.00013268237,0.0029940815,0.004205422,0.000007141912,0.00016134714,0.00025748878],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98792183,0.0034650203,0.0058099115,0.0010188513,0.000988049,0.0007963617],"domain_scores_gemma":[0.9262435,0.069845214,0.0020850098,0.0011421553,0.0002929518,0.00039116302],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04204199,0.00044589853,0.0021682058,0.00022016495,0.00019367009,0.00012418302,0.0004352432,0.0005411001,0.0001819307],"category_scores_gemma":[0.3325899,0.00036622773,0.00076599536,0.0008092604,0.0003728633,0.00018551946,0.0003983947,0.0007395615,0.000078268946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.22445054,0.00877569,0.07180156,0.0066259145,0.0019438983,0.0006840348,0.0020962125,0.000022725279,0.112918004,0.09901439,0.028900927,0.4427661],"study_design_scores_gemma":[0.13842164,0.0105687445,0.15855685,0.0032651117,0.00035244512,0.000020129966,0.00012302304,0.0008100663,0.0051756618,0.6809149,0.000481519,0.0013099464],"about_ca_topic_score_codex":0.00007815064,"about_ca_topic_score_gemma":0.000009935949,"teacher_disagreement_score":0.6590249,"about_ca_system_score_codex":0.0000876308,"about_ca_system_score_gemma":0.0003038908,"threshold_uncertainty_score":0.99987894},"labels":[],"label_agreement":null},{"id":"W4387807553","doi":"10.1136/bmj-2023-076387","title":"Enhancing reporting quality and impact of early phase dose-finding clinical trials: CONSORT Dose-finding Extension (CONSORT-DEFINE) guidance","year":2023,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Robarts Clinical Trials; Women's College Hospital; University of Toronto","funders":"Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Consolidated Standards of Reporting Trials; Interim; Guideline; Clinical trial; Medicine; Checklist; CLARITY; Medical physics; Tolerability; Adverse effect; Psychology; Pharmacology; Internal medicine","score_opus":0.9059150168922551,"score_gpt":0.7330936093589617,"score_spread":0.17282140753329334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387807553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97114825,0.000089511756,0.024457077,0.00029353777,0.0012461867,0.0015816947,0.00013875857,0.00031872667,0.000726227],"genre_scores_gemma":[0.67900026,0.00007994844,0.31966245,0.000065898595,0.0008864799,0.000058341036,0.0000050826216,0.000078459365,0.0001630447],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96607006,0.010464396,0.02003469,0.0013530693,0.0010981354,0.0009796504],"domain_scores_gemma":[0.6278749,0.35183287,0.017273208,0.0017886116,0.0005908447,0.0006395303],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20480858,0.00045610935,0.0038525413,0.00026210994,0.00022862792,0.000107255255,0.000306537,0.00053210754,0.00019629805],"category_scores_gemma":[0.8712219,0.00036815053,0.0011101386,0.000789958,0.00043027653,0.00017032093,0.0003622104,0.00079559983,0.000042040614],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008045149,0.0020300676,0.4724357,0.002847705,0.0025227906,0.0013188825,0.0017356032,0.000027597038,0.20171538,0.052601382,0.01452652,0.24019322],"study_design_scores_gemma":[0.012563704,0.0016025474,0.5211887,0.00247213,0.0007857617,0.000097563774,0.0004258372,0.001294547,0.00716666,0.45118243,0.00008546168,0.0011346908],"about_ca_topic_score_codex":0.00013634498,"about_ca_topic_score_gemma":0.000010978182,"teacher_disagreement_score":0.6664133,"about_ca_system_score_codex":0.00008265165,"about_ca_system_score_gemma":0.00038232564,"threshold_uncertainty_score":0.99987704},"labels":[],"label_agreement":null},{"id":"W4387881889","doi":"10.1016/j.euf.2023.10.003","title":"Pros and Cons of Noninferiority Trials","year":2023,"lang":"en","type":"review","venue":"European Urology Focus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Sigrid Juséliuksen Säätiö; Suomen Lääketieteen Säätiö; Helsingin ja Uudenmaan Sairaanhoitopiiri; Helsingin Yliopisto","keywords":"cons; Medicine; Medical physics","score_opus":0.8730877263038359,"score_gpt":0.653089692625577,"score_spread":0.21999803367825888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387881889","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026366013,0.98120636,0.0043880404,0.000082545346,0.0010935151,0.002164099,0.0007128823,0.00022662645,0.010123308],"genre_scores_gemma":[0.0000024305627,0.92326105,0.07552103,0.000026710442,0.0005536201,0.000048973787,0.0000042396728,0.00017888173,0.00040304786],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.972333,0.022624798,0.00373778,0.0006937116,0.0002281967,0.00038250603],"domain_scores_gemma":[0.8225858,0.17448877,0.0019724707,0.0007252239,0.000080767844,0.00014693433],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025907686,0.0004775806,0.0070817275,0.00018539697,0.000055589328,0.000023339557,0.00049271225,0.00043751407,0.00019225036],"category_scores_gemma":[0.37564436,0.0003447155,0.00072552613,0.00027916822,0.0007033669,0.000016700646,0.00055549457,0.00087806815,0.0004153735],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003284848,0.00007412728,0.0000023155892,0.010773324,0.0005891263,0.00017750458,0.000028044567,9.168729e-9,4.450728e-7,0.058327094,0.0023854726,0.9276097],"study_design_scores_gemma":[0.0006556878,0.00037065378,0.000008000027,0.0018819692,0.003922574,0.000052679497,0.0000018864431,7.975881e-7,0.0000010924704,0.32872614,0.66406035,0.00031818138],"about_ca_topic_score_codex":0.0000024752,"about_ca_topic_score_gemma":0.0000013507649,"teacher_disagreement_score":0.9272915,"about_ca_system_score_codex":0.00001605548,"about_ca_system_score_gemma":0.00015093945,"threshold_uncertainty_score":0.99990046},"labels":[],"label_agreement":null},{"id":"W4387891881","doi":"10.48550/arxiv.2310.13349","title":"DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"False discovery rate; Voxel; Neuroimaging; Computer science; Artificial intelligence; Segmentation; Multiple comparisons problem; Deep learning; Pattern recognition (psychology); Machine learning; Mathematics; Psychology; Neuroscience","score_opus":0.6565402295534531,"score_gpt":0.5467922017018985,"score_spread":0.10974802785155469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387891881","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000111773676,0.00010794408,0.9817259,0.0028366202,0.0037762662,0.007310266,0.0032256905,0.00076818647,0.00013738187],"genre_scores_gemma":[0.008079092,0.000037603688,0.97280616,0.0010354199,0.0014008558,0.014857305,0.0002734014,0.00039395425,0.0011161905],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98783624,0.006014943,0.0020860045,0.0021952386,0.00063336577,0.0012341975],"domain_scores_gemma":[0.7549537,0.2406426,0.0011713328,0.002698089,0.00022249356,0.00031179874],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031945933,0.00070001336,0.0022661116,0.00024478097,0.00017389831,0.0006014654,0.0023229055,0.00056460657,0.000022306574],"category_scores_gemma":[0.5760843,0.0006439271,0.00058236124,0.00025935684,0.00019092111,0.00017219686,0.002292405,0.0019442029,0.000024042432],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038375352,0.0010356093,0.0014939806,0.009527478,0.0030515725,0.00027200405,0.00012170458,0.01966743,0.000051788094,0.041348554,0.01621701,0.9033753],"study_design_scores_gemma":[0.0028862527,0.000030916995,0.0025789107,0.00011102206,0.0011979011,0.0000013571585,0.000012430288,0.2236076,0.00007430069,0.7671603,0.0017395046,0.00059951784],"about_ca_topic_score_codex":0.000038125374,"about_ca_topic_score_gemma":0.00003238446,"teacher_disagreement_score":0.9027758,"about_ca_system_score_codex":0.0001407141,"about_ca_system_score_gemma":0.00019057069,"threshold_uncertainty_score":0.9996012},"labels":[],"label_agreement":null},{"id":"W4387930839","doi":"10.1089/bio.2022.0190","title":"Biospecimen Qualification in a Clinical Biobank of Urological Diseases","year":2023,"lang":"en","type":"article","venue":"Biopreservation and Biobanking","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Biobank; Biomarker discovery; Biorepository; Workflow; Context (archaeology); Biomarker; Medicine; Medical physics; Computer science; Bioinformatics; Biology; Database","score_opus":0.7818091384601079,"score_gpt":0.6197198261396243,"score_spread":0.16208931232048363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387930839","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937538,0.00006985664,0.0029499324,0.0019364093,0.00029693186,0.00039890167,0.00007540216,0.00016223974,0.0003565424],"genre_scores_gemma":[0.93695146,0.00023969631,0.062348407,0.0001722704,0.00017421934,0.0000262538,0.000015875503,0.000014091854,0.000057736946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972755,0.0006561292,0.0012456005,0.00034605272,0.0002764082,0.00020033952],"domain_scores_gemma":[0.9861387,0.013085727,0.0003272024,0.00028613184,0.00008475733,0.00007745544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003856782,0.00011634824,0.00043811608,0.00017276748,0.000044832206,0.000024153196,0.00018122156,0.00019696813,0.00013185323],"category_scores_gemma":[0.039155193,0.000092621856,0.0000898742,0.0006798888,0.00023402028,0.00007430326,0.00014175675,0.00014397521,0.000019294379],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022157263,0.00034655226,0.6121364,0.00016470366,0.000031727493,0.000007404158,0.00009847204,0.0000010408068,0.0018155504,0.34931624,0.0019876747,0.033872668],"study_design_scores_gemma":[0.00052997656,0.0000818544,0.5012691,0.000043389682,0.000018483439,3.178772e-7,0.000041998206,0.00095358473,0.00022189389,0.49630594,0.00044712564,0.000086315995],"about_ca_topic_score_codex":0.000017203804,"about_ca_topic_score_gemma":0.000004949856,"teacher_disagreement_score":0.1469897,"about_ca_system_score_codex":0.000013058093,"about_ca_system_score_gemma":0.000022456146,"threshold_uncertainty_score":0.9689384},"labels":[],"label_agreement":null},{"id":"W4388075741","doi":"10.1016/j.metip.2023.100127","title":"Effect sizes for equivalence testing: Incorporating the equivalence interval","year":2023,"lang":"en","type":"article","venue":"Methods in Psychology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Institute of Mental Health; Social Sciences and Humanities Research Council of Canada; National Institutes of Health","keywords":"Equivalence (formal languages); Mathematics; Monte Carlo method; Statistics; Interval (graph theory); Statistical hypothesis testing; Applied mathematics; Statistical physics; Econometrics; Combinatorics; Discrete mathematics; Physics","score_opus":0.7565199999694227,"score_gpt":0.7018465159510007,"score_spread":0.05467348401842198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388075741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010548198,0.00006597308,0.9791927,0.0015788024,0.003378523,0.0014745571,0.000027511518,0.00034581177,0.0033879257],"genre_scores_gemma":[0.0053938306,0.000016272252,0.99242145,0.00070130796,0.00044388935,0.0007762435,0.0000010194344,0.00006858639,0.00017740327],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9843281,0.012134682,0.0015667479,0.0008906088,0.00028538206,0.0007944909],"domain_scores_gemma":[0.60058975,0.39798465,0.00042044488,0.00081965566,0.00010672556,0.00007876136],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05995009,0.00031747753,0.0009945898,0.0001934855,0.0001600031,0.00004259553,0.0011233838,0.0003159789,0.00007890611],"category_scores_gemma":[0.5688584,0.00021766647,0.0002175878,0.0014681165,0.0006472577,0.00005944031,0.00041071017,0.0007203263,0.000055263128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041149362,0.000118394564,0.0023162887,0.0005118447,0.00005276334,0.0000335048,0.00023622865,0.00001073904,0.012083169,0.056619924,0.003373479,0.9242322],"study_design_scores_gemma":[0.0012038246,0.0011034318,0.0010055162,0.00020136512,0.000059582104,0.000018591198,0.0000425747,0.004562112,0.0027671526,0.9883481,0.00045194293,0.00023579557],"about_ca_topic_score_codex":0.0000053354165,"about_ca_topic_score_gemma":0.0000027171611,"teacher_disagreement_score":0.9317282,"about_ca_system_score_codex":0.000040809562,"about_ca_system_score_gemma":0.00003957932,"threshold_uncertainty_score":0.9679792},"labels":[],"label_agreement":null},{"id":"W4388500358","doi":"10.1093/eurheartj/ehad718","title":"Endpoint adjudication in cardiovascular clinical trials","year":2023,"lang":"en","type":"article","venue":"European Heart Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton; Impact","funders":"","keywords":"Medicine; Adjudication; Clinical endpoint; Surrogate endpoint; Endpoint Determination; Unstable angina; Clinical trial; Myocardial infarction; Blinding; Generalizability theory; Randomized controlled trial; Intensive care medicine; Cardiology; Internal medicine; Statistics","score_opus":0.8982108558697043,"score_gpt":0.6717259174122281,"score_spread":0.2264849384574762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388500358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3842995,0.0028049212,0.49700126,0.018895451,0.02795836,0.0047578686,0.00018536457,0.0019562976,0.06214098],"genre_scores_gemma":[0.17604607,0.0018089316,0.809265,0.0010088931,0.010840973,0.000020439598,0.000004552675,0.00023146413,0.00077363144],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9519663,0.04278233,0.0036022041,0.0004193141,0.00076357095,0.00046631208],"domain_scores_gemma":[0.9285689,0.06987736,0.0005086133,0.0006089567,0.0001070528,0.00032912337],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22016819,0.00017684288,0.0015236962,0.00024424386,0.00011481139,0.00009685492,0.00033712428,0.00010606006,0.00049204606],"category_scores_gemma":[0.4640812,0.00014117821,0.0012470732,0.0005401176,0.00011682374,0.000081245555,0.0001532333,0.0011904422,0.0015276144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005861232,0.00071006996,0.029210905,0.00015500942,0.0013899474,0.0028424403,0.00046061169,0.00014883891,0.0003178445,0.024780542,0.37619105,0.5632066],"study_design_scores_gemma":[0.0037627905,0.0002668045,0.30512413,0.00026870304,0.000260642,0.00019123782,0.00010248676,0.00034788673,0.000080945945,0.5715519,0.11768323,0.0003592296],"about_ca_topic_score_codex":0.0000012002849,"about_ca_topic_score_gemma":5.614178e-7,"teacher_disagreement_score":0.5628474,"about_ca_system_score_codex":0.000050602168,"about_ca_system_score_gemma":0.00008248503,"threshold_uncertainty_score":0.9992498},"labels":[],"label_agreement":null},{"id":"W4388569182","doi":"10.1016/j.conctc.2023.101229","title":"A promising biomarker adaptive Phase 2/3 design – Explained and expanded","year":2023,"lang":"en","type":"article","venue":"Contemporary Clinical Trials Communications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Canada Research Chairs; Michael Smith Health Research BC","keywords":"Biomarker; Interim; Population; Phase (matter); Interim analysis; Computer science; Oncology; Statistics; Medicine; Internal medicine; Biology; Mathematics; Clinical trial; Chemistry; Environmental health; Genetics; Geography","score_opus":0.9770189941231097,"score_gpt":0.7283008112332489,"score_spread":0.2487181828898608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388569182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013549011,0.002099188,0.937808,0.017745975,0.0020657366,0.011685076,0.00071212393,0.0023980332,0.011936879],"genre_scores_gemma":[0.31958023,0.0011151996,0.67765427,0.00036612994,0.0002773965,0.00047680302,0.000034128858,0.000084200336,0.00041164452],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9516116,0.0405378,0.00611735,0.00082321593,0.00044165953,0.00046837257],"domain_scores_gemma":[0.44345897,0.5508902,0.0017299011,0.0031004865,0.00030433707,0.0005161232],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09806287,0.00040275563,0.0025737123,0.00025573344,0.0004554151,0.00014635653,0.0013218987,0.00049033883,0.00011956746],"category_scores_gemma":[0.57271993,0.00033550995,0.00059650507,0.00094146957,0.0012796177,0.0002543514,0.0010938925,0.0008241123,0.00015034596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010770545,0.006162103,0.0010382421,0.00022705382,0.002789726,0.00011851692,0.0012693027,0.0000016306651,0.0032421465,0.26320302,0.21107484,0.5001029],"study_design_scores_gemma":[0.01445812,0.00083884783,0.00044317043,0.00034266931,0.0003082078,0.0000057810084,0.0004896415,0.013001582,0.0002175328,0.9646258,0.0047524045,0.000516282],"about_ca_topic_score_codex":0.00000951291,"about_ca_topic_score_gemma":0.0000029059308,"teacher_disagreement_score":0.70142275,"about_ca_system_score_codex":0.00003589784,"about_ca_system_score_gemma":0.00040371247,"threshold_uncertainty_score":0.9999097},"labels":[],"label_agreement":null},{"id":"W4388674303","doi":"10.3233/cbm-230181","title":"Subgroup identification of targeted therapy effects on biomarker for time to event data","year":2023,"lang":"en","type":"article","venue":"Cancer Biomarkers","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua","funders":"","keywords":"Biomarker; Oncology; Medicine; Event (particle physics); Identification (biology); Markov chain Monte Carlo; non-small cell lung cancer (NSCLC); Hazard ratio; Internal medicine; Lung cancer; Bayesian probability; Computer science; Artificial intelligence; Confidence interval","score_opus":0.4912394440649165,"score_gpt":0.5702434041205268,"score_spread":0.07900396005561028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388674303","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49716222,0.0010095245,0.4327637,0.013709585,0.011694521,0.021902263,0.019169329,0.0015205584,0.0010682866],"genre_scores_gemma":[0.28612027,0.0007027681,0.69635737,0.0022823254,0.0017384231,0.0051500117,0.0010284492,0.0005962379,0.0060241204],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974433,0.00043722708,0.00084081566,0.0006012225,0.00036236038,0.00031508534],"domain_scores_gemma":[0.9723607,0.025875906,0.00032642702,0.0011730915,0.00013081392,0.00013307431],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0045565804,0.00019124865,0.00048546758,0.00018399634,0.000059571365,0.000023045297,0.0006527396,0.00013171473,0.00029847666],"category_scores_gemma":[0.033012226,0.00016177954,0.00013193289,0.00078671484,0.00008047685,0.000051931052,0.00013854838,0.00005947839,0.00020722821],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020227225,0.00017091022,0.00015330105,0.0005097761,0.00071789743,0.0000030787533,0.00007764276,0.0000042951974,0.22552888,0.0013350657,0.32067338,0.44880304],"study_design_scores_gemma":[0.0077631506,0.0012296533,0.05881413,0.0010094364,0.00046806879,8.7138693e-7,0.00006222923,0.01684005,0.44553027,0.44080374,0.02631361,0.001164797],"about_ca_topic_score_codex":0.0000118113185,"about_ca_topic_score_gemma":0.0000018615773,"teacher_disagreement_score":0.44763824,"about_ca_system_score_codex":0.00007723117,"about_ca_system_score_gemma":0.00006475079,"threshold_uncertainty_score":0.9751331},"labels":[],"label_agreement":null},{"id":"W4389031975","doi":"10.1093/ofid/ofad500.448","title":"378. Cost-effectiveness of an adaptive platform trial design compared to sequential conventional clinical trials for comparative drug evaluations in bloodstream infections: a simulation study","year":2023,"lang":"en","type":"article","venue":"Open Forum Infectious Diseases","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto","funders":"","keywords":"Medicine; Clinical trial; Randomized controlled trial; Interim analysis; Standard deviation; Computer science; Statistics; Surgery; Internal medicine; Mathematics","score_opus":0.8875750236122256,"score_gpt":0.70748198118888,"score_spread":0.18009304242334567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389031975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5210022,0.0000059885133,0.42533606,0.000028420918,0.0015625521,0.049905658,0.0017843599,0.00020075505,0.00017402005],"genre_scores_gemma":[0.96524256,0.0000022438853,0.021608753,0.00003268777,0.0002341162,0.01262877,0.00016877647,0.00005391314,0.000028195462],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9744373,0.019847592,0.0036218732,0.0009113554,0.00068496214,0.00049690943],"domain_scores_gemma":[0.7417456,0.25559676,0.0010872129,0.0005021808,0.000749427,0.00031880967],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03935736,0.00040182925,0.0026591239,0.00050680724,0.00036039206,0.00020329714,0.0004972568,0.00018677762,0.00017479413],"category_scores_gemma":[0.18884851,0.00037328975,0.0005857366,0.0012468287,0.00021148114,0.00053380284,0.00033677163,0.00027834528,0.000036706206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.35466102,0.07417441,0.060682684,0.0003617379,0.003916144,0.000021363778,0.0012395619,0.4237682,0.00005227374,0.063530765,0.0028271792,0.014764672],"study_design_scores_gemma":[0.13155502,0.014766914,0.021087084,0.0003189635,0.0015095097,9.394597e-7,0.0019142588,0.12026265,0.0002014296,0.7078168,0.000025532448,0.00054091925],"about_ca_topic_score_codex":0.00026621195,"about_ca_topic_score_gemma":0.0006364202,"teacher_disagreement_score":0.64428604,"about_ca_system_score_codex":0.00026700232,"about_ca_system_score_gemma":0.00066453096,"threshold_uncertainty_score":0.9998719},"labels":[],"label_agreement":null},{"id":"W4389083440","doi":"10.1002/9781118445112.stat08443","title":"Partially Adaptive Treatment Strategies","year":2023,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval; Centre hospitalier de l'Université Laval","funders":"","keywords":"Adaptive strategies; Outcome (game theory); Computer science; Order (exchange); Function (biology); Mathematical optimization; Mathematics; Business","score_opus":0.629000070886294,"score_gpt":0.5615811766476559,"score_spread":0.067418894238638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389083440","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006117799,0.00038327536,0.7109483,0.000114224626,0.0022066687,0.0019887122,0.1728531,0.002965593,0.10853403],"genre_scores_gemma":[0.000028064018,0.0050687455,0.77652216,0.00005278002,0.0010484225,0.00020132204,0.00070604275,0.0021869668,0.21418552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99345076,0.0010062801,0.0019002276,0.0014070986,0.0011317562,0.0011038823],"domain_scores_gemma":[0.96992207,0.026476067,0.0013442751,0.0014305384,0.00031349374,0.00051353785],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008185902,0.0012432261,0.0024803744,0.00038288953,0.00012233909,0.00017028423,0.0007246416,0.00095462124,0.0063801887],"category_scores_gemma":[0.01692837,0.0010151768,0.00021373136,0.00043938172,0.00064532633,0.00007230723,0.00022384714,0.0008708344,0.0010718439],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015145144,0.0007510236,0.000008650098,0.00023095518,0.00069212884,0.00030487636,0.00007804159,0.0000061304095,0.0000049262962,0.5485498,0.37248263,0.07673944],"study_design_scores_gemma":[0.0013691684,0.0013755388,0.00003374421,0.0010282738,0.0006709809,0.000004126285,0.0002809477,0.00043533256,0.000009415549,0.807739,0.18604009,0.0010133841],"about_ca_topic_score_codex":0.0009006496,"about_ca_topic_score_gemma":0.014021246,"teacher_disagreement_score":0.25918925,"about_ca_system_score_codex":0.0003785781,"about_ca_system_score_gemma":0.0009872424,"threshold_uncertainty_score":0.9997059},"labels":[],"label_agreement":null},{"id":"W4389246535","doi":"10.1182/blood-2023-188791","title":"An Examination of Aggregate Side-Effects Mapped to Therapies Experienced By Patients with Relapsed Large B-Cell Lymphomas - an Analysis from the Lymphoma Coalition's 2022 Global Patient Survey","year":2023,"lang":"en","type":"article","venue":"Blood","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Spinal Cord Injury BC","funders":"","keywords":"Incidence (geometry); Medicine; Odds ratio; Statistic; Confidence interval; Contingency table; Statistics; Internal medicine; Mathematics","score_opus":0.08118743290582679,"score_gpt":0.39637385794495456,"score_spread":0.31518642503912775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389246535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9801791,0.000030703723,0.014077232,0.0000265308,0.00015866423,0.0009828347,0.004348116,0.00012659468,0.0000702427],"genre_scores_gemma":[0.96127146,0.00000844416,0.037666645,0.00016395065,0.00003308509,0.00018971684,0.0006146438,0.00003666043,0.000015398828],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9926428,0.004579305,0.0008032819,0.0006410005,0.00094255497,0.00039103982],"domain_scores_gemma":[0.98115647,0.016749615,0.00053522526,0.0010075129,0.00033793753,0.00021325286],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028023936,0.0002848807,0.0007180377,0.00009131777,0.00017108412,0.000073627016,0.00046922424,0.00015276436,0.00007877855],"category_scores_gemma":[0.011656563,0.00019613132,0.00012757222,0.0018160809,0.00012190504,0.00014119325,0.00011206457,0.0000658712,0.000013387315],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031555588,0.047123156,0.7999811,0.000260141,0.0053576184,0.00007296621,0.02812799,0.00007106213,0.0054146433,0.007930725,0.0023422735,0.100162745],"study_design_scores_gemma":[0.010070473,0.0018699573,0.9512301,0.000059234353,0.00094376906,1.5655742e-7,0.0015430131,0.00049507467,0.009668791,0.023708638,0.000020850888,0.00038991682],"about_ca_topic_score_codex":0.00039870522,"about_ca_topic_score_gemma":0.0002890349,"teacher_disagreement_score":0.151249,"about_ca_system_score_codex":0.000068545625,"about_ca_system_score_gemma":0.000051959843,"threshold_uncertainty_score":0.9966687},"labels":[],"label_agreement":null},{"id":"W4389887411","doi":"10.1200/op.23.00363","title":"Probability of Regulatory Approval Over Time: A Cohort Study of Cancer Therapies","year":2023,"lang":"en","type":"article","venue":"JCO Oncology Practice","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; Thunder Bay Regional Health Sciences Centre; McGill University","funders":"","keywords":"Medicine; Clinical trial; Cohort; Hazard ratio; Food and drug administration; Cancer; Cancer drugs; Oncology; Drug; Internal medicine; Confidence interval; Pharmacology","score_opus":0.5416582212158485,"score_gpt":0.6211935414001712,"score_spread":0.07953532018432274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389887411","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99020094,0.000038572984,0.00036533832,0.00091128267,0.00054476236,0.002236351,0.000038679096,0.00011535287,0.0055487393],"genre_scores_gemma":[0.39916986,0.000100900965,0.5977861,0.00029143458,0.00032430427,0.0007729166,0.0000015002266,0.00007306927,0.0014798839],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99339235,0.0041610347,0.0012393353,0.0004152186,0.0005555273,0.00023655209],"domain_scores_gemma":[0.87937737,0.11832386,0.0011689824,0.0006756267,0.0003947628,0.000059372425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013836462,0.00015652819,0.001063135,0.00007881189,0.000048359616,0.0000058243786,0.00028245436,0.00026066456,0.0006065713],"category_scores_gemma":[0.16166992,0.00012822295,0.00010459571,0.00048740034,0.00039449925,0.00011870895,0.00020659651,0.00038335318,0.000030007272],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013370367,0.052011266,0.5158215,0.002496021,0.011569646,0.00022020981,0.019990662,0.00013174055,0.010871437,0.16250587,0.06568216,0.14532913],"study_design_scores_gemma":[0.0041070306,0.0029630007,0.36259046,0.000058267287,0.001727485,0.0000067455353,0.0019192587,0.0003198115,0.00066034775,0.6180716,0.0072794207,0.00029654137],"about_ca_topic_score_codex":0.00016733022,"about_ca_topic_score_gemma":0.000033936038,"teacher_disagreement_score":0.59742075,"about_ca_system_score_codex":0.00013093674,"about_ca_system_score_gemma":0.00028966792,"threshold_uncertainty_score":0.8453917},"labels":[],"label_agreement":null},{"id":"W4390116414","doi":"10.1016/j.ajog.2023.12.025","title":"Reply: when the clinical point gets lost in the decimal point","year":2023,"lang":"en","type":"letter","venue":"American Journal of Obstetrics and Gynecology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University Health Centre; Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Rounding; Decimal; Arithmetic; Point (geometry); Medicine; Set (abstract data type); Position (finance); Mathematical economics; Statistics; Mathematics; Computer science; Programming language; Operating system; Economics","score_opus":0.34591481448451633,"score_gpt":0.5002201119885037,"score_spread":0.15430529750398736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390116414","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075412327,0.00076562597,0.004026865,0.9758581,0.010162348,0.0007758546,0.00009077228,0.000020894153,0.00075832225],"genre_scores_gemma":[0.0021096577,0.0034563155,0.18328871,0.80573744,0.0048353863,0.000026411168,0.0000034579682,0.00014860072,0.00039404465],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9860059,0.007988144,0.003894274,0.000524134,0.00087752915,0.000710046],"domain_scores_gemma":[0.40048125,0.59521455,0.0031002332,0.0007498952,0.0003337463,0.000120305514],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.020530041,0.00041787117,0.0024329734,0.0004263604,0.00011562703,0.000112375215,0.0014928484,0.00060448464,0.00014025021],"category_scores_gemma":[0.6502667,0.00021857618,0.0006291262,0.00071392604,0.0017878708,0.000053463733,0.00036429567,0.006522114,0.000044611774],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058251873,0.0001562257,0.0012147133,0.000051393763,0.00030442417,0.005130648,0.00047051537,6.32582e-7,1.9965174e-7,0.0013298191,0.8684726,0.1228106],"study_design_scores_gemma":[0.0010881877,0.0025418417,0.0036362188,0.00009217235,0.00039206652,0.00030832138,0.00071767747,0.000019647965,4.6236028e-7,0.5607074,0.430233,0.00026300634],"about_ca_topic_score_codex":0.00002977338,"about_ca_topic_score_gemma":0.000012007187,"teacher_disagreement_score":0.62973666,"about_ca_system_score_codex":0.00014464447,"about_ca_system_score_gemma":0.00032481574,"threshold_uncertainty_score":0.99576986},"labels":[],"label_agreement":null},{"id":"W4390192845","doi":"10.1002/alz.071534","title":"Outcome imbalance in clinical trials: Mitigating loss of statistical power","year":2023,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Covariate; Placebo; Medicine; Statistical power; Clinical trial; Dementia; Internal medicine; Statistics; Mathematics; Pathology; Alternative medicine; Disease","score_opus":0.6570225338237523,"score_gpt":0.6211792348968838,"score_spread":0.03584329892686855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390192845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4746877,0.010637435,0.46755698,0.004309177,0.018673593,0.008098282,0.0028692472,0.0016312014,0.011536382],"genre_scores_gemma":[0.5853962,0.000032571763,0.41418245,0.00014771447,0.00014574325,0.000041364874,0.0000063022526,0.00004034712,0.000007334444],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9860669,0.005559646,0.006412434,0.00064293446,0.00068775425,0.00063035876],"domain_scores_gemma":[0.8507665,0.14732562,0.00096572825,0.00062130863,0.000120486264,0.00020038772],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04168694,0.00027608318,0.0020275158,0.00014730463,0.00004832504,0.0000303923,0.00045689926,0.00028516926,0.0011726747],"category_scores_gemma":[0.26915812,0.00023894985,0.00039259793,0.00059239357,0.00042384755,0.00007461131,0.0002757999,0.00056625606,0.000269148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000395884,0.00091872993,0.47345138,0.000121186145,0.009614203,0.00025750246,0.00025212494,0.0000060821635,0.00022936298,0.42662096,0.017225696,0.07090687],"study_design_scores_gemma":[0.0027761864,0.00022743846,0.11535003,0.00011595957,0.005357529,0.0000025739325,0.00010419569,0.0006301862,0.0007658504,0.8737349,0.00055561645,0.00037953854],"about_ca_topic_score_codex":0.00001904102,"about_ca_topic_score_gemma":0.000010102448,"teacher_disagreement_score":0.44711393,"about_ca_system_score_codex":0.0000067500064,"about_ca_system_score_gemma":0.00007524906,"threshold_uncertainty_score":0.99974036},"labels":[],"label_agreement":null},{"id":"W4390192940","doi":"10.1002/alz.074336","title":"Simulation‐based effect size analysis in the absence of drug effects to inform the design of clinical trials in Alzheimer’s disease","year":2023,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Quebec - Clinical Research Organization in Cancer; Baycrest Hospital; University of Toronto; Montreal Neurological Institute and Hospital; Mila - Quebec Artificial Intelligence Institute; NeuroRx Research (Canada); Douglas Mental Health University Institute; McGill University","funders":"","keywords":"Placebo; Clinical trial; Randomization; Sample size determination; Medicine; Clinical endpoint; Randomized controlled trial; Clinical study design; Cognition; Alzheimer's disease; Cognitive decline; Disease; Statistics; Internal medicine; Dementia; Mathematics; Psychiatry","score_opus":0.5450740890218915,"score_gpt":0.5880025888336123,"score_spread":0.042928499811720866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390192940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32955804,0.009177606,0.6205392,0.005588672,0.0028411099,0.031252448,0.00036536696,0.00031101573,0.0003665187],"genre_scores_gemma":[0.91769785,0.000013322147,0.08148668,0.00039640718,0.00007261355,0.00030276974,0.000004585344,0.00002434272,0.0000014496497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.97117275,0.021995818,0.0048250593,0.0004979443,0.0010632013,0.00044520298],"domain_scores_gemma":[0.4044254,0.5933754,0.001016457,0.0009427799,0.00011244694,0.00012751402],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.094196156,0.00028484236,0.0021172294,0.00034405373,0.00006749786,0.00003410106,0.0008934361,0.00013471291,0.00013378635],"category_scores_gemma":[0.46448144,0.0001624808,0.0008231356,0.0037779785,0.00023690466,0.00007176546,0.00017350199,0.000335249,0.000034176355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00775315,0.0024484566,0.18345724,0.00039649027,0.064040944,0.00012114419,0.0029058512,0.48811227,0.00022530466,0.016491253,0.004194402,0.22985351],"study_design_scores_gemma":[0.0064742444,0.0007168651,0.4222622,0.00032479476,0.11507556,8.2107654e-8,0.000120203105,0.2763986,0.0034673496,0.17444457,0.00012507213,0.0005904524],"about_ca_topic_score_codex":0.000053551015,"about_ca_topic_score_gemma":0.000033475968,"teacher_disagreement_score":0.5881398,"about_ca_system_score_codex":0.000005175178,"about_ca_system_score_gemma":0.00012732515,"threshold_uncertainty_score":0.93271565},"labels":[],"label_agreement":null},{"id":"W4390232703","doi":"10.1111/sjos.12703","title":"Consistent covariances estimation for stratum imbalances under minimization method for covariate‐adaptive randomization","year":2023,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Cancer Society; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Estimator; Mathematics; Minification; Lemma (botany); Inference; Statistical inference; Statistics; Nominal level; Econometrics; Consistency (knowledge bases); Mathematical optimization; Computer science; Confidence interval; Artificial intelligence","score_opus":0.45836697133443993,"score_gpt":0.5438542984223877,"score_spread":0.08548732708794782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390232703","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001343149,0.00003506292,0.99390876,0.0004735824,0.0019125266,0.0012918996,0.0021339292,0.000043783384,0.00006615501],"genre_scores_gemma":[0.010104056,0.00007550945,0.9889085,0.00008318341,0.00041079076,0.000086588836,0.00007041557,0.00005070042,0.00021023191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99640703,0.0007060189,0.0017974059,0.00026741956,0.00047234425,0.0003497707],"domain_scores_gemma":[0.93271315,0.063883305,0.0017841739,0.00016521032,0.0012950676,0.00015907879],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059082303,0.00023849675,0.000992259,0.00022080076,0.00021255836,0.00011565183,0.00021998711,0.00016597631,0.000052626754],"category_scores_gemma":[0.060467325,0.00020078738,0.00021722882,0.00040381736,0.00014191962,0.00016416145,0.000023062132,0.0001784107,0.0000036874872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046520117,0.00015128283,0.0000647594,0.00051755836,0.00051442126,0.000015014588,0.000329789,0.011413988,0.00011896206,0.92341447,0.03212676,0.02668098],"study_design_scores_gemma":[0.0075782184,0.00080926827,0.00028041026,0.00024894153,0.0005842465,0.000020652249,0.00033043156,0.18001334,0.00024818568,0.8095917,0.0001075881,0.00018697379],"about_ca_topic_score_codex":0.000002740337,"about_ca_topic_score_gemma":0.0000045571855,"teacher_disagreement_score":0.16859937,"about_ca_system_score_codex":0.00012468014,"about_ca_system_score_gemma":0.00026863164,"threshold_uncertainty_score":0.94744676},"labels":[],"label_agreement":null},{"id":"W4390236152","doi":"10.1002/pst.2357","title":"Evaluation of a flexible piecewise linear mixed‐effects model in the analysis of randomized cross‐over trials","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Government of Canada","keywords":"Univariate; Mixed model; Random effects model; Generalized linear mixed model; Piecewise; Linear model; Statistics; Computer science; Sample size determination; Residual; Piecewise linear function; Econometrics; Meta-analysis; Mathematics; Medicine; Algorithm; Multivariate statistics; Internal medicine","score_opus":0.8296799381412743,"score_gpt":0.7032816473815637,"score_spread":0.12639829075971054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390236152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06910845,0.00016224835,0.9245887,0.000105194544,0.00047284257,0.0030507187,0.001959478,0.000059774076,0.0004926128],"genre_scores_gemma":[0.49075413,0.00018071194,0.50822026,0.00011702666,0.000104036895,0.00048055314,0.000041985855,0.000039326467,0.0000619612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96993154,0.021211246,0.004484775,0.00051848846,0.0033015402,0.0005523951],"domain_scores_gemma":[0.6906849,0.30705062,0.0008885551,0.0004858894,0.0007715098,0.0001185088],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12584095,0.0002765193,0.0033474043,0.00047673608,0.000052915715,0.000032896496,0.00045913222,0.00019006077,0.00065582583],"category_scores_gemma":[0.55810446,0.00018180275,0.00070809165,0.0026111628,0.00064684835,0.00005416464,0.00012483395,0.0003991924,0.000017261122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021737363,0.0015442921,0.00047885554,0.0009988544,0.0073683406,0.0000241526,0.0014841121,0.048607476,0.00057222694,0.8505479,0.0030880342,0.06354836],"study_design_scores_gemma":[0.031168723,0.00002550489,0.00066881126,0.000029393104,0.0131392935,1.4860264e-7,0.000017051212,0.50647855,0.0008874774,0.44748405,0.000005172753,0.00009583998],"about_ca_topic_score_codex":0.000025762372,"about_ca_topic_score_gemma":0.000006401874,"teacher_disagreement_score":0.45787108,"about_ca_system_score_codex":0.0000755614,"about_ca_system_score_gemma":0.00016532018,"threshold_uncertainty_score":0.9001307},"labels":[],"label_agreement":null},{"id":"W4390261761","doi":"10.1016/j.jns.2023.121747","title":"The neuro genomics partnership: A new consortium dedicated to a fully open patient to patient (P2P) integrative R&amp;D approach","year":2023,"lang":"en","type":"article","venue":"Journal of the Neurological Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"General partnership; Neuroscience; Genomics; Medicine; Computational biology; Computer science; Psychology; Biology; Business; Genetics; Genome; Gene","score_opus":0.6271965198336298,"score_gpt":0.5360306364603269,"score_spread":0.09116588337330289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390261761","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.905663,0.000028488741,0.012670762,0.07523636,0.0021199614,0.0020453404,0.000018901448,0.000055940898,0.002161223],"genre_scores_gemma":[0.432912,0.000054739256,0.53460807,0.031059219,0.00060936,0.00010708616,2.752865e-7,0.000041879182,0.0006073753],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936377,0.0027123012,0.0014425237,0.00046390842,0.0011562338,0.00058732356],"domain_scores_gemma":[0.95544046,0.042253636,0.0009693787,0.00046833119,0.00024084793,0.0006273328],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007114543,0.00023606542,0.00062497595,0.000096277785,0.00061026507,0.00043997043,0.003484392,0.00010620722,0.000051101535],"category_scores_gemma":[0.21624625,0.00009241541,0.00025969476,0.0017624311,0.00064037007,0.000093433075,0.0018511184,0.00073867216,0.00005516366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054250667,0.0017046388,0.0057668076,0.00003487941,0.0002752198,0.00019445748,0.008881004,0.0070168027,0.0035349315,0.10937467,0.67953587,0.17825566],"study_design_scores_gemma":[0.00062715635,0.00810687,0.005540604,0.00006137224,0.00010009356,0.00010816487,0.0010489924,0.0007165462,0.00045567838,0.90587,0.07705156,0.00031294348],"about_ca_topic_score_codex":0.000009945612,"about_ca_topic_score_gemma":0.000012450658,"teacher_disagreement_score":0.7964953,"about_ca_system_score_codex":0.000045711095,"about_ca_system_score_gemma":0.00030930003,"threshold_uncertainty_score":0.7903556},"labels":[],"label_agreement":null},{"id":"W4390298060","doi":"10.1002/pds.5746","title":"Assessing cumulative effects of medication use: New insights and new challenges","year":2023,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Spurious relationship; Pharmacoepidemiology; Covariate; Cumulative incidence; Econometrics; Cumulative effects; Intensive care medicine; Actuarial science; Pharmacology; Statistics; Cohort; Internal medicine; Economics","score_opus":0.6520777044900588,"score_gpt":0.6033826546866505,"score_spread":0.04869504980340822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390298060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.338384,0.019179983,0.5818292,0.051008873,0.0039804424,0.002350637,0.00003680382,0.00075927615,0.0024708223],"genre_scores_gemma":[0.37049618,0.037244815,0.58944774,0.0012341866,0.0009369798,0.00002418611,0.000009413199,0.000050323015,0.0005561965],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946546,0.0036717146,0.0008850298,0.00040414731,0.00013631694,0.00024820396],"domain_scores_gemma":[0.72248197,0.27668738,0.00036808697,0.0001672352,0.00003912802,0.00025620937],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0057092644,0.00018106884,0.00085296005,0.00009387586,0.00009102824,0.000008303375,0.00010338135,0.00018249058,0.00003478363],"category_scores_gemma":[0.16469784,0.00014153156,0.000058564972,0.00015823332,0.00027576945,0.0001995867,0.00014298328,0.00030924153,0.0000074705117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036858124,0.000103092556,0.0032516348,0.001397549,0.0004278621,0.000023243474,0.0042899,0.000015166278,0.00169031,0.44790813,0.031786423,0.5087381],"study_design_scores_gemma":[0.0016681977,0.000042110714,0.0407789,0.00020745836,0.00019966948,0.0000033464548,0.000084307045,0.0019170496,0.0011778884,0.9512922,0.0024788945,0.00014996566],"about_ca_topic_score_codex":0.000059035203,"about_ca_topic_score_gemma":0.00000586134,"teacher_disagreement_score":0.50858814,"about_ca_system_score_codex":0.000013772888,"about_ca_system_score_gemma":0.000065870736,"threshold_uncertainty_score":0.84233826},"labels":[],"label_agreement":null},{"id":"W4390443395","doi":"10.1093/ibd/izad314","title":"The Clinical Interpretation of Noninferiority Trials","year":2023,"lang":"en","type":"review","venue":"Inflammatory Bowel Diseases","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute; Lawson Health Research Institute; Western University","funders":"","keywords":"Interpretation (philosophy); Medicine; Clinical trial; Intensive care medicine; Medical physics; Computer science; Internal medicine","score_opus":0.6835547578576393,"score_gpt":0.6370260637667221,"score_spread":0.0465286940909172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390443395","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011598153,0.9868064,0.0029348717,0.000023232622,0.0046741273,0.0032793717,0.0016091171,0.00034830466,0.0003129751],"genre_scores_gemma":[0.0000023202037,0.9871203,0.010423735,0.000014844685,0.0014313861,0.0005537012,0.000018774064,0.00015348263,0.00028151067],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97035366,0.017586758,0.010025738,0.000714489,0.0008532705,0.00046606213],"domain_scores_gemma":[0.546108,0.44706833,0.0048455354,0.0014007714,0.00027303983,0.00030428972],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.027018955,0.0006244959,0.0067690476,0.00014909152,0.0001799089,0.00012251797,0.001170055,0.000719293,0.00012888326],"category_scores_gemma":[0.64840686,0.0003654762,0.0038902864,0.00032690977,0.000921745,0.0000772898,0.00043395348,0.0008200261,0.00031883322],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015761008,0.00012764476,0.00006293176,0.025782647,0.0011319498,0.000041538464,0.000013888078,1.800106e-7,1.11926495e-8,0.03081129,0.005739563,0.93613076],"study_design_scores_gemma":[0.0005192678,0.00009659655,0.00026282246,0.019347128,0.0071146367,0.0000022468882,0.000020872714,0.000033535693,1.769745e-7,0.58067816,0.39145473,0.00046985524],"about_ca_topic_score_codex":0.0000018838059,"about_ca_topic_score_gemma":0.0000057085736,"teacher_disagreement_score":0.9356609,"about_ca_system_score_codex":0.00008722687,"about_ca_system_score_gemma":0.0011156156,"threshold_uncertainty_score":0.9998797},"labels":[],"label_agreement":null},{"id":"W4390489379","doi":"10.2174/0118743641266764231019092255","title":"Characteristics of Design and Statistical Analysis of NEI-funded Ophthalmic Clinical Trials","year":2023,"lang":"en","type":"article","venue":"The Open Ophthalmology Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Conestoga College","funders":"","keywords":"Medicine; Clinical trial; Sample size determination; Randomized controlled trial; Research design; Statistical analysis; Descriptive statistics; Ophthalmology; Optometry; Surgery; Statistics; Internal medicine","score_opus":0.8642453158032709,"score_gpt":0.6840842963498837,"score_spread":0.18016101945338725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390489379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76780194,0.00004968093,0.22721602,0.00066755153,0.0012355305,0.0013890492,0.0005030164,0.00002203736,0.0011151753],"genre_scores_gemma":[0.57924724,0.00023174747,0.41997036,0.00004358768,0.00020102564,0.00002134367,0.000006186943,0.000036624257,0.00024187968],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9670229,0.025833884,0.005699217,0.00043568306,0.0005346662,0.00047365908],"domain_scores_gemma":[0.7054135,0.29063702,0.0027783336,0.00062720483,0.00030415447,0.00023974084],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11060458,0.00026445548,0.0039631133,0.00035691328,0.00018190552,0.000097302254,0.0014045193,0.00035026373,0.0023270648],"category_scores_gemma":[0.30349,0.00016559343,0.0005197392,0.0011203911,0.001220943,0.00008479329,0.0007383592,0.00087365194,0.000017153488],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020445764,0.0037685975,0.23430847,0.0006495148,0.04629783,0.0048407987,0.0014848475,0.00025417778,0.0027393631,0.56876904,0.017320171,0.09912142],"study_design_scores_gemma":[0.0016154986,0.00093045464,0.21343714,0.00006460922,0.004938175,0.0010507362,0.00011980273,0.0027280273,0.000104999584,0.7748184,0.000014553877,0.00017756745],"about_ca_topic_score_codex":0.00001777323,"about_ca_topic_score_gemma":2.929997e-7,"teacher_disagreement_score":0.26480314,"about_ca_system_score_codex":0.00002322123,"about_ca_system_score_gemma":0.00021655502,"threshold_uncertainty_score":0.9985849},"labels":[],"label_agreement":null},{"id":"W4390533163","doi":"10.1007/s11606-023-08582-w","title":"Clinician’s Approach to Advanced Statistical Methods: Win Ratios, Restricted Mean Survival Time, Responder Analyses, and Standardized Mean Differences","year":2024,"lang":"en","type":"review","venue":"Journal of General Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Kelowna General Hospital; Interior Health","funders":"","keywords":"Medicine; Comprehension; Outcome (game theory); GRASP; MEDLINE; Medical physics; Statistics; Computer science","score_opus":0.6741069546110572,"score_gpt":0.6648238089072688,"score_spread":0.009283145703788409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390533163","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020407359,0.5256703,0.4678497,0.00028568957,0.0031012257,0.000833958,0.00036167275,0.000043237545,0.0018338283],"genre_scores_gemma":[0.0000023720393,0.43841094,0.5566893,0.0001170219,0.0026691416,0.000020325797,0.000009969188,0.00010516295,0.0019757384],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97736174,0.0113659315,0.0075813397,0.0010138851,0.0020454163,0.00063170947],"domain_scores_gemma":[0.92458785,0.069747105,0.0031001177,0.00069420016,0.0008131146,0.0010576289],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.017337091,0.0010865609,0.009964375,0.0011888399,0.000088927576,0.00016354256,0.0011287897,0.0006164055,0.00046347696],"category_scores_gemma":[0.1396505,0.00060940284,0.00090947683,0.0010471843,0.00055535306,0.00011525869,0.00041380315,0.0027906054,0.000021099922],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019149095,0.0002814084,0.0000022044878,0.0072316946,0.0042669894,0.0005191141,0.00038359442,0.0000015395827,0.00017303383,0.013135372,0.053870596,0.91821957],"study_design_scores_gemma":[0.006164312,0.007484916,0.000040029667,0.068762824,0.034934603,0.0011970656,0.000482364,0.00073518255,0.00003888764,0.37653312,0.5017216,0.0019050568],"about_ca_topic_score_codex":0.0000389294,"about_ca_topic_score_gemma":0.0000075103508,"teacher_disagreement_score":0.9163145,"about_ca_system_score_codex":0.00036471942,"about_ca_system_score_gemma":0.00058498856,"threshold_uncertainty_score":0.99963576},"labels":[],"label_agreement":null},{"id":"W4390543639","doi":"10.28924/2291-8639-22-2024-4","title":"Comparison of Test Statistics for Mean Difference Testing Between Two Independent Populations","year":2024,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Rajamangala University of Technology Phra Nakhon","keywords":"Mathematics; Statistics; Laplace distribution; Z-test; Gamma distribution; Normal distribution; Exponential function; Laplace transform; Exponential distribution; Normal population; Log-normal distribution; Type I and type II errors; Anderson–Darling test; Mann–Whitney U test; Population; Kolmogorov–Smirnov test; Statistical hypothesis testing; Mathematical analysis; Test statistic; Medicine","score_opus":0.6338973606985229,"score_gpt":0.6392526808591578,"score_spread":0.005355320160634891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390543639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015644185,0.00008152241,0.98254794,0.000266955,0.000109107255,0.00016429923,0.0010797036,0.000011297256,0.000094995004],"genre_scores_gemma":[0.53487396,0.000007649798,0.46478447,0.000006287273,0.00027205743,0.000012919785,0.00001130828,0.0000062917547,0.000025051686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978784,0.00007221644,0.0013650857,0.0001560643,0.0004420476,0.00008621828],"domain_scores_gemma":[0.9652133,0.032907,0.00069946045,0.00012600831,0.0009704563,0.00008374987],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011427088,0.00009512703,0.0005220057,0.00033656042,0.00005552462,0.00009042804,0.00027998444,0.00004512456,0.00003425734],"category_scores_gemma":[0.009787658,0.00007748456,0.00018627831,0.00044001525,0.000080099206,0.000047829875,0.000049843988,0.00017208821,9.305915e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000158111,0.000363303,0.24873306,0.00008921424,0.0024149248,0.000002156088,0.00017899735,0.00021165141,0.0010981711,0.5626458,0.0002972361,0.18394965],"study_design_scores_gemma":[0.0002881984,0.00009730788,0.051281888,0.00008737015,0.0027187,0.0000039813826,0.00007150128,0.018323865,0.00044025588,0.9263589,0.00023648357,0.00009156272],"about_ca_topic_score_codex":0.000017636867,"about_ca_topic_score_gemma":0.000027694392,"teacher_disagreement_score":0.51922977,"about_ca_system_score_codex":0.00003967788,"about_ca_system_score_gemma":0.0000562677,"threshold_uncertainty_score":0.99855334},"labels":[],"label_agreement":null},{"id":"W4390571373","doi":"10.1038/s41598-023-50694-0","title":"Magnitude of effect and sample size justification in trials supporting anti-cancer drug approval by the US Food and Drug Administration","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Université de Sherbrooke; Kingston Health Sciences Centre; Princess Margaret Cancer Centre; University of Toronto","funders":"National Breast Cancer Foundation","keywords":"Food and drug administration; Drug; Sample size determination; Medicine; Drug approval; Sample (material); Drug trial; Drug administration; Cancer drugs; Clinical trial; Administration (probate law); Pharmacology; Statistics; Internal medicine; Political science; Mathematics; Law; Chemistry","score_opus":0.24804629855162694,"score_gpt":0.5233359054179799,"score_spread":0.27528960686635295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390571373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99201185,0.00045348704,0.0025098072,0.00054283877,0.0029132238,0.0013204515,0.0001123864,0.00004693047,0.00008900725],"genre_scores_gemma":[0.9407124,0.000025211823,0.058572754,0.000010119128,0.00009882801,0.00011433535,0.000008096118,0.000019385392,0.00043889147],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995043,0.0013654636,0.0020564976,0.00077458844,0.0005239249,0.00023655902],"domain_scores_gemma":[0.9079926,0.09018601,0.0010132157,0.0005941813,0.000118543685,0.00009548129],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045301758,0.00016185376,0.000663384,0.00007983867,0.00012912936,0.00037959832,0.00010043789,0.00007854785,0.000092354516],"category_scores_gemma":[0.2179743,0.000105707884,0.00009546461,0.00039643206,0.0004495681,0.00011391106,0.00007304049,0.00020143368,7.7537925e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005563632,0.001086376,0.042065527,0.012890332,0.0006416709,0.00027461705,0.0076926467,0.00002207364,0.34590283,0.025861097,0.09424726,0.4687592],"study_design_scores_gemma":[0.0004561125,0.000105084575,0.0013159583,0.00033785836,0.00031774788,0.000044617722,0.00018104979,0.00061452005,0.20911038,0.7862627,0.0010400001,0.00021399737],"about_ca_topic_score_codex":0.000042953212,"about_ca_topic_score_gemma":0.000047109916,"teacher_disagreement_score":0.76040155,"about_ca_system_score_codex":0.000025951693,"about_ca_system_score_gemma":0.00014175051,"threshold_uncertainty_score":0.98306274},"labels":[],"label_agreement":null},{"id":"W4390603547","doi":"10.1200/po.23.00441","title":"Handling Incomplete or Late-Onset Toxicities in Early-Phase Dose-Finding Clinical Trials: Current Practice and Future Prospects","year":2024,"lang":"en","type":"article","venue":"JCO Precision Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research","funders":"National Institute for Health and Care Research; Cancer Research UK","keywords":"Clinical trial; Clinical study design; Limiting; Medicine; Research design; Toxicity; Medical physics; Computer science; Internal medicine; Statistics; Mathematics; Engineering","score_opus":0.7710930725259459,"score_gpt":0.7075061255547076,"score_spread":0.06358694697123835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390603547","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85568506,0.00664962,0.08454189,0.00998527,0.03246893,0.006281411,0.00046569295,0.00070210994,0.003220026],"genre_scores_gemma":[0.0961214,0.0048598694,0.89177513,0.00051156426,0.00592483,0.00030827068,0.0000076209253,0.00011477335,0.00037653573],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9809581,0.012762968,0.0041684443,0.0010161089,0.0005512102,0.0005431911],"domain_scores_gemma":[0.6285784,0.3700326,0.0006450256,0.00038034588,0.00012990592,0.00023372266],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054774866,0.00035687705,0.0022558447,0.00033015688,0.00013017304,0.00025111137,0.00032639384,0.0007449366,0.00046493084],"category_scores_gemma":[0.46362916,0.00024373253,0.00026903162,0.0005272851,0.00029493237,0.00029111654,0.00041164874,0.0018277518,0.0000773524],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056409277,0.001080217,0.00039281702,0.0003098905,0.00013647335,0.0005664504,0.0011845845,9.3289896e-7,0.000042408297,0.023725023,0.004023665,0.9628966],"study_design_scores_gemma":[0.008919994,0.0044954796,0.0011145262,0.0011676695,0.00043485546,0.00013019437,0.0005095192,0.0030354613,0.00008718701,0.7488206,0.23081376,0.00047077963],"about_ca_topic_score_codex":0.0000086065675,"about_ca_topic_score_gemma":0.000039382216,"teacher_disagreement_score":0.9624258,"about_ca_system_score_codex":0.00019938896,"about_ca_system_score_gemma":0.0004967667,"threshold_uncertainty_score":0.9939124},"labels":[],"label_agreement":null},{"id":"W4390606967","doi":"10.21203/rs.3.rs-3829844/v1","title":"Adaptive designs in clinical trials: a systematic review-part I","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; SickKids Foundation; George & Fay Yee Centre for Healthcare Innovation; University of Toronto; Robarts Clinical Trials; Institute for Clinical Evaluative Sciences; University of Calgary; University of Manitoba","funders":"Canadian Institutes of Health Research; Seqirus; Research Manitoba; Natural Sciences and Engineering Research Council of Canada; GlaxoSmithKline","keywords":"Clinical trial; Psychological intervention; MEDLINE; Medicine; Clinical study design; Systematic review; Alternative medicine; Adaptive design; Research design; Medical physics; Pathology; Psychiatry","score_opus":0.9597932867401129,"score_gpt":0.773089904623649,"score_spread":0.18670338211646387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390606967","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010860802,0.48230422,0.1619821,0.019730406,0.0265612,0.24670273,0.008509318,0.0027402493,0.050383687],"genre_scores_gemma":[0.0073924935,0.084106825,0.8651163,0.0007690616,0.0075355293,0.027565997,0.00005903476,0.0008295586,0.0066251974],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7407141,0.23165599,0.017748915,0.0029845587,0.0050556767,0.0018407829],"domain_scores_gemma":[0.2559802,0.7358876,0.0019214372,0.0038318904,0.0015955493,0.00078330893],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.462166,0.00071366894,0.010024168,0.00078497606,0.0000972039,0.00029804726,0.0017948163,0.0016675161,0.0009541802],"category_scores_gemma":[0.93245965,0.00051203044,0.0021950556,0.0013596662,0.0006406805,0.000039833692,0.0044088815,0.011638161,0.0015654538],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023037982,0.0005733526,0.00001224414,0.856067,0.00061619794,0.0004687105,0.00011373179,0.0000017668743,8.8662205e-7,0.078457646,0.06167027,0.0017878007],"study_design_scores_gemma":[0.00037161284,0.00027076993,0.0000069883436,0.4223702,0.0006899652,0.0000034610262,0.0001261634,0.0007084172,0.0000050339077,0.5751025,0.00006370976,0.0002811645],"about_ca_topic_score_codex":0.000043450367,"about_ca_topic_score_gemma":0.000036775786,"teacher_disagreement_score":0.7031342,"about_ca_system_score_codex":0.000683848,"about_ca_system_score_gemma":0.0017365087,"threshold_uncertainty_score":0.9999591},"labels":[],"label_agreement":null},{"id":"W4390612672","doi":"10.1007/s11121-023-01615-0","title":"Correction: Sample Size Requirements to Test Subgroup-Specific Treatment Effects in Cluster-Randomized Trials","year":2024,"lang":"en","type":"erratum","venue":"Prevention Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences","keywords":"Sample size determination; Health psychology; Test (biology); Randomized controlled trial; Subgroup analysis; Public health; Cluster (spacecraft); Medicine; Psychology; Information retrieval; Statistics; Internal medicine; Computer science; Mathematics; Meta-analysis; Biology; Pathology","score_opus":0.5394783156114161,"score_gpt":0.5874439239453587,"score_spread":0.04796560833394259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390612672","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003396439,0.0009183296,0.62450653,0.0011789241,0.3333114,0.018807964,0.0003553657,0.00045119887,0.020130618],"genre_scores_gemma":[0.00091141346,0.0007333073,0.8121463,0.00016852359,0.0033402925,0.0030532402,0.00001697189,0.00011669506,0.17951325],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.984908,0.0065513495,0.004029916,0.0018461541,0.0018713397,0.00079327216],"domain_scores_gemma":[0.42023367,0.5760887,0.0015050682,0.0013499189,0.00036602397,0.00045660435],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.062694415,0.0006335881,0.004062059,0.00067439285,0.00020600657,0.0005211868,0.0008866307,0.00047895464,0.0007105076],"category_scores_gemma":[0.82069886,0.00047276367,0.00097415183,0.0023096334,0.0005273669,0.00020605882,0.00041143413,0.0007740986,0.00037303122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006987149,0.0021020356,0.000021702821,0.0009703172,0.00022567259,0.0000512321,0.00048442103,0.000008883809,0.00026967065,0.010961736,0.88351244,0.094404735],"study_design_scores_gemma":[0.029566295,0.0009174809,0.000068466616,0.0034647586,0.00053573557,0.0000051428315,0.000021257527,0.0008793274,0.00035643653,0.93414414,0.029515233,0.00052572106],"about_ca_topic_score_codex":0.00007987026,"about_ca_topic_score_gemma":0.0001366703,"teacher_disagreement_score":0.9231824,"about_ca_system_score_codex":0.0013573221,"about_ca_system_score_gemma":0.00079268834,"threshold_uncertainty_score":0.9997724},"labels":[],"label_agreement":null},{"id":"W4390690845","doi":"10.21203/rs.3.rs-3829888/v1","title":"Part II: Adaptive designs in pediatric clinical trials: specific examples, comparison with adult trials and a discussion for the child health community","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; George & Fay Yee Centre for Healthcare Innovation; University of Toronto; Robarts Clinical Trials; University of Calgary; University of Manitoba","funders":"Canadian Institutes of Health Research; Seqirus; Research Manitoba; GlaxoSmithKline","keywords":"Clinical trial; Frequentist inference; Medicine; Clinical study design; Medical physics; Research design; Adaptive design; Randomization; Bayesian probability; Computer science; Artificial intelligence; Bayesian inference; Pathology; Statistics","score_opus":0.9446607035116983,"score_gpt":0.7205767458541128,"score_spread":0.2240839576575855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390690845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03787714,0.05783417,0.63184714,0.09327423,0.008844676,0.14584033,0.021653704,0.0010069954,0.001821614],"genre_scores_gemma":[0.20259246,0.043056868,0.73207945,0.00024732368,0.011843236,0.009093331,0.00020809815,0.0004891574,0.0003900611],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7248802,0.25637972,0.011658697,0.0021672717,0.0030570165,0.0018570883],"domain_scores_gemma":[0.25219148,0.7416268,0.002236909,0.002361964,0.00090925576,0.0006735733],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.43138325,0.0006819938,0.006430499,0.00054883986,0.0013125939,0.0004485075,0.0013125702,0.001012185,0.00009700694],"category_scores_gemma":[0.6200443,0.00031596486,0.00089700264,0.0009228014,0.0009911004,0.000044623095,0.003636815,0.013329937,0.0000136193075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028162759,0.0075375405,0.0043994724,0.021425769,0.0016648707,0.000045434237,0.009050722,0.00010206538,0.0000012447439,0.26870307,0.2415916,0.41731545],"study_design_scores_gemma":[0.005382079,0.0051343283,0.0032585203,0.0069772205,0.0005071521,0.0000033691301,0.0049964376,0.002094563,0.000007631705,0.96743906,0.003677159,0.0005224593],"about_ca_topic_score_codex":0.00042857908,"about_ca_topic_score_gemma":0.001286365,"teacher_disagreement_score":0.698736,"about_ca_system_score_codex":0.0003947965,"about_ca_system_score_gemma":0.0015074337,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W4390692803","doi":"10.1208/s12248-023-00884-5","title":"Experience Learned and Perspectives on Using Model-Integrated Evidence in the Regulatory Context for Generic Drug Products—a Meeting Report","year":2024,"lang":"en","type":"article","venue":"The AAPS Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex (Canada)","funders":"U.S. Food and Drug Administration","keywords":"Regulatory science; Context (archaeology); Risk analysis (engineering); New product development; Computer science; Drug development; Management science; Best practice; Product (mathematics); Process management; Drug; Knowledge management; Business; Engineering; Medicine; Pharmacology; Marketing; Political science","score_opus":0.7837870201971107,"score_gpt":0.577030103451559,"score_spread":0.20675691674555163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390692803","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88802165,0.004237656,0.10031479,0.0060353656,0.00051063846,0.00069740694,0.0000047917733,0.000041011994,0.00013668029],"genre_scores_gemma":[0.7322923,0.0002064745,0.26663825,0.00014381768,0.0004709258,0.000027318682,7.112717e-8,0.000026218746,0.00019460163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969907,0.001243492,0.0007492094,0.00035546484,0.00041310964,0.0002480221],"domain_scores_gemma":[0.972753,0.02622246,0.00030031012,0.00044518887,0.00022417527,0.00005488479],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014908422,0.00015718196,0.0003228331,0.00006531342,0.00028591536,0.00023611813,0.00034278262,0.000051675866,0.000013503164],"category_scores_gemma":[0.103911296,0.00007780716,0.00009069631,0.00027670685,0.000298313,0.00014446901,0.0000545605,0.00065641163,0.0000010131627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023650415,0.00054143753,0.00033781925,0.00089796376,0.00047623814,0.0013492852,0.314869,0.004461833,0.050328292,0.52033895,0.01045117,0.09358296],"study_design_scores_gemma":[0.00031716592,0.0001156968,0.00007089006,0.0017350061,0.00012492221,0.0012177684,0.026580803,0.10525426,0.002441145,0.8617516,0.00019404407,0.00019665876],"about_ca_topic_score_codex":0.000011252154,"about_ca_topic_score_gemma":0.000002758035,"teacher_disagreement_score":0.34141266,"about_ca_system_score_codex":0.00011503382,"about_ca_system_score_gemma":0.00018556467,"threshold_uncertainty_score":0.9036368},"labels":[],"label_agreement":null},{"id":"W4391151740","doi":"10.1093/jpp/rgae004","title":"Exploring various measures of the area under the curve for the assessment of dose-proportionality and estimation of bioavailability","year":2024,"lang":"en","type":"article","venue":"Journal of Pharmacy and Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bioavailability; Proportionality (law); Pharmacokinetics; Area under the curve; Medicine; Area under curve; Pharmacology; Bioequivalence; Statistics; Mathematics; Law","score_opus":0.7901763475622181,"score_gpt":0.6177284978515124,"score_spread":0.1724478497107057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391151740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78698504,0.0014894564,0.20198135,0.00622057,0.0022877604,0.0008473721,0.00013064916,0.000006649785,0.00005116172],"genre_scores_gemma":[0.9655832,0.0006176374,0.033510834,0.00009749374,0.00015451056,0.000023227723,1.4612927e-7,0.000007762771,0.0000051886445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973224,0.0010410843,0.0011157027,0.00011248636,0.00030794894,0.00010038786],"domain_scores_gemma":[0.95609635,0.04265739,0.00078374875,0.0001185985,0.00030344242,0.000040442857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0094626,0.00009742311,0.00040574206,0.00003705691,0.00008155047,0.000011494786,0.00020526226,0.000033337823,0.00011846758],"category_scores_gemma":[0.0041840747,0.000043798344,0.00016565877,0.00013098965,0.0005612472,0.000090716305,0.00007621096,0.00033990032,4.8030785e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004743972,0.0028093075,0.023154275,0.011634192,0.008146243,0.000014730823,0.0044245725,0.0059278184,0.27782682,0.3495895,0.009405833,0.30232272],"study_design_scores_gemma":[0.0029684778,0.00032339495,0.025949704,0.00018528741,0.002721306,0.00005025538,0.0002603579,0.04876099,0.087179594,0.83045894,0.0010314829,0.00011022983],"about_ca_topic_score_codex":0.000012482475,"about_ca_topic_score_gemma":0.0000014216062,"teacher_disagreement_score":0.4808694,"about_ca_system_score_codex":0.000026966465,"about_ca_system_score_gemma":0.00018405366,"threshold_uncertainty_score":0.50090307},"labels":[],"label_agreement":null},{"id":"W4391214865","doi":"10.1164/rccm.202401-0101cp","title":"The Rise of Adaptive Platform Trials in Critical Care","year":2024,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Efficacy and Mechanism Evaluation Programme; Health Research Council of New Zealand; Medical Research Council; Canadian Institutes of Health Research; Minderoo Foundation; National Health and Medical Research Council; Novo Nordisk Fonden; National Institute for Health and Care Research; Novo Nordisk; FP7 Health; Medical Center, University of Pittsburgh; University of Pittsburgh; National University Health System; European Commission; Office of Health and Medical Research; NIHR Imperial Biomedical Research Centre; Dagmar Marshalls Fond; Wellcome Trust; National Sanitarium Association","keywords":"Medicine; Intensive care medicine; Critical illness; Intensive care; Critically ill","score_opus":0.4965038821477272,"score_gpt":0.596219751178647,"score_spread":0.09971586903091978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391214865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4816345,0.32494092,0.14538622,0.026759831,0.010228286,0.0019417297,0.0005159648,0.00014523836,0.008447302],"genre_scores_gemma":[0.965851,0.00021446437,0.0325462,0.00032759903,0.0010202897,0.0000098714545,1.2108771e-7,0.000027057415,0.0000033677495],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9929007,0.0030345817,0.0026837394,0.00025821725,0.0007820762,0.00034064025],"domain_scores_gemma":[0.7662598,0.23212498,0.0003069108,0.00023352078,0.00075661275,0.00031820964],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.013586636,0.00022192857,0.0018956779,0.00020989994,0.000092862065,0.00003685449,0.00027861586,0.00010999104,0.00009644842],"category_scores_gemma":[0.3968564,0.0001203227,0.00027457761,0.00044303294,0.0046275896,0.00010683457,0.000066499844,0.0009304512,0.0000013596929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013650788,0.00006199744,0.0004504318,0.000988781,0.00009967848,0.0005872353,0.0035799434,4.376249e-7,0.0001981991,0.4887588,0.00078208593,0.50312734],"study_design_scores_gemma":[0.002291632,0.019241156,0.0007155711,0.0044415826,0.0013146129,0.00013477824,0.11464653,0.000052874715,0.000852178,0.84636134,0.009598771,0.00034895833],"about_ca_topic_score_codex":0.000011279473,"about_ca_topic_score_gemma":0.000008121953,"teacher_disagreement_score":0.50277835,"about_ca_system_score_codex":0.000084349966,"about_ca_system_score_gemma":0.00025918317,"threshold_uncertainty_score":0.99808127},"labels":[],"label_agreement":null},{"id":"W4391302286","doi":"10.1200/jco.2024.42.4_suppl.110","title":"Toxicity-benefit analysis of advanced prostate cancer trials using weighted toxicity scoring.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Prostate cancer; Toxicity; Internal medicine; Oncology; Clinical endpoint; Hazard ratio; Clinical trial; Adverse effect; Cancer; Confidence interval","score_opus":0.741817832009525,"score_gpt":0.6914602367720749,"score_spread":0.05035759523745009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391302286","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93876445,0.0010995303,0.050171424,0.0016649074,0.0069769938,0.0005193635,0.00022818222,0.000043052303,0.00053208997],"genre_scores_gemma":[0.28774282,0.0016972403,0.7077492,0.00043518288,0.0020922364,0.00001212951,9.3095105e-7,0.000051164694,0.00021908],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97956,0.0054132724,0.013161548,0.0005023971,0.0009252963,0.00043747269],"domain_scores_gemma":[0.76469636,0.22630015,0.007053723,0.0004372297,0.001054164,0.0004584006],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0564492,0.0003057724,0.007987604,0.000652097,0.000053816406,0.000042617117,0.0005342694,0.0007403979,0.0010699498],"category_scores_gemma":[0.31341445,0.00020695993,0.0028933315,0.0016691949,0.00042484023,0.00021010422,0.0001620023,0.0015417736,0.000005015388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008090063,0.003361236,0.008053753,0.0007339196,0.026417581,0.00064822333,0.00040502258,0.0020484799,0.009643158,0.04886169,0.0018525077,0.88988435],"study_design_scores_gemma":[0.0067687714,0.006169799,0.007010848,0.0014374432,0.030079508,0.00003266364,0.00019074678,0.016459893,0.005949271,0.91871506,0.0066375113,0.0005484972],"about_ca_topic_score_codex":0.000021684875,"about_ca_topic_score_gemma":0.00004576111,"teacher_disagreement_score":0.8893359,"about_ca_system_score_codex":0.00030040677,"about_ca_system_score_gemma":0.0015965449,"threshold_uncertainty_score":0.9998432},"labels":[],"label_agreement":null},{"id":"W4391592232","doi":"10.3390/a17020075","title":"Assessing the Impact of Patient Characteristics on Genetic Clinical Pathways: A Regression Approach","year":2024,"lang":"en","type":"article","venue":"Algorithms","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Regression; Computer science; Regression analysis; Computational biology; Statistics; Mathematics; Biology; Machine learning","score_opus":0.594224206129209,"score_gpt":0.6069177949075084,"score_spread":0.012693588778299403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391592232","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6411808,0.00034936308,0.3504408,0.00016130507,0.003135307,0.0011566792,0.00025847956,0.0002491585,0.0030680515],"genre_scores_gemma":[0.41011998,0.000070693015,0.5889449,0.00005037616,0.00069639366,0.000033779976,0.0000038535713,0.000051725547,0.000028303573],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955447,0.0015416736,0.0015797869,0.00048298694,0.00054133317,0.00030953964],"domain_scores_gemma":[0.95433366,0.044301417,0.00039681976,0.000718426,0.00011121565,0.00013846358],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003560162,0.00026260005,0.0007749268,0.00006704447,0.000084189094,0.00015889987,0.00031997476,0.00023924679,0.00010027766],"category_scores_gemma":[0.031171132,0.00013074097,0.0005292562,0.00029027776,0.00027311928,0.00006416932,0.00014096279,0.00068780885,0.000033428252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054151322,0.00082446996,0.0006303932,0.00020242165,0.00027170323,0.000096042546,0.00038538716,0.000009747216,0.00010105549,0.00898268,0.002378273,0.98606366],"study_design_scores_gemma":[0.0008158072,0.0023346152,0.03360382,0.0016114593,0.00039247546,0.000071802555,0.00031142723,0.12837446,0.00040153388,0.83122206,0.00032057424,0.0005399931],"about_ca_topic_score_codex":0.000008916228,"about_ca_topic_score_gemma":3.8492853e-8,"teacher_disagreement_score":0.9855237,"about_ca_system_score_codex":0.00006816395,"about_ca_system_score_gemma":0.00016013275,"threshold_uncertainty_score":0.97698975},"labels":[],"label_agreement":null},{"id":"W4391613583","doi":"10.1177/10731911231225191","title":"The Effect of Missing Item Data on the Relative Predictive Accuracy of Correctional Risk Assessment Tools","year":2024,"lang":"en","type":"article","venue":"Assessment","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Carleton University","funders":"","keywords":"Psychology; Predictive validity; Missing data; Risk assessment; Clinical psychology; Applied psychology; Statistics; Computer science","score_opus":0.503237064702961,"score_gpt":0.6197641104501955,"score_spread":0.11652704574723449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391613583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020632468,0.00017703777,0.9480452,0.002510752,0.0038691442,0.00250336,0.00200578,0.00010589836,0.020150375],"genre_scores_gemma":[0.6848544,0.0001337375,0.31421414,0.00004156552,0.000340733,0.00018663587,0.000020473453,0.00004854066,0.00015980013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931756,0.0042371177,0.0010227851,0.00043502985,0.0009157721,0.00021364588],"domain_scores_gemma":[0.57331985,0.4252635,0.00045856662,0.00082378485,0.000095082745,0.000039236817],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014329958,0.00021081188,0.00054778514,0.000041658877,0.00023100695,0.0001292594,0.00068914844,0.0001015858,0.000150714],"category_scores_gemma":[0.16246031,0.00010061215,0.00018514202,0.0002694877,0.0003195015,0.0001921115,0.0003932787,0.00082959904,0.0000060188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000345618,0.00025472933,0.002443012,0.00035468474,0.0017941953,0.0000119019915,0.00022056536,0.00003900653,0.00019711579,0.7061333,0.015586473,0.27261943],"study_design_scores_gemma":[0.000663189,0.0019944801,0.01692461,0.0011902796,0.0009329344,0.000004686975,0.00025448075,0.05646123,0.0023607577,0.9175451,0.00149217,0.00017612231],"about_ca_topic_score_codex":0.000012942075,"about_ca_topic_score_gemma":0.0000018002153,"teacher_disagreement_score":0.6642219,"about_ca_system_score_codex":0.0001693281,"about_ca_system_score_gemma":0.00028430115,"threshold_uncertainty_score":0.84459466},"labels":[],"label_agreement":null},{"id":"W4391635477","doi":"10.1177/09622802241227957","title":"Covariate adjustment in Bayesian adaptive randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Covariate; Frequentist inference; Statistics; Econometrics; Bayesian probability; Early stopping; Propensity score matching; Sample size determination; Bayes' theorem; Statistical power; Computer science; Mathematics; Bayesian inference; Machine learning","score_opus":0.7649940798972175,"score_gpt":0.7342759921159407,"score_spread":0.030718087781276715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391635477","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002816643,0.0022505254,0.9670026,0.0048548253,0.0023528575,0.0069857165,0.00017021762,0.00014740672,0.01620773],"genre_scores_gemma":[0.005347639,0.0012706058,0.98775417,0.0002533924,0.00089013035,0.0037984946,0.0000056303375,0.000111161404,0.0005687728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.554706,0.41536453,0.014720243,0.0026996734,0.009288176,0.0032214096],"domain_scores_gemma":[0.050114468,0.946977,0.0003615649,0.00082053273,0.00044337343,0.0012830548],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6087418,0.00061509066,0.011988528,0.0016223936,0.00010306066,0.00022573635,0.0010461356,0.0010518493,0.022439327],"category_scores_gemma":[0.975462,0.00038219837,0.0010029912,0.0024364346,0.0029617534,0.000102776154,0.00056644593,0.005670205,0.00016262053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.056511637,0.00038355554,0.0000021060723,0.00029503848,0.00034648654,0.0010767775,0.00017549844,0.0000012674892,0.00002343387,0.6258604,0.0018057429,0.31351808],"study_design_scores_gemma":[0.12315683,0.00027350165,0.000040899427,0.0014917002,0.00022279489,0.000009698261,0.00014715563,0.10959825,0.000044611996,0.7643821,0.00034536823,0.00028704604],"about_ca_topic_score_codex":0.0002504678,"about_ca_topic_score_gemma":0.00007278492,"teacher_disagreement_score":0.53161246,"about_ca_system_score_codex":0.0006358026,"about_ca_system_score_gemma":0.0017689648,"threshold_uncertainty_score":0.99986297},"labels":[],"label_agreement":null},{"id":"W4391650553","doi":"10.1002/pst.2365","title":"Assessing the performance of group‐based trajectory modeling method to discover different patterns of medication adherence","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of Victoria; Public Health Ontario; University of Toronto; Cascades (Canada); Université Laval; NeuroDevNet","funders":"","keywords":"Covariate; Nonparametric statistics; Variance (accounting); Trajectory; Statistics; Computer science; Medicine; Repeated measures design; Quality (philosophy); Medication adherence; Random effects model; Mathematics; Econometrics; Internal medicine; Meta-analysis","score_opus":0.620705524597161,"score_gpt":0.6302486008024275,"score_spread":0.00954307620526651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391650553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09073558,0.00007821642,0.90714574,0.00022154427,0.00061604736,0.00047102716,0.0006203146,0.000051120125,0.00006044019],"genre_scores_gemma":[0.5211497,0.00002925788,0.47856155,0.00010046329,0.000085666245,0.00003495572,0.0000054772067,0.00002536257,0.000007547335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959903,0.0010983549,0.0013205202,0.00039343355,0.0008612642,0.0003361429],"domain_scores_gemma":[0.9496598,0.049446624,0.00019315987,0.00035789376,0.00014602169,0.00019646934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035379138,0.00024110766,0.0006116077,0.00008430226,0.00006663129,0.00006954826,0.00040200487,0.0000991919,0.0004176266],"category_scores_gemma":[0.010244667,0.00015484708,0.00011890466,0.00025125104,0.0001583527,0.00009877673,0.00011912767,0.00051085785,0.0000075233515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003607734,0.0011133214,0.00396829,0.010372874,0.00045969547,0.000021530099,0.0008265578,0.004615426,0.017271256,0.45965737,0.000650346,0.5006826],"study_design_scores_gemma":[0.00039308227,0.0001960902,0.0011992818,0.0006716483,0.0004257342,0.000001572131,0.000052594663,0.88655704,0.012196591,0.09804442,0.000077636985,0.00018430158],"about_ca_topic_score_codex":0.00001941526,"about_ca_topic_score_gemma":0.0000029084147,"teacher_disagreement_score":0.8819416,"about_ca_system_score_codex":0.000074638585,"about_ca_system_score_gemma":0.00010380544,"threshold_uncertainty_score":0.9980925},"labels":[],"label_agreement":null},{"id":"W4391652457","doi":"10.1002/sim.10034","title":"Correction to “Using principal stratification in analysis of clinical trials”","year":2024,"lang":"en","type":"erratum","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Statistics; Principal (computer security); Stratification (seeds); Computer science; Econometrics; Mathematics; Biology","score_opus":0.7621167309528273,"score_gpt":0.699804452428747,"score_spread":0.06231227852408028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391652457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002214159,0.00027273872,0.8579487,0.00032411003,0.12789401,0.0017128381,0.002182731,0.000052534855,0.009390866],"genre_scores_gemma":[0.0012677747,0.0005971269,0.9739206,0.00014988001,0.005026922,0.00009438788,0.0005193707,0.00013026214,0.018293684],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9772938,0.007675082,0.011974127,0.0011706472,0.0014311885,0.00045519316],"domain_scores_gemma":[0.8048681,0.19114675,0.00240065,0.0009155444,0.00042481846,0.00024411581],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06774205,0.0004829765,0.006878934,0.0024443148,0.000025297164,0.000025714839,0.00046093934,0.00094546174,0.0008946944],"category_scores_gemma":[0.76153326,0.00039671577,0.00037958648,0.0038535262,0.00041731953,0.000026446884,0.0001392418,0.00318184,0.000014609168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037599975,0.00037922247,0.0007128298,0.0012603842,0.0014425052,0.00012073932,0.0006270888,0.00020456617,0.00002028086,0.08292353,0.8675707,0.044362184],"study_design_scores_gemma":[0.0014280367,0.0006665721,0.0061943475,0.005385965,0.010864818,0.0000018060715,0.00032369726,0.16262414,0.0000058215687,0.80593437,0.00606669,0.0005037626],"about_ca_topic_score_codex":0.0006329586,"about_ca_topic_score_gemma":0.0036612512,"teacher_disagreement_score":0.86150396,"about_ca_system_score_codex":0.00033208122,"about_ca_system_score_gemma":0.0007261274,"threshold_uncertainty_score":0.9998485},"labels":[],"label_agreement":null},{"id":"W4391714990","doi":"10.1016/j.ygyno.2024.02.003","title":"High grade adverse event reporting and enrolment in gynecologic oncology clinical trials","year":2024,"lang":"en","type":"article","venue":"Gynecologic Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Saskatchewan; Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Medicine; Clinical trial; Odds ratio; Adverse effect; Internal medicine; Odds; Gynecologic oncology; Oncology; Logistic regression","score_opus":0.7534761201980854,"score_gpt":0.6731920710918551,"score_spread":0.08028404910623033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391714990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9113693,0.001294973,0.02018782,0.020061988,0.02773448,0.0064453674,0.00012334788,0.0010907876,0.011691905],"genre_scores_gemma":[0.5085989,0.0011521127,0.48569676,0.0020087438,0.0011305213,0.0007980958,0.000008887322,0.000068158784,0.00053781254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9575475,0.025038576,0.013727724,0.0019152029,0.00048099825,0.0012900223],"domain_scores_gemma":[0.5243251,0.47002628,0.0042771874,0.00072581746,0.00013719067,0.00050844444],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.13495357,0.00058712263,0.0052345735,0.00038527386,0.0001495617,0.00005277893,0.0005126903,0.0022623092,0.002802555],"category_scores_gemma":[0.71404684,0.0004396219,0.000757426,0.00057820755,0.00088251434,0.00011607712,0.00069746235,0.002312653,0.00019755716],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065947726,0.0041444213,0.011927143,0.00048391006,0.0006688884,0.010526241,0.0003947488,0.00004759369,0.00032660307,0.24620615,0.019028807,0.705586],"study_design_scores_gemma":[0.004339131,0.006345054,0.022800406,0.00011601504,0.000559338,0.00020510815,0.0004739724,0.0008185296,0.00007952609,0.9142018,0.049524207,0.0005368861],"about_ca_topic_score_codex":0.000046852794,"about_ca_topic_score_gemma":0.0003077959,"teacher_disagreement_score":0.70504916,"about_ca_system_score_codex":0.0014464321,"about_ca_system_score_gemma":0.001162582,"threshold_uncertainty_score":0.99998903},"labels":[],"label_agreement":null},{"id":"W4391728595","doi":"10.1007/978-3-031-17299-1_974","title":"F-Ratio","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Geology","score_opus":0.8421445345605199,"score_gpt":0.612784474269569,"score_spread":0.2293600602909509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391728595","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.2213104e-8,0.0000056965023,0.09364143,0.00024085221,0.0011316793,0.00031104582,0.000095943906,0.00047119503,0.9041021],"genre_scores_gemma":[4.045063e-7,0.000032559565,0.41708112,0.00013336624,0.000477199,0.000007863653,0.0000020638222,0.000091935435,0.5821735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809057,0.000065986496,0.0008752745,0.0003763046,0.00041065182,0.00018123946],"domain_scores_gemma":[0.93289685,0.066103324,0.00023153394,0.00057742576,0.000088461515,0.00010238948],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015438414,0.0002607961,0.000791693,0.00007070861,0.000032967615,0.000028287222,0.0002392101,0.000571402,0.014473151],"category_scores_gemma":[0.05444899,0.00020907425,0.00024495527,0.00002072114,0.00011046614,0.000013187921,0.00014562263,0.00045557032,0.0073453537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005272998,0.0000054123875,1.0624762e-7,0.00006344663,0.00007132279,0.000022316766,0.000003938958,2.5378418e-8,0.0000010716304,0.8818867,0.10971328,0.008227106],"study_design_scores_gemma":[0.00013537332,0.000040100673,7.564905e-7,0.0001166627,0.00011514769,0.0000011688239,0.0000012250015,0.000013838542,0.000015362986,0.9369198,0.062411383,0.00022914643],"about_ca_topic_score_codex":0.0000012131234,"about_ca_topic_score_gemma":0.0000056817953,"teacher_disagreement_score":0.3234397,"about_ca_system_score_codex":0.000029837325,"about_ca_system_score_gemma":0.000048154736,"threshold_uncertainty_score":0.9934275},"labels":[],"label_agreement":null},{"id":"W4391744832","doi":"10.1136/bmj-2023-076460","title":"Process guide for inferential studies using healthcare data from routine clinical practice to evaluate causal effects of drugs (PRINCIPLED): considerations from the FDA Sentinel Innovation Center","year":2024,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; U.S. Food and Drug Administration","keywords":"Computer science; Emulation; Robustness (evolution); Protocol (science); Causal inference; Data science; Health care; Process (computing); Data mining; Risk analysis (engineering); Medical physics; Management science; Medicine; Alternative medicine; Psychology","score_opus":0.8129981009244894,"score_gpt":0.7172472921381222,"score_spread":0.09575080878636721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391744832","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37537014,0.00065824535,0.5491831,0.054389473,0.007930909,0.0068253535,0.0053263605,0.00018963453,0.00012679087],"genre_scores_gemma":[0.18545844,0.000024103685,0.8088803,0.002281641,0.0029417463,0.00017753764,0.00015741913,0.00005034749,0.000028426688],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99325275,0.0022920878,0.002873729,0.00069434906,0.00062846806,0.00025858844],"domain_scores_gemma":[0.5670399,0.4271892,0.0012268602,0.0017366506,0.0026821063,0.00012531695],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012198533,0.0002178591,0.0007915259,0.000060567236,0.00015303875,0.000114756265,0.0003413943,0.00015221145,0.000046857727],"category_scores_gemma":[0.6312706,0.00015296093,0.00009634885,0.0003743926,0.00013586362,0.00020946033,0.0005920015,0.00035713977,0.000014474527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002641841,0.0025228863,0.010755457,0.0077166473,0.010787849,0.00011712246,0.011821661,0.00011962401,0.0028245214,0.34386256,0.5815957,0.025234135],"study_design_scores_gemma":[0.0031337994,0.00019699713,0.002135407,0.0023793178,0.0021171975,0.0000050612794,0.0010293213,0.019986158,0.0013929001,0.9649061,0.002367919,0.000349839],"about_ca_topic_score_codex":0.00018074877,"about_ca_topic_score_gemma":0.000086989494,"teacher_disagreement_score":0.6210435,"about_ca_system_score_codex":0.00005924591,"about_ca_system_score_gemma":0.0005424278,"threshold_uncertainty_score":0.6237565},"labels":[],"label_agreement":null},{"id":"W4391787823","doi":"10.1016/j.jeph.2024.202198","title":"Practical considerations for sample size calculation for cluster randomized trials","year":2024,"lang":"en","type":"article","venue":"Journal of Epidemiology and Population Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"Medical Research Council","keywords":"Sample size determination; CRTS; Statistics; Cluster (spacecraft); Computer science; Cluster randomised controlled trial; Sample (material); Covariate; Correlation; Statistical power; A priori and a posteriori; Econometrics; Randomized controlled trial; Mathematics; Medicine","score_opus":0.8556723633553084,"score_gpt":0.7092489836697732,"score_spread":0.1464233796855352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391787823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083065795,0.0005174679,0.90829927,0.086807765,0.00143504,0.001959037,0.00012656295,0.000018604464,0.000005573244],"genre_scores_gemma":[0.024358151,0.0002612083,0.96992403,0.0040271934,0.0012926518,0.00008630917,0.0000078527555,0.000016558333,0.000026049913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97855747,0.01565582,0.0051961886,0.00022119128,0.00011067477,0.0002586399],"domain_scores_gemma":[0.10032634,0.897095,0.0020277943,0.000103044666,0.00027126633,0.00017654298],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15856466,0.00012634131,0.0026594563,0.00010106757,0.00017511506,0.000025160236,0.00002523226,0.00024273545,0.00009366462],"category_scores_gemma":[0.9643921,0.000083061015,0.0005593678,0.00005629819,0.00010957918,0.00012183483,0.000009180667,0.00026933514,5.355132e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011781702,0.000038572332,0.00028558171,0.00043456565,0.0002203945,5.8250424e-7,0.00008860715,0.000058296508,0.0000016090954,0.92121935,0.061223567,0.004647171],"study_design_scores_gemma":[0.020110063,0.0003182288,0.00035817426,0.00014116052,0.00037952873,0.00006053957,0.0000113036185,0.022060566,0.0000016102468,0.95458406,0.0019051298,0.00006960594],"about_ca_topic_score_codex":0.000024939693,"about_ca_topic_score_gemma":0.000009837989,"teacher_disagreement_score":0.8814392,"about_ca_system_score_codex":0.000063131396,"about_ca_system_score_gemma":0.00026361088,"threshold_uncertainty_score":0.86643475},"labels":[],"label_agreement":null},{"id":"W4391883872","doi":"10.1080/03610918.2024.2316281","title":"Adjustment of selection bias for clinical trials: a simulation study","year":2024,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Selection (genetic algorithm); Selection bias; Computer science; Psychology; Econometrics; Statistics; Artificial intelligence; Mathematics","score_opus":0.9281858327685717,"score_gpt":0.7468491497132794,"score_spread":0.18133668305529227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391883872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012337884,0.0003694656,0.9835122,0.000107740736,0.0005160201,0.0027004208,0.0002694948,0.0001108652,0.00007588738],"genre_scores_gemma":[0.54941446,0.00009720397,0.45020267,0.000015702428,0.00007637752,0.000110538895,0.000043968044,0.000021666032,0.000017440596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9903411,0.0054176515,0.0033429167,0.00041826922,0.00031691615,0.00016309645],"domain_scores_gemma":[0.7490261,0.24944682,0.00059860403,0.00041114097,0.00045418815,0.00006310092],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017470537,0.00019572428,0.0008446957,0.00034094538,0.00013212182,0.000092648974,0.00021626432,0.0001666215,0.000030183926],"category_scores_gemma":[0.10222085,0.00018728401,0.00012764901,0.0005657618,0.00017581326,0.00013518464,0.00011708059,0.00031056817,0.0000033420156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028416666,0.0015377011,0.0030526123,0.00037186278,0.00020098795,6.984691e-7,0.0012182278,0.17110834,0.000007729241,0.21013933,0.00039665966,0.6116817],"study_design_scores_gemma":[0.001058657,0.00031675887,0.0058424775,0.00008996061,0.00019652529,2.8703064e-7,0.0001814878,0.6021959,0.000001866622,0.38977605,0.00023671512,0.00010331986],"about_ca_topic_score_codex":0.000014596857,"about_ca_topic_score_gemma":0.00004293958,"teacher_disagreement_score":0.6115784,"about_ca_system_score_codex":0.000092586255,"about_ca_system_score_gemma":0.000110200795,"threshold_uncertainty_score":0.9053415},"labels":[],"label_agreement":null},{"id":"W4392101232","doi":"10.51387/24-nejsds60","title":"Nonparametric E-tests of Symmetry","year":2024,"lang":"en","type":"article","venue":"The New England Journal of Statistics in Data Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Symmetry (geometry); Statistical physics; Mathematics; Computer science; Physics; Econometrics; Geometry","score_opus":0.449767996736839,"score_gpt":0.56192055813586,"score_spread":0.11215256139902097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392101232","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018521484,0.00079289597,0.974714,0.00071793754,0.0029683781,0.00020410198,0.0012435968,0.0000137592615,0.00082384126],"genre_scores_gemma":[0.19007346,0.00035707533,0.80907834,0.000027448328,0.00040155987,3.373506e-7,0.000001045289,0.000011276522,0.000049443515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99664766,0.0003709561,0.0013296589,0.0002585584,0.0011256794,0.00026747936],"domain_scores_gemma":[0.886828,0.11123164,0.0005230942,0.00095129316,0.00028201772,0.00018393039],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021722296,0.0001187391,0.0004741533,0.00044356065,0.000053158783,0.00012536242,0.0025470105,0.000049718994,0.000079645804],"category_scores_gemma":[0.27393147,0.00006873372,0.000035185818,0.002138008,0.00079261954,0.00035800066,0.00050164765,0.0005949019,0.0000071530717],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104671046,0.0001254161,0.0003997435,0.00023130536,0.000047079928,0.00018267486,0.0003656808,0.000019283434,0.00057843537,0.6982177,0.023643082,0.27608496],"study_design_scores_gemma":[0.00087280164,0.00018030367,0.001511639,0.00033037024,0.00009221252,0.00012166987,0.000042571595,0.003869255,0.0003115725,0.99074227,0.0018374469,0.000087911765],"about_ca_topic_score_codex":0.000021042282,"about_ca_topic_score_gemma":0.000017520819,"teacher_disagreement_score":0.29252458,"about_ca_system_score_codex":0.00005388515,"about_ca_system_score_gemma":0.0007513599,"threshold_uncertainty_score":0.7528558},"labels":[],"label_agreement":null},{"id":"W4392188999","doi":"10.1093/aje/kwae015","title":"Standardizing to specific target populations in distributed networks and multisite pharmacoepidemiologic studies","year":2024,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Jewish General Hospital; McGill University","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Medicine; MEDLINE; Computer science; Biology","score_opus":0.711098140236725,"score_gpt":0.6450536034300726,"score_spread":0.06604453680665245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392188999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06138761,0.009952231,0.9207401,0.006174508,0.0013955192,0.00021188028,0.00008550576,0.000034327866,0.000018291492],"genre_scores_gemma":[0.22589664,0.0022830677,0.770361,0.0008863638,0.00053718215,0.000009071206,0.0000016131947,0.000020287875,0.000004750519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98985195,0.0064143143,0.002722131,0.00037940324,0.00012636892,0.0005058152],"domain_scores_gemma":[0.8031908,0.1954636,0.00073936343,0.00018034736,0.00016092659,0.00026491896],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026229698,0.00022508876,0.0022874079,0.00026350762,0.00005717609,0.00001260249,0.00020036277,0.00009202953,0.000048758277],"category_scores_gemma":[0.283476,0.00015934187,0.00019962568,0.00063044,0.0006096778,0.000075375596,0.00012462617,0.00078863476,0.0000038432127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010312118,0.00016726884,0.18407898,0.00017640524,0.0010281182,0.00064130354,0.0006824737,0.02485687,0.00014100851,0.37293825,0.06649178,0.34776634],"study_design_scores_gemma":[0.00041234703,0.00070302136,0.011820022,0.00043364626,0.0001041182,0.0001135717,0.0004953024,0.006035083,0.000006185247,0.97330123,0.006366033,0.00020944954],"about_ca_topic_score_codex":0.00001883773,"about_ca_topic_score_gemma":0.0000071677787,"teacher_disagreement_score":0.60036296,"about_ca_system_score_codex":0.00017877885,"about_ca_system_score_gemma":0.000030204024,"threshold_uncertainty_score":0.90907425},"labels":[],"label_agreement":null},{"id":"W4392587482","doi":"10.3390/curroncol31030104","title":"The REthinking Clinical Trials Program Retreat 2023: Creating Partnerships to Optimize Quality Cancer Care","year":2024,"lang":"en","type":"article","venue":"Current Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University; Ottawa Hospital; Champlain Regional College; Agricultural Research Institute of Ontario; University of Ottawa","funders":"","keywords":"Clinical trial; Medicine; Quality (philosophy); Alternative medicine; Health care; Medical education; Pathology; Political science","score_opus":0.966224249869411,"score_gpt":0.7965497604144846,"score_spread":0.16967448945492647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392587482","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11383166,0.11219973,0.2694964,0.08731995,0.27878183,0.04312069,0.002629615,0.0079868585,0.08463327],"genre_scores_gemma":[0.02239969,0.0032982547,0.9585754,0.00041865074,0.010647295,0.0034980464,0.00001777297,0.00014195072,0.0010029277],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96824807,0.02460107,0.004598603,0.0010772018,0.0006611208,0.0008139608],"domain_scores_gemma":[0.6242582,0.37364352,0.00064809434,0.0007150029,0.00035707245,0.0003780925],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06680782,0.00035652946,0.0020867828,0.000057710775,0.00037632283,0.00028049978,0.0006449275,0.0005718636,0.000392977],"category_scores_gemma":[0.5453352,0.00021974789,0.0007571514,0.00050263345,0.00047101366,0.000055082597,0.00038038476,0.0017792151,0.00010807645],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040276794,0.00020058973,0.0008288759,0.00046669465,0.00021587014,0.000020369087,0.0012831091,0.0000021447597,0.0000057346188,0.09129219,0.027548762,0.8777329],"study_design_scores_gemma":[0.0013674357,0.0010079582,0.00028329875,0.0010925943,0.00074968266,0.000004032329,0.001164358,0.00083634857,0.00006358734,0.5455719,0.44743595,0.00042282717],"about_ca_topic_score_codex":0.000021075566,"about_ca_topic_score_gemma":0.0001963278,"teacher_disagreement_score":0.8773101,"about_ca_system_score_codex":0.00052514864,"about_ca_system_score_gemma":0.000659094,"threshold_uncertainty_score":0.9609177},"labels":[],"label_agreement":null},{"id":"W4392589823","doi":"10.1007/s40471-024-00347-1","title":"Methodological Considerations on the Use of Cohort Designs in Drug-Drug Interaction Studies in Pharmacoepidemiology","year":2024,"lang":"en","type":"article","venue":"Current Epidemiology Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Charité – Universitätsmedizin Berlin","keywords":"Pharmacoepidemiology; Drug; Medicine; Epidemiology; Pharmacology; Internal medicine","score_opus":0.9834283021717272,"score_gpt":0.7453473391801506,"score_spread":0.23808096299157655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392589823","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7626843,0.01040034,0.16868746,0.025562424,0.026943035,0.004854738,0.00007442914,0.00036589408,0.000427406],"genre_scores_gemma":[0.4815727,0.0035467024,0.51216096,0.0013308071,0.00042558127,0.0008373156,0.000008362577,0.000043950655,0.00007363335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95017135,0.042835344,0.005234092,0.0010298654,0.00018065661,0.0005486669],"domain_scores_gemma":[0.26150134,0.7367463,0.0009705396,0.000566053,0.00013390477,0.00008184266],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07366663,0.00031455065,0.002279246,0.00028956207,0.00006148256,0.000009287263,0.00012442206,0.00021389678,0.00024159024],"category_scores_gemma":[0.83271533,0.00019000859,0.000292724,0.00035684436,0.00095978216,0.00010150532,0.00015728899,0.001514756,0.000012069562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018071484,0.0006043837,0.12908937,0.000563165,0.00056261104,0.0008603499,0.000794188,0.0025194408,0.00013516437,0.649035,0.20806287,0.0075927316],"study_design_scores_gemma":[0.00014681234,0.000052480922,0.004578922,0.0007685356,0.00015506927,0.00016982255,0.000084417814,0.0036274446,0.00023747617,0.98769367,0.002314602,0.00017077135],"about_ca_topic_score_codex":0.00006934685,"about_ca_topic_score_gemma":0.000043996748,"teacher_disagreement_score":0.7590487,"about_ca_system_score_codex":0.00017979075,"about_ca_system_score_gemma":0.00010399416,"threshold_uncertainty_score":0.95385516},"labels":[],"label_agreement":null},{"id":"W4392986539","doi":"10.1001/jamanetworkopen.2024.3109","title":"Characteristics, Progression, and Output of Randomized Platform Trials","year":2024,"lang":"en","type":"review","venue":"JAMA Network Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Moderna; National Science Foundation","keywords":"Randomized controlled trial; Medicine; Clinical trial; MEDLINE; Research design; Surgery; Pathology; Statistics","score_opus":0.7314667375683529,"score_gpt":0.6387401967170189,"score_spread":0.09272654085133403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392986539","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.65349e-7,0.97709537,0.0035489788,0.00011353342,0.0026312836,0.012240846,0.00057854096,0.0000714179,0.0037194737],"genre_scores_gemma":[4.068669e-7,0.6852257,0.3102756,0.000035113266,0.0023236768,0.00094340864,0.000034607456,0.000117940486,0.0010435085],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97631276,0.011877897,0.009624708,0.0009759594,0.00064127066,0.00056743214],"domain_scores_gemma":[0.72804457,0.26582685,0.004865887,0.0008589821,0.0001773206,0.0002263727],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.094837695,0.00075705006,0.023421625,0.00012495003,0.00007927898,0.00064424233,0.0012780308,0.0011140447,0.00031605814],"category_scores_gemma":[0.39325532,0.00042032107,0.0017218363,0.00040432304,0.00044633404,0.000115657145,0.001924411,0.0011371465,0.000072363466],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046685496,0.00005953485,4.8099406e-7,0.028120866,0.0016150735,0.000022853457,0.000027916649,1.08765645e-8,2.2935527e-9,0.10162039,0.03119964,0.83266467],"study_design_scores_gemma":[0.014363114,0.000054499764,3.7272713e-7,0.071932934,0.010543681,0.0000100565685,0.0000019877546,0.000020966236,7.910901e-8,0.47861743,0.4241527,0.00030217526],"about_ca_topic_score_codex":0.0000044384624,"about_ca_topic_score_gemma":6.2794544e-7,"teacher_disagreement_score":0.83236253,"about_ca_system_score_codex":0.000052397278,"about_ca_system_score_gemma":0.00034932152,"threshold_uncertainty_score":0.9998249},"labels":[],"label_agreement":null},{"id":"W4393038237","doi":"10.3389/jpps.2024.12398","title":"The bioequivalence study design recommendations for immediate-release solid oral dosage forms in the international pharmaceutical regulators programme participating regulators and organisations: differences and commonalities","year":2024,"lang":"en","type":"review","venue":"Journal of Pharmacy & Pharmaceutical Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"World Health Organization","keywords":"Bioequivalence; Guideline; Medicine; Pharmacology; Harmonization; Pharmacokinetics; Product (mathematics); Drug; Mathematics","score_opus":0.8279063205838922,"score_gpt":0.6643875318621865,"score_spread":0.16351878872170578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393038237","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008726562,0.9616306,0.0036233624,0.016298799,0.0032069793,0.006163211,0.00025406556,0.00006511529,0.00003134098],"genre_scores_gemma":[0.020757202,0.9366266,0.0405952,0.00026832908,0.00090817566,0.000760694,0.0000021266844,0.00005396871,0.000027704897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907175,0.0034866624,0.0030881679,0.00058932486,0.0013408326,0.00077754416],"domain_scores_gemma":[0.918425,0.0795945,0.0011568203,0.00021438977,0.00022189633,0.00038736546],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02793996,0.00054316845,0.0015116435,0.0002830761,0.00078360765,0.0011174781,0.0016024223,0.0001225713,0.000068955334],"category_scores_gemma":[0.024478378,0.00025523806,0.00035890692,0.00085101,0.0019839166,0.00040490323,0.0004214032,0.0013778224,0.0000023108214],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016089446,0.0006338271,0.0005841414,0.0017062183,0.0005194004,0.000031962165,0.0012315825,9.054716e-7,0.0000039479055,0.023381004,0.0013260557,0.97042006],"study_design_scores_gemma":[0.0035227896,0.0011645186,0.00007219603,0.004289802,0.00871326,0.00029819642,0.005308519,0.009506108,0.00004871603,0.35249957,0.61372787,0.00084846007],"about_ca_topic_score_codex":0.00001258049,"about_ca_topic_score_gemma":0.0000114136255,"teacher_disagreement_score":0.9695716,"about_ca_system_score_codex":0.00015700085,"about_ca_system_score_gemma":0.000526012,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W4393039792","doi":"10.1037/met0000507","title":"The Bayes factor, HDI-ROPE, and frequentist equivalence tests can all be reverse engineered—Almost exactly—From one another: Reply to Linde et al. (2021).","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Bayes factor; Rope; Bayesian probability; Bayes' theorem; Statistical hypothesis testing; Statistics; Equivalence (formal languages); Null hypothesis; Econometrics; Frequentist probability; Bayes' rule; Type I and type II errors; Mathematics; Bayesian inference; Computer science; Algorithm; Discrete mathematics","score_opus":0.6313980920682659,"score_gpt":0.6237437826978459,"score_spread":0.007654309370419998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393039792","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010545998,0.0020896194,0.90877885,0.068539254,0.0036262989,0.0014426231,0.0010016764,0.00054596266,0.0034297106],"genre_scores_gemma":[0.0044266805,0.0013262413,0.96444416,0.028362151,0.0003590778,0.00016056545,0.0000058095957,0.00010292862,0.0008123835],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99028474,0.005292278,0.0013956234,0.001583614,0.000642711,0.0008010072],"domain_scores_gemma":[0.8774553,0.12038993,0.0002013628,0.0013537684,0.00013399696,0.00046565794],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0113413865,0.00053773023,0.0010336355,0.00009486435,0.00017568997,0.00042897236,0.00086766464,0.00036100275,0.0015235175],"category_scores_gemma":[0.16123556,0.0003489009,0.00023807284,0.0005987626,0.0004661259,0.00009803714,0.00040476085,0.0012528831,0.00007448737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039773996,0.00072123157,0.00023215299,0.0001715834,0.00071666134,0.00031938488,0.0007775679,0.0000020988357,0.038541995,0.08809594,0.09960217,0.77042145],"study_design_scores_gemma":[0.0005359441,0.0006602589,0.0059552407,0.00036607383,0.00019950085,0.00002790042,0.000053484822,0.00013543418,0.0018802744,0.71393865,0.27562913,0.0006181348],"about_ca_topic_score_codex":0.00011725074,"about_ca_topic_score_gemma":0.000026290634,"teacher_disagreement_score":0.76980335,"about_ca_system_score_codex":0.00008853965,"about_ca_system_score_gemma":0.000046868823,"threshold_uncertainty_score":0.9998963},"labels":[],"label_agreement":null},{"id":"W4393219600","doi":"10.1016/j.jclinepi.2024.111336","title":"Randomized controlled trials of switching to a new medication vs continuing a chronic medication may underestimate the risk of adverse events in those continuing because of asymmetric depletion of susceptibles","year":2024,"lang":"en","type":"letter","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; St. Michael's Hospital; Sinai Health System","funders":"","keywords":"Medicine; Adverse effect; Randomized controlled trial; Intensive care medicine; Internal medicine","score_opus":0.5116991747776183,"score_gpt":0.6037577730203197,"score_spread":0.09205859824270146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393219600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0647161,0.0049172556,0.767059,0.15163332,0.0051890104,0.0062047928,0.00019527628,0.000024921741,0.00006029342],"genre_scores_gemma":[0.28302416,0.01739632,0.68018854,0.011123408,0.0077426406,0.00017438653,0.000026217182,0.0001867222,0.00013759015],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7252874,0.19097647,0.07942755,0.0010468104,0.0023432267,0.0009185865],"domain_scores_gemma":[0.07470493,0.84796375,0.075032964,0.0009114494,0.0011193508,0.0002675421],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4750215,0.00059432915,0.03410593,0.0014904992,0.000023734074,0.0000039670676,0.0012156818,0.0021738624,0.00014725207],"category_scores_gemma":[0.9735036,0.0003282446,0.0060969545,0.0008076746,0.00088458095,0.00008885339,0.00025026122,0.0045782356,0.0000038147436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.57456654,0.002142202,0.028698841,0.014280876,0.037344962,0.000121522746,0.003042163,0.0019397243,0.00071612996,0.032552194,0.13599846,0.16859637],"study_design_scores_gemma":[0.20186546,0.0016807675,0.0030354203,0.018322328,0.0128538385,0.000017877954,0.00009246861,0.0034510654,0.00010035057,0.7577309,0.0005483088,0.00030119394],"about_ca_topic_score_codex":0.0003105901,"about_ca_topic_score_gemma":0.000057763402,"teacher_disagreement_score":0.7251787,"about_ca_system_score_codex":0.00016576573,"about_ca_system_score_gemma":0.0009972524,"threshold_uncertainty_score":0.999917},"labels":[],"label_agreement":null},{"id":"W4393460561","doi":"10.5281/zenodo.3988468","title":"In silico prediction of ARB resistance: A first step in creating personalized ARB therapy","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"In silico; Resistance (ecology); Computational biology; Computer science; Biology; Genetics; Gene","score_opus":0.3436238533226868,"score_gpt":0.441407091339479,"score_spread":0.09778323801679217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393460561","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001801379,0.00011131097,0.0020264443,0.00045345424,0.00019525293,0.0014092711,0.98959506,0.00020764295,0.0058214087],"genre_scores_gemma":[0.000680731,0.0033488716,0.062372938,0.00044401482,0.0010424515,0.0000018231668,0.9280144,0.0033353537,0.00075944344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99444133,0.0023796658,0.0013313306,0.0006968452,0.00076104206,0.00038979732],"domain_scores_gemma":[0.9943911,0.003769455,0.0006069927,0.0007148452,0.0003564269,0.00016121293],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036875925,0.00029089017,0.00084053446,0.0003794131,0.00038893893,0.00020833263,0.0011719726,0.0003129876,0.011247941],"category_scores_gemma":[0.07704152,0.00029788702,0.00012191428,0.0010096099,0.00030475,0.000116190604,0.0007234755,0.0009970422,0.0007509895],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006962583,0.00037635388,0.0000017651066,0.00087675726,0.000060123464,0.000042649182,0.00049580104,0.0000030857543,0.00008153321,0.0030182437,0.99232435,0.0020230855],"study_design_scores_gemma":[0.0022795375,0.00031051153,0.000113343085,0.00059174094,0.000032523836,0.000006692578,0.00017195214,0.00012065335,0.00003630492,0.013195841,0.982928,0.00021291678],"about_ca_topic_score_codex":0.000050983952,"about_ca_topic_score_gemma":0.000008000993,"teacher_disagreement_score":0.073353924,"about_ca_system_score_codex":0.00028370682,"about_ca_system_score_gemma":0.000016248618,"threshold_uncertainty_score":0.9999473},"labels":[],"label_agreement":null},{"id":"W4393798584","doi":"10.5281/zenodo.3988469","title":"In silico prediction of ARB resistance: A first step in creating personalized ARB therapy","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"In silico; Resistance (ecology); Computer science; Computational biology; Biology; Genetics; Ecology","score_opus":0.3436238533226868,"score_gpt":0.441407091339479,"score_spread":0.09778323801679217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393798584","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001801379,0.00011131097,0.0020264443,0.00045345424,0.00019525293,0.0014092711,0.98959506,0.00020764295,0.0058214087],"genre_scores_gemma":[0.000680731,0.0033488716,0.062372938,0.00044401482,0.0010424515,0.0000018231668,0.9280144,0.0033353537,0.00075944344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99444133,0.0023796658,0.0013313306,0.0006968452,0.00076104206,0.00038979732],"domain_scores_gemma":[0.9943911,0.003769455,0.0006069927,0.0007148452,0.0003564269,0.00016121293],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036875925,0.00029089017,0.00084053446,0.0003794131,0.00038893893,0.00020833263,0.0011719726,0.0003129876,0.011247941],"category_scores_gemma":[0.07704152,0.00029788702,0.00012191428,0.0010096099,0.00030475,0.000116190604,0.0007234755,0.0009970422,0.0007509895],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006962583,0.00037635388,0.0000017651066,0.00087675726,0.000060123464,0.000042649182,0.00049580104,0.0000030857543,0.00008153321,0.0030182437,0.99232435,0.0020230855],"study_design_scores_gemma":[0.0022795375,0.00031051153,0.000113343085,0.00059174094,0.000032523836,0.000006692578,0.00017195214,0.00012065335,0.00003630492,0.013195841,0.982928,0.00021291678],"about_ca_topic_score_codex":0.000050983952,"about_ca_topic_score_gemma":0.000008000993,"teacher_disagreement_score":0.073353924,"about_ca_system_score_codex":0.00028370682,"about_ca_system_score_gemma":0.000016248618,"threshold_uncertainty_score":0.9999473},"labels":[],"label_agreement":null},{"id":"W4394090898","doi":"10.6084/m9.figshare.22927936","title":"A Bayesian Adaptive Umbrella Trial Design with Robust Information Borrowing for Screening Multiple Combination Therapies","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Bayesian probability; Adaptive design; Computer science; Medicine; Clinical trial; Artificial intelligence; Internal medicine","score_opus":0.7003996622566823,"score_gpt":0.4994523670938252,"score_spread":0.2009472951628571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394090898","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.5195347e-8,0.0000090648555,0.27614644,0.00002997448,0.0002504881,0.003735632,0.71966106,0.00015494274,0.000012321439],"genre_scores_gemma":[0.0000010120324,0.0000028924046,0.40179566,0.000060793533,0.0003255769,0.0020605114,0.5956834,0.00005043472,0.000019725578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99661857,0.0007566468,0.0011267869,0.0004160076,0.00066150475,0.00042048193],"domain_scores_gemma":[0.8779619,0.11979257,0.0011067167,0.0005394258,0.00048233592,0.00011706539],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016529859,0.0004597455,0.0009460392,0.00023391166,0.00023631306,0.00024828414,0.0005071716,0.0006483401,0.0041238284],"category_scores_gemma":[0.28575918,0.0003853425,0.00022868792,0.00034445425,0.000024393423,0.0003170975,0.0001415272,0.0005677907,0.0006096749],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008831339,0.000080869824,3.597215e-8,0.00095409696,0.00020312192,0.0000052970076,0.000048924056,0.00015538248,8.349302e-8,0.000055779365,0.9865576,0.0031074702],"study_design_scores_gemma":[0.09052598,0.0071073,0.000009386218,0.022543158,0.00090922316,0.0000069358957,0.00047835536,0.042948984,0.00005896021,0.115355335,0.7178523,0.0022040745],"about_ca_topic_score_codex":0.000023781753,"about_ca_topic_score_gemma":0.00002745907,"teacher_disagreement_score":0.2841062,"about_ca_system_score_codex":0.00008960452,"about_ca_system_score_gemma":0.00018891733,"threshold_uncertainty_score":0.99985987},"labels":[],"label_agreement":null},{"id":"W4394142622","doi":"10.6084/m9.figshare.22575157.v1","title":"What is a randomization test?","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Randomization; Test (biology); Restricted randomization; Computer science; Psychology; Medicine; Randomized controlled trial; Biology; Internal medicine","score_opus":0.67800825717898,"score_gpt":0.5872659920947213,"score_spread":0.09074226508425864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394142622","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.031012e-9,0.00007814112,0.000018367573,0.00015803159,0.0012140397,0.0009058101,0.99739796,0.00018508086,0.000042541313],"genre_scores_gemma":[2.5244586e-9,0.00024242557,0.017723322,0.00063119386,0.0010290024,0.0006902746,0.9787004,0.000076641976,0.0009067406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99722767,0.00044836284,0.0009246216,0.00053655263,0.00055436144,0.0003084284],"domain_scores_gemma":[0.7780526,0.21997263,0.00059872674,0.0010153139,0.0002190151,0.00014165862],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007762161,0.00032283153,0.0010175714,0.000110618435,0.000063943924,0.00029698657,0.0006006764,0.0007494123,0.34210703],"category_scores_gemma":[0.73044235,0.00029508572,0.0002764807,0.00033799506,0.000012697745,0.000118867436,0.00034763195,0.0005746034,0.08701602],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003116021,0.00005545748,1.4616792e-8,0.0013952247,0.00005174963,0.000035603505,0.0000061174605,1.0370002e-7,6.530978e-8,0.0000061887963,0.9966778,0.0017405073],"study_design_scores_gemma":[0.0013307974,0.000037921407,0.0000010320407,0.008100345,0.000120994715,0.0000016969411,0.000005620743,0.000020028552,0.000010114526,0.16977283,0.8203195,0.0002791775],"about_ca_topic_score_codex":0.000004098327,"about_ca_topic_score_gemma":0.000006878864,"teacher_disagreement_score":0.7296662,"about_ca_system_score_codex":0.00004705165,"about_ca_system_score_gemma":0.0001002594,"threshold_uncertainty_score":0.9999501},"labels":[],"label_agreement":null},{"id":"W4394189541","doi":"10.6084/m9.figshare.23518962","title":"Bayesian Modeling and Inference for One-Shot Experiments","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Inference; Bayesian inference; Bayesian probability; Shot (pellet); Econometrics; Computer science; Artificial intelligence; Machine learning; Statistics; Mathematics; Chemistry","score_opus":0.8959912511485137,"score_gpt":0.6434976447272281,"score_spread":0.2524936064212856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394189541","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9566231e-7,0.000037446138,0.0029854528,0.000021268474,0.00023022582,0.0009708574,0.9956196,0.00009808391,0.00003686342],"genre_scores_gemma":[0.0000010427965,0.000017333197,0.16923074,0.00009300351,0.00039642307,0.0011377353,0.82901174,0.00005611389,0.000055867426],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978415,0.00017591761,0.00073578075,0.00057565904,0.00032601526,0.00034513176],"domain_scores_gemma":[0.9475548,0.051220294,0.0002761077,0.0006342093,0.00014437904,0.00017020368],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00045246418,0.0003133888,0.00080794067,0.000084724255,0.000088641136,0.0001053596,0.0004367388,0.00054460514,0.025880696],"category_scores_gemma":[0.3675745,0.00030416533,0.00012310904,0.00010444981,0.0000122053025,0.000042559477,0.00041112315,0.0003847228,0.001109851],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019536734,0.000045489716,3.2182776e-8,0.0020085918,0.000056708857,0.000005963447,0.000008373102,0.0000027416183,7.104337e-7,0.000064062864,0.99727774,0.00051006593],"study_design_scores_gemma":[0.0008618251,0.00017336762,8.06411e-7,0.009963597,0.00017886721,0.0000012092987,0.000020366831,0.009394216,0.000044116125,0.6137632,0.3648608,0.0007376203],"about_ca_topic_score_codex":0.000011682124,"about_ca_topic_score_gemma":0.000011614333,"teacher_disagreement_score":0.6324169,"about_ca_system_score_codex":0.000034014512,"about_ca_system_score_gemma":0.000081895945,"threshold_uncertainty_score":0.99994105},"labels":[],"label_agreement":null},{"id":"W4394255645","doi":"10.6084/m9.figshare.19329384","title":"Bayesian Optimal Phase II Design for Randomized Clinical Trials","year":2022,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Bayesian probability; Phase (matter); Randomized controlled trial; Computer science; Statistics; Mathematics; Artificial intelligence; Medicine; Internal medicine; Chemistry","score_opus":0.8556465411061355,"score_gpt":0.6767526664510932,"score_spread":0.17889387465504225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394255645","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2510458e-8,0.00012824872,0.062604755,0.00011916564,0.0018229223,0.012267055,0.9228677,0.00015028146,0.000039819533],"genre_scores_gemma":[1.5516196e-8,0.000032379387,0.3869062,0.00031445868,0.0018354355,0.010995002,0.5996153,0.00009249358,0.00020870609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9446548,0.044338472,0.007863729,0.0013896787,0.000983959,0.0007693379],"domain_scores_gemma":[0.09870739,0.8935135,0.0049254266,0.0019390536,0.00036299377,0.0005516166],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.085829735,0.000852808,0.009323575,0.00020577555,0.00043809254,0.0001519065,0.0017082476,0.0014700934,0.93768257],"category_scores_gemma":[0.97726464,0.0006854622,0.0037426571,0.0002512299,0.00009842367,0.00006290546,0.0010135501,0.0019199125,0.0004306429],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06332058,0.0012526509,7.815763e-10,0.0010386949,0.00084466074,0.000055061744,0.000006771027,0.000005235176,1.0910426e-7,0.00010868202,0.9267225,0.0066450117],"study_design_scores_gemma":[0.17435817,0.0012374346,3.002896e-9,0.0008365396,0.001621214,0.000004556863,0.000004544984,0.0007051916,0.000007199527,0.11499593,0.7056711,0.00055814843],"about_ca_topic_score_codex":0.0000023466907,"about_ca_topic_score_gemma":7.6937835e-7,"teacher_disagreement_score":0.9372519,"about_ca_system_score_codex":0.00010378031,"about_ca_system_score_gemma":0.00070378854,"threshold_uncertainty_score":0.9998262},"labels":[],"label_agreement":null},{"id":"W4394492950","doi":"10.6084/m9.figshare.23260145","title":"A real-world data analysis of topotecan in the FDA Adverse Event Reporting System (FAERS) database","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Adverse Event Reporting System; Database; Adverse effect; Medicine; Computer science; Pharmacology","score_opus":0.7881289878826887,"score_gpt":0.6132042625295757,"score_spread":0.174924725353113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394492950","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005001845,0.000009592457,0.000028553075,0.000035073786,0.00021991528,0.00092678407,0.99856246,0.00007627464,0.00013633468],"genre_scores_gemma":[0.000011632237,0.000017824874,0.022922954,0.00004303308,0.00031066136,0.00028684532,0.97630656,0.000046208777,0.00005430522],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904435,0.0020460708,0.004816521,0.0010856994,0.0011770326,0.0004311284],"domain_scores_gemma":[0.8785264,0.104431346,0.008488591,0.008208731,0.00020362383,0.00014132587],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011120859,0.00039374307,0.002310782,0.0007057054,0.00006648195,0.000046344227,0.0030370133,0.00025986004,0.017996449],"category_scores_gemma":[0.61543185,0.00029455218,0.00044862152,0.0035529998,0.00003552988,0.00007454098,0.0020277102,0.0009756556,0.0009704956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023570103,0.00009176118,0.000007624933,0.0042596175,0.0007771467,0.00069567957,0.000020915802,0.000011623801,1.885347e-7,0.00007813882,0.99370986,0.0003238517],"study_design_scores_gemma":[0.0013776281,0.00016323161,0.002910393,0.05553878,0.019689493,0.000020994858,0.00199738,0.00685889,0.000012717218,0.007261425,0.90222526,0.0019438298],"about_ca_topic_score_codex":0.0025566944,"about_ca_topic_score_gemma":0.013699089,"teacher_disagreement_score":0.604311,"about_ca_system_score_codex":0.00015949692,"about_ca_system_score_gemma":0.00023156038,"threshold_uncertainty_score":0.99995065},"labels":[],"label_agreement":null},{"id":"W4394620826","doi":"10.1101/2024.04.04.24305236","title":"Adaptive trials in stroke: Current use &amp; future directions","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Calgary","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research; Allergan; Shionogi; National Institutes of Health; H. Lundbeck A/S; Australian Government; State Government of Victoria; Pfizer; European Stroke Organisation; Veski; Teva Pharmaceutical Industries; AstraZeneca; Eli Lilly and Company","keywords":"Clinical trial; Protocol (science); Flexibility (engineering); Adaptive design; Rehabilitation; Clinical study design; Stroke (engine); Inclusion (mineral); Medicine; Research design; Physical therapy; Physical medicine and rehabilitation; Alternative medicine; Computer science; Medical physics; Psychology; Engineering; Pathology; Social psychology","score_opus":0.7554215542136008,"score_gpt":0.6022027152504522,"score_spread":0.15321883896314858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394620826","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37578067,0.024295278,0.33264923,0.00850973,0.21286058,0.015857216,0.01999533,0.0029772816,0.0070746783],"genre_scores_gemma":[0.007825379,0.0036536118,0.9777768,0.000060487855,0.007300533,0.0009824035,0.000023657225,0.00020144973,0.0021756378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98623306,0.007948728,0.0033582258,0.0012262301,0.0007342663,0.0004994846],"domain_scores_gemma":[0.8616895,0.13563663,0.00090178335,0.0013312333,0.00020095271,0.00023986153],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.020170804,0.0006019557,0.0030523315,0.00043957256,0.00005541812,0.00022469257,0.0005570979,0.0008514655,0.0006435224],"category_scores_gemma":[0.3572891,0.00047780425,0.0010182201,0.00042847137,0.00015712019,0.00004233669,0.0013993043,0.0041056196,0.00030811364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010725264,0.0025691094,0.0050888755,0.005407006,0.0022599928,0.00022776471,0.0027175173,0.000064701686,0.0001817725,0.52296925,0.0726506,0.38479087],"study_design_scores_gemma":[0.00047748548,0.00003441221,0.0012559559,0.001306168,0.0006102749,0.0000021213714,0.000036884638,0.00013712964,0.000058530484,0.93482286,0.06081659,0.00044159617],"about_ca_topic_score_codex":0.000045614193,"about_ca_topic_score_gemma":0.00023611625,"teacher_disagreement_score":0.6451276,"about_ca_system_score_codex":0.00025289078,"about_ca_system_score_gemma":0.00029637138,"threshold_uncertainty_score":0.99976736},"labels":[],"label_agreement":null},{"id":"W4394792693","doi":"10.1080/10543406.2024.2341674","title":"Adaptive promising zone design for cancer immunotherapy with heterogeneous delayed treatment effect","year":2024,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Sample size determination; Interim analysis; Interim; Statistics; Test statistic; Rank (graph theory); Log-rank test; Cancer immunotherapy; Piecewise; Computer science; Mathematics; Statistic; Hazard ratio; Cancer; Immunotherapy; Medicine; Clinical trial; Proportional hazards model; Statistical hypothesis testing; Internal medicine; Confidence interval","score_opus":0.48115898615679503,"score_gpt":0.5727411869840863,"score_spread":0.09158220082729124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394792693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005014383,0.0023278208,0.98912245,0.00026462082,0.001034793,0.001368751,0.0007773366,0.00008038265,0.0000094451225],"genre_scores_gemma":[0.04079437,0.00093205256,0.9571696,0.00010534265,0.0006724988,0.00011144655,0.0000013158804,0.00014384589,0.00006955668],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99651426,0.0008885309,0.0012633115,0.0003199549,0.0005436428,0.0004702934],"domain_scores_gemma":[0.9380585,0.06069255,0.00040864447,0.0001717069,0.00035877817,0.00030983888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025433595,0.00040076772,0.0010976369,0.00012226704,0.00008934358,0.00014438048,0.00021068609,0.00015728221,0.0001632133],"category_scores_gemma":[0.0039409176,0.00023273285,0.00027130716,0.00022118249,0.00023364775,0.000074090196,0.000020837431,0.00040614107,0.000005028403],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.032210406,0.0009226103,0.000030195835,0.00082929956,0.006673967,0.0019025918,0.0004200213,0.00094139314,0.010342714,0.024499312,0.0027524617,0.91847503],"study_design_scores_gemma":[0.01902779,0.051838465,0.000031052114,0.001778645,0.007700158,0.0011123955,0.000054119122,0.16913056,0.14400712,0.5901685,0.013877569,0.0012736422],"about_ca_topic_score_codex":0.000006867652,"about_ca_topic_score_gemma":0.0000026089688,"teacher_disagreement_score":0.9172014,"about_ca_system_score_codex":0.00045228907,"about_ca_system_score_gemma":0.00034321414,"threshold_uncertainty_score":0.94905704},"labels":[],"label_agreement":null},{"id":"W4394808583","doi":"10.1111/jdv.20030","title":"Adaptive designs in dermatology clinical trials: Current status and future perspectives","year":2024,"lang":"en","type":"review","venue":"Journal of the European Academy of Dermatology and Venereology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovaderm (Canada)","funders":"","keywords":"Adaptive design; Clinical trial; Risk analysis (engineering); Clinical study design; Limiting; Drug development; Computer science; Medicine; Intensive care medicine; Field (mathematics); Medical physics; Management science; Drug; Engineering; Pathology; Pharmacology","score_opus":0.7608716892957742,"score_gpt":0.6425289689462116,"score_spread":0.11834272034956261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394808583","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017686351,0.993432,0.0006946956,0.0025059786,0.0022783475,0.0005688239,0.000052040392,0.000012836451,0.00027841373],"genre_scores_gemma":[0.00063769054,0.97962934,0.018191438,0.000077796845,0.0013744344,0.0000062500308,3.9294903e-7,0.0000687272,0.000013916549],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9220241,0.069723964,0.0069356738,0.0005729786,0.00023772637,0.00050560175],"domain_scores_gemma":[0.92825687,0.06617305,0.0050052353,0.00024275218,0.00008925081,0.00023286742],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.015309877,0.0005518685,0.0076106205,0.0005113899,0.00006671789,0.000016258884,0.00076848955,0.00112497,0.000022667304],"category_scores_gemma":[0.047687102,0.00030657728,0.0011818958,0.0003221253,0.0019169572,0.00006186974,0.0006683752,0.0052299565,0.00000823559],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025666985,0.00024247973,0.0006133352,0.007053717,0.0013552126,0.00042419837,0.0004132131,7.931669e-8,2.1568297e-7,0.15517934,0.0040636933,0.83039784],"study_design_scores_gemma":[0.0017325286,0.00010018226,0.00039266126,0.0071310066,0.006691434,0.013937762,0.00030759146,0.000009416541,0.0000014687619,0.411176,0.5581456,0.0003743454],"about_ca_topic_score_codex":3.923995e-7,"about_ca_topic_score_gemma":7.771233e-7,"teacher_disagreement_score":0.8300235,"about_ca_system_score_codex":0.000052659554,"about_ca_system_score_gemma":0.00031774814,"threshold_uncertainty_score":0.9999386},"labels":[],"label_agreement":null},{"id":"W4396234464","doi":"10.7326/m23-2515","title":"The Benefits and Risks of Receiving Investigational Solid Tumor Drugs in Randomized Trials","year":2024,"lang":"en","type":"review","venue":"Annals of Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; University of Ottawa; McGill University","funders":"National Science Foundation Graduate Research Fellowship Program; Canadian Institutes of Health Research; Réseau de cancérologie Rossy","keywords":"Medicine; Randomized controlled trial; Investigational Drugs; Intensive care medicine; Clinical trial; Internal medicine","score_opus":0.8262045934351618,"score_gpt":0.6656365234000565,"score_spread":0.16056807003510531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396234464","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009630997,0.99480957,0.00032422287,0.0012777571,0.0012227715,0.0015557928,0.00015678853,0.000014726079,0.00054206786],"genre_scores_gemma":[0.000060941566,0.98290926,0.015765121,0.00015965826,0.000788283,0.00014996705,0.000002975584,0.000052274794,0.000111488574],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98254824,0.007690511,0.008245538,0.00042608046,0.0008067446,0.00028286898],"domain_scores_gemma":[0.51847064,0.47629747,0.004263979,0.00043251086,0.00037048146,0.00016492362],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07445267,0.00044195415,0.011326127,0.00036753464,0.000028128072,0.000021179092,0.00054897764,0.000242976,0.00011464455],"category_scores_gemma":[0.72599477,0.00020537701,0.0010148311,0.00035559427,0.0014649078,0.000031916963,0.0002323812,0.00086579344,0.000005012459],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002457168,0.000041118747,0.000001735269,0.01719188,0.0012383804,0.000009375336,0.0002369689,1.2811063e-7,8.21861e-7,0.07858272,0.0050251107,0.8952146],"study_design_scores_gemma":[0.010599429,0.00015832079,0.0000023836003,0.20216082,0.002682553,0.00001850133,0.000043425167,0.00003212993,0.000032367938,0.7697343,0.014368808,0.00016697161],"about_ca_topic_score_codex":0.000120308505,"about_ca_topic_score_gemma":0.000008419269,"teacher_disagreement_score":0.8950476,"about_ca_system_score_codex":0.000020520567,"about_ca_system_score_gemma":0.00019736715,"threshold_uncertainty_score":0.9530457},"labels":[],"label_agreement":null},{"id":"W4396555757","doi":"10.1177/09622802241247736","title":"Sample size and power calculation for testing treatment effect heterogeneity in cluster randomized crossover designs","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging; National Institutes of Health; Patient-Centered Outcomes Research Institute","keywords":"Crossover; Sample size determination; Crossover study; Covariate; Randomized controlled trial; Statistics; Statistical power; Cluster (spacecraft); Cluster size; Statistical hypothesis testing; Computer science; Mathematics; Medicine; Artificial intelligence","score_opus":0.7061155154350921,"score_gpt":0.7199084202257027,"score_spread":0.013792904790610572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396555757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0092365835,0.00025479106,0.98440444,0.0008401657,0.00045455317,0.004022916,0.00023836369,0.00007419284,0.00047398737],"genre_scores_gemma":[0.029776191,0.00005948413,0.96809477,0.000098298406,0.00019552518,0.0016264247,0.0000042385273,0.00007369091,0.00007139456],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95795697,0.035551004,0.0021591524,0.0012525675,0.0017941622,0.0012861307],"domain_scores_gemma":[0.088939786,0.90976,0.00008064751,0.00040039164,0.00021238644,0.00060680695],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11878254,0.00037883702,0.0019746718,0.00034225642,0.00013588587,0.00021350439,0.00028444824,0.0005646896,0.0008799994],"category_scores_gemma":[0.95009714,0.00025146746,0.00019886604,0.00092015916,0.0016520021,0.00007562396,0.00026234775,0.0012933739,0.000010269474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029531822,0.00040742592,0.0005260642,0.001315329,0.000161595,0.00031292107,0.0002985268,0.000004552995,0.0003516675,0.2804694,0.0003491713,0.68627155],"study_design_scores_gemma":[0.040587775,0.0008815339,0.0006340821,0.0005493054,0.00007150983,0.000009704519,0.000014505095,0.10896288,0.00039549402,0.84748805,0.00018841565,0.00021675522],"about_ca_topic_score_codex":0.00026881404,"about_ca_topic_score_gemma":0.00006418896,"teacher_disagreement_score":0.874209,"about_ca_system_score_codex":0.00046700504,"about_ca_system_score_gemma":0.00039902164,"threshold_uncertainty_score":0.99999374},"labels":[],"label_agreement":null},{"id":"W4396723746","doi":"10.1002/sim.10104","title":"Adaptive designs in public health: Vaccine and cluster randomized trials go Bayesian","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"National Institute of Environmental Health Sciences; National Institute on Aging","keywords":"Bayes' theorem; Bayesian probability; Computer science; Randomized controlled trial; Clinical trial; Flexibility (engineering); Psychological intervention; Non-communicable disease; Cluster (spacecraft); Public health; Matching (statistics); Cluster randomised controlled trial; Medicine; Econometrics; Risk analysis (engineering); Statistics; Artificial intelligence; Economics; Mathematics; Nursing","score_opus":0.6838323276886842,"score_gpt":0.60154715796384,"score_spread":0.08228516972484423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396723746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008627733,0.0018900265,0.9774287,0.015307692,0.0013171049,0.0025163095,0.00030651063,0.00008323368,0.0010641826],"genre_scores_gemma":[0.030974206,0.0015034328,0.965063,0.0012615075,0.0006033127,0.00023651039,0.000017122706,0.000071954964,0.00026899972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97774947,0.015117271,0.004863894,0.0007907441,0.00073019596,0.0007483983],"domain_scores_gemma":[0.6319265,0.3669459,0.00040665068,0.00031749328,0.00010158421,0.0003019084],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08639028,0.0003658873,0.004199752,0.00061957905,0.000049097995,0.000060319977,0.0002169182,0.00021109595,0.000919689],"category_scores_gemma":[0.57981646,0.00025063774,0.000096971235,0.00072067865,0.0004919573,0.00007758046,0.000102184626,0.00084067223,0.000014914224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069303806,0.00011792023,0.00004287665,0.0007048364,0.0001640017,0.00021835153,0.0017302269,0.0000016933978,0.000007016096,0.84856313,0.035530012,0.10598953],"study_design_scores_gemma":[0.07384375,0.0003978106,0.000101362806,0.0012346867,0.000146082,0.000012062379,0.0002645967,0.017720288,0.0000031476127,0.90550274,0.0005663019,0.000207193],"about_ca_topic_score_codex":0.00014045855,"about_ca_topic_score_gemma":0.00028349293,"teacher_disagreement_score":0.49342617,"about_ca_system_score_codex":0.0002158182,"about_ca_system_score_gemma":0.00027979648,"threshold_uncertainty_score":0.9999946},"labels":[],"label_agreement":null},{"id":"W4396736053","doi":"10.1007/s00769-024-01595-w","title":"New statistical framework for interlaboratory evaluation of anti-doping testing results by WADA","year":2024,"lang":"en","type":"article","venue":"Accreditation and Quality Assurance","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"World Anti-Doping Agency; National Research Council Canada","funders":"National Research Council Canada","keywords":"Commercial law; Statistical analysis; Analytical Chemistry (journal); Statistics; Engineering; Accounting; Mathematics; Chemistry; Business; Chromatography; Political science; Law","score_opus":0.6683357042775011,"score_gpt":0.6183950536970836,"score_spread":0.04994065058041752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396736053","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014699875,0.0003583006,0.9808011,0.00083028094,0.0010868971,0.0005583538,0.0013321026,0.00008637159,0.00024670057],"genre_scores_gemma":[0.20809717,0.000014735003,0.79140276,0.00007077685,0.00031506686,0.0000329947,0.00002355491,0.000017875715,0.000025055253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964415,0.001159846,0.0012327273,0.00039640407,0.0005981366,0.0001714226],"domain_scores_gemma":[0.7899643,0.20857729,0.00037617018,0.00024737575,0.0007231969,0.000111621586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012614057,0.00013616536,0.00043033445,0.000047002148,0.000060847655,0.00008185132,0.00010107673,0.00014874042,0.000028441358],"category_scores_gemma":[0.4549669,0.00012626823,0.000046378325,0.00029556692,0.00009493798,0.00015792531,0.000024494804,0.00020661566,0.000002962785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016512605,0.000050864048,0.0001614411,0.0012827307,0.000081153434,6.177023e-7,0.0006361542,0.00001071952,0.0017176615,0.7095304,0.03091426,0.25544888],"study_design_scores_gemma":[0.00091609353,0.0001138222,0.003184166,0.0007781668,0.00013684318,5.083043e-7,0.00018944386,0.009015632,0.0014416766,0.9834502,0.0006137119,0.0001597688],"about_ca_topic_score_codex":0.000029972536,"about_ca_topic_score_gemma":0.000006137993,"teacher_disagreement_score":0.44235286,"about_ca_system_score_codex":0.000040514828,"about_ca_system_score_gemma":0.00028424297,"threshold_uncertainty_score":0.54962415},"labels":[],"label_agreement":null},{"id":"W4396799016","doi":"10.1002/sim.10089","title":"Novel non‐linear models for clinical trial analysis with longitudinal data: A tutorial using <scp>SAS</scp> for both frequentist and Bayesian methods","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Veterinarians of British Columbia","funders":"National Institute on Aging; National Institutes of Health","keywords":"Frequentist inference; Categorical variable; Bayesian probability; Repeated measures design; Random effects model; Computer science; Inference; Mixed model; Statistics; Bayesian inference; Linear model; Generalized linear mixed model; Mathematics; Econometrics; Artificial intelligence; Medicine","score_opus":0.7321217157620442,"score_gpt":0.6629236950961048,"score_spread":0.06919802066593939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396799016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051490625,0.00028047425,0.983961,0.00013621782,0.00448552,0.0027898776,0.0076711867,0.00007320737,0.00008763756],"genre_scores_gemma":[0.0011948255,0.00013840935,0.9923129,0.00008524227,0.005524468,0.00018839569,0.0002837432,0.00012421205,0.00014778328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931164,0.00088527775,0.003041702,0.0015457826,0.00072865427,0.0006822125],"domain_scores_gemma":[0.79044443,0.20742746,0.0005140492,0.0009834865,0.00030818948,0.00032238287],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025351943,0.00049614644,0.0026796255,0.00045527113,0.00015392588,0.00012302151,0.00057892414,0.000390653,0.000031381198],"category_scores_gemma":[0.20573637,0.0003705869,0.00019428592,0.00083497376,0.0009284158,0.00018543654,0.0002225081,0.000704678,5.278357e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01567122,0.0014722509,0.00074817473,0.0046676653,0.0091243405,0.00029451295,0.0011466977,0.00057743065,0.00023244826,0.8817662,0.034544233,0.049754824],"study_design_scores_gemma":[0.021433061,0.001276211,0.00004426779,0.00029688375,0.005806467,0.000008004302,0.00008671925,0.5004306,0.000005537885,0.46962446,0.00084683805,0.00014095256],"about_ca_topic_score_codex":0.0001444941,"about_ca_topic_score_gemma":0.0002464135,"teacher_disagreement_score":0.49985316,"about_ca_system_score_codex":0.00011086399,"about_ca_system_score_gemma":0.00039897396,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W4396812245","doi":"10.1016/j.cct.2024.107560","title":"Designing a Bayesian adaptive clinical trial to evaluate novel mechanical ventilation strategies in acute respiratory failure using integrated nested Laplace approximations","year":2024,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; University of Toronto; University Health Network; Institute for Clinical Evaluative Sciences; Public Health Ontario; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Medicine; Bayesian probability; Mechanical ventilation; Acute respiratory failure; Clinical trial; Intensive care medicine; Respiratory failure; Randomized controlled trial; Laplace transform; Artificial intelligence; Anesthesia; Surgery; Internal medicine","score_opus":0.8742907154392562,"score_gpt":0.6583211563281324,"score_spread":0.2159695591111238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396812245","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039506357,0.00020104,0.9432854,0.0010254765,0.0062520267,0.008331917,0.00041600267,0.00059267774,0.00038909208],"genre_scores_gemma":[0.25817788,0.000020135343,0.73812443,0.0005122934,0.0024241118,0.00044834646,0.000026614134,0.00016858183,0.00009762163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.938469,0.04004325,0.016799651,0.0024256348,0.001348205,0.00091428484],"domain_scores_gemma":[0.68568844,0.30889368,0.0023739934,0.0014008115,0.0006856508,0.0009574027],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1598282,0.0008364581,0.0051114485,0.00066193973,0.00019193625,0.0006705605,0.0008802154,0.0016914769,0.0002640085],"category_scores_gemma":[0.44142926,0.00069198856,0.0017469052,0.0020373263,0.0004542868,0.0008397046,0.00036743828,0.0027026357,0.00010352585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.39682758,0.009661558,0.0007682646,0.00091389543,0.007840759,0.0014607181,0.0011317828,0.00056941056,0.01582297,0.4324172,0.037135825,0.09545003],"study_design_scores_gemma":[0.10658035,0.0073837503,0.00023244927,0.004237737,0.0024086987,0.000017990013,0.001476608,0.08512886,0.0008734438,0.7851272,0.004637173,0.0018956997],"about_ca_topic_score_codex":0.000031478925,"about_ca_topic_score_gemma":0.00004034216,"teacher_disagreement_score":0.35271004,"about_ca_system_score_codex":0.00027633773,"about_ca_system_score_gemma":0.0035919799,"threshold_uncertainty_score":0.9996045},"labels":[],"label_agreement":null},{"id":"W4396870682","doi":"10.1002/bimj.202300398","title":"Comparative review of novel model‐assisted designs for phase I/II clinical trials","year":2024,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Sample size determination; Selection (genetic algorithm); Design of experiments; Optimal design; Mixed model; Maximum tolerated dose; Limiting; Model selection; Clinical trial; Mathematical optimization; Statistics; Machine learning; Mathematics; Medicine; Engineering","score_opus":0.9787822344457127,"score_gpt":0.7827430936798301,"score_spread":0.19603914076588258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396870682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004021581,0.013112677,0.98072845,0.00126283,0.0018886799,0.0014707221,0.00069577456,0.00007024065,0.0003684897],"genre_scores_gemma":[0.0057274257,0.0055062994,0.98670006,0.00044058537,0.0013179282,0.00005880634,0.0000047627777,0.000045535744,0.000198603],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98740745,0.00366556,0.0070096133,0.00050714915,0.00096457015,0.00044566955],"domain_scores_gemma":[0.6116416,0.38371226,0.0021641497,0.000528063,0.0011555699,0.0007983514],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07180599,0.0003153941,0.0037330787,0.0008604817,0.00015165441,0.00010372163,0.0005438991,0.0003519623,0.0004205702],"category_scores_gemma":[0.5453642,0.0002074962,0.0019529565,0.0030182407,0.00031701472,0.00011457825,0.00013102542,0.0008534462,0.000011328472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015719705,0.010098651,0.0000036089455,0.008843945,0.0022182886,0.000042214946,0.00007661711,0.000004649627,0.0050201924,0.12349168,0.2836274,0.5650008],"study_design_scores_gemma":[0.017258389,0.008476442,0.000015239213,0.01631156,0.0040830886,0.00021080322,0.000030108671,0.09366205,0.0020280024,0.83712536,0.020055342,0.00074363133],"about_ca_topic_score_codex":3.7101856e-7,"about_ca_topic_score_gemma":5.6530443e-8,"teacher_disagreement_score":0.71363366,"about_ca_system_score_codex":0.000115543844,"about_ca_system_score_gemma":0.0005073196,"threshold_uncertainty_score":0.9557711},"labels":[],"label_agreement":null},{"id":"W4396943299","doi":"10.3150/23-bej1658","title":"Kernel-weighted specification testing under general distributions","year":2024,"lang":"en","type":"article","venue":"Bernoulli","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Mathematics; Kernel (algebra); Statistics; Applied mathematics; Econometrics; Discrete mathematics","score_opus":0.6425468127766307,"score_gpt":0.5567862035939477,"score_spread":0.08576060918268302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396943299","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01847442,0.00017796605,0.96429837,0.0015128652,0.0013166551,0.00034070108,0.00024715796,0.0006161547,0.013015733],"genre_scores_gemma":[0.06790102,0.000019180135,0.92792207,0.00007162306,0.0012672859,0.000048724323,0.000023262639,0.000048405236,0.0026984033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998107,0.00027378925,0.0006434475,0.0004009586,0.00029150303,0.00028331208],"domain_scores_gemma":[0.975499,0.023776652,0.00008768392,0.00039836057,0.000114632145,0.00012367794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00119801,0.00016195729,0.00028226728,0.000052104144,0.000110160756,0.00013307277,0.00018507367,0.0001437269,0.0007615082],"category_scores_gemma":[0.020770913,0.00013656511,0.00011288313,0.00048265827,0.00011742663,0.00006509819,0.0000660466,0.00029688198,0.0005196533],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062701106,0.00008515082,0.00016070178,0.000058478963,0.000048635244,0.000015644493,0.000023912406,0.0000023251912,0.0013115689,0.9672922,0.010824753,0.020170365],"study_design_scores_gemma":[0.0001567278,0.000033474847,0.001762296,0.00010879782,0.00009578603,0.000011711712,0.000012643465,0.004793366,0.0013132615,0.9826645,0.008871642,0.00017579421],"about_ca_topic_score_codex":0.000014616377,"about_ca_topic_score_gemma":0.000002594712,"teacher_disagreement_score":0.049426604,"about_ca_system_score_codex":0.0001178598,"about_ca_system_score_gemma":0.000070310176,"threshold_uncertainty_score":0.98747754},"labels":[],"label_agreement":null},{"id":"W4396958533","doi":"10.1177/17407745241247334","title":"A comparison of computational algorithms for the Bayesian analysis of clinical trials","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Manitoba; University of Toronto; University Health Network; University of Ottawa; Public Health Ontario; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; LifeArc; Research Manitoba; University of Ottawa; National Institutes of Health; CancerCare Manitoba Foundation; National Heart, Lung, and Blood Institute; Heart and Stroke Foundation of Canada; Amgen","keywords":"Bayesian probability; Computer science; Clinical trial; Algorithm; Artificial intelligence; Medicine; Internal medicine","score_opus":0.9497491743628205,"score_gpt":0.789153977816664,"score_spread":0.1605951965461565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396958533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025582877,0.0009033124,0.98247284,0.0017783627,0.0065082246,0.0031148873,0.0023094432,0.00011016068,0.00024446842],"genre_scores_gemma":[0.16921936,0.00022937427,0.8263965,0.00021818018,0.00347004,0.00019606989,0.000037871967,0.00006893613,0.00016365566],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88958293,0.061843876,0.04499275,0.0014494886,0.0015539868,0.0005769892],"domain_scores_gemma":[0.08143471,0.90983194,0.0065562353,0.0011031997,0.00074919674,0.00032471403],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45515433,0.0003923371,0.014142803,0.00036115426,0.00010262893,0.000097299555,0.00092323753,0.0008736051,0.001098686],"category_scores_gemma":[0.9168802,0.00022822621,0.009886997,0.0016556971,0.0012359098,0.0000656376,0.00018983176,0.00094492343,0.000016194368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028439884,0.0022835182,0.0045267954,0.00062966184,0.03159267,0.000004729732,0.00016488181,0.00091100804,0.000018886081,0.23601037,0.032180086,0.6888334],"study_design_scores_gemma":[0.0032733798,0.0008029044,0.0025032049,0.0002117085,0.024064898,4.2047486e-7,0.00010182632,0.27697423,0.00011032587,0.6884815,0.0032547521,0.00022085888],"about_ca_topic_score_codex":0.000010042026,"about_ca_topic_score_gemma":0.000006097021,"teacher_disagreement_score":0.84798807,"about_ca_system_score_codex":0.000024209263,"about_ca_system_score_gemma":0.00051999016,"threshold_uncertainty_score":0.99981445},"labels":[],"label_agreement":null},{"id":"W4396999272","doi":"10.1681/asn.20203110s1502b","title":"STAGED-PKD: Patient Enrichment and Modeling-Driven Efficient ADPKD Trial Design","year":2020,"lang":"en","type":"article","venue":"Journal of the American Society of Nephrology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Urology; Internal medicine; Intensive care medicine","score_opus":0.4005303314776953,"score_gpt":0.4771735032413771,"score_spread":0.0766431717636818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396999272","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56902003,0.000060136033,0.42257515,0.0076908744,0.00020619344,0.0004160991,0.000012190095,0.000009199785,0.00001014239],"genre_scores_gemma":[0.36877516,0.000112906775,0.624661,0.006083507,0.0003422091,0.000004544239,4.6441084e-8,0.000017858103,0.000002756575],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959467,0.0016557726,0.0013685437,0.0002067106,0.00054238335,0.00027987052],"domain_scores_gemma":[0.98524547,0.011869237,0.0022105621,0.00025502956,0.00022477577,0.0001949323],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022107197,0.00017548756,0.001108174,0.000022259695,0.00008487605,0.0000117020245,0.00042285296,0.00008765208,0.00003114898],"category_scores_gemma":[0.008636379,0.00011224987,0.00056838675,0.00023717176,0.00072234636,0.00002233618,0.00027391943,0.00053381344,0.000001120891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.22032599,0.0057685133,0.00045777825,0.00075351,0.007786399,0.00007734073,0.03325686,0.1833769,0.11834988,0.010348619,0.3144664,0.10503184],"study_design_scores_gemma":[0.06907895,0.05005965,0.0005396499,0.00021845613,0.0024060917,0.00013823388,0.00736991,0.53567606,0.002752848,0.32644954,0.0043422394,0.0009683534],"about_ca_topic_score_codex":0.0000067039905,"about_ca_topic_score_gemma":1.2463491e-7,"teacher_disagreement_score":0.35229918,"about_ca_system_score_codex":0.000056055753,"about_ca_system_score_gemma":0.00013170177,"threshold_uncertainty_score":0.9997143},"labels":[],"label_agreement":null},{"id":"W4397040181","doi":"10.1177/17407745241244801","title":"Comparison of Bayesian and frequentist monitoring boundaries motivated by the Multiplatform Randomized Clinical Trial","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; McGill University Health Centre","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Frequentist inference; Randomized controlled trial; Bayesian probability; Statistics; Bayesian inference; Computer science; Econometrics; Medicine; Mathematics; Internal medicine","score_opus":0.8181638928621595,"score_gpt":0.7025413679078226,"score_spread":0.11562252495433689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397040181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37457347,0.008920529,0.52156454,0.0043031583,0.06965177,0.017008923,0.00091561885,0.0009757335,0.0020862734],"genre_scores_gemma":[0.758102,0.0009614505,0.23407128,0.00010621124,0.0058823386,0.00026663474,0.000010496026,0.000118226155,0.00048136147],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.939075,0.038767178,0.0192618,0.0012479704,0.0010261177,0.00062194973],"domain_scores_gemma":[0.16918759,0.8263784,0.0027113664,0.0010379908,0.0002503462,0.00043430628],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23389673,0.0004941155,0.008289931,0.0000935147,0.00031309886,0.0006898059,0.00066569814,0.0009770684,0.00030045232],"category_scores_gemma":[0.85149825,0.00028210817,0.0023263902,0.00038312742,0.0052777375,0.00015661286,0.00030536167,0.0018125045,0.000027258753],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.48887464,0.0020769467,0.004008443,0.0005907396,0.0039481334,0.000024032215,0.00039017823,5.88128e-7,0.00014952704,0.14569798,0.038414683,0.3158241],"study_design_scores_gemma":[0.34035566,0.00082260696,0.0000932612,0.00051174243,0.001808064,0.000002686689,0.00013174774,0.0019979926,0.0007561167,0.64831924,0.0048743566,0.00032652536],"about_ca_topic_score_codex":0.000030133722,"about_ca_topic_score_gemma":0.0000028962124,"teacher_disagreement_score":0.7876112,"about_ca_system_score_codex":0.000037263337,"about_ca_system_score_gemma":0.0003049307,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4398168682","doi":"10.1177/17407745241251812","title":"A comparison of alternative ranking methods in two-stage clinical trials with multiple interventions: An application to the anxiolysis for laceration repair in children trial","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; McGill University Health Centre","funders":"","keywords":"Psychological intervention; Medicine; Clinical trial; Ranking (information retrieval); Medical physics; Physical therapy; Computer science; Artificial intelligence; Psychiatry; Internal medicine","score_opus":0.8793479848945522,"score_gpt":0.7802434970391408,"score_spread":0.09910448785541148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398168682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10882166,0.00023519914,0.8705546,0.0007625772,0.0019380809,0.016935987,0.00056759594,0.0001569164,0.000027363205],"genre_scores_gemma":[0.19611385,0.00007774365,0.7974218,0.00016592458,0.0029379206,0.003107631,0.00004109947,0.00007894942,0.00005504845],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.811163,0.1537976,0.030993443,0.0023758018,0.0009566772,0.00071346463],"domain_scores_gemma":[0.33653992,0.65771586,0.0038047067,0.0013424435,0.00033204074,0.00026505327],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.47129273,0.00042978278,0.0065166894,0.0004248342,0.000092145245,0.00013771841,0.0007610698,0.0004953165,0.00009354695],"category_scores_gemma":[0.8080659,0.00027003893,0.0028397564,0.0011315421,0.0003281109,0.00020615743,0.00018626153,0.0010675213,0.000009936953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.1327877,0.007332915,0.038233977,0.00058504025,0.00243112,0.000004697312,0.0009216354,0.001537752,0.0002163436,0.054255087,0.0016434885,0.76005024],"study_design_scores_gemma":[0.16790822,0.009650179,0.008391774,0.002820138,0.0034847674,0.0000023292964,0.00063238165,0.24619815,0.0014521593,0.55628204,0.0021830134,0.0009948508],"about_ca_topic_score_codex":0.00012711078,"about_ca_topic_score_gemma":0.00074892206,"teacher_disagreement_score":0.7590554,"about_ca_system_score_codex":0.000119111115,"about_ca_system_score_gemma":0.00024538365,"threshold_uncertainty_score":0.9999752},"labels":[],"label_agreement":null},{"id":"W4398239163","doi":"10.22541/au.171646200.08833594/v1","title":"Commentary: Use of point-in-time or window approach in the case-crossover design, implications for pharmacoepidemiologic research using registries.","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Window (computing); Crossover; Point (geometry); Computer science; Research design; Statistics; Econometrics; Mathematics; Artificial intelligence; World Wide Web","score_opus":0.9466363642768737,"score_gpt":0.6949749033944104,"score_spread":0.25166146088246333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398239163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016764224,0.00014152151,0.95207936,0.014388896,0.00033814975,0.013237609,0.0025318123,0.00009384732,0.0004246],"genre_scores_gemma":[0.010914811,0.00006680321,0.98590255,0.0012385705,0.00022508636,0.0013171687,0.000029610857,0.000073170435,0.00023220944],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98408824,0.0109341,0.0027308324,0.001073972,0.0004275092,0.0007453586],"domain_scores_gemma":[0.66060245,0.33743453,0.0004236571,0.0012111296,0.00024805948,0.000080176535],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05622393,0.00039289135,0.0015884351,0.00033603187,0.0001312403,0.00020216635,0.0011818558,0.00062319683,0.00015360142],"category_scores_gemma":[0.19322264,0.00023577445,0.0003158067,0.0008151118,0.00073234393,0.00005902916,0.0018033403,0.0024707518,0.0000054159036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041739405,0.0037824863,0.0013789779,0.0076375804,0.0008422684,0.0005771372,0.0014953507,0.0024799216,0.0008577557,0.31021902,0.66007346,0.0064820894],"study_design_scores_gemma":[0.0010309151,0.00011057815,0.0000511525,0.00039000416,0.00022360332,0.000109461726,0.00026752174,0.02550386,0.00020775034,0.9716421,0.00020428657,0.0002587717],"about_ca_topic_score_codex":0.0010385184,"about_ca_topic_score_gemma":0.00004206588,"teacher_disagreement_score":0.6614231,"about_ca_system_score_codex":0.00039833412,"about_ca_system_score_gemma":0.0003485795,"threshold_uncertainty_score":0.9998306},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4399074169","doi":"10.1371/journal.pone.0299494","title":"Adaptive clinical trials in surgery: A scoping review of methodological and reporting quality","year":2024,"lang":"en","type":"review","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Hamilton Health Sciences; McMaster University; McGill University; Impact","funders":"","keywords":"Blinding; Medicine; Clinical trial; Consolidated Standards of Reporting Trials; Randomized controlled trial; Sample size determination; Interim analysis; Medical physics; Clinical study design; Research design; Interim; Randomization; Physical therapy; Surgery; Internal medicine; Statistics","score_opus":0.9957737852501989,"score_gpt":0.8077363281011734,"score_spread":0.18803745714902553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399074169","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000579824,0.9899805,0.0036637378,0.00009762653,0.00031109247,0.0054475055,0.00016028764,0.000082208906,0.00025122843],"genre_scores_gemma":[9.484757e-8,0.5504779,0.44882998,0.00005551949,0.0002908284,0.00027925253,0.000003848487,0.000046387537,0.000016152031],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.6673406,0.24398337,0.08350128,0.0025268223,0.0018221184,0.0008258556],"domain_scores_gemma":[0.027929489,0.941718,0.028699374,0.0011063968,0.00028852726,0.00025825365],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.566822,0.00060511887,0.042567264,0.0002439105,0.000024938256,0.00003245276,0.00030655632,0.0010610839,0.00025796323],"category_scores_gemma":[0.9881206,0.00039332133,0.003041225,0.0007767738,0.00036809169,0.000038488564,0.0005026684,0.0019801187,0.000017157474],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025469106,0.000502587,0.000011859183,0.5973273,0.00083637633,0.000047129473,0.0000045735674,3.4678965e-10,1.2041579e-7,0.0037345092,0.0001767751,0.3973333],"study_design_scores_gemma":[0.00012044387,0.0000858986,0.0000025063955,0.79192114,0.0103066405,0.000006228733,0.0000043702194,0.0000017791457,0.000002035604,0.19699623,0.00024443705,0.00030830133],"about_ca_topic_score_codex":0.0000076094293,"about_ca_topic_score_gemma":0.0000031102666,"teacher_disagreement_score":0.6977346,"about_ca_system_score_codex":0.00006435565,"about_ca_system_score_gemma":0.0008202287,"threshold_uncertainty_score":0.9998519},"labels":[],"label_agreement":null},{"id":"W4399080701","doi":"10.1007/s12561-024-09432-x","title":"Analysis of Recurrent Event Processes with Dynamic Models for Event Counts","year":2024,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Event (particle physics); Computer science; Covariate; Biostatistics; Econometrics; Cluster analysis; Estimation; Parametric statistics; Statistics; Data mining; Machine learning; Mathematics; Medicine; Epidemiology; Engineering","score_opus":0.3809228862421378,"score_gpt":0.5811723911560625,"score_spread":0.20024950491392463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399080701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010812685,0.00022753075,0.99505293,0.000055214565,0.00049341854,0.00030891475,0.0023433878,0.00002219671,0.00041516198],"genre_scores_gemma":[0.29231542,0.00016255227,0.70730907,0.0000098810415,0.000014213222,0.000045337143,0.000007144079,0.0000087968265,0.0001275707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984739,0.00008253604,0.0005504578,0.0003083598,0.000406871,0.00017792202],"domain_scores_gemma":[0.98079026,0.018726801,0.0001332722,0.000149848,0.00015656636,0.000043277465],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015583835,0.00010302267,0.0003733411,0.00024060076,0.00002892307,0.000036204565,0.00020240387,0.000042220185,0.00008265063],"category_scores_gemma":[0.013494834,0.000070233786,0.00004971767,0.0013065633,0.00026470682,0.000044700948,0.000026869187,0.00007530867,0.000002264588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006361963,0.00025062662,0.00019890489,0.0019060305,0.00028267762,0.000007878982,0.00042525984,0.001008644,0.000017468185,0.95838,0.0011068707,0.03635205],"study_design_scores_gemma":[0.00007627492,0.00016347707,0.000105402,0.00020563738,0.00031010495,2.9304218e-7,0.00005830832,0.25444186,0.00003241295,0.74442583,0.00009680519,0.00008358145],"about_ca_topic_score_codex":0.000005624267,"about_ca_topic_score_gemma":0.00019687561,"teacher_disagreement_score":0.29123414,"about_ca_system_score_codex":0.000048976606,"about_ca_system_score_gemma":0.0002714375,"threshold_uncertainty_score":0.99481493},"labels":[],"label_agreement":null},{"id":"W4399135197","doi":"10.1016/j.jointm.2024.04.002","title":"Adaptive platform trials in critical care","year":2024,"lang":"en","type":"editorial","venue":"Journal of Intensive Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; Queen's University","funders":"","keywords":"Computer science","score_opus":0.7245509537399367,"score_gpt":0.6600429668569011,"score_spread":0.0645079868830356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399135197","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018359418,0.006124326,0.012189982,0.0045308536,0.9747057,0.00051592925,0.00035880765,0.000025660156,0.0015304026],"genre_scores_gemma":[0.00024011634,0.00062079,0.119767725,0.0005232515,0.8784428,0.00001364715,0.00000721601,0.00012309973,0.0002613389],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98522943,0.0027426833,0.008191804,0.00052316947,0.0027924704,0.00052046805],"domain_scores_gemma":[0.19009504,0.7805941,0.0038720912,0.0006295361,0.024248747,0.00056044414],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.03271121,0.0006386236,0.007996017,0.0009793501,0.000033857603,0.00004459392,0.00069804164,0.0015960368,0.0006755503],"category_scores_gemma":[0.98102987,0.0003768441,0.0009979904,0.0004379934,0.00087076466,0.00009819203,0.00019235114,0.0065462734,0.00004205489],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016826289,0.000055118486,8.487747e-7,0.0013563809,0.000409692,0.0030588063,0.0013903575,2.8069852e-7,0.000017727554,0.010065384,0.9778182,0.0041445987],"study_design_scores_gemma":[0.0033105859,0.0039399983,0.0000017987026,0.019872297,0.0025473582,0.00009545218,0.011391363,0.000013381104,0.00004629211,0.79181266,0.16663861,0.00033022254],"about_ca_topic_score_codex":0.000029273066,"about_ca_topic_score_gemma":0.00001848279,"teacher_disagreement_score":0.94831866,"about_ca_system_score_codex":0.0007090809,"about_ca_system_score_gemma":0.0010236411,"threshold_uncertainty_score":0.99986833},"labels":[],"label_agreement":null},{"id":"W4399175341","doi":"10.5539/ijsp.v13n2p46","title":"Inferences About a Robust Heteroscedastic Measure of Effect Size When There Are Two Covariates","year":2024,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covariate; Measure (data warehouse); Statistics; Mathematics; Heteroscedasticity; Econometrics; Sample size determination; Computer science; Data mining","score_opus":0.262258204164485,"score_gpt":0.4897067052255341,"score_spread":0.22744850106104914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399175341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12201486,0.0007056091,0.87208974,0.0005835638,0.0023262019,0.00035158903,0.0015954181,0.000025410422,0.00030762234],"genre_scores_gemma":[0.5304648,0.000061835206,0.46922484,0.000020351134,0.0001976702,0.0000043373893,8.8110914e-7,0.00001155013,0.0000137325715],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99681216,0.0007303943,0.0013133439,0.00022493707,0.00077426306,0.00014491018],"domain_scores_gemma":[0.93607676,0.06194762,0.0006729703,0.00014520707,0.0010463882,0.00011102223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004615388,0.00018568728,0.00065903395,0.000073164236,0.00003122217,0.00016054224,0.00034225883,0.000090853384,0.00037626724],"category_scores_gemma":[0.0938981,0.0001270304,0.00013976874,0.00007410052,0.00029222821,0.00010505121,0.00009300512,0.00039498415,0.000002337528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001524479,0.0005994153,0.03644961,0.0027923067,0.0020072,0.00029021557,0.00086590636,0.00019164907,0.00064691884,0.8154019,0.0020068455,0.13722353],"study_design_scores_gemma":[0.00081576314,0.00046566856,0.010757132,0.0011626581,0.0002048966,0.00004659673,0.000017688812,0.0015374911,0.00023461749,0.9845681,0.00007085563,0.00011849721],"about_ca_topic_score_codex":0.000025310865,"about_ca_topic_score_gemma":0.000021889342,"teacher_disagreement_score":0.40844995,"about_ca_system_score_codex":0.000064224536,"about_ca_system_score_gemma":0.00012719983,"threshold_uncertainty_score":0.9137344},"labels":[],"label_agreement":null},{"id":"W4399325374","doi":"10.1200/jco.2024.42.16_suppl.e14698","title":"Using exponential decay to model survival curves in immunotherapy trials.","year":2024,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Windsor; Western University","funders":"","keywords":"Medicine; Immunotherapy; Survival analysis; Proportional hazards model; Oncology; Internal medicine; Cancer","score_opus":0.9316817566096776,"score_gpt":0.754980948632271,"score_spread":0.1767008079774065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399325374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12233277,0.0020246934,0.8488499,0.0077395486,0.016207436,0.0006912743,0.000036175952,0.000044076147,0.0020741594],"genre_scores_gemma":[0.050533954,0.002032239,0.94218063,0.001682565,0.003359158,0.000008977298,2.5713862e-7,0.00006334577,0.00013889528],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9760672,0.010953845,0.01134125,0.00039975328,0.0008018787,0.00043610355],"domain_scores_gemma":[0.64929914,0.3466757,0.0025960691,0.00042231148,0.0004415749,0.00056520465],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11638846,0.00024072133,0.0047089728,0.00031093069,0.000030308476,0.00004726283,0.000557174,0.0006659485,0.00044844337],"category_scores_gemma":[0.38563925,0.00016916268,0.0013126847,0.0004213851,0.00019691665,0.00015859776,0.0001284065,0.0018144494,0.000025007665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01618171,0.0050620465,0.00094407506,0.00074958213,0.0020734936,0.0020888222,0.0005123511,0.0018510141,0.0043960745,0.14440875,0.030605555,0.79112655],"study_design_scores_gemma":[0.00596662,0.0032229866,0.0005201465,0.0017642189,0.0005280917,0.00007175457,0.000050581955,0.015159913,0.0002347131,0.963614,0.008549662,0.00031731703],"about_ca_topic_score_codex":0.000011912699,"about_ca_topic_score_gemma":0.000021736794,"teacher_disagreement_score":0.8192052,"about_ca_system_score_codex":0.00021132555,"about_ca_system_score_gemma":0.0019420675,"threshold_uncertainty_score":0.909864},"labels":[],"label_agreement":null},{"id":"W4399339598","doi":"10.1212/wnl.0000000000209533","title":"Prevalence and Impact of Bypassing or Overriding Phase 2 Trials in Neurologic Drug Development","year":2024,"lang":"en","type":"article","venue":"Neurology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; Della Martin Foundation","keywords":"Drug development; Medicine; Drug; Clinical trial; Intensive care medicine; Pharmacology; Internal medicine","score_opus":0.6486352195992298,"score_gpt":0.6254908834832205,"score_spread":0.0231443361160093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399339598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923351,0.0002257805,0.0058332602,0.0003852937,0.00056720135,0.00043667085,0.0000295436,0.00006718446,0.00011998903],"genre_scores_gemma":[0.9132026,0.00009455046,0.086319484,0.00019115445,0.000102207894,0.000030023728,3.1492306e-7,0.000025672985,0.000033985038],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943674,0.0032667296,0.0014634149,0.0004458652,0.00016509146,0.00029145714],"domain_scores_gemma":[0.8790007,0.1204622,0.00024731786,0.0001918029,0.000023477796,0.000074503674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008720306,0.00017891821,0.0010165245,0.00018030875,0.000027979791,0.000030158842,0.00015498935,0.00014899576,0.00032813282],"category_scores_gemma":[0.13593182,0.000117140335,0.0001198027,0.00023201626,0.00015674824,0.000056469296,0.00012935806,0.00040822226,0.000004740614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.040998805,0.0040643034,0.07122633,0.013088062,0.0010476111,0.006520372,0.0053003286,0.00016709193,0.04912394,0.09640931,0.0067688813,0.70528495],"study_design_scores_gemma":[0.006387907,0.0062511144,0.035391275,0.0003798557,0.00034870114,0.00024470882,0.000007217312,0.008568445,0.0039408887,0.9372518,0.00071229535,0.00051578094],"about_ca_topic_score_codex":0.000010383452,"about_ca_topic_score_gemma":0.0000059657805,"teacher_disagreement_score":0.8408425,"about_ca_system_score_codex":0.000021084134,"about_ca_system_score_gemma":0.00017319154,"threshold_uncertainty_score":0.8713466},"labels":[],"label_agreement":null},{"id":"W4399385251","doi":"10.1177/09622802241254211","title":"Group sequential methods based on supremum logrank statistics under proportional and nonproportional hazards","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ligue Contre le Cancer","keywords":"Infimum and supremum; Log-rank test; Statistics; Proportional hazards model; Interim analysis; Interim; Monte Carlo method; Statistical hypothesis testing; Multiple comparisons problem; Computer science; Mathematics; Clinical trial; Medicine; Internal medicine; Law","score_opus":0.6393074929333418,"score_gpt":0.7234070603281539,"score_spread":0.08409956739481217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399385251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014567062,0.0002205508,0.9887209,0.003912687,0.0016165791,0.0012061163,0.001088522,0.00020104411,0.0028879116],"genre_scores_gemma":[0.003411355,0.00012149773,0.99410856,0.00061367545,0.0007791974,0.00043543061,0.00007809595,0.00014896585,0.00030322006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95507807,0.031524863,0.0029331525,0.0020402716,0.006605081,0.001818586],"domain_scores_gemma":[0.64431125,0.35318568,0.00012529931,0.00064348365,0.00048082627,0.0012534783],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1115317,0.0005798167,0.0014375871,0.00097247824,0.00030976182,0.00034282287,0.00075629493,0.0009401193,0.017935514],"category_scores_gemma":[0.49534857,0.0004601462,0.00018629924,0.0016417925,0.0044021476,0.000116541596,0.00054740265,0.0051000747,0.00009193597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033662136,0.00043833922,0.00005193477,0.00063536555,0.00006436822,0.000689513,0.000027821276,0.0000038577946,0.00018940028,0.5802328,0.004549062,0.41278094],"study_design_scores_gemma":[0.0011067215,0.0007733837,0.0011942562,0.0005989212,0.000076510114,0.000042657797,0.000051176623,0.16621463,0.0001779001,0.82563525,0.0037240912,0.00040450582],"about_ca_topic_score_codex":0.00007708818,"about_ca_topic_score_gemma":0.000034077657,"teacher_disagreement_score":0.41237643,"about_ca_system_score_codex":0.00047851086,"about_ca_system_score_gemma":0.0019843865,"threshold_uncertainty_score":0.999785},"labels":[],"label_agreement":null},{"id":"W4399600420","doi":"10.1093/jrsssc/qlae028","title":"Two-phase biomarker studies for disease progression with multiple registries","year":2024,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling design; Sampling (signal processing); Inverse probability; Inverse probability weighting; Covariate; Pooling; Missing data; Stratified sampling; Statistics; Weighting; Simple random sample; Computer science; Mathematics; Bayesian probability; Artificial intelligence; Medicine; Posterior probability; Population","score_opus":0.2747011443187014,"score_gpt":0.5343761593589086,"score_spread":0.2596750150402072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399600420","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00077156,0.00072231976,0.9872036,0.0016721416,0.001507261,0.0012594971,0.006620772,0.00009771313,0.00014513769],"genre_scores_gemma":[0.04992408,0.00010661049,0.9482166,0.0001885555,0.00064331735,0.00015196613,0.000017422146,0.00011742439,0.0006340131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953166,0.00043139717,0.0018449294,0.000535594,0.0012274642,0.000644017],"domain_scores_gemma":[0.9379791,0.059507344,0.00084274,0.000484809,0.00071260176,0.00047341984],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002637791,0.00052291184,0.0012441273,0.000044380045,0.0005237976,0.00030043378,0.0005639418,0.00014876212,0.00013877387],"category_scores_gemma":[0.039177343,0.00028763252,0.00044295838,0.0003330114,0.0018643403,0.00012439034,0.00023576118,0.0007373751,0.0000062517724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064336266,0.0005500543,0.00006307243,0.0023707114,0.0017344769,0.00015174446,0.00053679215,0.00006023783,0.00012911674,0.7367904,0.2047108,0.04646897],"study_design_scores_gemma":[0.0043358286,0.0010292232,0.00023837878,0.0008474158,0.0018223525,0.000027513082,0.0008825041,0.011064403,0.00022529378,0.9668669,0.012187423,0.0004727371],"about_ca_topic_score_codex":0.0000026896682,"about_ca_topic_score_gemma":0.000007276572,"teacher_disagreement_score":0.23007654,"about_ca_system_score_codex":0.00025658455,"about_ca_system_score_gemma":0.0004750164,"threshold_uncertainty_score":0.99995756},"labels":[],"label_agreement":null},{"id":"W4399616639","doi":"10.1016/j.phacli.2024.04.006","title":"Intégration d’un score d’optimisation des analyses pharmaceutiques dans un système d’aide à la décision : un match pas gagné d’avance !","year":2024,"lang":"fr","type":"article","venue":"Le Pharmacien Clinicien","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.7124483491835933,"score_gpt":0.6112029761149739,"score_spread":0.10124537306861947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399616639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20466048,0.01320595,0.7614184,0.0036839305,0.0065912134,0.0018080046,0.0007395838,0.0009268592,0.0069655715],"genre_scores_gemma":[0.45587963,0.009303259,0.52963185,0.0008996331,0.0015942834,0.00016617763,0.00004119802,0.00020570547,0.0022782548],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9845369,0.0070860214,0.0038882745,0.0018451749,0.0013796879,0.0012639818],"domain_scores_gemma":[0.93103826,0.06585578,0.0008753191,0.0010124871,0.00055879937,0.00065933313],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017125245,0.00095700956,0.0016509397,0.00037860492,0.00071682496,0.00086907705,0.0011269748,0.0007631688,0.002450678],"category_scores_gemma":[0.035521075,0.0008997257,0.00088433846,0.002114677,0.0016827163,0.0010998442,0.000518909,0.0018830589,0.0006641577],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004980523,0.0018157391,0.00089519116,0.0032013538,0.0010604458,0.00063120393,0.005750537,0.001204044,0.029150799,0.05501415,0.0025852544,0.89819324],"study_design_scores_gemma":[0.0025256989,0.0003637792,0.0006276097,0.002499881,0.0024698311,0.00017752188,0.0006914529,0.11890383,0.26612443,0.5958333,0.008710193,0.0010724526],"about_ca_topic_score_codex":0.00028235704,"about_ca_topic_score_gemma":0.000012367402,"teacher_disagreement_score":0.8971208,"about_ca_system_score_codex":0.0005543969,"about_ca_system_score_gemma":0.0006244507,"threshold_uncertainty_score":0.99934536},"labels":[],"label_agreement":null},{"id":"W4399630953","doi":"10.1287/msom.2023.0246","title":"Adaptive Seamless Dose-Finding Trials","year":2024,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Leverage (statistics); Computer science; Matching (statistics); Range (aeronautics); Toxicity; Mathematical optimization; Mathematics; Machine learning; Medicine; Statistics","score_opus":0.6033093360047029,"score_gpt":0.5470555565121502,"score_spread":0.056253779492552725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399630953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030021157,0.00019833694,0.91261303,0.0068642865,0.004346272,0.004115266,0.0001905375,0.0014307231,0.040220406],"genre_scores_gemma":[0.18310836,0.00007587139,0.8103889,0.00093766866,0.00069514173,0.0004773721,0.000013109021,0.000098947996,0.0042046136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99581516,0.001050545,0.0013902076,0.0007451907,0.0005528344,0.00044603637],"domain_scores_gemma":[0.9864351,0.01249735,0.00011074447,0.000727339,0.00007739478,0.00015206795],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006401502,0.00035813238,0.000786132,0.00027994643,0.00032146744,0.0006995701,0.00048386512,0.0001318753,0.0014669459],"category_scores_gemma":[0.0024806494,0.00029335948,0.00023819944,0.00038570017,0.000038776492,0.00024953697,0.00039274758,0.00037351425,0.0007068401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008767133,0.00023590257,0.0000029649711,0.0017004135,0.0011689552,0.00019627252,0.0007739424,0.0034948788,0.00013678458,0.85791785,0.0047666375,0.12951775],"study_design_scores_gemma":[0.0013490458,0.00011701251,0.00040277542,0.0010807037,0.0012531314,0.000009494949,0.0011252858,0.019423734,0.010176977,0.95015883,0.014067832,0.00083517365],"about_ca_topic_score_codex":0.000054780205,"about_ca_topic_score_gemma":0.00007497896,"teacher_disagreement_score":0.1530872,"about_ca_system_score_codex":0.00019443779,"about_ca_system_score_gemma":0.00003627382,"threshold_uncertainty_score":0.99995184},"labels":[],"label_agreement":null},{"id":"W4399781691","doi":"10.3390/curroncol31060259","title":"How to Balance Prognostic Factors in Controlled Phase II Trials: Stratified Permuted Block Randomization or Minimization? An Analysis of Clinical Trials in Digestive Oncology","year":2024,"lang":"en","type":"review","venue":"Current Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Randomization; Clinical trial; Minification; Statistics; Internal medicine; Mathematics; Mathematical optimization","score_opus":0.884540025792915,"score_gpt":0.7413399817097063,"score_spread":0.14320004408320874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399781691","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006035286,0.8155866,0.08397536,0.00082869985,0.019644445,0.066191375,0.0072952528,0.00029406737,0.00014891186],"genre_scores_gemma":[0.0011707486,0.93205935,0.059273172,0.000030113053,0.001385716,0.004921362,0.00087856135,0.00015188857,0.00012911481],"study_design_codex":"design_other","study_design_gemma":"randomized_trial","domain_scores_codex":[0.8391419,0.13374801,0.023790171,0.0019105944,0.0006817593,0.0007275879],"domain_scores_gemma":[0.3353729,0.65156835,0.011013286,0.00089248037,0.00064289465,0.00051006925],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.109860994,0.0010835164,0.050357364,0.0027873856,0.00006263322,0.00010100676,0.00083323073,0.002331589,0.0003005992],"category_scores_gemma":[0.90263057,0.0006614306,0.003934388,0.0044674044,0.00036662858,0.000110560475,0.00026164443,0.0019286223,0.00000590756],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02624071,0.015047241,0.00033062574,0.006734903,0.00722648,0.000110134635,0.0007629861,0.000070044705,7.866506e-7,0.0028215337,0.00072001625,0.93993455],"study_design_scores_gemma":[0.31454352,0.027437108,0.00015908966,0.02501047,0.3058268,0.000013319934,0.00090609695,0.03337483,0.000002851536,0.026209394,0.26374578,0.002770732],"about_ca_topic_score_codex":0.000008746228,"about_ca_topic_score_gemma":0.0003532159,"teacher_disagreement_score":0.93716383,"about_ca_system_score_codex":0.00079311256,"about_ca_system_score_gemma":0.003885541,"threshold_uncertainty_score":0.9995837},"labels":[],"label_agreement":null},{"id":"W4399785917","doi":"10.1002/pds.5850","title":"Use of Point‐in‐Time or Window Approach in the Case‐Crossover Design, Implications for Pharmacoepidemiologic Research Using Registries","year":2024,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Window (computing); Pharmacoepidemiology; Crossover; Crossover study; Research design; Point (geometry); Statistics; Pharmacology; Medical prescription; Alternative medicine; Computer science; Artificial intelligence; World Wide Web","score_opus":0.8996671033285841,"score_gpt":0.6767634006556685,"score_spread":0.2229037026729156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399785917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060878433,0.0020854124,0.91542196,0.014927604,0.00039001263,0.0049953926,0.0009567944,0.000108747205,0.00023565684],"genre_scores_gemma":[0.21920896,0.0010986151,0.7774293,0.0012503059,0.00029329443,0.0005118906,0.000012140446,0.00004401281,0.00015149903],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9721364,0.023781821,0.0022632303,0.00084847887,0.00015952573,0.00081053673],"domain_scores_gemma":[0.5340781,0.4651571,0.0002198951,0.000353596,0.00010340327,0.00008791174],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09573895,0.00028274584,0.0012381354,0.00025981737,0.00026363417,0.000041193325,0.00045855704,0.00028158067,0.00007684938],"category_scores_gemma":[0.20199902,0.00017156165,0.00018002462,0.00084720727,0.0011937943,0.00020499197,0.00020359876,0.0011316228,0.0000032338917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013403912,0.001637991,0.021721067,0.0035431874,0.0006949657,0.0007420655,0.0031339058,0.0028816296,0.00525756,0.7483958,0.16003942,0.038548496],"study_design_scores_gemma":[0.0016270041,0.00010680781,0.0012057872,0.00018130861,0.00021221656,0.0006253943,0.0002455813,0.06523003,0.00028079993,0.9279808,0.002034627,0.00026965328],"about_ca_topic_score_codex":0.00018855213,"about_ca_topic_score_gemma":0.000011517151,"teacher_disagreement_score":0.44137526,"about_ca_system_score_codex":0.000103823244,"about_ca_system_score_gemma":0.00016688998,"threshold_uncertainty_score":0.9311271},"labels":[],"label_agreement":null},{"id":"W4399851207","doi":"10.7759/cureus.62769","title":"Translating Risk Ratios, Baseline Incidence, and Proportions Diseased to Correlations and Chi-Squared Statistics: Simulation Epidemiology","year":2024,"lang":"en","type":"article","venue":"Cureus","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Medicine; Statistics; Epidemiology; Incidence (geometry); Demography; Internal medicine","score_opus":0.4383869941747232,"score_gpt":0.5765670152101082,"score_spread":0.13818002103538501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399851207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003628507,0.0005071499,0.9897033,0.0008484985,0.00035093428,0.0007992323,0.0038625689,0.00016558792,0.00013424836],"genre_scores_gemma":[0.20292298,0.000074327116,0.79638255,0.00011713103,0.00023730187,0.00008377097,0.00006209303,0.000028536017,0.00009132097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996846,0.0012376842,0.0010564709,0.00046708345,0.0001582878,0.00023445916],"domain_scores_gemma":[0.8909832,0.108214565,0.00017883787,0.0002488267,0.000114020935,0.00026051397],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034900855,0.00017739856,0.00046204322,0.00008109046,0.0002010878,0.000053243748,0.00006904372,0.00013603969,0.00067711726],"category_scores_gemma":[0.24865523,0.0001522405,0.000050173137,0.00022657625,0.00015798297,0.00011292184,0.000043715307,0.0002832871,0.000022505334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017260668,0.0002282837,0.023772506,0.0007679819,0.00028279837,0.000038925507,0.001976514,0.0051412573,0.00008009705,0.70846593,0.015581929,0.24349114],"study_design_scores_gemma":[0.00019134616,0.000091472415,0.005858042,0.00012017094,0.00022650984,0.0000023095995,0.00003818893,0.37543878,0.0000016105481,0.61713374,0.00076453784,0.0001332945],"about_ca_topic_score_codex":0.000034488097,"about_ca_topic_score_gemma":0.00011709035,"teacher_disagreement_score":0.37029752,"about_ca_system_score_codex":0.000038319515,"about_ca_system_score_gemma":0.000085369524,"threshold_uncertainty_score":0.7576737},"labels":[],"label_agreement":null},{"id":"W4400043538","doi":"10.1002/mds.29899","title":"Advantages and Challenges of Platform Trials for Disease Modifying Therapies in Parkinson's Disease","year":2024,"lang":"en","type":"review","venue":"Movement Disorders","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Clinical trial; Expediting; Disease; Medicine; Parkinson's disease; Drug development; Timeline; Protocol (science); Intensive care medicine; Alternative medicine; Drug; Pharmacology; Pathology","score_opus":0.7477034886944454,"score_gpt":0.5919660402946858,"score_spread":0.15573744839975956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400043538","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000955295,0.9886135,0.00339563,0.0007700909,0.0004635655,0.004869507,0.0017466033,0.00005602584,0.00007554319],"genre_scores_gemma":[0.000017878532,0.96429205,0.03316386,0.00007847108,0.0001330059,0.0021130117,0.000018886696,0.00012249086,0.000060356353],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951942,0.00085291715,0.002405801,0.00076348917,0.00039237883,0.00039121753],"domain_scores_gemma":[0.9500211,0.048344214,0.0008376392,0.0005293209,0.000031293755,0.00023641696],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0058580507,0.0006057766,0.003971464,0.00030222308,0.000043476593,0.000050160314,0.0003067868,0.00020663315,0.000043510372],"category_scores_gemma":[0.036270775,0.00042224594,0.0009773078,0.00015946677,0.00017632503,0.00006846273,0.00018914833,0.00027141214,0.0000022613401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001621029,0.00023497407,0.000011287917,0.12274578,0.00040505306,0.000005167192,0.00009241792,2.9187805e-7,3.2542893e-8,0.103571005,0.00027640362,0.77249545],"study_design_scores_gemma":[0.00078167766,0.00007228397,0.000014081462,0.013772607,0.00244979,1.3487374e-8,0.00017770096,0.0000419928,1.033422e-7,0.7649239,0.21743554,0.0003303344],"about_ca_topic_score_codex":0.000004802342,"about_ca_topic_score_gemma":0.000017472594,"teacher_disagreement_score":0.7721651,"about_ca_system_score_codex":0.000079191304,"about_ca_system_score_gemma":0.00015384953,"threshold_uncertainty_score":0.9998229},"labels":[],"label_agreement":null},{"id":"W4400056122","doi":"10.1002/pst.2414","title":"<scp>T3</scp> + 3: 3 + 3 Design With Delayed Outcomes","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Isotonic regression; Maximum tolerated dose; Toxicity; Clinical trial; Outcome (game theory); Research design; Duration (music); Clinical study design; Computer science; Logistic regression; Medicine; Reliability engineering; Statistics; Mathematics; Internal medicine; Engineering; Machine learning","score_opus":0.6329948285871682,"score_gpt":0.5963440292239538,"score_spread":0.03665079936321436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400056122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005819221,0.0003239795,0.9912299,0.00044423083,0.0011941742,0.0008942167,0.0013330077,0.00069411116,0.003304461],"genre_scores_gemma":[0.011740908,0.00013681158,0.9847422,0.0008366454,0.00034965982,0.00012093694,0.0000113486685,0.00016729908,0.0018941456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99495566,0.0011207195,0.0011692422,0.0007869269,0.0010278639,0.0009395751],"domain_scores_gemma":[0.8190125,0.17965852,0.000119877244,0.00042972484,0.00019142732,0.0005879534],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030521774,0.000531802,0.00095029036,0.00012417827,0.00015193592,0.00029145562,0.00045267478,0.00022612482,0.00088146864],"category_scores_gemma":[0.0696193,0.00037526627,0.00014734088,0.00052145583,0.00050460413,0.00011864917,0.00015430494,0.0010157278,0.0007172267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010781425,0.000328533,0.0003167915,0.00051926816,0.0007400389,0.0008436135,0.0001574162,0.000027604197,0.000097059245,0.86467177,0.09624841,0.035941698],"study_design_scores_gemma":[0.0011999349,0.00039929498,0.0002247314,0.000119028926,0.0010187355,0.000047854006,0.00003572815,0.031971563,0.0012178357,0.9179447,0.04557063,0.0002499138],"about_ca_topic_score_codex":0.0000062231034,"about_ca_topic_score_gemma":0.0000026657403,"teacher_disagreement_score":0.1785378,"about_ca_system_score_codex":0.00012987043,"about_ca_system_score_gemma":0.00019882272,"threshold_uncertainty_score":0.99986994},"labels":[],"label_agreement":null},{"id":"W4400097380","doi":"10.14283/jpad.2024.136","title":"Pre-Randomization Predictors of Study Discontinuation in a Preclinical Alzheimer's Disease Randomized Controlled Trial","year":2024,"lang":"en","type":"article","venue":"The Journal of Prevention of Alzheimer s Disease","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Avid Radiopharmaceuticals; Genentech; National Institutes of Health; American Heart Association; GHR Foundation; Eli Lilly and Company; Bristol-Myers Squibb; BrightFocus Foundation; Biogen; Brigham and Women's Hospital; Foundation for Neurologic Diseases; Eisai; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Randomization; Discontinuation; Randomized controlled trial; Medicine; Disease; Internal medicine","score_opus":0.2570528478419533,"score_gpt":0.5235615186325131,"score_spread":0.2665086707905598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400097380","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88909876,0.0137932515,0.070040055,0.00074868184,0.0036583545,0.022394298,0.00011088461,0.000050302227,0.00010542265],"genre_scores_gemma":[0.9927307,0.00028555797,0.0060603837,0.000011918126,0.00053866813,0.00027832485,0.0000031102954,0.00004125347,0.00005012919],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9769245,0.0150238965,0.0062761265,0.00027583996,0.0012862768,0.00021336632],"domain_scores_gemma":[0.93642986,0.058997355,0.003269641,0.00051685754,0.00047016455,0.00031612144],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035779763,0.00029353265,0.0029828476,0.00035078518,0.000043777403,0.00004443144,0.0004365146,0.00010225079,0.0003041979],"category_scores_gemma":[0.10808145,0.0001691964,0.0017608674,0.00039330166,0.00038944246,0.0003063281,0.00009511745,0.00041963806,0.000002156964],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.98145115,0.005098068,0.00039282796,0.000092595634,0.005611182,0.000015574082,0.0006503265,0.00027363314,0.00001085294,0.0034832328,0.00016128214,0.0027592925],"study_design_scores_gemma":[0.68831724,0.001015479,0.0027697321,0.00084952754,0.035784345,8.597439e-7,0.00009765365,0.0034704148,0.000043403423,0.2675157,0.0000024803915,0.00013314505],"about_ca_topic_score_codex":0.000005984353,"about_ca_topic_score_gemma":0.0000034325233,"teacher_disagreement_score":0.29313385,"about_ca_system_score_codex":0.000024460933,"about_ca_system_score_gemma":0.00055310666,"threshold_uncertainty_score":0.99286765},"labels":[],"label_agreement":null},{"id":"W4400131760","doi":"10.1214/24-ejs2253","title":"Post-selection inference for e-value based confidence intervals","year":2024,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Confidence interval; Inference; Statistics; Selection (genetic algorithm); Value (mathematics); Confidence distribution; Artificial intelligence; Computer science","score_opus":0.2522498838553947,"score_gpt":0.5428647165319656,"score_spread":0.29061483267657084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400131760","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010029024,0.0004764871,0.9960151,0.00062766584,0.0010504484,0.0003394718,0.00035712085,0.00004943906,0.000081381644],"genre_scores_gemma":[0.20444326,0.0001351691,0.79449886,0.00020724953,0.00045205656,0.000014745171,0.000002670726,0.000047042107,0.00019892331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99678075,0.0004745895,0.0014352018,0.00024070757,0.00049450825,0.00057421945],"domain_scores_gemma":[0.92620784,0.07206539,0.0005066252,0.0001572176,0.0009303043,0.00013262672],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0055377497,0.00021271572,0.0006269092,0.00019014164,0.00006886864,0.00013492434,0.00032943007,0.000135611,0.00029789752],"category_scores_gemma":[0.11216283,0.00017531688,0.00021199812,0.00024118759,0.00012342686,0.00013053262,0.000024499464,0.0008540128,0.00001394707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025662832,0.00008534118,0.0000123789305,0.0003822078,0.00017847016,0.000019530813,0.00006291817,0.000040183026,0.0014439008,0.96604097,0.003936118,0.027541371],"study_design_scores_gemma":[0.0006723359,0.002424887,0.00003035544,0.00042148223,0.00034053012,0.00006673924,0.000028965062,0.022523563,0.002881015,0.96802855,0.0023989228,0.00018268565],"about_ca_topic_score_codex":0.000006399154,"about_ca_topic_score_gemma":0.00001575674,"teacher_disagreement_score":0.20344035,"about_ca_system_score_codex":0.00033599325,"about_ca_system_score_gemma":0.0016173964,"threshold_uncertainty_score":0.8953158},"labels":[],"label_agreement":null},{"id":"W4400308964","doi":"10.1093/icvts/ivae126","title":"Composite end points and competing risks analysis","year":2024,"lang":"en","type":"article","venue":"Interdisciplinary CardioVascular and Thoracic Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Context (archaeology); Outcome (game theory); Clinical trial; Ranking (information retrieval); Event (particle physics); Composite number; Computer science; Psychology; Statistics; Medicine; Artificial intelligence; Mathematics; History; Algorithm; Pathology","score_opus":0.3303492795888192,"score_gpt":0.5201507844602693,"score_spread":0.1898015048714501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400308964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6939295,0.01794832,0.28169167,0.00061042875,0.0015373146,0.00038568536,0.00015504817,0.00041782262,0.0033242034],"genre_scores_gemma":[0.916778,0.00041826605,0.08225025,0.000035303397,0.0003739551,0.000029790346,0.000010416625,0.000054885495,0.00004910483],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99561673,0.0017439435,0.0009118452,0.00083767617,0.0005119043,0.0003778941],"domain_scores_gemma":[0.9574434,0.041531753,0.000091807844,0.0006333278,0.0000710858,0.000228626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010702914,0.0003319776,0.001726245,0.0004952349,0.00022919891,0.00026522667,0.00012744412,0.00018274075,0.00012670124],"category_scores_gemma":[0.003994568,0.00027583574,0.0019316605,0.000800207,0.0003431241,0.0001480919,0.0008095599,0.00042987888,0.00001991692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025516615,0.00013296246,0.011633017,0.0019886359,0.034347795,0.001973343,0.0012520668,0.000035615874,0.00007507063,0.0067128423,0.00072672893,0.94086677],"study_design_scores_gemma":[0.00027137113,0.0000745927,0.025037015,0.0014078656,0.018542634,0.0006084297,0.0007555283,0.00853832,0.0006585494,0.9416358,0.0013708503,0.0010990291],"about_ca_topic_score_codex":0.000016378246,"about_ca_topic_score_gemma":0.0000031556874,"teacher_disagreement_score":0.9397677,"about_ca_system_score_codex":0.00003922747,"about_ca_system_score_gemma":0.000029522656,"threshold_uncertainty_score":0.99996936},"labels":[],"label_agreement":null},{"id":"W4400443106","doi":"10.1136/bmj-2023-078524","title":"Reporting of surrogate endpoints in randomised controlled trial reports (CONSORT-Surrogate): extension checklist with explanation and elaboration","year":2024,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; McMaster University; Women's College Hospital","funders":"Medical Research Council; Conselho Nacional de Desenvolvimento Científico e Tecnológico; University of Bristol; National Institute for Health and Care Research; Cancer Research UK; Parker Institute for Cancer Immunotherapy; Universität Basel","keywords":"Surrogate endpoint; Checklist; Surrogate data; Elaboration; Extension (predicate logic); Medicine; Randomized controlled trial; Surrogate model; Computer science; Psychology; Machine learning; Surgery; Internal medicine","score_opus":0.3133782206230655,"score_gpt":0.5237705161803778,"score_spread":0.21039229555731237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400443106","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96929497,0.00013078522,0.01868027,0.0007389854,0.001341836,0.0071653537,0.0000131854795,0.00012475516,0.002509888],"genre_scores_gemma":[0.8146017,0.000030433406,0.18429942,0.000024699673,0.00030224916,0.0004514951,0.000007398131,0.00003595285,0.00024662653],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9925107,0.0010418913,0.0053006555,0.00048365028,0.00047319155,0.00018994311],"domain_scores_gemma":[0.96796143,0.027740804,0.0035294776,0.00039952822,0.0002877726,0.00008097781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025938278,0.000182257,0.0013327132,0.00015446379,0.000038674723,0.000060555627,0.000044531866,0.00015799241,0.00006420887],"category_scores_gemma":[0.31872892,0.00012933652,0.0001191335,0.00030546973,0.00010245038,0.00013215108,0.000029979588,0.00021634763,0.0000015758699],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9085171,0.0008142811,0.0015348144,0.0016614073,0.00064091734,0.0050729024,0.0013068307,0.000054944565,0.012237583,0.041917454,0.0028328684,0.02340885],"study_design_scores_gemma":[0.5855115,0.00056302745,0.0009626219,0.0015246273,0.0004617712,0.00020133467,0.00021440664,0.0054978207,0.005776604,0.3988117,0.000101198086,0.00037336868],"about_ca_topic_score_codex":0.000024221012,"about_ca_topic_score_gemma":0.00004044861,"teacher_disagreement_score":0.35689425,"about_ca_system_score_codex":0.000040465213,"about_ca_system_score_gemma":0.00018130906,"threshold_uncertainty_score":0.8989741},"labels":[],"label_agreement":null},{"id":"W4400498564","doi":"10.1002/cam4.7447","title":"Examining external control arms in oncology: A scoping review of applications to date","year":2024,"lang":"en","type":"review","venue":"Cancer Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Context (archaeology); MEDLINE; Clinical trial; Scopus; Web of science; Alternative medicine; Randomized controlled trial; Clinical study design; Meta-analysis; Research design; Clinical Oncology; Internal medicine; Family medicine; Cancer; Oncology; Medical physics; Pathology","score_opus":0.8581522110242914,"score_gpt":0.7362195983410867,"score_spread":0.12193261268320466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400498564","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.7506627e-8,0.91630405,0.07581745,0.0006412589,0.000817521,0.005360186,0.00013943831,0.000034685025,0.0008853783],"genre_scores_gemma":[1.0486876e-7,0.87915623,0.1131274,0.0011409909,0.0012897414,0.0051436694,0.0000044353874,0.00006205344,0.00007534097],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99444604,0.0009928253,0.0032644814,0.00060916645,0.000397763,0.00028975264],"domain_scores_gemma":[0.95976025,0.0382396,0.001002848,0.0006728469,0.000121856436,0.00020260348],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070402506,0.00036814032,0.006057364,0.00024511476,0.0000143796515,0.0000049744253,0.00050806237,0.00025631822,0.0007397126],"category_scores_gemma":[0.049388774,0.0002381779,0.00020044777,0.0008587577,0.00019854511,0.000014993331,0.00012864138,0.0007538853,0.000046902212],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040393857,0.00001789658,3.7194079e-7,0.38085046,0.00006542155,0.000013930735,0.00003060085,3.648173e-8,5.203105e-7,0.0015448303,0.0013782916,0.6160936],"study_design_scores_gemma":[0.00035882866,0.000118106815,2.0844563e-7,0.70151293,0.0027918296,0.000006987335,0.000008184987,0.0000014340299,2.534518e-7,0.015360544,0.2797036,0.00013708266],"about_ca_topic_score_codex":0.000015658296,"about_ca_topic_score_gemma":0.000010033244,"teacher_disagreement_score":0.6159565,"about_ca_system_score_codex":0.0002551921,"about_ca_system_score_gemma":0.00085542165,"threshold_uncertainty_score":0.9712613},"labels":[],"label_agreement":null},{"id":"W4400871008","doi":"10.1016/j.cont.2024.101338","title":"Current clinical status of IC/BPS and what the future holds in basic &amp; translational science","year":2024,"lang":"en","type":"article","venue":"Continence","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Translational medicine; Translational science; Translational research; Biomarker; Data science; Biomarker discovery; Medicine; Computer science; Engineering ethics; Proteomics; Pathology; Biology; Engineering","score_opus":0.473315435139216,"score_gpt":0.5955941486862105,"score_spread":0.12227871354699454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400871008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83017296,0.034341916,0.11664273,0.008173968,0.008668641,0.0011562294,0.00011765616,0.0001072171,0.0006186967],"genre_scores_gemma":[0.6738156,0.008891339,0.31599542,0.00020936433,0.00096162857,0.00003493445,0.0000017475932,0.000024643296,0.000065274086],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99757415,0.00041372163,0.00088287337,0.00039749368,0.00044131398,0.00029046784],"domain_scores_gemma":[0.9701728,0.029147483,0.000111707566,0.00033104455,0.000117764976,0.00011918576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006778947,0.00011291262,0.00034795117,0.00007207203,0.000049283844,0.00016703627,0.00030108693,0.00007639576,0.00011391419],"category_scores_gemma":[0.030044915,0.00007160219,0.000080449536,0.000540437,0.0011522373,0.00030676735,0.00008719768,0.0004460156,0.000009661907],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004689371,0.00010708755,0.018565118,0.00022848205,0.000011727428,0.0000037053699,0.00063312566,6.839859e-7,0.00020596232,0.29842612,0.0005675925,0.6812035],"study_design_scores_gemma":[0.0006173953,0.000057262157,0.087410554,0.00074701436,0.000052519576,0.0000035693447,0.00021061175,0.00095054344,0.000096798925,0.87986803,0.029827138,0.00015859133],"about_ca_topic_score_codex":0.000002156143,"about_ca_topic_score_gemma":0.000020682593,"teacher_disagreement_score":0.68104494,"about_ca_system_score_codex":0.000015520478,"about_ca_system_score_gemma":0.00024140075,"threshold_uncertainty_score":0.97812545},"labels":[],"label_agreement":null},{"id":"W4401091908","doi":"10.1038/s41588-024-01854-z","title":"Genetic factors associated with reasons for clinical trial stoppage","year":2024,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; European Molecular Biology Laboratory; Wellcome Trust; Wellcome; GlaxoSmithKline","keywords":"Biology; Genetics; Computational biology","score_opus":0.6127446181983821,"score_gpt":0.6109378820626427,"score_spread":0.0018067361357394507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401091908","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.802914,0.002711772,0.17685443,0.000515791,0.010460761,0.0037901646,0.0011804891,0.0006443373,0.0009282545],"genre_scores_gemma":[0.27222157,0.0001927673,0.72381467,0.0002497532,0.002449889,0.00011358679,0.000020645202,0.00016443578,0.00077266846],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996116,0.0008065083,0.0012120451,0.0007636909,0.00060434634,0.0004974219],"domain_scores_gemma":[0.9107226,0.08791652,0.00024344695,0.00062247267,0.00024393176,0.000251011],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0035060293,0.0003481333,0.0008819271,0.00008560079,0.00009922104,0.00013536963,0.0004185443,0.0013824943,0.000118993135],"category_scores_gemma":[0.13142839,0.00024491534,0.00043239424,0.00038147168,0.00022388925,0.000025973774,0.00008350776,0.0014660944,0.000010479219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03731909,0.005593408,0.027912484,0.001995242,0.008515947,0.00043741506,0.0010067056,0.00003641043,0.00018753241,0.18948372,0.48639438,0.24111767],"study_design_scores_gemma":[0.029468771,0.0040029394,0.0133027155,0.00044236527,0.0019103097,0.0000045198217,0.00004874047,0.0013836683,0.00035809737,0.917479,0.030733857,0.0008650429],"about_ca_topic_score_codex":4.8097843e-7,"about_ca_topic_score_gemma":0.0000117774425,"teacher_disagreement_score":0.7279953,"about_ca_system_score_codex":0.000077215846,"about_ca_system_score_gemma":0.0002573934,"threshold_uncertainty_score":0.99991393},"labels":[],"label_agreement":null},{"id":"W4401160687","doi":"10.1080/10408363.2024.2379278","title":"Guidance for securing approvals for new biomarkers: from discovery to clinical implementation","year":2024,"lang":"en","type":"review","venue":"Critical Reviews in Clinical Laboratory Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; University of Toronto; University Health Network; Queen's University","funders":"","keywords":"Accreditation; Test (biology); Commercialization; Medical physics; Agency (philosophy); Medicine; Risk analysis (engineering); Computer science; Medical education; Business","score_opus":0.8614901721443221,"score_gpt":0.7523927129562727,"score_spread":0.10909745918804936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401160687","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006120374,0.8531843,0.12059494,0.0011389675,0.009717385,0.010006718,0.005183334,0.00010698656,0.00006125586],"genre_scores_gemma":[5.2130235e-7,0.5184891,0.47512054,0.0009694702,0.0035155972,0.0017436474,0.000020399782,0.00008485062,0.00005586221],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9710964,0.007475969,0.015523264,0.0036730173,0.0009113447,0.0013199943],"domain_scores_gemma":[0.46597588,0.5283136,0.002062281,0.0017900493,0.00048306666,0.001375156],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08869249,0.00109347,0.009355241,0.00033201257,0.0002286503,0.00079227827,0.0023681608,0.00126135,0.00014450731],"category_scores_gemma":[0.70446193,0.00076260406,0.003399026,0.0021265054,0.0016631563,0.00047579108,0.00064718287,0.001387301,0.00024436892],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006106796,0.00022008595,0.000024868357,0.020320792,0.00014478133,0.0000066409502,0.000015430875,2.2400634e-8,2.060608e-7,0.120726675,0.05430839,0.804171],"study_design_scores_gemma":[0.00042874285,0.000548544,0.0000047150743,0.027018972,0.0017032779,4.992555e-7,0.000029344565,0.000014515612,0.0000014007534,0.37277606,0.5968864,0.00058751967],"about_ca_topic_score_codex":0.000011309412,"about_ca_topic_score_gemma":0.000053767966,"teacher_disagreement_score":0.8035835,"about_ca_system_score_codex":0.00021939217,"about_ca_system_score_gemma":0.002787639,"threshold_uncertainty_score":0.9994825},"labels":[],"label_agreement":null},{"id":"W4401697231","doi":"10.1001/jamapediatrics.2024.2697","title":"Whole-of-Life Inclusion in Bayesian Adaptive Platform Clinical Trials","year":2024,"lang":"en","type":"article","venue":"JAMA Pediatrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of Toronto; Montreal Children's Hospital; St Joseph's Health Centre; Public Health Ontario; University of British Columbia","funders":"National Institute for Health and Care Research","keywords":"Clinical trial; Medicine; Bayesian probability; Randomized controlled trial; Sample size determination; Bayesian inference; Bayesian network; Clinical study design; Machine learning; Computer science; Artificial intelligence; Statistics; Surgery","score_opus":0.6651248507345182,"score_gpt":0.6057218035184695,"score_spread":0.05940304721604872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401697231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066240765,0.0029851948,0.90188223,0.0040557124,0.010323486,0.002790289,0.0010983286,0.00050696044,0.010117048],"genre_scores_gemma":[0.24475837,0.0008289394,0.74836105,0.0004228564,0.0052824644,0.00004839739,0.0000071908994,0.00009285096,0.00019786684],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885158,0.0037337954,0.005551499,0.00068404275,0.0010536904,0.000461191],"domain_scores_gemma":[0.6446084,0.35346285,0.0008255085,0.00056830724,0.00017564328,0.00035931554],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06216697,0.0002977538,0.0020340926,0.00042106636,0.00007831696,0.000091271824,0.00055410917,0.0008518723,0.00029890923],"category_scores_gemma":[0.60262173,0.00023378234,0.00062787783,0.0011951206,0.00017506805,0.00020739308,0.0013758453,0.0013185724,0.000092946095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016227798,0.0010141612,0.0049164672,0.0015449891,0.000179396,0.0002464632,0.0010800388,0.00001539576,0.000046198053,0.42234984,0.05950109,0.5074832],"study_design_scores_gemma":[0.0020770754,0.00036848735,0.0007198366,0.00020248276,0.00028186775,0.0000019980416,0.000109850385,0.0062645474,0.000038402384,0.98694074,0.0027171061,0.00027761978],"about_ca_topic_score_codex":0.000020561258,"about_ca_topic_score_gemma":0.000013573966,"teacher_disagreement_score":0.5645909,"about_ca_system_score_codex":0.00011286318,"about_ca_system_score_gemma":0.0005539461,"threshold_uncertainty_score":0.96569645},"labels":[],"label_agreement":null},{"id":"W4401706460","doi":"10.1177/00236772241246602","title":"Ditching the norm: Using alternative distributions for biological data analysis","year":2024,"lang":"en","type":"article","venue":"Laboratory Animals","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prioris.ai (Canada)","funders":"","keywords":"Computer science; Parametric statistics; Data mining; Software; Data science; Statistics; Mathematics; Programming language","score_opus":0.8293882129835543,"score_gpt":0.6393586783154291,"score_spread":0.1900295346681251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401706460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04632119,0.0003662376,0.9348633,0.00047442212,0.0005223116,0.00044544146,0.01679214,0.00013712388,0.00007781958],"genre_scores_gemma":[0.33528247,0.000026074493,0.66356057,0.00012702837,0.0008547452,0.00005039234,0.00005909387,0.00002379137,0.000015842905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99747884,0.00085238414,0.00063231436,0.00056172744,0.00020276217,0.0002719976],"domain_scores_gemma":[0.94311875,0.055621922,0.0001486122,0.00085551257,0.00017286504,0.000082349274],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005494786,0.00016804974,0.0004963404,0.00006385347,0.0002578218,0.00019547185,0.0007062445,0.00011999722,0.00019840292],"category_scores_gemma":[0.06803352,0.00009954805,0.00017307283,0.0011759691,0.00020287893,0.00012706334,0.00032089997,0.00027035028,0.000014702469],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005469972,0.000081003665,0.00050468696,0.00007986047,0.0016461127,0.000019928597,0.00009921931,0.000021968834,0.0026827506,0.9909166,0.0025634484,0.0013296875],"study_design_scores_gemma":[0.00014820673,0.000068201654,0.0004478262,0.000052198102,0.0017647987,0.0000011661142,0.000082474835,0.0402534,0.00095884094,0.9483502,0.007677288,0.0001953827],"about_ca_topic_score_codex":0.000008714207,"about_ca_topic_score_gemma":0.000009063665,"teacher_disagreement_score":0.2889613,"about_ca_system_score_codex":0.00005462989,"about_ca_system_score_gemma":0.000089440524,"threshold_uncertainty_score":0.93981683},"labels":[],"label_agreement":null},{"id":"W4401797296","doi":"10.1093/jrsssb/qkae084","title":"A nonparametric framework for treatment effect modifier discovery in high dimensions","year":2024,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Drug discovery; Computational biology; Computer science; Psychology; Econometrics; Mathematics; Biology; Bioinformatics","score_opus":0.36207862647150385,"score_gpt":0.5291868364183442,"score_spread":0.16710820994684034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401797296","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009266152,0.00041198503,0.98056084,0.0020944094,0.0044977902,0.0011969719,0.0018551534,0.000060592007,0.000056134646],"genre_scores_gemma":[0.028510543,0.00012075231,0.9695299,0.00030133704,0.0008430703,0.00014534901,0.0000059216327,0.0001065687,0.00043651267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9889621,0.005890429,0.0025562372,0.0007375502,0.00088210666,0.0009715679],"domain_scores_gemma":[0.6289477,0.36968595,0.00043400427,0.00044262136,0.00017392413,0.00031582534],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010924485,0.00065095053,0.0025803666,0.00014338239,0.0002608378,0.00025992608,0.0006670836,0.00069699384,0.00035084883],"category_scores_gemma":[0.32839847,0.00036199935,0.0011431727,0.0008896411,0.0012500943,0.00018434151,0.0002505408,0.0013975637,0.000014014633],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016656131,0.0004152878,0.00022366845,0.00059040403,0.00077683886,0.00016103835,0.00025926894,0.00019465756,0.000062654384,0.95913637,0.007854461,0.028659742],"study_design_scores_gemma":[0.0016381473,0.003222796,0.0019153532,0.00043444935,0.0013693458,0.000067476736,0.00010012089,0.005671397,0.000376595,0.98348063,0.0013346579,0.0003890416],"about_ca_topic_score_codex":0.000060691516,"about_ca_topic_score_gemma":0.000010168212,"teacher_disagreement_score":0.36379552,"about_ca_system_score_codex":0.0006667277,"about_ca_system_score_gemma":0.00035202003,"threshold_uncertainty_score":0.9998832},"labels":[],"label_agreement":null},{"id":"W4401814791","doi":"10.1016/j.cct.2024.107665","title":"Sample size planning for estimating the global win probability with precision and assurance","year":2024,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Confidence interval; Equivalence (formal languages); Sample size determination; Coverage probability; Receiver operating characteristic; Statistics; Limit (mathematics); Outcome (game theory); Mathematics","score_opus":0.8428037699283226,"score_gpt":0.6623149787238858,"score_spread":0.18048879120443684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401814791","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016481075,0.0011971893,0.9680387,0.004228438,0.0027289158,0.0052231406,0.00091397413,0.00034439703,0.0008441919],"genre_scores_gemma":[0.1459998,0.000015082198,0.85163635,0.00031600054,0.0016198613,0.00031191236,0.0000030013616,0.000042469146,0.000055513236],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98535234,0.008284411,0.0044213636,0.0010647485,0.00049785734,0.0003792881],"domain_scores_gemma":[0.07517471,0.92257416,0.0009499823,0.000812506,0.00021143217,0.00027722065],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09401607,0.00035476885,0.0021735823,0.000020043297,0.00021174617,0.0003391535,0.00041820676,0.0003477195,0.000056136094],"category_scores_gemma":[0.8872183,0.00018837792,0.0005066489,0.00030124007,0.0006279896,0.00018985153,0.00017478483,0.0005520548,0.000005897111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014842007,0.0009049587,0.037648838,0.0039564674,0.001949307,0.00009494266,0.0004143012,0.00009050339,0.000032372765,0.24508674,0.066921525,0.628058],"study_design_scores_gemma":[0.0027752656,0.0008117254,0.0014595732,0.0013188017,0.00025379198,0.000006777325,0.000031424246,0.010038754,0.000018376582,0.979251,0.00377448,0.0002600309],"about_ca_topic_score_codex":0.000011581388,"about_ca_topic_score_gemma":0.0000027968617,"teacher_disagreement_score":0.9142897,"about_ca_system_score_codex":0.00004835659,"about_ca_system_score_gemma":0.0004648679,"threshold_uncertainty_score":0.9329011},"labels":[],"label_agreement":null},{"id":"W4401818898","doi":"10.1002/psp4.13216","title":"Development and comparison of model‐integrated evidence approaches for bioequivalence studies with pharmacokinetic end points","year":2024,"lang":"en","type":"article","venue":"CPT Pharmacometrics & Systems Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hamilton Health Sciences Foundation","keywords":"Bioequivalence; Resampling; Type I and type II errors; Nonparametric statistics; Statistics; Sample size determination; Computer science; Sampling (signal processing); Confidence interval; Mathematics; Bioavailability","score_opus":0.8675392696483202,"score_gpt":0.634633286820038,"score_spread":0.23290598282828223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401818898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2531434,0.06372334,0.671591,0.0005775618,0.005254922,0.0047881994,0.0003447725,0.00042434642,0.00015250038],"genre_scores_gemma":[0.645086,0.0011904545,0.3523525,0.00007919749,0.00024221436,0.0007830543,0.0000035645792,0.000079159436,0.00018389555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943681,0.0009588084,0.002220333,0.0010216404,0.00072984543,0.0007013051],"domain_scores_gemma":[0.93373936,0.06441307,0.00065408164,0.00026249248,0.0006181224,0.00031285267],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0065105762,0.00057641615,0.001881948,0.0010530947,0.00016113273,0.000081988226,0.00057852623,0.00019242059,0.00006347592],"category_scores_gemma":[0.008989189,0.00043154406,0.00014312676,0.0022133454,0.00066862255,0.00022924272,0.0002640433,0.0005893085,0.00000853325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069816685,0.0046873987,0.0030104131,0.12328573,0.021231651,0.00032927966,0.015915733,0.009455176,0.21693973,0.13297832,0.083774745,0.38141015],"study_design_scores_gemma":[0.005083062,0.00089746324,0.000023957427,0.0023334308,0.004321479,0.000075498836,0.0013675579,0.7481447,0.21105431,0.016487798,0.00904633,0.0011644356],"about_ca_topic_score_codex":0.0000037134673,"about_ca_topic_score_gemma":6.003816e-7,"teacher_disagreement_score":0.7386895,"about_ca_system_score_codex":0.00027077142,"about_ca_system_score_gemma":0.0003482829,"threshold_uncertainty_score":0.9998136},"labels":[],"label_agreement":null},{"id":"W4402014457","doi":"10.1002/psp4.13217","title":"Evaluation of model‐integrated evidence approaches for pharmacokinetic bioequivalence studies using model averaging methods","year":2024,"lang":"en","type":"article","venue":"CPT Pharmacometrics & Systems Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hamilton Health Sciences Foundation","keywords":"Bioequivalence; Pharmacokinetics; Econometrics; Computer science; Medicine; Mathematics; Pharmacology","score_opus":0.9654321675280938,"score_gpt":0.7370173842571133,"score_spread":0.22841478327098053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402014457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025507346,0.053001676,0.9078482,0.00016425474,0.008353648,0.0043524997,0.00033088928,0.00031379936,0.00012770035],"genre_scores_gemma":[0.43464065,0.001735502,0.56175864,0.0000869184,0.0005476857,0.0009944591,0.0000031677655,0.00012267173,0.000110306246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9852685,0.0073872595,0.003129733,0.0013944234,0.0018546203,0.00096547673],"domain_scores_gemma":[0.8989143,0.09580293,0.0010765283,0.00052604364,0.003346732,0.000333463],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059284918,0.00071114564,0.002075812,0.0019247971,0.00021380656,0.00011073437,0.0009651482,0.0003154045,0.00011035731],"category_scores_gemma":[0.061474834,0.00062230474,0.0005206335,0.0039556758,0.00050070137,0.0004879889,0.0003603425,0.0008069385,0.000006653985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030917145,0.00041941318,0.0000144312335,0.00967948,0.0033198588,0.000012532406,0.00087273994,0.61460465,0.274982,0.0114804525,0.005448562,0.078856714],"study_design_scores_gemma":[0.0018533499,0.00010527823,3.6747e-7,0.0007007577,0.009394201,0.000021116412,0.00016358172,0.8007347,0.057380117,0.12907447,0.000105334424,0.00046674002],"about_ca_topic_score_codex":0.000009825695,"about_ca_topic_score_gemma":1.2936702e-7,"teacher_disagreement_score":0.40913332,"about_ca_system_score_codex":0.00116741,"about_ca_system_score_gemma":0.0010546454,"threshold_uncertainty_score":0.9996228},"labels":[],"label_agreement":null},{"id":"W4402375524","doi":"10.1089/bio.2024.0083","title":"MIBLood-EV: An Online Reporting Tool to Facilitate the Standardized Reporting of Preanalytical Variables and Quality Control of Plasma and Serum to Enhance Rigor and Reproducibility in Liquid Biopsy Research","year":2024,"lang":"en","type":"article","venue":"Biopreservation and Biobanking","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto","funders":"","keywords":"Reproducibility; Quality (philosophy); Medical physics; Medicine; Control (management); Computer science; Chromatography; Chemistry","score_opus":0.7615053759469612,"score_gpt":0.6096762529654356,"score_spread":0.15182912298152562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402375524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9804875,0.00017397842,0.015713017,0.002123124,0.000084974614,0.001062201,0.00028218565,0.000033003744,0.00003996933],"genre_scores_gemma":[0.83330774,0.00003194035,0.16647772,0.000042066018,0.00006020469,0.000022909511,0.0000019261772,0.0000120731365,0.000043406842],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99157584,0.0015163377,0.0046836487,0.0012866,0.0006181118,0.0003194812],"domain_scores_gemma":[0.97497433,0.021720132,0.0014582955,0.0010903745,0.0005983634,0.00015848411],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.085724555,0.00016610134,0.0008857313,0.00017403504,0.00011560737,0.00011549776,0.0001263886,0.00013953491,0.000012651151],"category_scores_gemma":[0.4641432,0.0001152219,0.000045597782,0.00061532157,0.00034566422,0.00014865943,0.00028057743,0.00030890148,1.104305e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065099383,0.00064133515,0.18817051,0.008012291,0.0003716273,0.000059361722,0.008834305,0.000021731492,0.56804544,0.08294428,0.00010622277,0.13628295],"study_design_scores_gemma":[0.0024644625,0.0021368226,0.290955,0.0037613134,0.00028849626,0.00005305046,0.0027951077,0.0178973,0.14186747,0.5363731,0.00062559586,0.0007822902],"about_ca_topic_score_codex":0.00048071417,"about_ca_topic_score_gemma":0.00020237788,"teacher_disagreement_score":0.4534288,"about_ca_system_score_codex":0.000030343102,"about_ca_system_score_gemma":0.00008898884,"threshold_uncertainty_score":0.941439},"labels":[],"label_agreement":null},{"id":"W4402561754","doi":"10.1016/j.annonc.2024.08.038","title":"29P Considering intra-patient response variability in clinical trials: Implications for treatment efficacy and survival","year":2024,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Medicine; Clinical trial; Complete response; Oncology; Internal medicine; Chemotherapy","score_opus":0.8990191969399026,"score_gpt":0.7285280157833078,"score_spread":0.17049118115659478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402561754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85807943,0.00038017883,0.103988394,0.029531697,0.0021948488,0.003819737,0.0007304553,0.00012344372,0.0011517876],"genre_scores_gemma":[0.5538869,0.0005445519,0.44456995,0.00028326456,0.00026778004,0.00039147874,0.000003021636,0.000031583117,0.000021485228],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97999424,0.015743889,0.0032879824,0.00056497654,0.000102223414,0.00030668927],"domain_scores_gemma":[0.3869614,0.6120467,0.00034798455,0.00036624618,0.00014360166,0.00013401988],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0655444,0.00016665479,0.0016964343,0.00011290197,0.00003535178,0.000019628811,0.00010801066,0.00032869843,0.000060528608],"category_scores_gemma":[0.58829886,0.0001298125,0.00028113046,0.00016817755,0.00035845753,0.000033686898,0.00007628938,0.0001726204,0.000003146591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047005587,0.001453616,0.0007134643,0.00013487926,0.00024539747,0.000010346208,0.000351839,0.000002143826,0.00037448975,0.16273113,0.0010441616,0.82823795],"study_design_scores_gemma":[0.0027371286,0.0059518185,0.009369371,0.00008747027,0.00017539633,0.0000066205657,0.000055367553,0.00027877517,0.0006025769,0.9604087,0.020191088,0.00013571176],"about_ca_topic_score_codex":0.000013665732,"about_ca_topic_score_gemma":0.000023493787,"teacher_disagreement_score":0.8281023,"about_ca_system_score_codex":0.00007462191,"about_ca_system_score_gemma":0.00042796016,"threshold_uncertainty_score":0.9622187},"labels":[],"label_agreement":null},{"id":"W4402967179","doi":"10.1093/biomet/asae049","title":"Testing the mean and variance by <i>e</i>-processes","year":2024,"lang":"en","type":"article","venue":"Biometrika","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Variance (accounting); Econometrics","score_opus":0.6026317662036541,"score_gpt":0.5441363605466614,"score_spread":0.05849540565699274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402967179","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033843383,0.043630626,0.8855703,0.0076125897,0.004379293,0.0016228125,0.0009368968,0.0017746825,0.020629441],"genre_scores_gemma":[0.09004383,0.0001989916,0.90783423,0.00036830897,0.0004972142,0.000034862747,9.3470464e-7,0.00004761921,0.00097398873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986278,0.00020972727,0.000382407,0.0003143747,0.000261391,0.00020434242],"domain_scores_gemma":[0.8561763,0.14333704,0.00006787038,0.00024967044,0.00008962689,0.00007947261],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030228149,0.0001247239,0.00023987945,0.000108405104,0.00009408654,0.00019928013,0.00021452311,0.0000908268,0.000078696765],"category_scores_gemma":[0.22480083,0.00007450365,0.000031658354,0.0027182708,0.00018971012,0.000054544842,0.00009787499,0.00019317713,0.000038440878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031102463,0.00016336165,0.00037637138,0.0026774092,0.00022697492,0.00004293393,0.00042476345,1.3252927e-7,0.012689045,0.18580393,0.13263679,0.6649272],"study_design_scores_gemma":[0.00018596415,0.000094333656,0.00013309505,0.00022161141,0.000096936965,0.000016906091,0.000044443885,0.00023102466,0.0027979428,0.9360532,0.059949204,0.00017531587],"about_ca_topic_score_codex":0.000007828123,"about_ca_topic_score_gemma":7.183547e-7,"teacher_disagreement_score":0.75024927,"about_ca_system_score_codex":0.000016197626,"about_ca_system_score_gemma":0.00005013064,"threshold_uncertainty_score":0.781729},"labels":[],"label_agreement":null},{"id":"W4403012555","doi":"10.1016/s1470-2045(24)00218-3","title":"The tyranny of non-inferiority trials","year":2024,"lang":"en","type":"review","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"","keywords":"Political science; Psychology","score_opus":0.9052723731323669,"score_gpt":0.7364709370930209,"score_spread":0.16880143603934594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403012555","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.8169122e-7,0.97357833,0.0028442317,0.0013971634,0.0054385182,0.0022496192,0.00039597464,0.00007375198,0.014021997],"genre_scores_gemma":[3.8136784e-7,0.91241175,0.08180082,0.000103971295,0.0044387556,0.0003752459,0.00000233569,0.00006640923,0.0008003554],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9779552,0.0168473,0.0038430234,0.0004417182,0.0003733167,0.000539394],"domain_scores_gemma":[0.60081035,0.3957396,0.0018634868,0.0014178358,0.00010109396,0.00006764244],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.064054616,0.00042963636,0.010303139,0.00005400709,0.00012926523,0.000049511626,0.0016894889,0.00082481734,0.00017563795],"category_scores_gemma":[0.27095753,0.00016361978,0.0014295712,0.0003754724,0.00080523075,0.000011957253,0.0005058956,0.0017022255,0.00031289316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000693018,0.00004270886,1.0982756e-7,0.010486083,0.00066037796,0.000011989503,0.000038632836,1.060566e-8,2.0578453e-7,0.15089156,0.04535218,0.79244685],"study_design_scores_gemma":[0.00025441765,0.00012404563,3.1440456e-7,0.001977669,0.0035448063,0.000012535808,0.000005879298,0.0000023479047,5.135898e-7,0.43797055,0.556011,0.000095899304],"about_ca_topic_score_codex":0.000007203046,"about_ca_topic_score_gemma":0.000013748642,"teacher_disagreement_score":0.79235095,"about_ca_system_score_codex":0.00015913397,"about_ca_system_score_gemma":0.00078688347,"threshold_uncertainty_score":0.96375275},"labels":[],"label_agreement":null},{"id":"W4403016814","doi":"10.1016/j.cjca.2024.09.027","title":"Optimal Statistical Methods for Analysing Survival Data on Quadriceps Thickness and Mortality in Heart Failure Patients","year":2024,"lang":"en","type":"letter","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medicine; Heart failure; Survival analysis; Internal medicine; Cardiology; Intensive care medicine","score_opus":0.4640163426518521,"score_gpt":0.5630110986730166,"score_spread":0.09899475602116448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403016814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010382677,0.00022531033,0.8939521,0.0901117,0.0059446497,0.0006896908,0.007766071,0.000011622935,0.00026063088],"genre_scores_gemma":[0.0008896654,0.000013962705,0.9739258,0.018467883,0.0063727247,0.000013500124,0.00019330913,0.00009933787,0.000023804978],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901167,0.006172683,0.0019115306,0.00073560275,0.00034789293,0.000715549],"domain_scores_gemma":[0.9348732,0.062920876,0.000530693,0.0008318988,0.00037948563,0.00046383502],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.013577592,0.0004138124,0.002978288,0.00060599187,0.000078157704,0.00011903252,0.00079589925,0.0012918529,0.00004172925],"category_scores_gemma":[0.11126243,0.0003481412,0.0003172399,0.00023509243,0.00049485127,0.00007304536,0.0001233692,0.00347062,0.0000036043518],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007789884,0.0000064351316,0.003588504,0.000594452,0.0011232034,0.00063074,0.000044235745,0.00006976448,0.0000011841175,0.0036582043,0.9838689,0.0063364785],"study_design_scores_gemma":[0.0010458056,0.00046106585,0.0058869924,0.00040772863,0.0019636806,0.00011236259,0.000048542926,0.00039737255,0.0000014752686,0.38923812,0.5999296,0.0005072942],"about_ca_topic_score_codex":0.000427749,"about_ca_topic_score_gemma":0.0009806551,"teacher_disagreement_score":0.3855799,"about_ca_system_score_codex":0.00026382515,"about_ca_system_score_gemma":0.0012677542,"threshold_uncertainty_score":0.99989706},"labels":[],"label_agreement":null},{"id":"W4403065939","doi":"10.1016/j.cardfail.2024.07.026","title":"POINT: Statistical Non-Significance, Likelihood Ratio, and The Interpretation of Clinical Trial Evidence: Insights from Heart Failure Randomized Trials","year":2024,"lang":"en","type":"article","venue":"Journal of Cardiac Failure","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Medicine; Randomized controlled trial; Heart failure; Statistical significance; Interpretation (philosophy); Clinical significance; Internal medicine; Intensive care medicine","score_opus":0.2373857978258273,"score_gpt":0.5225257657844833,"score_spread":0.285139967958656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403065939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031815946,0.0073338426,0.93161786,0.011185017,0.0117639555,0.0054861302,0.0004750034,0.000057665533,0.00026461002],"genre_scores_gemma":[0.5034244,0.0009993017,0.4905009,0.00017868746,0.004724283,0.00009009831,0.000003574008,0.00005248139,0.000026276455],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9599888,0.028513389,0.009190253,0.00052556384,0.0014788241,0.00030321965],"domain_scores_gemma":[0.6049031,0.39203838,0.0019353268,0.0003624328,0.00054260343,0.00021815069],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07414317,0.00039634737,0.007652221,0.00020774953,0.0000837744,0.00032594855,0.00041035505,0.0005064553,0.00027893577],"category_scores_gemma":[0.5458801,0.00020958405,0.0029115556,0.00034961483,0.0012660754,0.00042445975,0.0001192808,0.0015916545,0.000014057843],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7364487,0.00023580478,0.000030233468,0.00048089933,0.0048474637,0.000039745064,0.0015404591,0.000009575948,0.00059830927,0.12872887,0.100626774,0.026413184],"study_design_scores_gemma":[0.21122238,0.0007398242,0.000060279493,0.0018674383,0.004594555,0.000011698153,0.00043873597,0.0024002863,0.0003917987,0.77628744,0.0017585797,0.00022695998],"about_ca_topic_score_codex":0.000018581923,"about_ca_topic_score_gemma":0.000005313362,"teacher_disagreement_score":0.64755857,"about_ca_system_score_codex":0.000048319715,"about_ca_system_score_gemma":0.00071748864,"threshold_uncertainty_score":0.95336443},"labels":[],"label_agreement":null},{"id":"W4403072084","doi":"10.1093/clinchem/hvae106.645","title":"B-288 Turning False Positive Screening into True Positive Results","year":2024,"lang":"en","type":"article","venue":"Clinical Chemistry","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine","score_opus":0.45172817173925695,"score_gpt":0.5947773717425225,"score_spread":0.1430492000032656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403072084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40373132,0.0018444796,0.41279763,0.013254877,0.0061033485,0.0019327085,0.002498697,0.0029838136,0.15485314],"genre_scores_gemma":[0.3390417,0.000063116364,0.6547003,0.00052024313,0.0030954904,0.000037065576,0.00004601004,0.00009974249,0.0023963393],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937709,0.0009527314,0.002809509,0.0013149207,0.00057815755,0.0005738072],"domain_scores_gemma":[0.8317955,0.16627099,0.0003847395,0.00078462024,0.0002514131,0.0005127454],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008370864,0.00043724224,0.0011613147,0.000040381943,0.00015523695,0.00020322046,0.00054052327,0.00080659956,0.000277266],"category_scores_gemma":[0.2783758,0.00038398698,0.0007024919,0.00039258678,0.0006234542,0.000121839264,0.00029915344,0.0020398607,0.00014286257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005257853,0.0019435022,0.0012178511,0.003257923,0.003090121,0.0036513351,0.0017567101,0.0000123602995,0.015779562,0.07867774,0.061215114,0.82413995],"study_design_scores_gemma":[0.002026563,0.000259512,0.0008969079,0.0027642995,0.00052747974,0.000052790856,0.00020645357,0.0018787113,0.057132795,0.93130285,0.0020975552,0.00085407356],"about_ca_topic_score_codex":0.000008480041,"about_ca_topic_score_gemma":9.392398e-7,"teacher_disagreement_score":0.85262513,"about_ca_system_score_codex":0.00010374881,"about_ca_system_score_gemma":0.00015922391,"threshold_uncertainty_score":0.9998612},"labels":[],"label_agreement":null},{"id":"W4403112191","doi":"10.1186/s12874-024-02272-9","title":"Adaptive designs in clinical trials: a systematic review-part I","year":2024,"lang":"en","type":"review","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital Research Institute of Manitoba; Robarts Clinical Trials; Institute for Clinical Evaluative Sciences; University of Calgary; University of Manitoba; University of Toronto; George & Fay Yee Centre for Healthcare Innovation; Hospital for Sick Children; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Research Manitoba","keywords":"Clinical trial; MEDLINE; Medicine; Research design; Computer science; Adaptive design; Medical physics; Data science; Pathology; Statistics; Mathematics; Biology","score_opus":0.9961486734106785,"score_gpt":0.8582480544456738,"score_spread":0.13790061896500472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403112191","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2694775e-8,0.74205035,0.24067293,0.00025631065,0.0030853688,0.012873145,0.00013270204,0.00014395868,0.00078523054],"genre_scores_gemma":[3.7077983e-9,0.5624415,0.42959547,0.00021863198,0.0017874801,0.0048699277,0.000008602727,0.00017487591,0.0009035047],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.10308693,0.85403585,0.030223975,0.0032833642,0.006814051,0.002555802],"domain_scores_gemma":[0.009351381,0.98082,0.0034881865,0.0033056694,0.0008135106,0.0022212504],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.88251334,0.001327629,0.04695457,0.0016711823,0.00011967502,0.00010411217,0.0041761557,0.0054325117,0.004055193],"category_scores_gemma":[0.99757975,0.00077521295,0.0058910907,0.003745652,0.0028226816,0.000060436774,0.0022647139,0.016234795,0.003007709],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008013692,0.00024692653,1.0965693e-7,0.61556804,0.00068753655,0.00061992777,0.000014440787,4.339095e-9,4.7827085e-9,0.05357938,0.032547574,0.2966559],"study_design_scores_gemma":[0.0004294347,0.00039435143,3.308493e-8,0.5541704,0.0065943007,0.00012161363,0.000037849,0.000057809808,4.4685976e-8,0.36546746,0.07233884,0.00038784818],"about_ca_topic_score_codex":0.000034061206,"about_ca_topic_score_gemma":0.00014574487,"teacher_disagreement_score":0.31188807,"about_ca_system_score_codex":0.0006873711,"about_ca_system_score_gemma":0.012473065,"threshold_uncertainty_score":0.9999475},"labels":[],"label_agreement":null},{"id":"W4403214867","doi":"10.1177/17407745241276137","title":"A review of current practice in the design and analysis of extremely small stepped-wedge cluster randomized trials","year":2024,"lang":"en","type":"review","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Institute for Clinical Evaluative Sciences; Hospital for Sick Children; Public Health Ontario; SickKids Foundation; University of Toronto; Ottawa Hospital; Western University","funders":"National Institute on Aging; National Institutes of Health; Ottawa Hospital Research Institute; Canadian Institutes of Health Research; Patient-Centered Outcomes Research Institute","keywords":"Randomized controlled trial; Cluster (spacecraft); Wedge (geometry); Sample size determination; Cluster randomised controlled trial; Medicine; Statistics; Computer science; Mathematics; Surgery","score_opus":0.9585951229149452,"score_gpt":0.7585002061861219,"score_spread":0.2000949167288233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403214867","genre_codex":"review","genre_gemma":"review","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2975252e-7,0.8827507,0.089273185,0.00038644188,0.0018468461,0.024709895,0.0008193652,0.000030578372,0.00018285855],"genre_scores_gemma":[8.654854e-8,0.77196026,0.22540742,0.00041265707,0.0007038244,0.0013796632,0.00002304822,0.000078214616,0.00003480257],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.29447696,0.63429725,0.066849545,0.0021074289,0.0015758423,0.0006929339],"domain_scores_gemma":[0.010948995,0.9611708,0.024777027,0.0021955122,0.0006520188,0.00025563527],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.7777001,0.0010753454,0.072136484,0.00084805256,0.000035986708,0.00010496792,0.0014510808,0.0012670393,0.00030850532],"category_scores_gemma":[0.992398,0.00050699944,0.017248148,0.0033037842,0.0010718941,0.000071645205,0.00049294607,0.0024372966,0.000031220363],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00866956,0.0010183847,2.2949231e-7,0.17627615,0.011998757,0.000013606011,0.000046894555,1.2588997e-7,2.8597132e-8,0.007203208,0.010138152,0.7846349],"study_design_scores_gemma":[0.034113914,0.00023000038,1.4858169e-7,0.19287513,0.36870718,0.0000055927458,0.000011938222,0.00005850688,1.8700027e-7,0.12830116,0.2752975,0.00039874346],"about_ca_topic_score_codex":0.0000050504127,"about_ca_topic_score_gemma":0.0000017840837,"teacher_disagreement_score":0.7842362,"about_ca_system_score_codex":0.000055601675,"about_ca_system_score_gemma":0.0009214494,"threshold_uncertainty_score":0.9998641},"labels":[],"label_agreement":null},{"id":"W4403497067","doi":"10.1002/sim.10247","title":"A Nonparametric Global Win Probability Approach to the Analysis and Sizing of Randomized Controlled Trials With Multiple Endpoints of Different Scales and Missing Data: Beyond O'Brien–Wei–Lachin","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Statistics; Confidence interval; Nonparametric statistics; Coverage probability; Point estimation; Mathematics; Type I and type II errors; Clinical endpoint; Sample size determination; Computer science; Randomized controlled trial; Medicine","score_opus":0.303822623694461,"score_gpt":0.5183622358018237,"score_spread":0.21453961210736272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403497067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037317257,0.0015326585,0.95459104,0.0004917549,0.00016738,0.0036947303,0.0019440632,0.00001921424,0.00024192875],"genre_scores_gemma":[0.4194494,0.00010718393,0.5802401,0.000024058127,0.00006543046,0.00007330105,0.000022290555,0.000012142809,0.000006108593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877424,0.00656714,0.0038027926,0.0007101142,0.0009042283,0.00027331902],"domain_scores_gemma":[0.66195875,0.3361341,0.0008644245,0.0007075893,0.00017671134,0.00015842567],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050077047,0.00032534482,0.007588797,0.00037255994,0.00005278495,0.000050938794,0.00032891458,0.00010774006,0.000024095627],"category_scores_gemma":[0.61940104,0.0001483875,0.00016629839,0.0014510498,0.0014038187,0.00004212881,0.00023457546,0.0003104824,1.40053e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16475679,0.0016010951,0.0155304065,0.00784021,0.01577051,0.00004647645,0.0046838745,0.00015670074,0.0002982253,0.6199685,0.0006532375,0.16869402],"study_design_scores_gemma":[0.08216166,0.0002287428,0.0035642532,0.0006422456,0.009089221,0.0000045223187,0.00028717323,0.11311322,0.000035268662,0.790709,0.0000025694287,0.00016208291],"about_ca_topic_score_codex":0.00016441147,"about_ca_topic_score_gemma":0.00022734606,"teacher_disagreement_score":0.56932396,"about_ca_system_score_codex":0.000052599775,"about_ca_system_score_gemma":0.00007018615,"threshold_uncertainty_score":0.9781456},"labels":[],"label_agreement":null},{"id":"W4403512422","doi":"10.1093/neuonc/noae144.473","title":"P27.11.A GLOBAL EXPANSION OF GBM AGILE: A PHASE 2/3 ADAPTIVE PLATFORM TRIAL TO EVALUATE MULTIPLE REGIMENS IN NEWLY DIAGNOSED AND RECURRENT GLIOBLASTOMA","year":2024,"lang":"en","type":"article","venue":"Neuro-Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Glioblastoma; Agile software development; Medicine; Phase (matter); Oncology; Internal medicine; Computer science; Cancer research; Software engineering; Physics","score_opus":0.35388210331361186,"score_gpt":0.5455905287246768,"score_spread":0.19170842541106498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403512422","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979399,0.00010755528,0.011166737,0.001053543,0.0042037372,0.003054207,0.00044626766,0.00013445741,0.00043447965],"genre_scores_gemma":[0.69093657,0.00013409709,0.30690292,0.00059204816,0.00077290944,0.0005582986,0.000004221192,0.000078972625,0.000019960666],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995032,0.001590437,0.0015673987,0.00082319404,0.0004935442,0.0004934304],"domain_scores_gemma":[0.9231426,0.07570939,0.00029962842,0.00041264758,0.00013600884,0.00029974576],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032414317,0.0003245823,0.0012723767,0.00019698702,0.00004520445,0.000030088255,0.00026019,0.00037987615,0.00012156782],"category_scores_gemma":[0.103140146,0.00025736363,0.00016938009,0.00062645925,0.00023272193,0.00009133754,0.00032078632,0.000499944,0.000032849315],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16194424,0.0032166021,0.00012934729,0.00035977826,0.0001517726,0.0018449763,0.0021127944,0.000030097506,0.019267019,0.030597202,0.015908433,0.76443774],"study_design_scores_gemma":[0.24314214,0.08980405,0.00028858308,0.0010965025,0.0007560972,0.00014606616,0.00071965915,0.02257892,0.01260144,0.60418,0.023696546,0.000990018],"about_ca_topic_score_codex":0.000042316373,"about_ca_topic_score_gemma":0.00037575592,"teacher_disagreement_score":0.7634477,"about_ca_system_score_codex":0.0003522579,"about_ca_system_score_gemma":0.00041166737,"threshold_uncertainty_score":0.99998784},"labels":[],"label_agreement":null},{"id":"W4403562922","doi":"","title":"Critical concepts in adaptive clinical trials","year":2018,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Psychology","score_opus":0.9469908304507865,"score_gpt":0.8234241964745217,"score_spread":0.12356663397626477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403562922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4994445,0.01195138,0.32931894,0.003459625,0.028261678,0.010029102,0.00137626,0.00047100664,0.115687504],"genre_scores_gemma":[0.6919817,0.0025656703,0.3002564,0.0011366471,0.003456436,0.00012942906,0.0000019928543,0.00014498286,0.0003267397],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9715266,0.017635077,0.007650269,0.0010254055,0.0013450533,0.00081759895],"domain_scores_gemma":[0.7305358,0.26437932,0.0023024967,0.00097150274,0.001116741,0.00069410616],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07401159,0.0005108352,0.0044831587,0.000607721,0.00019434383,0.00087297853,0.0037046308,0.00056980026,0.039383225],"category_scores_gemma":[0.6465455,0.0004167007,0.00076736015,0.0012077785,0.001987838,0.001276208,0.0015950182,0.0014287016,0.00013429251],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008418975,0.0050270795,0.21226792,0.00040638822,0.0013143562,0.00044463464,0.0005081893,0.000003978495,0.0075983936,0.22492747,0.3114615,0.22762111],"study_design_scores_gemma":[0.0022163854,0.00012423354,0.07914076,0.00091244676,0.00026459506,0.0000082076085,0.00008987082,0.00015119463,0.004092527,0.9105661,0.0019426816,0.00049102935],"about_ca_topic_score_codex":0.00014569877,"about_ca_topic_score_gemma":0.000044748547,"teacher_disagreement_score":0.6856386,"about_ca_system_score_codex":0.00012577127,"about_ca_system_score_gemma":0.0003725628,"threshold_uncertainty_score":0.99982846},"labels":[],"label_agreement":null},{"id":"W4403613288","doi":"10.1002/cjs.11833","title":"True and false discoveries with independent and sequential <i>e</i>‐values","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Mathematics","score_opus":0.26272510045073366,"score_gpt":0.45386771199779447,"score_spread":0.1911426115470608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403613288","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0934828,0.002094152,0.89869875,0.0008465123,0.0014589969,0.00025622582,0.0026060087,0.000019250132,0.00053729134],"genre_scores_gemma":[0.26330978,0.00020259885,0.73584974,0.00009786811,0.0002904,0.0000018889908,0.0000013880626,0.000037137357,0.00020921654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985434,0.00019503389,0.0005942399,0.00016568787,0.0002616358,0.00024003818],"domain_scores_gemma":[0.9910328,0.007904015,0.0001649001,0.00011391465,0.00014748867,0.0006369209],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011733258,0.00015365212,0.00041975518,0.00014510649,0.00009336054,0.0003190125,0.000102220925,0.00007954562,0.00015382309],"category_scores_gemma":[0.010164288,0.00011168431,0.000030325251,0.000099611876,0.0005314961,0.0001302301,0.000019581283,0.00036074154,0.0000019627732],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010614692,0.000016981288,0.0020216275,0.0005909627,0.0003419013,0.0034679568,0.0013528342,0.000003949444,0.000052672844,0.93142754,0.00945319,0.051164247],"study_design_scores_gemma":[0.00047988415,0.00043370566,0.0013063847,0.00039821083,0.00031476718,0.0006148908,0.00031348513,0.00014759188,0.00007049723,0.9926655,0.003078621,0.00017645588],"about_ca_topic_score_codex":0.0003455977,"about_ca_topic_score_gemma":0.0041743177,"teacher_disagreement_score":0.16982698,"about_ca_system_score_codex":0.00006734633,"about_ca_system_score_gemma":0.0008194971,"threshold_uncertainty_score":0.99817353},"labels":[],"label_agreement":null},{"id":"W4403909425","doi":"10.1002/bimj.70002","title":"Estimating the Sampling Distribution of Posterior Decision Summaries in Bayesian Clinical Trials","year":2024,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Posterior probability; Sample size determination; Computer science; Bayesian probability; Posterior predictive distribution; Prior probability; Sampling (signal processing); Bayesian linear regression; Statistics; Bayes factor; Econometrics; Bayesian hierarchical modeling; Parametric statistics; Bayesian inference; Categorical distribution; Machine learning; Artificial intelligence; Mathematics","score_opus":0.7636220642333744,"score_gpt":0.668941481929084,"score_spread":0.09468058230429044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403909425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07842374,0.0007733517,0.9155578,0.0008866011,0.0037990252,0.00033014966,0.00015513932,0.000038730876,0.000035482182],"genre_scores_gemma":[0.29696178,0.00008275176,0.7016169,0.000038363298,0.0012611453,0.000006052957,0.0000026370515,0.000022622187,0.00000773126],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98774606,0.0051322817,0.0054619703,0.00035846248,0.0009120562,0.00038916027],"domain_scores_gemma":[0.46907613,0.5288475,0.0010926055,0.00041428057,0.00026679845,0.000302708],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0784964,0.00020082925,0.0013687521,0.00061691896,0.00013390729,0.0003583638,0.00048348226,0.0003126536,0.00019174919],"category_scores_gemma":[0.7370912,0.000111479,0.0006642031,0.0032659613,0.00031514606,0.00012413997,0.00018799154,0.0011404293,0.000013054824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034213587,0.00021681369,0.0024301542,0.00010999101,0.000116421026,0.00006127492,0.00004477634,0.000012019406,0.00013791895,0.01365309,0.0017837301,0.9810917],"study_design_scores_gemma":[0.0010124067,0.0003727913,0.010801484,0.0010842419,0.00021255725,0.00013050341,0.000047051064,0.01513693,0.0001303799,0.96994865,0.0009477225,0.00017525708],"about_ca_topic_score_codex":0.000005825461,"about_ca_topic_score_gemma":0.0000011817964,"teacher_disagreement_score":0.98091644,"about_ca_system_score_codex":0.00013949534,"about_ca_system_score_gemma":0.00018447547,"threshold_uncertainty_score":0.94888186},"labels":[],"label_agreement":null},{"id":"W4403996423","doi":"10.1007/s11538-024-01375-0","title":"Steady-State Drug Exposure of Repeated IV Bolus Administration for a One Compartment Pharmacokinetic Model with Sigmoidal Hill Elimination","year":2024,"lang":"en","type":"article","venue":"Bulletin of Mathematical Biology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Compartment (ship); Pharmacokinetics; Intravenous bolus; Sigmoid function; Bolus (digestion); Drug administration; Steady state (chemistry); Drug; Pharmacology; Medicine; Chemistry; Anesthesia; Computer science; Internal medicine","score_opus":0.273178409763145,"score_gpt":0.478727836155624,"score_spread":0.20554942639247897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403996423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05119378,0.00013291622,0.9399355,0.0042863977,0.00014826196,0.0020332981,0.00041292954,0.00014274677,0.0017141406],"genre_scores_gemma":[0.48566422,0.000015993004,0.5135769,0.000054080047,0.000048954134,0.00017662146,0.000019131874,0.000033795903,0.0004102654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965293,0.00062093296,0.001750258,0.0004745478,0.00030919895,0.00031580904],"domain_scores_gemma":[0.97110283,0.027643358,0.00046958087,0.00035814245,0.00031058173,0.00011550734],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033480567,0.00026652,0.0010518666,0.00010080359,0.000034523822,0.000017711505,0.00022917085,0.00017305164,0.0005708123],"category_scores_gemma":[0.011851777,0.00019770948,0.00018858437,0.00012915288,0.00038168483,0.00001561005,0.00006728198,0.00021320663,0.00002493961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026163918,0.0023841334,0.000009041275,0.0074748253,0.00063208805,0.000012289041,0.0006532658,0.00031724473,0.0118272025,0.95196956,0.008016535,0.014087425],"study_design_scores_gemma":[0.0017815271,0.0017190054,0.000011137793,0.00063136354,0.00047662383,0.000011917083,0.000058861475,0.07410015,0.024445038,0.895918,0.0005973387,0.00024901427],"about_ca_topic_score_codex":0.0000020034872,"about_ca_topic_score_gemma":0.0000010540683,"teacher_disagreement_score":0.43447042,"about_ca_system_score_codex":0.000039222887,"about_ca_system_score_gemma":0.00009277331,"threshold_uncertainty_score":0.9964718},"labels":[],"label_agreement":null},{"id":"W4404016422","doi":"10.1101/2024.10.31.621375","title":"A Scalable Framework for Identifying Allelic Series from Summary Statistics","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistics; Series (stratigraphy); Coding (social sciences); Test (biology); Computer science; Mathematics; Biology","score_opus":0.2560169915255375,"score_gpt":0.44360774146244636,"score_spread":0.18759074993690888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404016422","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01330643,0.0018714711,0.9509813,0.0005149606,0.0098026255,0.0024519688,0.019848054,0.0012040357,0.000019135583],"genre_scores_gemma":[0.014328972,0.00043753666,0.9804985,0.00026406607,0.0028383795,0.0010608232,0.0000017334099,0.0005162491,0.00005372159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934053,0.00069929153,0.0021009615,0.001966879,0.0008378592,0.0009897235],"domain_scores_gemma":[0.962075,0.033299174,0.00093841436,0.002388428,0.0008083638,0.0004906031],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0035639596,0.0009984332,0.0020134416,0.0002560281,0.00024319142,0.0008888736,0.0011345722,0.0016737743,0.00034485504],"category_scores_gemma":[0.08400117,0.0010370865,0.00046432004,0.00048387205,0.00034029453,0.00011859583,0.0019090453,0.0024239952,0.00022442918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030687897,0.00044229158,0.00022335167,0.009141598,0.0017735446,0.00023312724,0.00004192349,0.000009819586,0.02659998,0.92950815,0.031685088,0.000034216082],"study_design_scores_gemma":[0.00056619354,0.00009841696,0.00069212617,0.0045229243,0.0013453226,1.2476752e-8,0.0000080147165,0.00067776354,0.028710186,0.9583148,0.0037097766,0.0013544841],"about_ca_topic_score_codex":0.000054091157,"about_ca_topic_score_gemma":0.0000052934897,"teacher_disagreement_score":0.080437206,"about_ca_system_score_codex":0.0003540058,"about_ca_system_score_gemma":0.00077845453,"threshold_uncertainty_score":0.99987745},"labels":[],"label_agreement":null},{"id":"W4404021399","doi":"10.1093/ibd/izae256","title":"The Clinical Interpretation of Cluster Trials","year":2024,"lang":"en","type":"review","venue":"Inflammatory Bowel Diseases","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Population Health Research Institute; Lawson Health Research Institute; Western University","funders":"","keywords":"Interpretation (philosophy); Cluster (spacecraft); Cluster randomised controlled trial; Psychological intervention; Clinical trial; Computer science; Medical physics; Medicine; Data mining; Pathology; Nursing","score_opus":0.573335264549322,"score_gpt":0.6219844553621589,"score_spread":0.04864919081283681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404021399","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002770121,0.9872547,0.0029129197,0.000047826747,0.0053970423,0.0026178379,0.0010534211,0.00018075947,0.00053272134],"genre_scores_gemma":[0.0000032665778,0.9846552,0.012285186,0.000040857798,0.0018034192,0.0005278367,0.000014450996,0.00015180712,0.00051800144],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97375757,0.015048456,0.009326981,0.00073316984,0.000743344,0.00039046197],"domain_scores_gemma":[0.6578501,0.3373988,0.0030352406,0.0012579712,0.0001931567,0.00026474515],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.020979827,0.00065275526,0.0055846125,0.00015662218,0.00010501997,0.00017989356,0.0010094355,0.000684053,0.00016249115],"category_scores_gemma":[0.4500916,0.0003371547,0.004413982,0.00022915691,0.0008093037,0.000072410665,0.0004450117,0.00090793293,0.00038067618],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016578138,0.00010192027,0.0000071978875,0.036320228,0.0012956271,0.000033378845,0.000016805769,1.2969271e-7,6.4516814e-9,0.034370586,0.033183616,0.8945047],"study_design_scores_gemma":[0.0002655872,0.000055973138,0.0000100293255,0.01818095,0.011574208,0.0000030825659,0.000010685145,0.000042599702,7.967636e-8,0.44388184,0.5256967,0.00027826737],"about_ca_topic_score_codex":5.450051e-7,"about_ca_topic_score_gemma":0.0000020432792,"teacher_disagreement_score":0.89422643,"about_ca_system_score_codex":0.00008375557,"about_ca_system_score_gemma":0.00082632195,"threshold_uncertainty_score":0.99990803},"labels":[],"label_agreement":null},{"id":"W4404046189","doi":"10.1136/thorax-2024-btsabstracts.316","title":"P155 Interobserver variability in cause of death in a lung cancer screening trial: a pilot method study","year":2024,"lang":"en","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Lung cancer; Medicine; Cancer; Cause of death; Lung cancer screening; Oncology; Internal medicine; Disease","score_opus":0.7303328527510417,"score_gpt":0.6535127709397492,"score_spread":0.0768200818112924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404046189","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31035906,0.0000557576,0.6850921,0.00015035304,0.00073480676,0.0027276818,0.00003882902,0.00010393355,0.00073751906],"genre_scores_gemma":[0.38728088,0.00000628219,0.6121353,0.000034484743,0.00007442953,0.0003013749,2.1393697e-7,0.00003119782,0.000135847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98959905,0.0066753165,0.002239137,0.0007178428,0.0004176792,0.00035099225],"domain_scores_gemma":[0.88027775,0.1188145,0.00015793869,0.0005823293,0.00008018132,0.000087287306],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031563614,0.00023766703,0.0012059571,0.00023082437,0.000014099601,0.000045152297,0.00031495764,0.00013012711,0.0010086576],"category_scores_gemma":[0.11538643,0.00018372537,0.00013844925,0.0008020707,0.000050784027,0.000102730744,0.00026923584,0.0005828545,0.0000023692426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04521532,0.017041268,0.2919804,0.0052935863,0.0021593694,0.00056047365,0.007874286,0.00023453985,0.0004523061,0.5610374,0.0012541019,0.06689692],"study_design_scores_gemma":[0.029954536,0.0014588414,0.020761106,0.0012640363,0.00048614576,0.0000015355274,0.0003711008,0.039186645,0.00036434236,0.9057363,0.000016622835,0.00039874943],"about_ca_topic_score_codex":0.0026270715,"about_ca_topic_score_gemma":0.0021675436,"teacher_disagreement_score":0.3446989,"about_ca_system_score_codex":0.00019965043,"about_ca_system_score_gemma":0.0001368975,"threshold_uncertainty_score":0.9999046},"labels":[],"label_agreement":null},{"id":"W4404129156","doi":"10.1002/sim.10253","title":"Generalized Fused Lasso for Treatment Pooling in Network Meta‐Analysis","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pooling; Lasso (programming language); Meta-analysis; Computer science; Statistics; Mathematics; Econometrics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.6714134504704429,"score_gpt":0.6145489179625329,"score_spread":0.056864532507910015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404129156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003833306,0.002845303,0.9920829,0.0012622972,0.0010161307,0.0010210043,0.00082373753,0.00008636537,0.00047893715],"genre_scores_gemma":[0.007919317,0.00053133356,0.9892571,0.0002569475,0.0008036568,0.00042292388,0.00006219357,0.000058236594,0.0006882759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959935,0.00085242867,0.0016405231,0.0005796551,0.0004044512,0.00052945124],"domain_scores_gemma":[0.8960379,0.10320985,0.00015386597,0.0003918819,0.00008081599,0.00012567811],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061355755,0.00031583128,0.0025887473,0.0004176548,0.000042657128,0.000031236003,0.00018594995,0.00015760589,0.001059857],"category_scores_gemma":[0.037998125,0.00021738224,0.0003360144,0.0013493893,0.00016731578,0.000025549005,0.00003577503,0.00020974969,0.000008328338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001746748,0.00015661799,0.00019152155,0.00037176922,0.02757287,0.00024068916,0.0005141171,0.0011687581,0.000018894718,0.9537044,0.008980288,0.006905355],"study_design_scores_gemma":[0.001971633,0.00030704992,0.000097348806,0.00008544513,0.05983062,0.0000011207287,0.000041573254,0.05131338,0.000014840576,0.8844751,0.0016739183,0.00018797905],"about_ca_topic_score_codex":0.00021441946,"about_ca_topic_score_gemma":0.0010716832,"teacher_disagreement_score":0.102357425,"about_ca_system_score_codex":0.00021308048,"about_ca_system_score_gemma":0.000083844694,"threshold_uncertainty_score":0.9998533},"labels":[],"label_agreement":null},{"id":"W4404136056","doi":"10.1016/j.cjca.2024.11.002","title":"Bayesian Analytical Methods in Cardiovascular Clinical Trials: Why, When, and How","year":2024,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Bayesian probability; Clinical trial; Intensive care medicine; Medical physics; Internal medicine; Statistics","score_opus":0.8144866509768289,"score_gpt":0.6700181455763807,"score_spread":0.1444685054004482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404136056","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2401182e-7,0.7029973,0.29062194,0.0005288042,0.0042970544,0.00058524846,0.00014109709,0.000009314466,0.0008191165],"genre_scores_gemma":[0.0000020356604,0.6668259,0.32812688,0.000058660436,0.0047994168,0.000019336274,0.0000017931225,0.00009747875,0.00006851029],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.92637247,0.065653145,0.0059774304,0.0008204346,0.00037699845,0.0007995239],"domain_scores_gemma":[0.8462032,0.14921446,0.001552906,0.00095361145,0.00029155004,0.0017842434],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.15199494,0.0007505124,0.022246476,0.0014181271,0.000055852168,0.00018799766,0.00086437707,0.002339577,0.000060757087],"category_scores_gemma":[0.50916463,0.0005180888,0.008362574,0.0005596592,0.0009792083,0.000068834706,0.00012517448,0.0042747017,0.000010660074],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001446065,0.0000032707803,0.00002041586,0.004068013,0.006835337,0.001991769,0.00001639671,0.0000018411337,5.9357235e-9,0.009821724,0.050752442,0.92647433],"study_design_scores_gemma":[0.00049021933,0.00017742525,0.0000032139528,0.0045597195,0.017857376,0.0012665582,0.000021185086,0.000026668671,1.6935417e-8,0.22483608,0.7504214,0.0003401081],"about_ca_topic_score_codex":0.00008316576,"about_ca_topic_score_gemma":0.00023548171,"teacher_disagreement_score":0.9261342,"about_ca_system_score_codex":0.00041013042,"about_ca_system_score_gemma":0.004268485,"threshold_uncertainty_score":0.9997271},"labels":[],"label_agreement":null},{"id":"W4404198666","doi":"10.1177/17407745241290729","title":"Pragmatic monitoring of emerging efficacy data in randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; Impact; McMaster University; Population Health Research Institute","funders":"","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.8746604636711833,"score_gpt":0.7229113298889603,"score_spread":0.151749133782223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404198666","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0952856,0.02686813,0.706262,0.00877337,0.08338855,0.06705075,0.0019363465,0.001751832,0.008683443],"genre_scores_gemma":[0.14079489,0.003821306,0.8459755,0.000080238424,0.0079900455,0.0007234671,0.000019595484,0.00016794006,0.00042698954],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5752973,0.337715,0.08024097,0.0029213512,0.002530194,0.0012951829],"domain_scores_gemma":[0.011173506,0.9802506,0.0056558643,0.0023889767,0.00021716593,0.00031387815],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.74294084,0.0005487765,0.035724804,0.00046492254,0.0000493001,0.00019960478,0.0014222106,0.00069082633,0.0009382004],"category_scores_gemma":[0.99334073,0.00032639498,0.0050714826,0.000761732,0.0006025265,0.00021403225,0.0005704436,0.0012660644,0.000080172445],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.39519,0.0029702906,0.0005768191,0.0030314184,0.013076942,0.00020431295,0.00047012183,0.00002978816,0.00047979382,0.23660317,0.0065942537,0.34077308],"study_design_scores_gemma":[0.35495073,0.000109815475,0.000048037375,0.0029511629,0.004241491,0.0000015530791,0.0000658121,0.0049769897,0.00013228501,0.6319307,0.00031325765,0.00027812773],"about_ca_topic_score_codex":0.000011946208,"about_ca_topic_score_gemma":0.0000012475142,"teacher_disagreement_score":0.6425356,"about_ca_system_score_codex":0.000049032675,"about_ca_system_score_gemma":0.00042658555,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W4404200990","doi":"10.1007/978-3-031-71452-8_17","title":"Case Studies: Clinical Examples","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Computer science","score_opus":0.9235178541312693,"score_gpt":0.6885610619328729,"score_spread":0.23495679219839638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404200990","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007691674,0.0011024899,0.010231946,0.000277163,0.0056300466,0.00075076823,0.0003366065,0.0005351012,0.9811282],"genre_scores_gemma":[0.0000077770155,0.0008024871,0.45016202,0.0002598624,0.0018153781,0.000016268019,0.0000011492243,0.00013329768,0.54680175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99464995,0.00028296496,0.003188196,0.0010587099,0.00049107446,0.00032910952],"domain_scores_gemma":[0.77760524,0.22062282,0.00038405915,0.0009461011,0.00021910331,0.0002227001],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0073988046,0.00059647014,0.0025035779,0.000111884365,0.00006746914,0.000060400478,0.0003078988,0.0010922003,0.007294255],"category_scores_gemma":[0.13318686,0.0004214847,0.00090379885,0.000034421086,0.000725526,0.000023003277,0.00058232713,0.0015265803,0.0031579505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001834741,0.00003064366,4.1775724e-7,0.00058887876,0.0011486276,0.012988569,0.000028268869,1.1130707e-8,5.9583858e-8,0.8523631,0.11481751,0.018015562],"study_design_scores_gemma":[0.00024441574,0.0001734226,4.5817526e-8,0.0004947717,0.0011421697,0.0009604371,0.000044372904,0.000007515023,0.0000013180041,0.81747615,0.17905544,0.00039994007],"about_ca_topic_score_codex":0.0000025860888,"about_ca_topic_score_gemma":0.000020246773,"teacher_disagreement_score":0.43993005,"about_ca_system_score_codex":0.00008153127,"about_ca_system_score_gemma":0.00009162357,"threshold_uncertainty_score":0.9998237},"labels":[],"label_agreement":null},{"id":"W4404246294","doi":"10.1017/asb.2024.30","title":"Weekly dynamic motor insurance ratemaking with a telematics signals bonus-malus score","year":2024,"lang":"en","type":"article","venue":"Astin Bulletin","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agencia Estatal de Investigación; Fonds de recherche du Québec – Nature et technologies; Institució Catalana de Recerca i Estudis Avançats","keywords":"Telematics; Automobile insurance; Actuarial science; Business; Economics; Econometrics; Computer science; Telecommunications","score_opus":0.261766194600081,"score_gpt":0.47470408770613476,"score_spread":0.21293789310605377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404246294","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13616353,0.0011238091,0.84211826,0.0070314608,0.0016569616,0.0025625008,0.00046113844,0.001398323,0.0074839853],"genre_scores_gemma":[0.38129237,0.000021190275,0.6155741,0.00021203344,0.00025892505,0.00013590747,0.0000022351833,0.00012229936,0.0023808845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99595094,0.0007461997,0.0012877708,0.00071931456,0.00070221734,0.00059354707],"domain_scores_gemma":[0.9523082,0.04645081,0.00029462145,0.0006073101,0.00014878217,0.00019027792],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003352638,0.00042767226,0.00094298506,0.00013311714,0.00012771915,0.00024259186,0.00042136907,0.00021668071,0.0021168685],"category_scores_gemma":[0.036551457,0.00031939286,0.00018314034,0.0004543762,0.00026886663,0.000045406494,0.00014741915,0.0006757531,0.000787599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033032836,0.0022078012,0.0062728855,0.03274677,0.0030396185,0.0071830135,0.0028366263,0.0005216534,0.014193327,0.530813,0.16247395,0.23440811],"study_design_scores_gemma":[0.0028233128,0.0018002033,0.0029115498,0.016005749,0.000698689,0.0003166896,0.00037405008,0.01041334,0.002352424,0.93704045,0.023239356,0.00202421],"about_ca_topic_score_codex":0.000007832967,"about_ca_topic_score_gemma":0.000004709919,"teacher_disagreement_score":0.40622747,"about_ca_system_score_codex":0.00008843246,"about_ca_system_score_gemma":0.00011958051,"threshold_uncertainty_score":0.9999904},"labels":[],"label_agreement":null},{"id":"W4404298071","doi":"10.1093/jnci/djae281","title":"Supporting evidence in phase 2 cancer trial protocols: a content analysis","year":2024,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Protocol (science); Clinical trial; Medicine; Attrition; Sample size determination; Evidence-based practice; Typology; Evidence-based medicine; Medical physics; Alternative medicine; Internal medicine; Statistics; Pathology","score_opus":0.9056552129969474,"score_gpt":0.726209888188033,"score_spread":0.1794453248089144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404298071","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53249407,0.007305653,0.28399986,0.06306935,0.057149466,0.05178201,0.002143011,0.00022038512,0.0018361786],"genre_scores_gemma":[0.78345394,0.0004513273,0.19091387,0.0020638853,0.012717137,0.0088485805,0.0000012923857,0.00007237181,0.0014776142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952866,0.00052203215,0.0021966058,0.00023350379,0.001528263,0.0002330354],"domain_scores_gemma":[0.98710406,0.010661899,0.0011518864,0.00015173858,0.00082761975,0.0001028064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0083975345,0.00016022811,0.0007171923,0.00034971736,0.00007414655,0.000119637756,0.0005545489,0.000101391204,0.00048386864],"category_scores_gemma":[0.093969174,0.000097392,0.00060939544,0.0014354222,0.00015300428,0.00043371937,0.000082137536,0.000661974,0.0000025949764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11881247,0.005177601,0.011747444,0.0038422693,0.01986642,0.0008715722,0.0034936734,0.02355264,0.010348027,0.4631829,0.09347466,0.24563032],"study_design_scores_gemma":[0.03261268,0.00053692935,0.0011565889,0.006769934,0.0026050846,0.000036543937,0.00003928457,0.0081976745,0.0026445212,0.92711544,0.017885296,0.00040000863],"about_ca_topic_score_codex":0.00009684791,"about_ca_topic_score_gemma":0.00029711446,"teacher_disagreement_score":0.46393254,"about_ca_system_score_codex":0.00089929084,"about_ca_system_score_gemma":0.0018382726,"threshold_uncertainty_score":0.91366273},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4404435360","doi":"10.1093/jrsssc/qlae058","title":"Bayesian optimization for personalized dose-finding trials with combination therapies","year":2024,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series C (Applied Statistics)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada","keywords":"Bayesian probability; Personalized medicine; Computer science; Bayesian optimization; Medicine; Medical physics; Artificial intelligence; Bioinformatics; Biology","score_opus":0.24858919498272727,"score_gpt":0.47452656675349447,"score_spread":0.2259373717707672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404435360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012443478,0.00014387256,0.9930589,0.0014560049,0.0012880897,0.0012518164,0.0022649108,0.000077381104,0.00033459577],"genre_scores_gemma":[0.019169776,0.000078527984,0.9788772,0.00020828715,0.0006505253,0.0000919221,0.00002125365,0.000115860705,0.00078665983],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99455285,0.0010373683,0.0023258168,0.00041642596,0.0011604935,0.00050701684],"domain_scores_gemma":[0.9245002,0.07322281,0.0012172554,0.00029170574,0.0005436845,0.00022433297],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008371309,0.0004409831,0.0015796659,0.000062318744,0.0004730535,0.00046661272,0.00048721497,0.00026174457,0.00110748],"category_scores_gemma":[0.02925061,0.00025829906,0.00054691324,0.0003123298,0.00080382585,0.00014143508,0.00008466069,0.0007411455,0.0000041707494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016778308,0.00019381622,0.00001212827,0.0007449502,0.0011349852,0.000013503133,0.001008322,0.0015685613,0.000081311846,0.9425778,0.038017876,0.012968914],"study_design_scores_gemma":[0.0029903406,0.0008191852,0.00008928533,0.00029621756,0.0014468377,0.000024436362,0.00082938507,0.06175098,0.0001496876,0.9276798,0.003548247,0.00037562958],"about_ca_topic_score_codex":0.0000037330476,"about_ca_topic_score_gemma":0.0000026470725,"teacher_disagreement_score":0.072185434,"about_ca_system_score_codex":0.0002832175,"about_ca_system_score_gemma":0.00035822784,"threshold_uncertainty_score":0.99998695},"labels":[],"label_agreement":null},{"id":"W4404685489","doi":"10.1002/pds.70048","title":"Core Concepts in Pharmacoepidemiology: New‐User Designs","year":2024,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; GlaxoSmithKline (Canada)","funders":"National Institute on Aging; National Institutes of Health; Wellcome Trust","keywords":"Pharmacoepidemiology; Medicine; Core (optical fiber); Pharmacology; Engineering","score_opus":0.8501668821614412,"score_gpt":0.6983936277080788,"score_spread":0.15177325445336243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404685489","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024762778,0.9695563,0.020195056,0.0016514437,0.0040998566,0.0023360513,0.0005070709,0.00033463858,0.0013171495],"genre_scores_gemma":[0.000002649013,0.8336859,0.15963958,0.0021245473,0.0017496682,0.00028184685,0.00004905192,0.00017874742,0.0022880111],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9652309,0.024501422,0.006294842,0.002226443,0.00025122295,0.0014951623],"domain_scores_gemma":[0.6518979,0.34534404,0.0013033715,0.0006783746,0.00006038764,0.00071594905],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.0398593,0.0014870961,0.010372121,0.0004659531,0.00015233882,0.000022443855,0.0009612307,0.0016069901,0.001581322],"category_scores_gemma":[0.1701731,0.0010725941,0.0012261869,0.0007327294,0.0010005175,0.000108435954,0.0007286905,0.0046384926,0.00056062074],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015599182,0.000093045426,0.0000882903,0.012195683,0.0006802675,0.00017597842,0.00008894216,0.0000013787728,6.748399e-7,0.092164665,0.28648865,0.6078664],"study_design_scores_gemma":[0.00089796056,0.000032692533,0.0000040210484,0.0045874454,0.0032467223,0.000079998965,0.000009011738,0.00010203149,7.2574755e-7,0.3916851,0.598731,0.0006233105],"about_ca_topic_score_codex":0.00007751862,"about_ca_topic_score_gemma":0.00002137595,"teacher_disagreement_score":0.6072431,"about_ca_system_score_codex":0.00027092212,"about_ca_system_score_gemma":0.00064437365,"threshold_uncertainty_score":0.9997878},"labels":[],"label_agreement":null},{"id":"W4404691850","doi":"10.4171/owr/2024/24","title":"Game-theoretic Statistical Inference: Optional Sampling, Universal Inference, and Multiple Testing Based on E-values","year":2024,"lang":"en","type":"article","venue":"Oberwolfach Reports","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inference; Statistical inference; Computer science; Martingale (probability theory); Notation; Statistical hypothesis testing; Artificial intelligence; Machine learning; Interpretation (philosophy); Meaning (existential); Game theory; Theoretical computer science; Data science; Mathematical economics; Mathematics; Epistemology; Statistics; Programming language","score_opus":0.4245189506016742,"score_gpt":0.526775350920045,"score_spread":0.1022564003183708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404691850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07506264,0.000056687888,0.91056985,0.00016792802,0.0011316532,0.00062018284,0.00024629108,0.0005580748,0.011586679],"genre_scores_gemma":[0.5228798,0.0000055708765,0.47667524,0.00005496714,0.00015017149,0.00001579517,0.00001596847,0.000036743957,0.00016576506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99623895,0.0005210633,0.0011847293,0.00086208293,0.00075351377,0.0004396671],"domain_scores_gemma":[0.86812735,0.13064785,0.00024738323,0.0004920083,0.00019588087,0.00028953925],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033335637,0.00034416933,0.00060641,0.00018048621,0.00013332964,0.00023981166,0.00013044104,0.00024359327,0.000762187],"category_scores_gemma":[0.22669527,0.00029140076,0.00009719719,0.00032770378,0.0005472601,0.000096578326,0.00012714269,0.00063413515,0.000033182994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012638404,0.00039571457,0.0343693,0.0009926712,0.0001144845,0.0020973613,0.00017851,0.00067798706,0.0002266333,0.9108768,0.0010148827,0.048929267],"study_design_scores_gemma":[0.00032400183,0.00024688616,0.0058545545,0.00067209196,0.00013525656,0.00007107822,0.000024661182,0.099592716,0.00009713323,0.8920559,0.0005941678,0.00033151434],"about_ca_topic_score_codex":0.000025870933,"about_ca_topic_score_gemma":0.000002487866,"teacher_disagreement_score":0.44781715,"about_ca_system_score_codex":0.00010442631,"about_ca_system_score_gemma":0.00034262432,"threshold_uncertainty_score":0.9999538},"labels":[],"label_agreement":null},{"id":"W4404727371","doi":"10.1177/17407745241297947","title":"Detecting irregularities in randomized controlled trials using machine learning","year":2024,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; Hamilton Health Sciences; McMaster University; Population Health Research Institute; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Interquartile range; Artificial intelligence; Machine learning; Concordance; Outlier; Clinical trial; Computer science; Randomized controlled trial; Receiver operating characteristic; Medicine; Anomaly detection; Algorithm; Statistics; Data mining; Mathematics; Surgery; Pathology","score_opus":0.8686945249905104,"score_gpt":0.6957301326060387,"score_spread":0.1729643923844717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404727371","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10775707,0.022069175,0.80450946,0.0028033126,0.02900927,0.027012963,0.00025983562,0.0021176003,0.0044613397],"genre_scores_gemma":[0.16606973,0.0017776516,0.8216071,0.0003322949,0.0076926267,0.0007849278,0.0000069757466,0.00024877777,0.0014799146],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.61205536,0.34204257,0.041590694,0.0018000992,0.0013556876,0.0011555861],"domain_scores_gemma":[0.028325949,0.96647674,0.0040078764,0.0006431999,0.00020900296,0.0003372425],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.71683794,0.00064737996,0.032498185,0.00054303784,0.00016094183,0.00051874947,0.00045380136,0.00097383786,0.0016736038],"category_scores_gemma":[0.9900886,0.0003986767,0.008414073,0.0006554119,0.00068885944,0.00016184176,0.00023266225,0.0024089846,0.00006542906],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.48429504,0.00095719635,0.0005704246,0.0014371318,0.009303787,0.0005035646,0.00043349652,0.00017077102,0.0013790139,0.30826572,0.00072668574,0.19195716],"study_design_scores_gemma":[0.2671473,0.00012846608,0.0000043331615,0.0010284178,0.0027193585,0.000007768889,0.000065401015,0.05848923,0.00021686644,0.6694762,0.00037420163,0.00034244472],"about_ca_topic_score_codex":0.00006119238,"about_ca_topic_score_gemma":0.000014665249,"teacher_disagreement_score":0.6244342,"about_ca_system_score_codex":0.00011748977,"about_ca_system_score_gemma":0.00034428752,"threshold_uncertainty_score":0.9998925},"labels":[],"label_agreement":null},{"id":"W4404936882","doi":"10.1101/2024.11.29.24318211","title":"Methods for analytical validation of novel digital clinical measures: A simulation study","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Arnold Ventures","keywords":"Computer science; Model validation; Reliability engineering; Data science; Engineering","score_opus":0.8446405011541336,"score_gpt":0.7065212277254581,"score_spread":0.13811927342867547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404936882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12680766,0.00003568179,0.866296,0.00012422352,0.0026546915,0.0030717312,0.0004687492,0.00015713582,0.00038412015],"genre_scores_gemma":[0.36453003,0.000003147704,0.63443774,0.000012990855,0.00064281514,0.00017067294,0.000011225186,0.000083512816,0.00010787707],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99072766,0.00248565,0.004356018,0.0012693338,0.00081572507,0.00034558467],"domain_scores_gemma":[0.79969805,0.19724028,0.00097257586,0.0011706268,0.0007282947,0.00019013825],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030520124,0.00045946808,0.0022410285,0.00022896912,0.000042648433,0.0001793437,0.00062288047,0.0007950232,0.000048481357],"category_scores_gemma":[0.50071216,0.00037947836,0.0010622845,0.0003168975,0.00024390967,0.00004925978,0.0011375195,0.0012389713,0.000012937012],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034125163,0.031209696,0.051628474,0.011550222,0.01108756,0.00003219477,0.0021844578,0.009659863,0.00023092977,0.20070739,0.0012874886,0.6770092],"study_design_scores_gemma":[0.0013719432,0.00051380653,0.00067309296,0.0003127982,0.0018566038,5.5558394e-7,0.000064390784,0.163598,0.00018617233,0.83085924,0.00023381981,0.00032958973],"about_ca_topic_score_codex":0.000002743934,"about_ca_topic_score_gemma":8.305987e-7,"teacher_disagreement_score":0.6766796,"about_ca_system_score_codex":0.00007613375,"about_ca_system_score_gemma":0.00025597826,"threshold_uncertainty_score":0.9998657},"labels":[],"label_agreement":null},{"id":"W4405223579","doi":"10.1093/jnci/djae318","title":"Justification, margin values, and analysis populations for oncologic noninferiority and equivalence trials: a meta-epidemiological study","year":2024,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"National Cancer Institute; University of Texas MD Anderson Cancer Center; National Institutes of Health; Andrew Sabin Family Foundation","keywords":"Margin (machine learning); Equivalence (formal languages); Clinical endpoint; Meta-analysis; Population; Medicine; Statistics; Clinical trial; Mathematics; Computer science; Internal medicine","score_opus":0.9378516184211011,"score_gpt":0.7058903326026658,"score_spread":0.23196128581843534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405223579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20692088,0.008233471,0.73804027,0.02862268,0.011824166,0.003979298,0.002065611,0.00008925046,0.00022439107],"genre_scores_gemma":[0.50676787,0.00035752295,0.49063343,0.00033950646,0.0013994066,0.0002090844,0.0000021281658,0.000012832541,0.00027822892],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950238,0.0019754404,0.0018881058,0.00029956,0.00066420186,0.00014887868],"domain_scores_gemma":[0.948314,0.04958966,0.0010089622,0.00015083546,0.0008272994,0.00010925217],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02820563,0.00018845056,0.0015118021,0.00021188057,0.0002371892,0.0001092648,0.0002874849,0.00012366392,0.00009834002],"category_scores_gemma":[0.23235579,0.000095346426,0.0006980029,0.000645889,0.0002725653,0.00021259584,0.000101433216,0.00037312336,4.8961044e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011814173,0.001257664,0.024005197,0.00075286964,0.037470937,0.000024761623,0.0009520547,0.00583053,0.00034941448,0.859831,0.035056915,0.03328726],"study_design_scores_gemma":[0.000667743,0.0001662181,0.03853773,0.000056607558,0.020113777,0.000018804196,0.000039250554,0.0040590954,0.000014529057,0.934044,0.0021628907,0.00011933185],"about_ca_topic_score_codex":0.000019628415,"about_ca_topic_score_gemma":0.000056800603,"teacher_disagreement_score":0.29984698,"about_ca_system_score_codex":0.00022346996,"about_ca_system_score_gemma":0.0003412136,"threshold_uncertainty_score":0.97755647},"labels":[{"model":"gemma","categories":["metaresearch","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","metaepi_narrow","metaepi_broad"],"domain":"methods","study_design":"meta_analysis","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4405299132","doi":"10.1371/journal.pone.0303315","title":"Methodological review to develop a list of bias items for adaptive clinical trials: Protocol and rationale","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cochrane; University of Toronto; University Health Network; Hamilton Health Sciences; McMaster University; University of British Columbia; Impact","funders":"","keywords":"Protocol (science); MEDLINE; Publication bias; Cochrane Library; Psychological intervention; Grey literature; Reporting bias; Systematic review; Selection bias; Computer science; Quality (philosophy); Clinical trial; Randomized controlled trial; Citation; Medicine; Data science; Medical physics; Meta-analysis; Alternative medicine; World Wide Web; Nursing","score_opus":0.9898691530909965,"score_gpt":0.7452978360433072,"score_spread":0.2445713170476893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405299132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055049727,0.00089927064,0.76689845,0.004898685,0.0002123031,0.2252984,0.00048147282,0.00015220215,0.00060873904],"genre_scores_gemma":[0.00003825581,0.00023683846,0.8957444,0.00065720803,0.00048206554,0.102524444,0.000002309064,0.00002838655,0.0002861194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9840271,0.01109307,0.0035849435,0.0005755374,0.0005022544,0.00021713684],"domain_scores_gemma":[0.420172,0.57806027,0.0005275824,0.00032317152,0.0007066353,0.00021033979],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.090072766,0.0001873037,0.0024252369,0.00006246441,0.00003651488,0.000035896057,0.00018365371,0.00021049833,0.00034513345],"category_scores_gemma":[0.90331125,0.00012662236,0.0002504646,0.00044235232,0.0001611285,0.00004272432,0.00013594537,0.0002877073,0.000020113983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034583644,0.004430036,0.00015365842,0.053107396,0.0024927931,0.000015851068,0.00021382702,1.7646998e-7,0.002117214,0.63240165,0.053336337,0.24827269],"study_design_scores_gemma":[0.0011619014,0.0013980225,0.000055887213,0.012092639,0.0009804232,0.0000016376581,0.000014132523,0.00058259635,0.0028465262,0.9732679,0.007377926,0.00022039836],"about_ca_topic_score_codex":0.0000013407209,"about_ca_topic_score_gemma":0.0000016742954,"teacher_disagreement_score":0.8132385,"about_ca_system_score_codex":0.000025148041,"about_ca_system_score_gemma":0.00021118458,"threshold_uncertainty_score":0.9369616},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W4405366937","doi":"10.1093/biomtc/ujae141","title":"An adaptive enrichment design using Bayesian model averaging for selection and threshold-identification of predictive variables","year":2024,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University","funders":"Canadian Statistical Sciences Institute; National Institute of Mental Health; National Institutes of Health","keywords":"Bayesian probability; Computer science; Feature selection; Personalized medicine; Machine learning; Clinical study design; Precision medicine; Identification (biology); Medicine; Population; Clinical trial; Artificial intelligence; Bioinformatics; Internal medicine","score_opus":0.5389790871329021,"score_gpt":0.5280648069140222,"score_spread":0.010914280218879857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405366937","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005330765,0.00016776205,0.9930931,0.000012659831,0.0003085447,0.0008053536,0.00017379204,0.00008530889,0.000022719421],"genre_scores_gemma":[0.4044468,0.00002399673,0.5953885,0.0000044268836,0.00007030809,0.00003110074,0.0000016099435,0.000019837411,0.000013421754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825585,0.00021846191,0.0006689061,0.0003885319,0.0002925777,0.00017567398],"domain_scores_gemma":[0.9842842,0.015002618,0.00020874287,0.00017296708,0.00025095473,0.000080489925],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0041921707,0.00013264672,0.00030649753,0.00080228294,0.00008364633,0.000088844936,0.00010331642,0.00014406112,0.000005772994],"category_scores_gemma":[0.012756351,0.00012215479,0.000055924924,0.0018529579,0.00005812486,0.00016144155,0.000030658553,0.00009734104,3.1777603e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093462033,0.0010157942,0.0004268335,0.0020377254,0.00077397143,0.000004036787,0.0016725436,0.04236111,0.15530191,0.7127302,0.00058490963,0.08215628],"study_design_scores_gemma":[0.00013488076,0.00021306265,0.000025602127,0.000045174154,0.00015298405,0.0000011255809,0.000033068496,0.5559145,0.0074220146,0.43598717,0.0000018516071,0.000068566005],"about_ca_topic_score_codex":0.0000060472494,"about_ca_topic_score_gemma":2.1923718e-7,"teacher_disagreement_score":0.5135534,"about_ca_system_score_codex":0.0001460552,"about_ca_system_score_gemma":0.00010019254,"threshold_uncertainty_score":0.99555963},"labels":[],"label_agreement":null},{"id":"W4405382992","doi":"10.1177/09622802241293750","title":"Approximation to the optimal allocation for response adaptive designs","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Bayesian probability; Statistical power; Mathematical optimization; Markov decision process; Coverage probability; Mathematics; Computer science; Randomization; Posterior probability; Probability distribution; Operator (biology); Statistics; Markov process; Clinical trial; Confidence interval","score_opus":0.8459332953070716,"score_gpt":0.7486349097033211,"score_spread":0.09729838560375048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405382992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020896501,0.0001214367,0.97545373,0.01932429,0.0007958822,0.0029485666,0.00021137483,0.00011486889,0.000820902],"genre_scores_gemma":[0.0042843884,0.000027442458,0.99177647,0.0003461162,0.0006118362,0.0023847437,0.0000056136573,0.00007880811,0.00048455966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9551313,0.037088826,0.001805074,0.001206186,0.0034289202,0.0013397043],"domain_scores_gemma":[0.34106052,0.65702564,0.000056217195,0.00063502725,0.0005298822,0.0006927076],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19591086,0.00026411275,0.0006933758,0.00048766675,0.00025138087,0.0002107012,0.0009854034,0.00044660512,0.0016110266],"category_scores_gemma":[0.8611473,0.00017441183,0.00012920078,0.0018405081,0.00096259284,0.00008150903,0.0003813212,0.0020656546,0.00016596934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019013921,0.00010946123,7.3719815e-7,0.0001699396,0.000031618012,0.00004659898,0.0003846926,0.000009049756,0.00033445776,0.54334486,0.01076749,0.44289973],"study_design_scores_gemma":[0.00045048515,0.0008930748,0.000114848444,0.0003872073,0.000032334923,0.0000081683365,0.00033867243,0.15718366,0.0008446628,0.8270915,0.012474663,0.00018067542],"about_ca_topic_score_codex":0.000024037401,"about_ca_topic_score_gemma":0.000017153256,"teacher_disagreement_score":0.6652364,"about_ca_system_score_codex":0.00040116123,"about_ca_system_score_gemma":0.0010144691,"threshold_uncertainty_score":0.9993016},"labels":[],"label_agreement":null},{"id":"W4405475036","doi":"10.1024/2673-8627/a000069","title":"The Bayesian One-Sample <i>t</i>-Test Supersedes Correlation Analysis as a Test of Validity","year":2024,"lang":"en","type":"article","venue":"European Journal of Psychology Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Parkwood Institute; Western University","funders":"","keywords":"Bayesian probability; Measure (data warehouse); Correlation; Statistics; Computer science; Sample (material); Statistical hypothesis testing; Sample size determination; Data mining; Test (biology); Monte Carlo method; Econometrics; Mathematics","score_opus":0.5797112499887458,"score_gpt":0.584753160565871,"score_spread":0.005041910577125219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405475036","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011871046,0.00022979957,0.92909926,0.004950994,0.0019477046,0.00044785795,0.0001508925,0.00003364976,0.05126882],"genre_scores_gemma":[0.48648807,0.00020003397,0.5119782,0.0003384985,0.0004576179,0.0000023821694,0.0000019102351,0.00005164591,0.00048163065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934707,0.003868923,0.0018021443,0.00027612413,0.00036129195,0.00022080273],"domain_scores_gemma":[0.8864692,0.11186295,0.0007400511,0.00053343765,0.00025590853,0.00013848578],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01901002,0.00015938099,0.00072347786,0.00018038288,0.00013254136,0.0001968753,0.0012464953,0.000064407854,0.0009789814],"category_scores_gemma":[0.14585602,0.00010532748,0.00039198805,0.00073182926,0.00034433036,0.00014230856,0.00019061884,0.00059983565,0.00009236811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032601876,0.007343025,0.12701115,0.0005414658,0.016350651,0.0025013487,0.0059280163,0.00018274937,0.0113237,0.3171248,0.21009144,0.29834145],"study_design_scores_gemma":[0.0016865233,0.0027542077,0.03813149,0.000358382,0.0032579077,0.00014964805,0.00023175105,0.0005614233,0.00027818422,0.9323777,0.01993382,0.0002789749],"about_ca_topic_score_codex":0.000009090112,"about_ca_topic_score_gemma":0.000009827241,"teacher_disagreement_score":0.6152529,"about_ca_system_score_codex":0.000023945713,"about_ca_system_score_gemma":0.0000730483,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W4405614054","doi":"10.1016/j.scijus.2024.12.002","title":"Cell site analysis; testing understanding via internal consistency checks","year":2024,"lang":"en","type":"article","venue":"Science & Justice","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Consistency (knowledge bases); Computer science; Artificial intelligence","score_opus":0.6749373401951616,"score_gpt":0.5689256189277885,"score_spread":0.10601172126737313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405614054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01213838,0.00010241076,0.92962056,0.00014569043,0.001831434,0.0001654468,0.000023609977,0.00022355872,0.055748925],"genre_scores_gemma":[0.53664654,0.0000031747877,0.46273237,0.00011896286,0.00016613527,0.0000038848207,2.2508165e-7,0.000012600748,0.00031608445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968412,0.00023452399,0.00077483704,0.00074210565,0.00086111296,0.0005462281],"domain_scores_gemma":[0.9504611,0.04838945,0.00018421416,0.00047953785,0.00020804422,0.0002776419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008445694,0.0001910535,0.00045173574,0.00041860127,0.0003700816,0.0004483155,0.0005695795,0.00007185858,0.00027777895],"category_scores_gemma":[0.10056068,0.00015789714,0.00017312668,0.004351763,0.0010578097,0.00025857243,0.00025625995,0.00043600355,0.00015856179],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057535206,0.0002986362,0.0030398022,0.002238878,0.00039670762,0.00047667316,0.0027169362,0.00023883976,0.039845016,0.9355242,0.002700659,0.012466097],"study_design_scores_gemma":[0.00015412514,0.00008421294,0.00029419776,0.0002121653,0.0031614557,0.000015908397,0.00079908886,0.104099356,0.0011411426,0.8897395,0.00004105785,0.00025778243],"about_ca_topic_score_codex":0.000034106604,"about_ca_topic_score_gemma":0.000008404431,"teacher_disagreement_score":0.5245082,"about_ca_system_score_codex":0.00031351057,"about_ca_system_score_gemma":0.00029010823,"threshold_uncertainty_score":0.9070157},"labels":[],"label_agreement":null},{"id":"W4405656062","doi":"10.2139/ssrn.5056623","title":"Bayesian Adaptive Enrichment Design in Multi-Arm Clinical Trials: The Bayesaet Package for R Users","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ottawa Hospital; University of British Columbia Hospital; University of Ottawa","funders":"","keywords":"R package; Bayesian probability; Adaptive design; Computer science; Clinical trial; Artificial intelligence; Medicine; Internal medicine; Computational science","score_opus":0.6762469616526232,"score_gpt":0.6036520194223982,"score_spread":0.072594942230225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405656062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003614046,0.0036911299,0.9822768,0.0028435679,0.005129586,0.0052624,0.00021111558,0.000108951375,0.00011502727],"genre_scores_gemma":[0.06726629,0.008508257,0.9176133,0.00036651897,0.0039058123,0.0010100506,0.000006733953,0.00031916023,0.0010038587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9572909,0.028209178,0.0076613408,0.0015340683,0.0010799271,0.00422462],"domain_scores_gemma":[0.7115671,0.283219,0.0030709533,0.0013748033,0.0003655301,0.00040259687],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2549131,0.0008923558,0.003539103,0.0003301895,0.00023126024,0.00034859485,0.0018007916,0.001366766,0.000110658344],"category_scores_gemma":[0.3033678,0.0005692619,0.0023422204,0.0003447547,0.00034930158,0.000055405253,0.0009033093,0.01964784,0.000041349045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003457387,0.0016625158,0.00012583936,0.00036496902,0.0047658943,0.000071586386,0.0005620293,0.0002318267,0.000017967544,0.8449126,0.0057777646,0.13804962],"study_design_scores_gemma":[0.004054656,0.0012728479,0.000033215638,0.0006665395,0.0015717371,0.000053161082,0.0011068961,0.011087455,0.000041392286,0.97928596,0.00022298901,0.0006031282],"about_ca_topic_score_codex":0.000030468434,"about_ca_topic_score_gemma":0.00030100837,"teacher_disagreement_score":0.25500983,"about_ca_system_score_codex":0.0025546786,"about_ca_system_score_gemma":0.008122971,"threshold_uncertainty_score":0.99992967},"labels":[],"label_agreement":null},{"id":"W4405801582","doi":"10.1134/s1995080224605435","title":"Fuzzy Method for Multiple Hypotheses Testing Procedure","year":2024,"lang":"en","type":"article","venue":"Lobachevskii Journal of Mathematics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Mathematics; Fuzzy logic; Algebra over a field; Calculus (dental); Artificial intelligence; Pure mathematics; Computer science; Orthodontics; Medicine","score_opus":0.6313142829333468,"score_gpt":0.567583129246376,"score_spread":0.0637311536869708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405801582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040499074,0.0005633502,0.98970574,0.00049523136,0.0010520625,0.0007362161,0.00008118123,0.00014903845,0.0031672807],"genre_scores_gemma":[0.0105291065,0.000022417511,0.98766834,0.000093356604,0.0011625027,0.000031306172,3.7044862e-7,0.0001148001,0.00037778806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99593204,0.00032633616,0.0023362732,0.00028763336,0.0006822048,0.00043553126],"domain_scores_gemma":[0.825472,0.17252427,0.0008626853,0.00033025985,0.00060508813,0.00020567926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009837125,0.000336781,0.0011847211,0.0001976617,0.00009589042,0.00019949167,0.00055734423,0.00024560437,0.000057543624],"category_scores_gemma":[0.35112354,0.0002403443,0.0005302317,0.00046099295,0.000100629324,0.00018296627,0.00008977992,0.00059200876,0.000022924756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019435667,0.0016436002,0.00024945024,0.017486392,0.0014518477,0.00024727435,0.0027990977,0.00009810396,0.006465438,0.8074379,0.029181968,0.13274455],"study_design_scores_gemma":[0.0007493104,0.00039938005,0.000015659109,0.0020504748,0.0006057456,0.0005989342,0.00047029622,0.0148138385,0.0025140503,0.97630095,0.0012183669,0.0002629894],"about_ca_topic_score_codex":9.98622e-7,"about_ca_topic_score_gemma":0.0000014546298,"teacher_disagreement_score":0.34128642,"about_ca_system_score_codex":0.00010060212,"about_ca_system_score_gemma":0.0002646599,"threshold_uncertainty_score":0.9800956},"labels":[],"label_agreement":null},{"id":"W4406069862","doi":"10.1016/s1470-2045(24)00717-4","title":"Non-inferiority trials: tyranny or good governance? – Authors' reply","year":2025,"lang":"en","type":"letter","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Certainty; Clinical trial; Outcome (game theory); Imperfect; Corporate governance; Psychology; Actuarial science; Sample size determination; Medicine; Economics; Internal medicine; Epistemology; Statistics; Management; Philosophy; Mathematics","score_opus":0.6947687374654694,"score_gpt":0.6143013693445082,"score_spread":0.08046736812096122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406069862","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000136905965,0.00013521969,0.019571558,0.90087664,0.013098044,0.0023442875,0.0016129735,0.0002966933,0.062050883],"genre_scores_gemma":[0.000008355221,0.00062525424,0.3445925,0.5831289,0.040414095,0.0004654847,0.000021399284,0.000095459174,0.030648524],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97843826,0.01482074,0.0035057217,0.0011578038,0.0008196999,0.0012577685],"domain_scores_gemma":[0.6560848,0.33780333,0.0028075175,0.0029161633,0.00026751298,0.000120675046],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.039307933,0.0007564858,0.007558109,0.000079049416,0.00022730691,0.00010247068,0.002449064,0.0030905306,0.0027235146],"category_scores_gemma":[0.41751784,0.00042903423,0.0008232122,0.0004640831,0.0006637509,0.00004710322,0.00069958554,0.007171985,0.00031151288],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013477699,0.000111370784,0.000012057352,0.0008321468,0.0005734477,0.0006002207,0.00009124133,1.6917582e-7,0.000005669575,0.028885778,0.95053226,0.017007884],"study_design_scores_gemma":[0.0020956497,0.0003129317,0.000038855214,0.00024587003,0.0007743508,0.00002464438,0.0000075060293,0.000018460962,0.000019538778,0.42218795,0.57398105,0.0002931827],"about_ca_topic_score_codex":0.00008944971,"about_ca_topic_score_gemma":0.00006314462,"teacher_disagreement_score":0.39330217,"about_ca_system_score_codex":0.0005679979,"about_ca_system_score_gemma":0.0014102415,"threshold_uncertainty_score":0.9998161},"labels":[],"label_agreement":null},{"id":"W4406200976","doi":"10.1002/alz.086509","title":"Diagnostic and analytical performance of plasma pTau181 and 217 in a clinical laboratory","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Clinical Practice; Internal medicine; Biomarker; Pathology; Oncology; Gastroenterology; Nuclear medicine; Chemistry; Physical therapy","score_opus":0.3217933486991366,"score_gpt":0.5137877887030853,"score_spread":0.19199444000394866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406200976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9772707,0.020206587,0.0008204407,0.00025693802,0.0005749565,0.0003504526,0.000049247486,0.00005074277,0.00041993865],"genre_scores_gemma":[0.87142307,0.0007685076,0.1275787,0.00007093748,0.00011191018,0.000019630901,7.025278e-7,0.000023155646,0.0000034029877],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99746716,0.00046668955,0.0011924191,0.00040748023,0.00022727602,0.00023898586],"domain_scores_gemma":[0.9524894,0.046967797,0.00010615947,0.0002483598,0.00005001646,0.00013826901],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035349317,0.0001627329,0.0005710548,0.000096601856,0.000026678126,0.000041069452,0.0001186102,0.000163235,0.00015068568],"category_scores_gemma":[0.022259831,0.00013851601,0.0000636968,0.0002546972,0.0004099894,0.00009683871,0.0001595251,0.000339926,0.000018984583],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030266895,0.00070554187,0.31613034,0.00068672,0.010297592,0.00020817906,0.00036776412,0.0000019137874,0.000094809475,0.19973923,0.0057877377,0.4656775],"study_design_scores_gemma":[0.0051218653,0.002082091,0.42375836,0.0019307958,0.041877005,0.00003466236,0.00015675624,0.06365301,0.0035844566,0.45050028,0.0059934026,0.0013073152],"about_ca_topic_score_codex":0.000005262823,"about_ca_topic_score_gemma":0.00000766637,"teacher_disagreement_score":0.4643702,"about_ca_system_score_codex":0.000002963231,"about_ca_system_score_gemma":0.00006397876,"threshold_uncertainty_score":0.9859761},"labels":[],"label_agreement":null},{"id":"W4406223934","doi":"10.1002/alz.086975","title":"A digital twin technique using external observational data to reduce sample sizes in clinical trials on Alzheimer’s disease","year":2024,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Randomized controlled trial; Observational study; Medicine; Placebo; Clinical trial; Sample size determination; Randomization; Internal medicine; Statistics; Alternative medicine; Pathology; Mathematics","score_opus":0.864579998259515,"score_gpt":0.6373158173684859,"score_spread":0.22726418089102918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406223934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015081008,0.024074811,0.9346875,0.003591135,0.0057943086,0.0069340044,0.008510834,0.00065627386,0.00067013106],"genre_scores_gemma":[0.18881316,0.0000315787,0.8088188,0.0006343977,0.001297012,0.00020722052,0.00009210638,0.000098770295,0.0000069272273],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99105215,0.0025295313,0.0036443747,0.0013643974,0.0008594035,0.0005501376],"domain_scores_gemma":[0.8802235,0.11684476,0.00045530268,0.0017743183,0.00011724955,0.0005848624],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019955166,0.0004162896,0.0012129587,0.0002240156,0.000085799744,0.00043590588,0.0011104295,0.0002294855,0.00088557857],"category_scores_gemma":[0.1600712,0.00036320687,0.00036937481,0.00054939394,0.0001691799,0.00047041933,0.000846175,0.00060965144,0.000140773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018384078,0.0017292254,0.0042248424,0.00006714164,0.010769689,0.0003765771,0.000071268296,0.00003514139,0.0010670391,0.07884308,0.024970526,0.8760071],"study_design_scores_gemma":[0.0014728182,0.00032534896,0.006670874,0.001233571,0.021293933,0.000009913136,0.000021629654,0.008398393,0.0018943048,0.9440405,0.0136710005,0.0009677485],"about_ca_topic_score_codex":0.0000380042,"about_ca_topic_score_gemma":0.000006709462,"teacher_disagreement_score":0.87503934,"about_ca_system_score_codex":0.000022034628,"about_ca_system_score_gemma":0.00040451656,"threshold_uncertainty_score":0.999882},"labels":[],"label_agreement":null},{"id":"W4406266450","doi":"10.1016/j.eclinm.2024.102987","title":"CONSORT-DEFINE explanation and elaboration: recommendations for enhancing reporting quality and impact of early phase dose-finding clinical trials","year":2025,"lang":"en","type":"article","venue":"EClinicalMedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Women's College Hospital; University of Toronto","funders":"National Key Research and Development Program of China; National Major Science and Technology Projects of China; Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Consolidated Standards of Reporting Trials; Checklist; Medicine; Clinical trial; Critical appraisal; Quality (philosophy); Alternative medicine; Family medicine; Medical education; Psychology; Pathology","score_opus":0.9090728403202267,"score_gpt":0.7739647424787213,"score_spread":0.13510809784150546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406266450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5476763,0.00020031336,0.441499,0.0070414506,0.0011384725,0.0017391889,0.00025410557,0.00007571013,0.00037542376],"genre_scores_gemma":[0.5176391,0.00031607464,0.48072734,0.000401706,0.00066412776,0.000087607405,0.000032539592,0.000023236224,0.00010825763],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9795545,0.004063727,0.015099703,0.00067883567,0.0003085067,0.00029477038],"domain_scores_gemma":[0.51870763,0.47011304,0.009521628,0.0006372809,0.0007197813,0.00030066818],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.123347186,0.00023854009,0.0027574115,0.00017569239,0.00015498695,0.000039388622,0.00012052287,0.0003499749,0.00013867198],"category_scores_gemma":[0.86267513,0.00018104915,0.00037246535,0.00038197608,0.00041131763,0.00011386263,0.00009454065,0.00046680323,7.607288e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060541173,0.002088904,0.13864009,0.0014864061,0.0020205686,0.000012649652,0.00057477463,0.0000013770133,0.004020854,0.26057777,0.015888156,0.56863433],"study_design_scores_gemma":[0.021345539,0.0030304806,0.077085055,0.0012565262,0.0011653698,0.000005841989,0.00029222958,0.0007229253,0.0005127707,0.893844,0.0004288272,0.00031044494],"about_ca_topic_score_codex":0.00003505872,"about_ca_topic_score_gemma":0.000020425428,"teacher_disagreement_score":0.73932797,"about_ca_system_score_codex":0.0000373682,"about_ca_system_score_gemma":0.00030697568,"threshold_uncertainty_score":0.9026986},"labels":[],"label_agreement":null},{"id":"W4406266557","doi":"10.1016/j.eclinm.2024.102988","title":"SPIRIT-DEFINE explanation and elaboration: recommendations for enhancing quality and impact of early phase dose-finding clinical trials protocols","year":2025,"lang":"en","type":"article","venue":"EClinicalMedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Women's College Hospital; University of Toronto","funders":"Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Elaboration; Medicine; Quality (philosophy); Phase (matter); Clinical trial; Intensive care medicine; Epistemology; Pathology; Humanities","score_opus":0.8981202568064411,"score_gpt":0.781721787791815,"score_spread":0.11639846901462614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406266557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19579946,0.00013790232,0.7586855,0.01861419,0.0010075019,0.024573755,0.0006552228,0.000119545475,0.000406874],"genre_scores_gemma":[0.1667133,0.00023023736,0.8270357,0.00074681075,0.0012934238,0.0037188993,0.00004744508,0.00004263979,0.00017153386],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.986743,0.004311187,0.0077098277,0.0006335988,0.0003155932,0.00028681528],"domain_scores_gemma":[0.7256887,0.2710704,0.0020703273,0.00047778044,0.00046547395,0.00022731633],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07615374,0.0002585464,0.0024947913,0.00017958,0.00013790671,0.000047563637,0.00016787808,0.00038175104,0.00017209914],"category_scores_gemma":[0.6300237,0.00019198969,0.00034759677,0.00041215884,0.00040170673,0.00013050302,0.00009908682,0.00046312608,0.0000013903787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009516671,0.003171286,0.043964494,0.0020048025,0.0014032273,0.0000043065907,0.00039851994,8.972938e-7,0.0030459652,0.3104056,0.02050661,0.6055776],"study_design_scores_gemma":[0.030214446,0.005589334,0.041730028,0.0016745894,0.0006968723,0.0000018322992,0.0001225351,0.00049710204,0.000564832,0.9170541,0.0015575268,0.00029680115],"about_ca_topic_score_codex":0.000023457325,"about_ca_topic_score_gemma":0.00001859363,"teacher_disagreement_score":0.6066485,"about_ca_system_score_codex":0.00003973124,"about_ca_system_score_gemma":0.0002932445,"threshold_uncertainty_score":0.9512941},"labels":[],"label_agreement":null},{"id":"W4406351953","doi":"10.1200/jco-24-01534","title":"Accelerating the Future of Oncology Drug Development: The Role of Consortia in the Delivery of Precision Oncology Early Phase Clinical Trials","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Snowball sampling; Medicine; Clinical trial; Scope (computer science); Drug development; Timeline; Government (linguistics); Clinical Oncology; Regulatory science; Oncology; Cancer; Internal medicine; Pharmacology; Drug; Pathology; Computer science","score_opus":0.8233383892293199,"score_gpt":0.7297194711303056,"score_spread":0.09361891809901435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406351953","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058974596,0.967634,0.0016826326,0.0030505196,0.011033582,0.005716731,0.00021389482,0.000014012823,0.0047571333],"genre_scores_gemma":[0.0008259465,0.84111136,0.1540184,0.0005804853,0.0032610856,0.000093207884,0.0000034982068,0.000050257993,0.00005574043],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.70571697,0.21701282,0.07319752,0.0010442167,0.002115954,0.0009125053],"domain_scores_gemma":[0.14162786,0.80461955,0.050461162,0.0012940982,0.0017334162,0.00026389337],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.33309528,0.00070160563,0.02385664,0.00040727935,0.0001413579,0.000026555683,0.0042205695,0.0038428153,0.00025106728],"category_scores_gemma":[0.60737836,0.0002977904,0.005395179,0.000997833,0.0024641433,0.00010276968,0.0008342525,0.008495801,0.000006947238],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033385577,0.00588417,0.00012336095,0.001945199,0.0019069846,0.00008204168,0.0006229779,0.0000010836154,0.0000015859583,0.009446716,0.0034151261,0.9732322],"study_design_scores_gemma":[0.008494185,0.009572606,0.00017770336,0.0065413527,0.006469852,0.00009713981,0.0011379882,0.000014799865,0.000013878721,0.105480134,0.86174357,0.00025681395],"about_ca_topic_score_codex":0.000016796357,"about_ca_topic_score_gemma":0.00010893596,"teacher_disagreement_score":0.9729754,"about_ca_system_score_codex":0.0002978945,"about_ca_system_score_gemma":0.019485842,"threshold_uncertainty_score":0.9999474},"labels":[],"label_agreement":null},{"id":"W4406468895","doi":"10.1016/s0029-7437(10)70272-x","title":"10.1016/s0029-7437(10)70272-x","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Labetalol; Affect (linguistics); Medicine; Psychology; Internal medicine; Communication; Blood pressure","score_opus":0.2629484434288294,"score_gpt":0.44143622122657933,"score_spread":0.17848777779774994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406468895","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058498885,0.000015117963,0.00033864882,0.000340536,0.0000016056687,0.00044627985,0.000084590414,0.0003143917,0.99840033],"genre_scores_gemma":[0.0000015552141,2.43385e-7,0.28074864,0.000057816418,0.00033693155,0.000034556,0.0000019409715,0.00004803504,0.71877027],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741775,0.00049862266,0.0007863006,0.00043437805,0.00041262986,0.00045033565],"domain_scores_gemma":[0.98038185,0.018357504,0.000102695994,0.00073553016,0.000095627845,0.0003267754],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018299356,0.00024527754,0.000637384,0.00006327623,0.00007988386,0.00005646579,0.00044148188,0.00018999842,0.99964446],"category_scores_gemma":[0.03335873,0.00021843042,0.00016359676,0.00027643697,0.00010131798,0.000055355624,0.00009587854,0.00024947478,0.997339],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015359437,0.00012028923,1.5091048e-8,0.000020663641,0.000031152853,0.0000068897243,0.0000070652404,0.0000017708256,0.000013722607,0.00018972735,0.72500914,0.27444595],"study_design_scores_gemma":[0.0004986107,0.0002422334,0.0000044299445,0.000047514466,0.00007206443,0.0000047958497,5.542011e-7,0.00011092477,0.00013799855,0.085276484,0.9133452,0.00025915555],"about_ca_topic_score_codex":0.000004574681,"about_ca_topic_score_gemma":6.897797e-8,"teacher_disagreement_score":0.28041,"about_ca_system_score_codex":0.000047509788,"about_ca_system_score_gemma":0.000036837093,"threshold_uncertainty_score":0.9747837},"labels":[],"label_agreement":null},{"id":"W4406489459","doi":"10.1017/pan.2024.24","title":"Decoupling Visualization and Testing when Presenting Confidence Intervals","year":2025,"lang":"en","type":"article","venue":"Political Analysis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Decoupling (probability); Confidence interval; Computer science; Visualization; Reliability engineering; Statistics; Data mining; Mathematics; Engineering; Control engineering","score_opus":0.5242550988197755,"score_gpt":0.599761551093115,"score_spread":0.07550645227333952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406489459","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069282,0.000027288877,0.9236815,0.00054484996,0.00007654146,0.00014068939,0.000011302733,0.00009953957,0.0061362977],"genre_scores_gemma":[0.6362359,0.0000017359888,0.3630662,0.00032404345,0.000070671835,0.000012138912,0.000001050815,0.000008544219,0.00027973484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997662,0.00041385644,0.0008906416,0.00039159154,0.00023646874,0.00040543717],"domain_scores_gemma":[0.92849636,0.070611425,0.00014949044,0.00030210774,0.00025659084,0.0001840229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021672372,0.00014117015,0.0006469056,0.00024761073,0.00011580386,0.00012399792,0.00016461428,0.00010479917,0.0002020713],"category_scores_gemma":[0.2541289,0.00012419176,0.00015669255,0.00088744774,0.00018896727,0.00006303472,0.00021735992,0.00015321594,0.0000062016697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049139358,0.000043312197,0.04191287,0.0001258127,0.0004682963,0.0000027075882,0.000044907873,0.0000038921225,0.00004317728,0.9557829,0.000057181507,0.0015100648],"study_design_scores_gemma":[0.00014041497,0.000011654935,0.0051999944,0.000093346694,0.0019760618,6.1689855e-7,0.000086017004,0.101655036,0.000711078,0.89000326,0.000015811009,0.0001067175],"about_ca_topic_score_codex":0.00013472195,"about_ca_topic_score_gemma":0.000014720933,"teacher_disagreement_score":0.5669539,"about_ca_system_score_codex":0.00004029766,"about_ca_system_score_gemma":0.000031209238,"threshold_uncertainty_score":0.7521539},"labels":[],"label_agreement":null},{"id":"W4406856422","doi":"10.2196/64611","title":"Leveraging Patient-Reported Outcome Measures for Optimal Dose Selection in Early Phase Cancer Trials","year":2025,"lang":"en","type":"review","venue":"JMIR Cancer","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Selection (genetic algorithm); Outcome (game theory); Phase (matter); Cancer; Computer science; Medicine; Medical physics; Oncology; Artificial intelligence; Internal medicine; Mathematics; World Wide Web; Physics","score_opus":0.8250779505726163,"score_gpt":0.6898320039324328,"score_spread":0.13524594664018352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406856422","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008436124,0.9314849,0.049876492,0.00007692433,0.0036004807,0.013114185,0.0014438403,0.0001805532,0.00013831258],"genre_scores_gemma":[0.000016902042,0.85310763,0.11780935,0.00011066865,0.0011907367,0.026668455,0.000014548014,0.00014974135,0.0009319953],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98931044,0.0027363845,0.0056278515,0.0010465293,0.00061943906,0.0006593332],"domain_scores_gemma":[0.9419886,0.054207195,0.0028355722,0.00045283203,0.0003576225,0.0001581738],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0074243676,0.0007490487,0.006951558,0.00046051628,0.00010473433,0.00010670526,0.0003736643,0.00080381177,0.00044101055],"category_scores_gemma":[0.10612367,0.0005831867,0.0014508244,0.0008942615,0.00007311742,0.00008838245,0.00010512222,0.00091149204,0.000004467714],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037262507,0.00030818945,0.000032028984,0.021036882,0.0007432707,0.000010941686,0.000119689656,0.000009369922,0.0000021136032,0.00054339995,0.0035011817,0.9733203],"study_design_scores_gemma":[0.008396046,0.00035347856,0.000014538228,0.04165548,0.0065821847,0.0000045948045,0.00001851826,0.00008260548,0.000034791323,0.045395266,0.8961788,0.0012836995],"about_ca_topic_score_codex":0.00025014346,"about_ca_topic_score_gemma":0.00008708657,"teacher_disagreement_score":0.9720366,"about_ca_system_score_codex":0.0010810136,"about_ca_system_score_gemma":0.0015415832,"threshold_uncertainty_score":0.999662},"labels":[],"label_agreement":null},{"id":"W4407028946","doi":"10.1016/b978-0-323-91790-2.00071-x","title":"Nonrandomized controlled clinical trials","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton Health Sciences","funders":"","keywords":"Medicine","score_opus":0.5823813281501349,"score_gpt":0.5947386996726649,"score_spread":0.012357371522530025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407028946","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.877552e-7,0.000616829,0.0061448477,0.00027031414,0.0057189795,0.008047146,0.00037563185,0.0002699982,0.9785554],"genre_scores_gemma":[0.0000024472154,0.0003310489,0.25983208,0.0008964143,0.002426779,0.00034316003,0.0000063066273,0.00014126356,0.7360205],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9713979,0.012059961,0.013316989,0.0014708198,0.0010958614,0.00065850624],"domain_scores_gemma":[0.5583191,0.43599373,0.0034320161,0.00150652,0.0003966507,0.00035197713],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.096101575,0.0011028247,0.016498297,0.00027509092,0.0001373871,0.00012288168,0.0009194112,0.0023700877,0.003935258],"category_scores_gemma":[0.6093645,0.00079403474,0.0059516374,0.00002551996,0.00063878775,0.000021637516,0.00039691405,0.002347487,0.0004215689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077881645,0.00007766813,2.9035013e-7,0.00020063807,0.002071601,0.00004323256,0.000009114448,1.1446603e-8,0.0000012981169,0.29766142,0.0075617013,0.68458486],"study_design_scores_gemma":[0.042840958,0.0001583508,1.7392242e-7,0.0009312939,0.003476825,0.0000020119273,0.0000010742827,0.000011415578,0.000004537887,0.56314546,0.38900837,0.0004195664],"about_ca_topic_score_codex":1.4682966e-7,"about_ca_topic_score_gemma":0.0000033076317,"teacher_disagreement_score":0.6841653,"about_ca_system_score_codex":0.000100901234,"about_ca_system_score_gemma":0.0006642151,"threshold_uncertainty_score":0.99995416},"labels":[],"label_agreement":null},{"id":"W4407095785","doi":"10.1016/s1470-2045(24)00451-0","title":"Common Sense Oncology principles for the design, analysis, and reporting of phase 3 randomised clinical trials","year":2025,"lang":"en","type":"review","venue":"The Lancet Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Queen's University; McMaster University; Kingston Health Sciences Centre; Cancer Care South East","funders":"","keywords":"Medicine; Clinical trial; Oncology; Internal medicine; Clinical Oncology; Medical physics; Cancer","score_opus":0.953424582561647,"score_gpt":0.7698343604004043,"score_spread":0.18359022216124266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407095785","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000058906944,0.55383503,0.43211195,0.0011948852,0.0013428584,0.010143661,0.00037904503,0.000054257747,0.000932407],"genre_scores_gemma":[0.0000027039791,0.65744865,0.3398357,0.00025990853,0.0012138875,0.00104789,0.000012006892,0.000029369021,0.00014991146],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.871587,0.10252151,0.023924889,0.00094526535,0.00034362724,0.0006777411],"domain_scores_gemma":[0.10240518,0.86902463,0.026533227,0.0016487093,0.00027241273,0.00011582296],"candidate_categories":["metaresearch","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.34676886,0.00050935533,0.027372519,0.00018605287,0.0002049711,0.00003105405,0.0008701417,0.0013141133,0.000070303795],"category_scores_gemma":[0.84880215,0.00022858649,0.0032375825,0.00066411553,0.0010819732,0.000014047758,0.00044453377,0.0013538963,0.0000019034866],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061388877,0.00044794954,0.0000049639775,0.007822587,0.008390175,0.000033819462,0.00005147986,0.000002017489,5.44584e-7,0.013000528,0.0035560862,0.96055096],"study_design_scores_gemma":[0.022693459,0.001102437,0.000003125547,0.0016983958,0.07495863,0.00004214493,0.000027511036,0.00041544854,0.000004894736,0.15907425,0.7397462,0.00023349121],"about_ca_topic_score_codex":0.000010247041,"about_ca_topic_score_gemma":0.000037816946,"teacher_disagreement_score":0.9603175,"about_ca_system_score_codex":0.0001359994,"about_ca_system_score_gemma":0.001510466,"threshold_uncertainty_score":0.9999824},"labels":[],"label_agreement":null},{"id":"W4407354537","doi":"10.1186/s13063-024-08684-8","title":"Statistical documentation for multi-disease, multi-domain platform trials: our experience with the Staphylococcus aureus Network Adaptive Platform trial","year":2025,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre; Health Sciences Centre; McGill University; McGill University Health Centre","funders":"Medical Research Council","keywords":"Clinical trial; Documentation; Medicine; Protocol (science); Computer science; Statistical analysis; Data science; Domain (mathematical analysis); Medical physics; Data mining; Alternative medicine; Pathology; Statistics","score_opus":0.731897373279013,"score_gpt":0.6193077308717803,"score_spread":0.11258964240723279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407354537","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004057323,0.00018709555,0.96976763,0.0007469486,0.0031564594,0.020007452,0.0016649002,0.0002100893,0.00020208267],"genre_scores_gemma":[0.015644442,0.00003978718,0.9726516,0.0005900628,0.00241029,0.0073587648,0.000045728146,0.0000946449,0.001164673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98554695,0.005777789,0.0053513893,0.0011576565,0.0010497802,0.0011164604],"domain_scores_gemma":[0.75211596,0.24372764,0.0023380816,0.0009735254,0.00042750308,0.00041730094],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04849694,0.00072613824,0.00367171,0.0001596334,0.00065265596,0.0003647727,0.0008021114,0.00038713054,0.00026513627],"category_scores_gemma":[0.31643036,0.00042496808,0.0007627241,0.0006127467,0.00038836064,0.00030442694,0.00018770777,0.000560977,0.000025235033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.33372775,0.001255096,0.00006981362,0.00024875972,0.0016302256,0.000030060039,0.0010391684,0.00015185298,0.00013245762,0.5714436,0.06372546,0.026545748],"study_design_scores_gemma":[0.17713027,0.0016234111,0.00026301105,0.00037482372,0.0020969417,7.4901857e-7,0.0042812265,0.0040033986,0.00043818963,0.80421144,0.004791232,0.0007852882],"about_ca_topic_score_codex":0.000039441158,"about_ca_topic_score_gemma":0.00008654922,"teacher_disagreement_score":0.26793343,"about_ca_system_score_codex":0.00027371332,"about_ca_system_score_gemma":0.0006947325,"threshold_uncertainty_score":0.99982023},"labels":[],"label_agreement":null},{"id":"W4407382069","doi":"10.3150/24-bej1768","title":"Multiple testing under negative dependence","year":2025,"lang":"en","type":"article","venue":"Bernoulli","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Econometrics; Statistics; Applied mathematics","score_opus":0.6405904209575329,"score_gpt":0.5728967973589012,"score_spread":0.06769362359863174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407382069","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026543593,0.000041668332,0.91760415,0.0007558852,0.00076166325,0.0005695061,0.000032286243,0.0002838261,0.053407405],"genre_scores_gemma":[0.18211459,0.0000030749557,0.81518155,0.00043908486,0.00010306465,0.000034204924,2.9865456e-7,0.000016710297,0.0021074247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982064,0.0003824827,0.00055112457,0.00034082218,0.00024107457,0.0002780935],"domain_scores_gemma":[0.859533,0.13970764,0.00014085755,0.00038417554,0.0001573544,0.00007698298],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013562093,0.00015074885,0.00037371353,0.000051745687,0.000113804585,0.000039048937,0.0002754623,0.00013720733,0.00019054818],"category_scores_gemma":[0.29842976,0.00013107053,0.000076791126,0.00038504775,0.00014179772,0.000046264024,0.0001594945,0.0002852145,0.00009415918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008696888,0.00031558,0.020581843,0.00016565269,0.00015619906,0.00002419672,0.000100018086,0.00003864077,0.0015181088,0.910844,0.0059782066,0.06019055],"study_design_scores_gemma":[0.00062713295,0.000028958537,0.0050801313,0.00016090267,0.000056778154,0.0000015676468,0.000082302584,0.0011385857,0.0035580879,0.98887306,0.00025666822,0.00013580872],"about_ca_topic_score_codex":0.000057818434,"about_ca_topic_score_gemma":0.000025632784,"teacher_disagreement_score":0.29707354,"about_ca_system_score_codex":0.00005776567,"about_ca_system_score_gemma":0.000088231056,"threshold_uncertainty_score":0.7074799},"labels":[],"label_agreement":null},{"id":"W4407918244","doi":"10.1007/978-3-031-77563-5_6","title":"Optimizing Recruitment in Randomized Controlled Trials","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fowler Kennedy Sport Medicine Clinic; Western University","funders":"","keywords":"Randomized controlled trial; Medicine; Internal medicine","score_opus":0.7903166916713059,"score_gpt":0.6023510510085082,"score_spread":0.18796564066279775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407918244","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.3686391e-7,0.0022337954,0.057873446,0.00072622596,0.0028008458,0.017416788,0.000086644206,0.00023923628,0.9186228],"genre_scores_gemma":[0.000002739245,0.0010238166,0.48050812,0.00013958232,0.00053486344,0.0012869731,0.0000026043053,0.0001125968,0.5163887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98057115,0.0050776936,0.011908356,0.0010253725,0.00095107884,0.00046637352],"domain_scores_gemma":[0.5492194,0.4486565,0.0014176812,0.0004970636,0.0000915394,0.00011780468],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11150542,0.0008045053,0.027112024,0.0005061173,0.000026732547,0.00013951804,0.00033387015,0.0010687418,0.016090661],"category_scores_gemma":[0.5323724,0.0004570002,0.0049099424,0.000048320922,0.0002503504,0.000025952217,0.00020697527,0.0011491418,0.0005806264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07868441,0.00003901915,5.94102e-9,0.00023222931,0.0022693486,0.00009556384,0.000045281926,0.000001520772,0.0000022401887,0.91074824,0.0033545399,0.0045276117],"study_design_scores_gemma":[0.28219756,0.000041384592,2.1785027e-9,0.0015584427,0.003140454,0.0000017361206,0.0000060394423,0.0002913126,0.000011952119,0.70550716,0.00691068,0.00033327617],"about_ca_topic_score_codex":0.0000053391436,"about_ca_topic_score_gemma":0.00000794814,"teacher_disagreement_score":0.4435788,"about_ca_system_score_codex":0.00020772433,"about_ca_system_score_gemma":0.00014803869,"threshold_uncertainty_score":0.99978817},"labels":[],"label_agreement":null},{"id":"W4408085214","doi":"10.1007/978-3-031-64350-7_66","title":"Finite-Sample Inference in Response-Adaptive Designs: An Application to Thompson Sampling","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Sample (material); Sampling (signal processing); Sampling design; Computer science; Statistics; Mathematics; Artificial intelligence; Sociology; Chromatography; Demography","score_opus":0.7360996112649789,"score_gpt":0.5860418154813277,"score_spread":0.1500577957836512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408085214","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000059457075,0.000012880937,0.91962284,0.00022173711,0.00018741112,0.001772391,0.0003712067,0.00016985036,0.07763574],"genre_scores_gemma":[0.0007979315,0.000023330545,0.94242495,0.0005472941,0.00017132793,0.00023974001,0.000015919843,0.00007657312,0.055702925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995775,0.0007792676,0.0015858185,0.0010193672,0.0004680703,0.00037249477],"domain_scores_gemma":[0.59169286,0.40671295,0.00030566193,0.0009025771,0.00021312622,0.00017278858],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058807936,0.0004906052,0.0012379937,0.00044723199,0.000069567184,0.0000654499,0.0006137037,0.0007814456,0.0009532196],"category_scores_gemma":[0.40001327,0.0004658596,0.000149279,0.00017336395,0.00010156363,0.00006531719,0.00027318092,0.00077540544,0.00013975734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011846605,0.00006532274,0.0000042521906,0.00007538312,0.000031404583,0.0000036553515,0.00010544334,0.00017654098,0.000054449647,0.9281286,0.00013941365,0.07003087],"study_design_scores_gemma":[0.00034117757,0.00037515527,0.00001856812,0.0006405823,0.00007782676,1.1074939e-7,0.000030144396,0.0038822077,0.000077831086,0.9870276,0.007042624,0.00048617128],"about_ca_topic_score_codex":0.000065965316,"about_ca_topic_score_gemma":0.00017462004,"teacher_disagreement_score":0.40593368,"about_ca_system_score_codex":0.00025987186,"about_ca_system_score_gemma":0.0002967382,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W4408406752","doi":"10.1016/j.ccell.2025.02.019","title":"Turning the kaleidoscope: Innovations shaping the future of clinical trial design","year":2025,"lang":"en","type":"article","venue":"Cancer Cell","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"Sociedad Española de Oncología Médica","keywords":"Kaleidoscope; Clinical trial; Medicine; Computer science; Internal medicine","score_opus":0.7426536553016683,"score_gpt":0.6343781306442571,"score_spread":0.10827552465741119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408406752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017246984,0.0033186974,0.9382082,0.007862741,0.014502915,0.0030351763,0.000051175295,0.00009025022,0.01568381],"genre_scores_gemma":[0.09318392,0.0011811395,0.8904755,0.004492004,0.0071049333,0.0005793782,0.0000014095598,0.00005842916,0.0029232665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957823,0.0019219244,0.0015718052,0.00026553043,0.0002539325,0.00020451575],"domain_scores_gemma":[0.8987099,0.099767104,0.000598105,0.0006552044,0.00023358916,0.000036123976],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009488597,0.00013676248,0.00055290514,0.000024429739,0.00018342953,0.000025940844,0.0006069257,0.0001850569,0.0004347754],"category_scores_gemma":[0.041131977,0.00007123832,0.00019048923,0.0005388727,0.00030125552,0.000034451332,0.00013565569,0.0006130672,0.000005441604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010392604,0.0005358695,0.00061215303,0.000409671,0.00046175625,0.0000023286966,0.0006207443,0.00013963065,0.00069358817,0.6343421,0.14055923,0.21123035],"study_design_scores_gemma":[0.014782606,0.00023739257,0.0005295633,0.00023662222,0.00039829794,2.3332588e-7,0.0005324941,0.0009132126,0.0027300168,0.9517991,0.027669597,0.00017088217],"about_ca_topic_score_codex":0.00001642162,"about_ca_topic_score_gemma":0.000013605884,"teacher_disagreement_score":0.31745702,"about_ca_system_score_codex":0.000040379717,"about_ca_system_score_gemma":0.0004113394,"threshold_uncertainty_score":0.966945},"labels":[],"label_agreement":null},{"id":"W4408442450","doi":"10.1073/pnas.2410849122","title":"Combining exchangeable <i>P</i> -values","year":2025,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Mathematics; Independence (probability theory); Algorithm; Set (abstract data type); Value (mathematics); Conditional independence; Computer science; Statistics; Discrete mathematics; Applied mathematics","score_opus":0.49265781309959583,"score_gpt":0.5500349371543858,"score_spread":0.05737712405478995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408442450","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46561745,0.00034507894,0.00070177094,0.022253355,0.00043395214,0.0012072116,0.0000750384,0.00011684428,0.50924927],"genre_scores_gemma":[0.6909343,0.00001594512,0.30749163,0.00058192806,0.00006267311,0.00001219347,7.34157e-9,0.0000033267847,0.0008979827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981328,0.000027843726,0.00056452473,0.00020315916,0.00093415723,0.00013746567],"domain_scores_gemma":[0.9883931,0.010776668,0.0004888611,0.000009286466,0.00030845858,0.000023585993],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006727245,0.00007671775,0.00027386934,0.00011796596,0.00015807098,0.000019538336,0.0008546093,0.00008859087,0.000028692324],"category_scores_gemma":[0.06565716,0.0000488689,0.00008784025,0.00090436265,0.0010372536,0.00014117322,0.00023788819,0.00017067892,9.5114234e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010835337,0.00004860413,0.0010243413,0.00014752772,0.000016562097,1.1743689e-9,0.00005369907,0.0000023189677,0.020098977,0.9714372,0.0064449916,0.0007149309],"study_design_scores_gemma":[0.00015990563,0.000021296002,0.0020458705,0.00022609715,0.00002057794,4.7675033e-7,0.000077506986,0.00028715798,0.14076936,0.8562168,0.00013423055,0.000040697985],"about_ca_topic_score_codex":0.0000014255999,"about_ca_topic_score_gemma":8.273347e-9,"teacher_disagreement_score":0.5083513,"about_ca_system_score_codex":0.000021030051,"about_ca_system_score_gemma":0.000031855623,"threshold_uncertainty_score":0.9422132},"labels":[],"label_agreement":null},{"id":"W4408621984","doi":"10.3390/curroncol32030176","title":"Understanding the Role of Patient-Reported Outcomes for Decision-Making in Early-Phase Dose-Finding Clinical Trials","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Clinical trial; Data collection; Adverse effect; Patient recruitment; Patient safety; Phase (matter); Patient participation; Medical physics; Intensive care medicine; MEDLINE; Health care; Pathology","score_opus":0.8895131241431848,"score_gpt":0.7283326696042207,"score_spread":0.16118045453896412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408621984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25466076,0.0002604341,0.734093,0.00035238618,0.00705149,0.0025833745,0.00006392733,0.00004433221,0.0008902952],"genre_scores_gemma":[0.8171756,0.000041099265,0.18235561,0.00007490559,0.00014535549,0.00017936592,0.0000011305667,0.000020254578,0.000006664394],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98904526,0.0045415256,0.005236039,0.0004744491,0.000305526,0.00039719237],"domain_scores_gemma":[0.46683386,0.5307086,0.0017602416,0.00048493565,0.00014269771,0.00006967287],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03011516,0.00021436746,0.0021510888,0.00024786894,0.00011206129,0.00002691038,0.0003947251,0.00034999728,0.000066796776],"category_scores_gemma":[0.6486881,0.00013991629,0.0005925834,0.0004200547,0.0002950005,0.000043410797,0.00022929728,0.00056731136,0.0000021243713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015185366,0.0015785606,0.07299276,0.00008678042,0.00024935734,0.0000060389234,0.00039018027,0.0000038407134,0.000018075238,0.29261756,0.0006632033,0.6298751],"study_design_scores_gemma":[0.005831965,0.00050842,0.0029488867,0.00058762915,0.00036063467,9.5020533e-7,0.0007430908,0.0010009866,0.00004246305,0.9855629,0.0022845387,0.00012753418],"about_ca_topic_score_codex":0.0000020405303,"about_ca_topic_score_gemma":0.00001498376,"teacher_disagreement_score":0.69294536,"about_ca_system_score_codex":0.00025514347,"about_ca_system_score_gemma":0.00030410747,"threshold_uncertainty_score":0.99870056},"labels":[],"label_agreement":null},{"id":"W4409015286","doi":"10.5539/ijsp.v14n1p24","title":"Comparing Two Independent Groups: Inferences About the Lower and Upper Tails of the Distribution of D = X − Y","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Combinatorics; Distribution (mathematics); Statistics; Mathematical analysis","score_opus":0.22760796069043857,"score_gpt":0.4903219808292206,"score_spread":0.2627140201387821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409015286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6799079,0.00008053804,0.3178293,0.0006332139,0.0007702028,0.00017314198,0.00039731167,0.0000016124361,0.00020675398],"genre_scores_gemma":[0.9189162,0.00005586901,0.08093884,0.000025784837,0.000046812096,0.0000020348837,9.389685e-7,0.0000023584046,0.000011116471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979783,0.00037618887,0.0010329457,0.000098492295,0.00044088665,0.00007313328],"domain_scores_gemma":[0.9852513,0.012972431,0.00074810535,0.00013741506,0.00085929205,0.000031472602],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002912889,0.000081026024,0.00032937236,0.000026647805,0.00004515853,0.000039424598,0.00031648812,0.00004291033,0.000029132523],"category_scores_gemma":[0.025883911,0.00004338275,0.00006624189,0.00006840904,0.0005108565,0.000044989123,0.00018742106,0.00024017048,7.578973e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017706095,0.00018500963,0.13604544,0.000103493316,0.00016307704,0.0000010091096,0.000113524125,0.000016621569,0.000037516722,0.8493735,0.00016883369,0.013614897],"study_design_scores_gemma":[0.0004716647,0.00006457322,0.22378433,0.00020359007,0.00007022391,0.000004935798,0.000029720766,0.0004591461,0.00021721137,0.77460235,0.0000618911,0.000030373298],"about_ca_topic_score_codex":0.00003342738,"about_ca_topic_score_gemma":0.000036188903,"teacher_disagreement_score":0.23900835,"about_ca_system_score_codex":0.000037018286,"about_ca_system_score_gemma":0.00009367271,"threshold_uncertainty_score":0.9823215},"labels":[],"label_agreement":null},{"id":"W4409067445","doi":"10.1007/s11590-025-02197-2","title":"Publisher Correction: A necessary condition for the guarantee of the superiorization method","year":2025,"lang":"en","type":"article","venue":"Optimization Letters","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computational intelligence; Computer science; Artificial intelligence","score_opus":0.17409348746357278,"score_gpt":0.49143962599326285,"score_spread":0.31734613852969007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409067445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000107739885,0.000012823795,0.97442806,0.017422918,0.0061428198,0.0009788375,0.000017085833,0.000041511536,0.00084819226],"genre_scores_gemma":[0.0030139277,0.000013876398,0.99150926,0.0038711806,0.00015739017,0.00019648352,0.000009761736,0.000022050797,0.0012060715],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998221,0.000638584,0.0005918389,0.0002082995,0.00021225751,0.00012805867],"domain_scores_gemma":[0.97317153,0.025872597,0.00029548505,0.00040169497,0.00024518667,0.000013479595],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018063418,0.000112127695,0.00025447545,0.000061561776,0.00021913605,0.00007480461,0.00028782312,0.00009986332,0.00014338232],"category_scores_gemma":[0.033514906,0.00006838211,0.00015202808,0.0005897199,0.00014573339,0.00014169305,0.00005167764,0.00013614305,6.00892e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018875812,0.00012217996,0.00044759945,0.00018072971,0.00023803623,2.2196181e-7,0.00022768087,0.35024443,0.00068357185,0.16366777,0.47328153,0.010717509],"study_design_scores_gemma":[0.0017595342,0.000045337143,0.0005605812,0.00018533849,0.0005454692,0.0000025935478,0.00021726545,0.69138724,0.0017127416,0.2987142,0.0046710726,0.0001986188],"about_ca_topic_score_codex":0.000006816623,"about_ca_topic_score_gemma":0.0000017078931,"teacher_disagreement_score":0.46861047,"about_ca_system_score_codex":0.00004162534,"about_ca_system_score_gemma":0.000050107406,"threshold_uncertainty_score":0.9746262},"labels":[],"label_agreement":null},{"id":"W4409095915","doi":"10.1016/j.annonc.2025.02.008","title":"Lessons from TROPiCS-04: ‘safety-first’ for success in late-stage clinical trials","year":2025,"lang":"en","type":"editorial","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Medicine; Tropics; Clinical trial; Stage (stratigraphy); Intensive care medicine; Internal medicine; Ecology","score_opus":0.8155101084363119,"score_gpt":0.7205218029517918,"score_spread":0.09498830548452009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409095915","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023355192,0.00039437323,0.04366511,0.011299312,0.9118225,0.0033136331,0.025016004,0.0000927467,0.0041627926],"genre_scores_gemma":[0.00007032909,0.006509478,0.37034255,0.000671135,0.61751026,0.00055527233,0.00042229143,0.00014471401,0.0037739528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9688917,0.015940214,0.011690546,0.0015993909,0.0009022523,0.00097593106],"domain_scores_gemma":[0.26099437,0.731816,0.004566077,0.0012426487,0.0011173751,0.00026352657],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06432695,0.0007037894,0.010267493,0.00039518872,0.00009819847,0.000044035238,0.0016540466,0.006632822,0.00063469046],"category_scores_gemma":[0.85966486,0.0006262877,0.0018911667,0.00037583822,0.00064213364,0.00007206612,0.000530316,0.002701517,0.00001908764],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005289094,0.001425873,0.000050901413,0.0008935389,0.0008762203,0.00004736477,0.000071037044,0.000011822468,0.000002179143,0.032976627,0.8934742,0.06488114],"study_design_scores_gemma":[0.0051291077,0.0013400753,0.00004108208,0.0005001354,0.00044285718,3.121752e-8,0.000013822705,0.00006706883,0.000045666584,0.4450306,0.5471,0.0002895218],"about_ca_topic_score_codex":0.0004000526,"about_ca_topic_score_gemma":0.001400717,"teacher_disagreement_score":0.79533786,"about_ca_system_score_codex":0.00016775691,"about_ca_system_score_gemma":0.002600208,"threshold_uncertainty_score":0.9996188},"labels":[],"label_agreement":null},{"id":"W4409109040","doi":"10.5539/ijsp.v14n1p29","title":"Comparing Two Independent Groups: Inferences About the Lower and Upper Tails of the Distribution of D = X − Y","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Distribution (mathematics); Combinatorics; Upper and lower bounds; Statistics; Mathematical analysis","score_opus":0.22760796069043857,"score_gpt":0.4903219808292206,"score_spread":0.2627140201387821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409109040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6799079,0.00008053804,0.3178293,0.0006332139,0.0007702028,0.00017314198,0.00039731167,0.0000016124361,0.00020675398],"genre_scores_gemma":[0.9189162,0.00005586901,0.08093884,0.000025784837,0.000046812096,0.0000020348837,9.389685e-7,0.0000023584046,0.000011116471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979783,0.00037618887,0.0010329457,0.000098492295,0.00044088665,0.00007313328],"domain_scores_gemma":[0.9852513,0.012972431,0.00074810535,0.00013741506,0.00085929205,0.000031472602],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002912889,0.000081026024,0.00032937236,0.000026647805,0.00004515853,0.000039424598,0.00031648812,0.00004291033,0.000029132523],"category_scores_gemma":[0.025883911,0.00004338275,0.00006624189,0.00006840904,0.0005108565,0.000044989123,0.00018742106,0.00024017048,7.578973e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017706095,0.00018500963,0.13604544,0.000103493316,0.00016307704,0.0000010091096,0.000113524125,0.000016621569,0.000037516722,0.8493735,0.00016883369,0.013614897],"study_design_scores_gemma":[0.0004716647,0.00006457322,0.22378433,0.00020359007,0.00007022391,0.000004935798,0.000029720766,0.0004591461,0.00021721137,0.77460235,0.0000618911,0.000030373298],"about_ca_topic_score_codex":0.00003342738,"about_ca_topic_score_gemma":0.000036188903,"teacher_disagreement_score":0.23900835,"about_ca_system_score_codex":0.000037018286,"about_ca_system_score_gemma":0.00009367271,"threshold_uncertainty_score":0.9823215},"labels":[],"label_agreement":null},{"id":"W4409368810","doi":"10.1002/sim.70049","title":"A Generalized Phase I/II Dose Optimization Trial Design With Multi‐Categorical and Multi‐Graded Outcomes","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Simon Fraser University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Categorical variable; Monotonic function; Benchmarking; Robustness (evolution); Computer science; Maximum tolerated dose; Optimal design; Clinical trial; Continuous variable; Reliability (semiconductor); Reliability engineering; Mathematical optimization; Medicine; Mathematics; Machine learning","score_opus":0.5347114705751628,"score_gpt":0.5995985752183284,"score_spread":0.0648871046431656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409368810","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020561283,0.000077128825,0.99397,0.00086601276,0.00074917806,0.0020389785,0.00009249491,0.00008173856,0.00006835194],"genre_scores_gemma":[0.006637603,0.00013358534,0.9917489,0.0004489562,0.00013247826,0.0001929787,0.000021625861,0.00004184213,0.00064198166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957371,0.0013295988,0.0014973476,0.0005644524,0.00048230842,0.0003892395],"domain_scores_gemma":[0.9596681,0.03919164,0.00033103337,0.00042377991,0.00019804151,0.0001873837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035831097,0.00035913833,0.0014037881,0.0002817375,0.00014286836,0.000026163076,0.00022304992,0.00021264334,0.00021387401],"category_scores_gemma":[0.12525445,0.00024275041,0.0000369579,0.0005311327,0.0005995711,0.00004435603,0.00010510023,0.00044920712,0.0000015389205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05786354,0.0056586936,0.0005736415,0.0005605763,0.00055923004,0.0004277707,0.0013430227,0.001324779,0.00018163635,0.8788407,0.010068171,0.04259825],"study_design_scores_gemma":[0.2666955,0.0031214773,0.00017558105,0.00020817848,0.0004924464,0.000004538228,0.0001217161,0.19418855,0.000047494363,0.5345702,0.000058322308,0.00031599408],"about_ca_topic_score_codex":0.000055825363,"about_ca_topic_score_gemma":0.000027867996,"teacher_disagreement_score":0.34427047,"about_ca_system_score_codex":0.00009320905,"about_ca_system_score_gemma":0.00013888645,"threshold_uncertainty_score":0.98990744},"labels":[],"label_agreement":null},{"id":"W4409393882","doi":"10.1093/ejcts/ezaf139","title":"Statistical primer: an introduction into the principles of Bayesian statistical analyses in clinical trials","year":2025,"lang":"en","type":"article","venue":"European Journal of Cardio-Thoracic Surgery","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Bayesian probability; Primer (cosmetics); Econometrics; Statistics; Computer science; Artificial intelligence; Mathematics; Chemistry","score_opus":0.6624310713212445,"score_gpt":0.6296678112620885,"score_spread":0.032763260059155974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409393882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06904715,0.0005445733,0.92315763,0.001612504,0.0036006346,0.00045086807,0.00008035191,0.00003512754,0.0014711439],"genre_scores_gemma":[0.464371,0.00031570074,0.5325262,0.00012376253,0.0025150154,0.0000051297984,0.0000064248475,0.00006489569,0.00007185613],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85929114,0.12609984,0.012070141,0.00066888257,0.0013052225,0.00056474615],"domain_scores_gemma":[0.75015503,0.24485782,0.0029665283,0.0009712627,0.00070590293,0.0003434688],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23914815,0.00036742495,0.0038310352,0.000619082,0.00010945005,0.00009853716,0.0006748289,0.00015139117,0.0002407132],"category_scores_gemma":[0.602062,0.000240241,0.0010838759,0.0008585906,0.00091555563,0.0001903187,0.00019252222,0.0013362359,0.000008441031],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040661576,0.0009983648,0.01671573,0.00042045538,0.0016438565,0.000829086,0.00037352156,0.00019271701,0.00038773095,0.082755,0.012622043,0.87899536],"study_design_scores_gemma":[0.0034897598,0.0018038079,0.28043422,0.0017839698,0.006315923,0.00029799412,0.002209763,0.0014705217,0.0039603617,0.6643274,0.03257445,0.0013318456],"about_ca_topic_score_codex":0.00000977959,"about_ca_topic_score_gemma":0.0000053092904,"teacher_disagreement_score":0.8776635,"about_ca_system_score_codex":0.000116780604,"about_ca_system_score_gemma":0.0006157819,"threshold_uncertainty_score":0.97967434},"labels":[],"label_agreement":null},{"id":"W4409472426","doi":"10.1016/j.cct.2025.107918","title":"Using Bayesian pre-trial simulations to optimize the design of adaptive clinical trials in childhood nephrotic syndrome","year":2025,"lang":"en","type":"article","venue":"Contemporary Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's College Hospital; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; ZOLL Medical Corporation","keywords":"Medicine; Nephrotic syndrome; Bayesian probability; Clinical trial; Research design; Clinical study design; Pediatrics; Intensive care medicine; Internal medicine; Statistics","score_opus":0.9070198397739502,"score_gpt":0.687451613104713,"score_spread":0.21956822666923714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409472426","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027055195,0.0003035861,0.9387333,0.0024945743,0.0064186472,0.02380896,0.00044715343,0.0001470145,0.0005916084],"genre_scores_gemma":[0.4845374,0.000058295696,0.5126195,0.0011251502,0.0011765686,0.00026674225,0.0000037317743,0.00007264629,0.00013998758],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6365946,0.30631775,0.051624473,0.0026208174,0.0016110198,0.0012313148],"domain_scores_gemma":[0.078488685,0.91066307,0.007232452,0.0024290874,0.00055596005,0.0006307662],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39768618,0.0007627102,0.012280946,0.0005377459,0.00022046347,0.0001483146,0.001646121,0.0014106891,0.00036753985],"category_scores_gemma":[0.93435115,0.0005166293,0.0031631703,0.0018087068,0.0009553132,0.00023551667,0.00064232876,0.0018766887,0.000022339273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5976932,0.029521389,0.011142072,0.0007366052,0.014285752,0.00045017342,0.001008543,0.028261868,0.0003191829,0.16792694,0.049693175,0.0989611],"study_design_scores_gemma":[0.10525163,0.0037943397,0.0039021522,0.0017952345,0.0017685108,0.0000045837846,0.00014682293,0.022691566,0.00007534152,0.85951984,0.00032407392,0.0007259249],"about_ca_topic_score_codex":0.000052261024,"about_ca_topic_score_gemma":0.000007412049,"teacher_disagreement_score":0.6915929,"about_ca_system_score_codex":0.00012089905,"about_ca_system_score_gemma":0.002488979,"threshold_uncertainty_score":0.9998857},"labels":[],"label_agreement":null},{"id":"W4409713431","doi":"10.1080/10543406.2025.2489292","title":"An improved biomarker-guided adaptive patient enrichment design for oncology trials","year":2025,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Amgen (Canada)","funders":"","keywords":"Biomarker; Adaptive design; Medicine; Oncology; Precision oncology; Internal medicine; Medical physics; Clinical trial; Cancer; Biology","score_opus":0.7704626813265696,"score_gpt":0.6589292886360004,"score_spread":0.11153339269056917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409713431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006573934,0.00020472718,0.99229455,0.00083841744,0.0027958842,0.0020047296,0.0009624454,0.00003552235,0.00020630454],"genre_scores_gemma":[0.022003176,0.00017359709,0.97634584,0.00091537513,0.00037863248,0.00008336629,0.0000035941698,0.000042584015,0.00005385722],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9879542,0.0056024366,0.0048319544,0.00041529827,0.0005888996,0.00060721487],"domain_scores_gemma":[0.8335169,0.16212574,0.00212055,0.00033526449,0.0013555803,0.000545962],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019905757,0.0003932901,0.0022692468,0.00028690463,0.00015570884,0.00008814558,0.00054073264,0.0003887094,0.0002802963],"category_scores_gemma":[0.18617314,0.0002925891,0.00043697946,0.00036380577,0.00034270855,0.00010150268,0.000100496494,0.0006220148,0.0000052327887],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01428659,0.003207978,0.000015020595,0.00031953794,0.001760967,0.00019315913,0.00016870479,0.000052623975,0.029433765,0.24392785,0.0688846,0.6377492],"study_design_scores_gemma":[0.0077820993,0.0060099796,0.00004293936,0.00013072311,0.0020705333,0.000044491597,0.00016150529,0.040623352,0.021426536,0.91175014,0.009620489,0.0003372083],"about_ca_topic_score_codex":0.00000293007,"about_ca_topic_score_gemma":6.801908e-7,"teacher_disagreement_score":0.6678223,"about_ca_system_score_codex":0.0004961561,"about_ca_system_score_gemma":0.0008048318,"threshold_uncertainty_score":0.9999526},"labels":[],"label_agreement":null},{"id":"W4409785689","doi":"10.2196/64114","title":"Real-Time, Risk-Based Clinical Trial Quality Management in China: Development of a Digital Monitoring Platform","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Clinical trial; Interim analysis; Computer science; Beijing; Warning system; Data mining; Quality (philosophy); Medical physics; Medicine; China; Pathology","score_opus":0.41007859764365107,"score_gpt":0.5959397820952466,"score_spread":0.1858611844515955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409785689","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86815524,0.0000038860926,0.09857576,0.000080751335,0.0011836,0.0021258423,0.00004561247,0.00016067213,0.029668603],"genre_scores_gemma":[0.063172184,0.00005555234,0.9360264,0.000063117484,0.00018830058,0.000244668,0.00000948492,0.000022983086,0.00021731916],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9898078,0.00047111773,0.007359886,0.00025451177,0.0016207519,0.0004859773],"domain_scores_gemma":[0.96693987,0.030597536,0.0013422696,0.00068715774,0.0001044514,0.00032873],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014683398,0.0003001977,0.0014025329,0.00026705742,0.000080396225,0.00006021794,0.00070827315,0.0005475104,0.00016105858],"category_scores_gemma":[0.061788544,0.00024310913,0.00028780775,0.0006057112,0.00033314584,0.00018599632,0.0004429561,0.000903886,0.0000460619],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015964147,0.0049579204,0.012165847,0.0039982,0.0007337247,0.000031691514,0.0022996191,0.000007995293,0.0000019049021,0.050615843,0.0022134318,0.90700966],"study_design_scores_gemma":[0.17670058,0.0011066571,0.055790514,0.004771252,0.00038255224,0.0000016194651,0.0026686213,0.013219315,0.00061556476,0.74080694,0.0025783808,0.0013580114],"about_ca_topic_score_codex":0.0000053949766,"about_ca_topic_score_gemma":0.000002130091,"teacher_disagreement_score":0.9056517,"about_ca_system_score_codex":0.00017568163,"about_ca_system_score_gemma":0.0005644585,"threshold_uncertainty_score":0.9913702},"labels":[],"label_agreement":null},{"id":"W4409875747","doi":"10.1007/s43678-025-00874-w","title":"CAEP 2024 Academic Symposium: adaptive platform trials in emergency medicine in Canada","year":2025,"lang":"en","type":"review","venue":"Canadian Journal of Emergency Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre de Recherche en Sciences Animales de Deschambault; Centre intégré de santé et de services sociaux de Chaudière-Appalaches; Health Sciences Centre; Centre Intégré de Santé et Services Sociaux de Chaudière-Appalache; Sunnybrook Health Science Centre; McGill University; Schwartz/Reisman Emergency Medicine Institute; University of British Columbia; University of Toronto; Canadian Patient Safety Institute; University of Alberta; Université Laval; University of Calgary","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Medicine; Emergency department; Emergency medicine; Medical emergency; Medical education; Family medicine; Psychiatry","score_opus":0.776912846446051,"score_gpt":0.6135651847488458,"score_spread":0.16334766169720516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409875747","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000074970067,0.92405635,0.00050936645,0.0020271416,0.060800888,0.0017407872,0.00036758996,0.0000060127495,0.010484355],"genre_scores_gemma":[0.000009907803,0.9888218,0.0020464982,0.00007977933,0.0050178193,0.00007777457,0.000013541316,0.00010352214,0.0038293672],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9718773,0.004387611,0.020451551,0.0007301535,0.0012910226,0.0012623848],"domain_scores_gemma":[0.9310799,0.057382274,0.0076905917,0.00086474844,0.0007252842,0.0022571573],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032762185,0.0010952388,0.013614941,0.002917449,0.00008741813,0.0000030206859,0.001798363,0.0010187393,0.031294696],"category_scores_gemma":[0.39220458,0.0007538597,0.00088421284,0.0034320548,0.00024423987,0.00012579208,0.000073329225,0.0048252186,0.0000088875395],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00009324468,0.000035751098,0.00029644268,0.020865688,0.00083775504,0.0011402325,0.00055076083,0.000005099256,7.4312527e-7,0.010058898,0.7712946,0.19482079],"study_design_scores_gemma":[0.0017137631,0.00046353636,0.00003163566,0.11248354,0.0034482027,0.00003394205,0.000613873,0.000009955767,2.5868056e-7,0.21189085,0.66862535,0.0006850986],"about_ca_topic_score_codex":0.8167503,"about_ca_topic_score_gemma":0.9806092,"teacher_disagreement_score":0.3594424,"about_ca_system_score_codex":0.0042295153,"about_ca_system_score_gemma":0.032241516,"threshold_uncertainty_score":0.9995931},"labels":[],"label_agreement":null},{"id":"W4409922211","doi":"10.1080/10543406.2025.2489286","title":"Application of complete N-of-1 trial design in bioequivalence-biosimilar drug development","year":2025,"lang":"en","type":"article","venue":"Journal of Biopharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Biosimilar; Bioequivalence; Drug development; Medicine; Drug; Drug approval; Clinical trial; Pharmacology; Mathematics; Computer science; Pharmacokinetics; Internal medicine","score_opus":0.5800350463900673,"score_gpt":0.5841014756488686,"score_spread":0.004066429258801296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409922211","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007964012,0.00016754898,0.9897691,0.00029508604,0.0007006316,0.0008006406,0.00017831435,0.000008433426,0.000116208495],"genre_scores_gemma":[0.117679186,0.00014984424,0.88193095,0.00010140948,0.00008674343,0.000012581813,0.0000011871036,0.00001580934,0.000022303611],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939011,0.0011429167,0.0037269846,0.00021731686,0.0007131448,0.00029855335],"domain_scores_gemma":[0.9566884,0.04088051,0.0014562171,0.0002398312,0.0005727604,0.00016227618],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0069377716,0.00021462764,0.0011940151,0.00032324746,0.000038375598,0.000014202492,0.00050119567,0.00015242053,0.00010087212],"category_scores_gemma":[0.032046795,0.00017934448,0.00014210738,0.00058865856,0.0004014851,0.000047673708,0.00011502498,0.00051180826,0.0000036580193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07441992,0.005575655,0.0017526153,0.0036354545,0.00096257514,0.00012439389,0.00056641124,0.00019218719,0.031409282,0.6004906,0.008825861,0.272045],"study_design_scores_gemma":[0.030276865,0.0007105383,0.0008894729,0.0005705548,0.00052169175,0.000006962426,0.00007829267,0.006395021,0.07027068,0.88773876,0.0022611523,0.0002799821],"about_ca_topic_score_codex":0.0000035015448,"about_ca_topic_score_gemma":0.000001334947,"teacher_disagreement_score":0.28724813,"about_ca_system_score_codex":0.0001375087,"about_ca_system_score_gemma":0.00042380928,"threshold_uncertainty_score":0.9761067},"labels":[],"label_agreement":null},{"id":"W4410101553","doi":"10.1016/j.cmpb.2025.108833","title":"Bayesian adaptive enrichment design in multi-arm clinical trials: The BayesAET package for R users","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Public Health Ontario; University of Toronto; Hospital for Sick Children; St. Paul's Hospital","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Bayesian probability; Computer science; Adaptive design; R package; Clinical trial; Artificial intelligence; Medicine; Programming language; Internal medicine","score_opus":0.8058341152996538,"score_gpt":0.6638759446691699,"score_spread":0.14195817063048388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410101553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019490338,0.00071661064,0.98981136,0.002292698,0.0022004463,0.004673328,0.00001443489,0.00006254883,0.000033649754],"genre_scores_gemma":[0.0022003164,0.0002309922,0.99535024,0.001029119,0.00045945446,0.0006463657,0.0000039047354,0.000029287832,0.000050327253],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9719624,0.022823164,0.0035070553,0.0008726904,0.00025861248,0.00057606644],"domain_scores_gemma":[0.7532448,0.24549699,0.00045394604,0.00054505427,0.00010171424,0.00015748016],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12372139,0.00035406125,0.0020954134,0.00028509166,0.00008788747,0.000070008275,0.00049039617,0.00037365165,0.000016225778],"category_scores_gemma":[0.08218156,0.00020903854,0.00027036498,0.0009169474,0.0007038375,0.000039570572,0.00025296386,0.00064474286,6.1546615e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006658047,0.0008766688,0.0019495864,0.00017182191,0.00017401813,0.0000127449275,0.000357148,0.0000014751764,0.000023680934,0.02011542,0.0011277416,0.9745239],"study_design_scores_gemma":[0.01053795,0.0020135816,0.0031544997,0.0008535219,0.00027733424,0.0000030890496,0.00031533977,0.09257638,0.00009787833,0.8856189,0.004253906,0.00029760267],"about_ca_topic_score_codex":0.00002131716,"about_ca_topic_score_gemma":0.000010255841,"teacher_disagreement_score":0.9742263,"about_ca_system_score_codex":0.00006916679,"about_ca_system_score_gemma":0.000097779746,"threshold_uncertainty_score":0.9255496},"labels":[],"label_agreement":null},{"id":"W4410169683","doi":"10.1111/aas.70044","title":"Adaptations and Heterogeneity of Treatment Effects in Platform Trials—Protocol for Two Methodological Studies","year":2025,"lang":"en","type":"article","venue":"Acta Anaesthesiologica Scandinavica","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Medicine; Protocol (science); Alternative medicine; Pathology","score_opus":0.8515623628999941,"score_gpt":0.6733801112062644,"score_spread":0.1781822516937297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410169683","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68192774,0.00036589068,0.061975256,0.0015076353,0.00035506947,0.25272802,0.00014511279,0.00020191395,0.0007933364],"genre_scores_gemma":[0.2509033,0.00009594562,0.60048664,0.00016377786,0.000041018513,0.14826638,0.0000015596898,0.000012800027,0.000028560657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943504,0.0030720413,0.0015568865,0.0005521561,0.00011946899,0.00034907597],"domain_scores_gemma":[0.79574317,0.2032327,0.0004975843,0.0003449573,0.0001044682,0.00007710199],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008137479,0.0003147934,0.0023060222,0.00016168806,0.00012260684,0.000016669976,0.00022276874,0.0002129071,0.0000161271],"category_scores_gemma":[0.18736245,0.00018386803,0.00030848995,0.00027564494,0.00040856696,0.00004370616,0.00011137737,0.00013667761,4.500465e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065425695,0.0016330054,0.025294904,0.0012359023,0.0008029543,0.00002901351,0.00030296983,0.000014303152,0.004030253,0.5503766,0.0009793283,0.40875816],"study_design_scores_gemma":[0.006329764,0.0034787955,0.020480512,0.00030181636,0.0002375869,0.0000014811516,0.0001235253,0.00019089037,0.002567896,0.96544844,0.00065465766,0.0001846097],"about_ca_topic_score_codex":0.00001991832,"about_ca_topic_score_gemma":0.000044324923,"teacher_disagreement_score":0.5385114,"about_ca_system_score_codex":0.00015918454,"about_ca_system_score_gemma":0.00006504622,"threshold_uncertainty_score":0.81948274},"labels":[],"label_agreement":null},{"id":"W4410278718","doi":"10.1016/j.jeph.2025.202994","title":"CO1.2 - G-computation for increasing performances of clinical trials with individual randomization and binary response","year":2025,"lang":"en","type":"article","venue":"Journal of Epidemiology and Population Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; The Quebec Population Health Research Network","funders":"","keywords":"Randomization; Binary number; Computation; Restricted randomization; Computer science; Clinical trial; Mathematics; Psychology; Medicine; Arithmetic; Algorithm; Internal medicine","score_opus":0.7986865989665263,"score_gpt":0.711800990182908,"score_spread":0.08688560878361828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410278718","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6277216,0.0005927325,0.367937,0.0030629276,0.00026145633,0.0004023405,0.000014489472,0.0000040442983,0.0000034142],"genre_scores_gemma":[0.45871395,0.00047062678,0.5401486,0.00052189495,0.00012951191,0.000003575023,0.000003960848,0.000004138959,0.0000037254772],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95690477,0.036322504,0.006286962,0.0001859593,0.00012859046,0.00017120293],"domain_scores_gemma":[0.57327604,0.42201763,0.004343726,0.00006372685,0.00020395346,0.00009491678],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2478156,0.00009189231,0.0020945556,0.0002029343,0.00011974522,0.000005769017,0.000044352066,0.00018637226,0.0000039035685],"category_scores_gemma":[0.5911385,0.000059434275,0.00011810472,0.00011584151,0.00016094798,0.0000913476,0.000015585185,0.00023076526,2.9742075e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.121780284,0.00015977876,0.62642,0.00087904854,0.00032254515,9.522413e-7,0.00025020353,0.0005121715,0.000009097119,0.055918936,0.0013897714,0.19235718],"study_design_scores_gemma":[0.007786636,0.0015442776,0.4697568,0.00043231196,0.0001945506,0.000019609191,0.00006297043,0.005209503,0.0000028723284,0.5148721,0.000072007155,0.000046372446],"about_ca_topic_score_codex":0.000017287413,"about_ca_topic_score_gemma":0.0000028461552,"teacher_disagreement_score":0.45895314,"about_ca_system_score_codex":0.000017217655,"about_ca_system_score_gemma":0.00022711049,"threshold_uncertainty_score":0.77453214},"labels":[],"label_agreement":null},{"id":"W4410301087","doi":"10.3390/e27050515","title":"Comparing Singlet Testing Schemes","year":2025,"lang":"en","type":"article","venue":"Entropy","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Perimeter Institute","funders":"Engineering and Physical Sciences Research Council; Institut Périmètre de physique théorique; Industry Canada; Government of Canada; UK Research and Innovation","keywords":"Statistical physics; Singlet state; Computer science; Physics; Mathematics; Quantum mechanics","score_opus":0.6836222503670467,"score_gpt":0.5744016413515077,"score_spread":0.10922060901553898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410301087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043261927,0.00005446448,0.90647805,0.0004546079,0.0009213132,0.00024475978,0.0000061831797,0.00028285105,0.04829583],"genre_scores_gemma":[0.23906675,9.4575e-7,0.7601222,0.0001792339,0.00015072408,0.000008102028,1.713507e-7,0.0000100242305,0.00046188582],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986782,0.000257811,0.00047296236,0.00021207811,0.00015381946,0.00022509278],"domain_scores_gemma":[0.9572971,0.042190213,0.00010470634,0.00028464105,0.00007073054,0.000052619056],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011170694,0.00010562425,0.00036820068,0.000046399393,0.000083804625,0.00004471704,0.00018326116,0.0000635967,0.0001743205],"category_scores_gemma":[0.18394698,0.00009314312,0.00006071898,0.00024535833,0.000076046264,0.000025446509,0.00012177191,0.0001982396,0.00005142785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020789486,0.00008716786,0.0136535885,0.00008424197,0.00004089179,0.0000063658917,0.000016257134,0.0000034120876,0.0013794686,0.96653366,0.0044008833,0.013773283],"study_design_scores_gemma":[0.0005289024,0.00002278666,0.0015390315,0.00016082756,0.000056295306,7.498309e-7,0.000014858753,0.002625256,0.0033045495,0.98939294,0.002259083,0.00009474596],"about_ca_topic_score_codex":0.0000032061985,"about_ca_topic_score_gemma":4.680602e-7,"teacher_disagreement_score":0.19580482,"about_ca_system_score_codex":0.00004044858,"about_ca_system_score_gemma":0.00003301352,"threshold_uncertainty_score":0.822927},"labels":[],"label_agreement":null},{"id":"W4410319524","doi":"10.1101/2025.05.08.652548","title":"α-Synuclein purification significantly impacts seed amplification assay performance and consistency","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; University of Toronto; McGill University","funders":"Canadian Institutes of Health Research; Parkinson Canada; McGill University","keywords":"Consistency (knowledge bases); Statistics; Chemistry; Biology; Mathematics; Computer science; Artificial intelligence","score_opus":0.16730252429082748,"score_gpt":0.3908862759069043,"score_spread":0.2235837516160768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410319524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8390938,0.00071231695,0.14699163,0.0012442992,0.0034488859,0.0048484555,0.0018478408,0.0014616802,0.00035107878],"genre_scores_gemma":[0.64973277,0.000472558,0.34901363,0.00013378957,0.00026792576,0.000277398,3.5786388e-7,0.00008068455,0.000020878415],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99427295,0.0012469104,0.0017879017,0.0014651463,0.00060604635,0.00062106864],"domain_scores_gemma":[0.98522466,0.009972797,0.0012854321,0.0021795745,0.00093222223,0.0004052858],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0064052213,0.0007025713,0.0013003176,0.00032969445,0.00027004335,0.00032076798,0.0006874942,0.0010238828,0.000057357724],"category_scores_gemma":[0.04794441,0.00072042627,0.00018628976,0.00057933043,0.00037926226,0.00015484089,0.0004769761,0.0012082634,0.00004847097],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004262085,0.0012635625,0.02788571,0.012427446,0.0011438199,0.000038283084,0.00007785501,0.000020566144,0.7225648,0.23087996,0.0030422604,0.00022952878],"study_design_scores_gemma":[0.0028530825,0.0003173917,0.62065023,0.0049741496,0.00214926,8.01467e-8,0.000020785976,0.0049493923,0.34167004,0.016610859,0.0022298684,0.0035748598],"about_ca_topic_score_codex":0.000021003192,"about_ca_topic_score_gemma":0.0000010314724,"teacher_disagreement_score":0.59276456,"about_ca_system_score_codex":0.00029757936,"about_ca_system_score_gemma":0.00078803016,"threshold_uncertainty_score":0.99952465},"labels":[],"label_agreement":null},{"id":"W4410551540","doi":"10.1016/j.cjco.2025.05.006","title":"Win Ratio in Biomedical Science: A Bibliometric Analysis","year":2025,"lang":"en","type":"review","venue":"CJC Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; McMaster University; University of Toronto; Health Sciences Centre; University of Ottawa; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Sunnybrook Research Institute","keywords":"Bibliometrics; Data science; Computer science; Library science","score_opus":0.73229820276352,"score_gpt":0.7017379755273739,"score_spread":0.030560227236146043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410551540","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.432383e-7,0.9405529,0.039515007,0.000068978276,0.0008857552,0.0033342226,0.00028967674,0.00004723576,0.015305285],"genre_scores_gemma":[5.565382e-7,0.6752685,0.3230221,0.00004469894,0.00010833217,0.0002932164,0.000013705852,0.000021180458,0.001227708],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923763,0.0019920312,0.0027478707,0.0011659729,0.00114824,0.00056955795],"domain_scores_gemma":[0.8960244,0.10118422,0.0007772328,0.001484444,0.0002047381,0.00032496767],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","insufficient_payload"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.024063462,0.0004153557,0.006966772,0.14862393,0.00011417027,0.0006519296,0.0043104882,0.0005537792,0.0015682301],"category_scores_gemma":[0.39596638,0.0003006214,0.0007098381,0.57717943,0.00072026404,0.00016819307,0.0024210557,0.0007790672,0.00014489066],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004654952,0.00021190726,0.0000065773434,0.0062024607,0.00042243014,0.000033801538,0.000007816317,4.5917925e-8,5.4700426e-8,0.022888709,0.0028553607,0.96736616],"study_design_scores_gemma":[0.0007158239,0.00008326102,0.00005533404,0.013029373,0.00818646,0.000003847856,0.000009456321,0.00006791462,6.957721e-7,0.33542296,0.64183044,0.00059441355],"about_ca_topic_score_codex":0.000046445417,"about_ca_topic_score_gemma":0.000010682792,"teacher_disagreement_score":0.9667718,"about_ca_system_score_codex":0.00032599445,"about_ca_system_score_gemma":0.0027521343,"threshold_uncertainty_score":0.99994457},"labels":[],"label_agreement":null},{"id":"W4410783369","doi":"10.1002/sim.70121","title":"Integrating Complex Selection Rules Into the Latent Overlapping Group Lasso for the Construction of Coherent Prediction Models","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Réseau Québécois de Recherche sur les Médicaments; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Interpretability; Feature selection; Lasso (programming language); Latent variable; Computer science; Variable (mathematics); Machine learning; Predictive modelling; Selection (genetic algorithm); Elastic net regularization; Proxy (statistics); Artificial intelligence; Data mining; Mathematics","score_opus":0.3549779274483894,"score_gpt":0.5195250836602353,"score_spread":0.1645471562118459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410783369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017327669,0.000090592715,0.9936487,0.0012442628,0.0012285558,0.0012066262,0.00022489423,0.000035650508,0.0005879289],"genre_scores_gemma":[0.063801266,0.00016751864,0.9353432,0.00015692723,0.00024855082,0.00018471769,0.000024926516,0.000016833961,0.000056031487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997416,0.0005339423,0.0012760274,0.00024752604,0.00032825457,0.00019822855],"domain_scores_gemma":[0.9372635,0.06172373,0.00042314586,0.00024909413,0.00031096296,0.000029589093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0044293213,0.00016460838,0.00053541316,0.000105580155,0.00020598757,0.000016445169,0.00021695225,0.00010396756,0.00006250115],"category_scores_gemma":[0.049777884,0.00009121151,0.000051338193,0.00033478587,0.0006386097,0.000035509933,0.00006017791,0.00037989952,4.106452e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012524184,0.000050961567,0.00049719785,0.00029274906,0.000105953695,2.9544108e-7,0.00070895575,0.00019084815,0.000541309,0.9333298,0.0041648727,0.05999177],"study_design_scores_gemma":[0.00093925395,0.00017503547,0.0014478012,0.00044692814,0.00019336097,0.000001236671,0.0009281923,0.2572146,0.000047387526,0.73833895,0.00021546187,0.000051777395],"about_ca_topic_score_codex":0.00026563683,"about_ca_topic_score_gemma":0.00033430892,"teacher_disagreement_score":0.25702375,"about_ca_system_score_codex":0.00015049102,"about_ca_system_score_gemma":0.00005535225,"threshold_uncertainty_score":0.95822626},"labels":[],"label_agreement":null},{"id":"W4410805241","doi":"10.1200/jco.2025.43.16_suppl.e19521","title":"Concordance between blinded independent central review committee and physician-assessed responses: Analyses based on a real-world external control arm in relapsed/refractory multiple myeloma using International Myeloma Working Group data.","year":2025,"lang":"en","type":"article","venue":"Journal of Clinical Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"EVERSANA (Canada)","funders":"Regeneron Pharmaceuticals","keywords":"Medicine; Multiple myeloma; Concordance; Internal medicine; Oncology","score_opus":0.6840623360066128,"score_gpt":0.6438534735256439,"score_spread":0.04020886248096889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410805241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6720893,0.001926188,0.3049367,0.0067909975,0.008184741,0.0022670352,0.00034866418,0.00007577238,0.0033806101],"genre_scores_gemma":[0.72921985,0.0010814542,0.26372728,0.004514583,0.0013830961,0.000009911372,0.0000044195594,0.000032617332,0.000026778884],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98063743,0.009536961,0.007487709,0.0007461355,0.0010478479,0.0005439449],"domain_scores_gemma":[0.76387084,0.22998364,0.004712346,0.00073927676,0.00037222827,0.00032167175],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.026232462,0.00040233252,0.0040957388,0.00054679497,0.00009512972,0.00006976484,0.0013926666,0.0005228708,0.00008323786],"category_scores_gemma":[0.20279089,0.00032905932,0.0005490225,0.0006171529,0.00049180526,0.00021255705,0.00034854884,0.0028637738,0.0000023758969],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02674631,0.006620312,0.5088454,0.00063012895,0.0016141515,0.0014798007,0.000044124765,0.0001471749,0.00046780484,0.0055280593,0.0013178173,0.44655892],"study_design_scores_gemma":[0.044079337,0.0033735998,0.79284596,0.01745523,0.0024047168,0.000022697406,0.00008339878,0.022907501,0.000075684286,0.10940685,0.0067058397,0.00063916517],"about_ca_topic_score_codex":0.000066110726,"about_ca_topic_score_gemma":0.00026191768,"teacher_disagreement_score":0.44591975,"about_ca_system_score_codex":0.00057316566,"about_ca_system_score_gemma":0.0015205396,"threshold_uncertainty_score":0.99991614},"labels":[],"label_agreement":null},{"id":"W4410807028","doi":"10.1016/j.jacadv.2025.101815","title":"Reply","year":2025,"lang":"en","type":"letter","venue":"JACC Advances","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology","score_opus":0.5085525428455807,"score_gpt":0.5990865869183026,"score_spread":0.09053404407272192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410807028","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.774582e-7,0.0007079915,0.09249485,0.81612736,0.0044394876,0.000611337,0.00030023177,0.0003266315,0.084991336],"genre_scores_gemma":[1.2077848e-7,0.00018608065,0.5007366,0.46867597,0.0046471325,0.00006240714,0.000007141218,0.00003235699,0.02565223],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99655837,0.00072043505,0.001080177,0.00070216437,0.0005175302,0.00042131747],"domain_scores_gemma":[0.8910464,0.1073412,0.00049287215,0.00095316116,0.00012260437,0.000043739346],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012500946,0.0003628797,0.0011897183,0.00010564505,0.00007016253,0.000050994906,0.0006313921,0.0007192892,0.0008678504],"category_scores_gemma":[0.15198952,0.00029354106,0.00028930506,0.00021647658,0.00017197024,0.00007607034,0.00017496072,0.0020332201,0.00012345416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000137851885,0.000018013432,0.0000045227566,0.0007741142,0.00005698897,0.00013676852,0.000006194132,1.16003925e-7,5.4107255e-7,0.0076839477,0.95520824,0.03609675],"study_design_scores_gemma":[0.00011824555,0.000022711363,9.753822e-7,0.00020199784,0.00007796423,0.000001463163,0.0000025759334,0.0000015296436,0.000035215777,0.49691364,0.5024651,0.00015852584],"about_ca_topic_score_codex":0.000003526313,"about_ca_topic_score_gemma":7.3207127e-7,"teacher_disagreement_score":0.4892297,"about_ca_system_score_codex":0.00005948624,"about_ca_system_score_gemma":0.00009360024,"threshold_uncertainty_score":0.99995166},"labels":[],"label_agreement":null},{"id":"W4410876964","doi":"10.1080/19420862.2025.2512217","title":"Does one model fit all mAbs? An evaluation of population pharmacokinetic models","year":2025,"lang":"en","type":"article","venue":"mAbs","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"","keywords":"Pharmacokinetics; Population; Population pharmacokinetics; Computer science; Computational biology; Medicine; Biology; Pharmacology","score_opus":0.8192363584553051,"score_gpt":0.6473883407274934,"score_spread":0.17184801772781166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410876964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20639296,0.00003502378,0.7874925,0.0009794916,0.00062798714,0.0010915556,0.00008792792,0.00010287102,0.003189688],"genre_scores_gemma":[0.59132373,0.0000105903255,0.40816504,0.00013336448,0.0000567075,0.000048354974,0.0000091249985,0.000013557686,0.00023956201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972606,0.00078662974,0.0008296518,0.0002999547,0.0006578586,0.00016531513],"domain_scores_gemma":[0.99453616,0.004395595,0.00023497731,0.0004635429,0.00030877665,0.000060961676],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043884595,0.00013367887,0.00041245075,0.00010170976,0.00003563363,0.000018805815,0.0001914675,0.00012712943,0.00034269242],"category_scores_gemma":[0.012199234,0.000094515555,0.000082544364,0.00015993357,0.000043594446,0.00012435914,0.00006727426,0.00013327281,0.0000053853587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026760547,0.0008802761,0.00012098699,0.0005028339,0.00018592077,5.9068657e-7,0.00022869273,0.10953493,0.0030831904,0.7743369,0.00089646195,0.109961666],"study_design_scores_gemma":[0.00061938947,0.000018861729,0.00023679706,0.000052449745,0.00030048864,5.0236512e-8,0.000005830458,0.48044157,0.0007619905,0.51749927,0.000005129597,0.000058174308],"about_ca_topic_score_codex":0.000033356908,"about_ca_topic_score_gemma":0.0000116946085,"teacher_disagreement_score":0.38493076,"about_ca_system_score_codex":0.00008179908,"about_ca_system_score_gemma":0.00004382766,"threshold_uncertainty_score":0.9961214},"labels":[],"label_agreement":null},{"id":"W4410975707","doi":"10.1093/jncics/pkaf053","title":"INTEGRATE pooled phase 2/3 results are robust to postprogression switching and the winner’s curse","year":2025,"lang":"en","type":"article","venue":"JNCI Cancer Spectrum","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Medical Research Council; National Health and Medical Research Council; Cancer Australia; Canadian Cancer Society; Medical Research Council; Australian Government; Bayer","keywords":"Censoring (clinical trials); Medicine; Pooling; Bayesian probability; Hazard ratio; Statistics; Confidence interval; Econometrics; Internal medicine; Mathematics; Artificial intelligence; Computer science","score_opus":0.29948855941522173,"score_gpt":0.5622787959171068,"score_spread":0.2627902365018851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410975707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31200257,0.0022055316,0.39264652,0.26238865,0.009085885,0.0052991523,0.00079611695,0.000656269,0.014919299],"genre_scores_gemma":[0.642263,0.000409158,0.34625584,0.0055480027,0.0015580612,0.00042691192,0.0000029722557,0.000087155386,0.003448876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99715173,0.0006520351,0.0009101792,0.00055847375,0.00031890158,0.00040868067],"domain_scores_gemma":[0.98544,0.013280627,0.00036661336,0.0006552098,0.0000929322,0.00016458896],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032125318,0.000266642,0.00074360415,0.00010780423,0.00022108974,0.00013324873,0.0003765079,0.00013495174,0.000085437925],"category_scores_gemma":[0.0407914,0.00015737694,0.00012423919,0.0004987523,0.0001844167,0.00005938202,0.0002579355,0.00055440806,0.000015785434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02320649,0.0007239271,0.000865358,0.00043188612,0.00060104084,0.00010187585,0.0018310451,0.000056039473,0.00066954765,0.63184214,0.057611786,0.28205886],"study_design_scores_gemma":[0.011776168,0.00019661876,0.0007589174,0.001465027,0.0003368081,0.0000034741097,0.0003545168,0.0020333438,0.0036752943,0.9767329,0.0023748376,0.00029206483],"about_ca_topic_score_codex":0.00024741006,"about_ca_topic_score_gemma":0.00028816282,"teacher_disagreement_score":0.34489077,"about_ca_system_score_codex":0.00014441746,"about_ca_system_score_gemma":0.00010413361,"threshold_uncertainty_score":0.96728843},"labels":[],"label_agreement":null},{"id":"W4411133310","doi":"10.1186/s12874-025-02593-3","title":"Comparison of total event analysis and first event analysis in relation to heterogeneity in cardiovascular trials","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; Impact; McMaster University; Population Health Research Institute","funders":"","keywords":"Event (particle physics); Cardiovascular event; Clinical trial; Medicine; Statistics; Internal medicine; Mathematics; Myocardial infarction","score_opus":0.8918162979523403,"score_gpt":0.7417101097785189,"score_spread":0.15010618817382138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411133310","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35205215,0.0005996645,0.64595324,0.0004905792,0.0001179248,0.0007015859,0.000015517506,0.00000879506,0.00006051185],"genre_scores_gemma":[0.48997986,0.00011638127,0.50965774,0.00002227096,0.00004374997,0.00014216448,0.0000035000774,0.000007987918,0.000026311618],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.853228,0.1373876,0.0047453907,0.0011171546,0.0027291693,0.0007927273],"domain_scores_gemma":[0.48311284,0.51512617,0.00027797322,0.00084269914,0.00027024248,0.00037006845],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31925398,0.00020651631,0.005450489,0.0034361351,0.00006566943,0.000017099537,0.00044131256,0.00064101035,0.00040995085],"category_scores_gemma":[0.8924835,0.0001705852,0.0012248445,0.008335308,0.00046095075,0.000029178356,0.00063074945,0.0010269923,0.0000038400726],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020879686,0.0012311368,0.84699917,0.0009892848,0.012831553,0.000047716636,0.0008023259,0.010882496,0.00016920737,0.028190067,0.00017964486,0.09558944],"study_design_scores_gemma":[0.0026312303,0.00032737636,0.7121949,0.00028899076,0.0044542486,0.0000011289972,0.0003600953,0.043406602,0.0014995836,0.23453513,0.00008512888,0.0002155793],"about_ca_topic_score_codex":0.0013597156,"about_ca_topic_score_gemma":0.011894126,"teacher_disagreement_score":0.5732295,"about_ca_system_score_codex":0.00024277087,"about_ca_system_score_gemma":0.00043342597,"threshold_uncertainty_score":0.7009713},"labels":[],"label_agreement":null},{"id":"W4411439860","doi":"10.1007/978-3-662-69359-9_189","title":"E-values (E for Expectation) in Hypothesis Testing","year":2025,"lang":"en","type":"book-chapter","venue":"International Encyclopedia of Statistical Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Psychology; Econometrics; Statistics; Mathematics; Computer science","score_opus":0.3553849541450152,"score_gpt":0.5088764397267439,"score_spread":0.1534914855817287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411439860","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003665251,0.000013290897,0.22261097,0.00020942926,0.0011378541,0.00063957204,0.0014842119,0.000036091096,0.77383196],"genre_scores_gemma":[0.00047321653,0.000070760885,0.93301827,0.00006672271,0.00026778202,0.00008149774,0.0000061421265,0.000030325944,0.0659853],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959664,0.00006142365,0.0016426054,0.0007697067,0.0012146008,0.000345275],"domain_scores_gemma":[0.8477604,0.15040289,0.00054659456,0.00029247324,0.0008750053,0.00012268849],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026590575,0.00030112072,0.00079208927,0.00048674256,0.000077727374,0.00004675044,0.0010374738,0.00021258461,0.0006504674],"category_scores_gemma":[0.4164,0.00028236987,0.000120515266,0.00020217098,0.0012636066,0.000122011785,0.00023903968,0.00032022924,0.000016360122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005805131,0.000063075735,0.00008135577,0.0001338975,0.00002779296,0.000009187633,0.00003823727,0.0000030708056,0.00001910035,0.9053612,0.0021094573,0.0920956],"study_design_scores_gemma":[0.00041820738,0.000100717756,0.0007409871,0.00058892893,0.000066859386,0.0000016976425,0.000012858697,0.0011794509,0.000046838933,0.9933561,0.0032264583,0.00026089055],"about_ca_topic_score_codex":0.00003609643,"about_ca_topic_score_gemma":0.00002137335,"teacher_disagreement_score":0.7104073,"about_ca_system_score_codex":0.0002693669,"about_ca_system_score_gemma":0.0006319451,"threshold_uncertainty_score":0.99996287},"labels":[],"label_agreement":null},{"id":"W4411505827","doi":"10.1093/biomtc/ujaf073","title":"Design of platform trials with a change in the control treatment arm","year":2025,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Frequentist inference; Type I and type II errors; Control (management); Conditional probability; Statistical power; Computer science; Power (physics); Statistics; Mathematics; Bayesian probability; Artificial intelligence; Bayesian inference","score_opus":0.8586986399465512,"score_gpt":0.6110839896227614,"score_spread":0.2476146503237897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411505827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00539376,0.00047831642,0.98813206,0.00065819774,0.00034555205,0.0038352506,0.00013971275,0.000033441887,0.000983714],"genre_scores_gemma":[0.30878124,0.00019476676,0.68993396,0.00036591195,0.00012278794,0.000498108,0.0000010263843,0.00001578848,0.000086420165],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99675876,0.0013811026,0.0010656925,0.00020900824,0.00036396793,0.00022146318],"domain_scores_gemma":[0.79818857,0.2009708,0.00035503908,0.0003710877,0.00008199713,0.000032510598],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012850553,0.0001583175,0.0010580185,0.0009333649,0.000028738408,0.000024383267,0.00027517322,0.00013598337,0.00004813238],"category_scores_gemma":[0.12269376,0.00007703288,0.00011217612,0.004330538,0.000101965394,0.00002944119,0.000020123764,0.00009445944,0.0000035468656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003834874,0.0049241325,0.0028666812,0.00040259233,0.0008820963,0.000060034436,0.0014883677,0.000008444417,0.00035221153,0.38408944,0.0012248001,0.59986633],"study_design_scores_gemma":[0.015994117,0.004179534,0.003684591,0.00024753643,0.0009332497,0.000003275072,0.00027552395,0.0011395654,0.0026534146,0.9694498,0.0011691063,0.00027027904],"about_ca_topic_score_codex":0.000051018385,"about_ca_topic_score_gemma":0.0000054443476,"teacher_disagreement_score":0.5995961,"about_ca_system_score_codex":0.00009942469,"about_ca_system_score_gemma":0.00008232087,"threshold_uncertainty_score":0.8846962},"labels":[],"label_agreement":null},{"id":"W4411654307","doi":"10.1093/biomtc/ujaf074","title":"Power calculation for cross-sectional stepped wedge cluster randomized trials with a time-to-event endpoint","year":2025,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; Claude Pepper Older Americans Independence Center, Wake Forest School of Medicine; National Institute on Aging; National Institutes of Health; Georgia Clinical and Translational Science Alliance","keywords":"CRTS; Sample size determination; Context (archaeology); Computer science; Statistics; Mathematics","score_opus":0.41889502217972463,"score_gpt":0.574672411786123,"score_spread":0.15577738960639842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411654307","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00832228,0.000047128553,0.98130226,0.0005161872,0.0012818824,0.006327925,0.00040654233,0.000110789275,0.0016850203],"genre_scores_gemma":[0.01733142,0.000004295097,0.9674325,0.0005954091,0.0003091515,0.00089787226,0.00002142111,0.000050877577,0.013357027],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939363,0.0021147958,0.0023796286,0.0005561427,0.00064152194,0.00037159034],"domain_scores_gemma":[0.7574495,0.24077359,0.0006040124,0.00040588007,0.0006087107,0.00015827632],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03171262,0.00027170702,0.0019467796,0.0014262944,0.00013074097,0.00017743997,0.0002517553,0.00031237426,0.0009885837],"category_scores_gemma":[0.5591775,0.00018708465,0.00063371257,0.0030391102,0.00016900957,0.00005708572,0.00011918309,0.0001595638,0.00012907598],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.62569684,0.0022561313,0.0020128444,0.0010898183,0.003500546,0.000011150001,0.00017093832,0.00019954427,0.0013805714,0.23626782,0.10555893,0.021854844],"study_design_scores_gemma":[0.30586016,0.0005892481,0.006413018,0.00014939893,0.0007462008,0.0000030143046,0.000009206094,0.00434937,0.0015504116,0.6679866,0.0117382975,0.0006050862],"about_ca_topic_score_codex":0.000003962265,"about_ca_topic_score_gemma":5.105528e-7,"teacher_disagreement_score":0.52746487,"about_ca_system_score_codex":0.0002081639,"about_ca_system_score_gemma":0.0001532326,"threshold_uncertainty_score":0.99992466},"labels":[],"label_agreement":null},{"id":"W4411706285","doi":"10.1093/humupd/dmaf016","title":"Bias busters: using the right risk-of-bias tools","year":2025,"lang":"en","type":"article","venue":"Human Reproduction Update","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Information bias; Medicine; Psychology; Selection bias; Statistics; Mathematics","score_opus":0.7018083221095339,"score_gpt":0.5619299593600996,"score_spread":0.13987836274943433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411706285","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72483885,0.00024725276,0.25400177,0.0030997593,0.005700162,0.0018870755,0.00013843007,0.00032362502,0.009763053],"genre_scores_gemma":[0.16977338,0.00010912589,0.8205648,0.00036428653,0.0019137884,0.00005409846,0.00000848688,0.00006761926,0.0071443873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957878,0.0018472108,0.0011870558,0.00063564663,0.00031461453,0.00022769996],"domain_scores_gemma":[0.98631203,0.010709987,0.00083174545,0.0018327046,0.0002703146,0.000043214077],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008874856,0.00018462286,0.00053283945,0.00011403163,0.00034013498,0.00008605661,0.00034759328,0.0001195799,0.00064191286],"category_scores_gemma":[0.10084495,0.00012335993,0.00019689661,0.00045110294,0.0003606955,0.00009423129,0.0001643833,0.00038975247,0.000033821987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019645921,0.00044138468,0.0018280543,0.0004336259,0.0006422259,0.000008048344,0.0004119426,0.0001478016,0.0034130083,0.92259276,0.027896397,0.04198828],"study_design_scores_gemma":[0.00043489342,0.00003590131,0.00074630266,0.00012697859,0.00040842802,0.000005520291,0.00007846226,0.0001496762,0.024393905,0.960006,0.013461694,0.0001522602],"about_ca_topic_score_codex":0.00002423838,"about_ca_topic_score_gemma":0.0000054214133,"teacher_disagreement_score":0.56656307,"about_ca_system_score_codex":0.000050725925,"about_ca_system_score_gemma":0.000045742087,"threshold_uncertainty_score":0.906729},"labels":[],"label_agreement":null},{"id":"W4411721164","doi":"10.1101/2025.06.24.661262","title":"Generation of virtual populations for quantitative systems pharmacology through advanced sampling methods","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Pfizer","keywords":"Sampling (signal processing); Systems pharmacology; Computer science; Pharmacology; Computational biology; Medicine; Medical physics; Data science; Biology; Drug; Telecommunications","score_opus":0.643959710657186,"score_gpt":0.5826955811956139,"score_spread":0.061264129461572114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411721164","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021286929,0.0006435222,0.96125597,0.00012449687,0.010634197,0.0031276457,0.0026763382,0.00023955246,0.000011342885],"genre_scores_gemma":[0.036355324,0.000096436765,0.96112573,0.00011602888,0.0007967638,0.0013953192,0.0000010698637,0.00010202538,0.000011290077],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9935231,0.0022734555,0.002268296,0.0011000846,0.0003508556,0.00048419164],"domain_scores_gemma":[0.96687424,0.028596472,0.00176863,0.0010149914,0.001607899,0.0001377658],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0051678824,0.0005653536,0.0018532004,0.00024756204,0.00019770481,0.00008071659,0.00057019334,0.00083554885,0.00003166169],"category_scores_gemma":[0.05511736,0.0005952565,0.00036065746,0.00049564947,0.00021245732,0.0001284491,0.00040235673,0.00070389424,0.000003055171],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014504546,0.00021974114,0.000027206306,0.001639693,0.00044854422,0.0000014136693,0.000024833951,0.0025508779,0.4218825,0.57235885,0.0006796019,0.000021675432],"study_design_scores_gemma":[0.0053453133,0.0010147416,0.00053146883,0.0025603813,0.004235962,1.7905556e-8,0.000054777167,0.06711967,0.8491599,0.062124252,0.005340943,0.0025125407],"about_ca_topic_score_codex":0.000022164631,"about_ca_topic_score_gemma":0.0000010547001,"teacher_disagreement_score":0.5102346,"about_ca_system_score_codex":0.00026760504,"about_ca_system_score_gemma":0.0005929175,"threshold_uncertainty_score":0.9996499},"labels":[],"label_agreement":null},{"id":"W4411734450","doi":"10.1007/978-3-031-87083-5_27","title":"Simple Statistical Tests and P Values","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Simple (philosophy); Statistics; Mathematics; Computer science; Philosophy; Epistemology","score_opus":0.5200463516005565,"score_gpt":0.5776289361878528,"score_spread":0.05758258458729637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411734450","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010391876,0.00006666655,0.22894171,0.00012520631,0.00027692178,0.00040512008,0.00069273607,0.00014368672,0.7693469],"genre_scores_gemma":[0.000010518945,0.00007733261,0.5550346,0.00025169857,0.00017605025,0.0000073548176,0.0000070359824,0.00003914351,0.4443963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99756575,0.00015700066,0.0010263032,0.00060088316,0.00038802478,0.00026204548],"domain_scores_gemma":[0.8649086,0.1341264,0.00018205887,0.00049494253,0.00011335817,0.00017467151],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013671736,0.0003897755,0.0011979314,0.00008986728,0.00006444429,0.000056779332,0.00020163985,0.0005759798,0.007622138],"category_scores_gemma":[0.09227056,0.00031499146,0.000114105416,0.000020569069,0.00038886492,0.000019324854,0.0003053866,0.0005491632,0.00011625362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018509036,0.000017991453,0.0000061820633,0.00026600674,0.000093905066,0.000024869902,0.0000042407387,8.510526e-9,8.160614e-7,0.8383187,0.12722857,0.03402021],"study_design_scores_gemma":[0.00031331927,0.00010216752,0.00003090642,0.00019516733,0.00033584045,0.000003364529,0.0000024957897,0.000050802413,0.000008162058,0.9511483,0.04749778,0.0003117168],"about_ca_topic_score_codex":0.0000056185013,"about_ca_topic_score_gemma":0.0000071723753,"teacher_disagreement_score":0.32609287,"about_ca_system_score_codex":0.000038302715,"about_ca_system_score_gemma":0.00009694551,"threshold_uncertainty_score":0.9999302},"labels":[],"label_agreement":null},{"id":"W4411734499","doi":"10.1007/978-3-031-87083-5_28","title":"Confidence Intervals","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Statistics; Robust confidence intervals; Confidence interval; Mathematics","score_opus":0.6931062297369026,"score_gpt":0.5979970457672934,"score_spread":0.09510918396960921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411734499","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.4843122e-8,0.000043462805,0.32684058,0.00026691033,0.0007886911,0.00030658473,0.00007904608,0.00012856173,0.6715461],"genre_scores_gemma":[0.0000023008427,0.000057547415,0.4430619,0.00052303885,0.00016927175,0.000007556915,8.291202e-7,0.000026617501,0.556151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99762434,0.00012779747,0.001214861,0.00048424897,0.0003540705,0.00019469159],"domain_scores_gemma":[0.9129757,0.08566653,0.0003211536,0.0007639135,0.00017457003,0.00009810388],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018272074,0.00033084326,0.0011730143,0.00009004089,0.000029137762,0.000038148144,0.00046996624,0.0006120624,0.025681939],"category_scores_gemma":[0.08586669,0.00026823342,0.00034077335,0.000019197852,0.00020504236,0.000018460585,0.00029005672,0.00059905613,0.0007198905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012925662,0.000009366626,1.2527741e-7,0.00019301358,0.00009949183,0.00001437392,0.000004280038,4.7539195e-9,0.0000011307018,0.83730954,0.14728668,0.015069046],"study_design_scores_gemma":[0.00016116313,0.000045051744,2.7030117e-7,0.0009114953,0.00018424315,0.0000017494544,0.0000017192843,0.0000070463907,0.00006640746,0.8736022,0.124786496,0.00023215207],"about_ca_topic_score_codex":0.0000034383766,"about_ca_topic_score_gemma":0.000004411419,"teacher_disagreement_score":0.11622129,"about_ca_system_score_codex":0.000051220803,"about_ca_system_score_gemma":0.000102833845,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W4411735566","doi":"10.1177/17407745251350598","title":"Afternoon discussion: Statistical issues in clinical trials conference on dose finding","year":2025,"lang":"en","type":"article","venue":"Clinical Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"","keywords":"Clinical trial; Medicine; Medical physics; Internal medicine","score_opus":0.9141793752863242,"score_gpt":0.7548013895193272,"score_spread":0.15937798576699702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411735566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06790112,0.0007430345,0.70851624,0.0909717,0.06652648,0.021762125,0.0032623592,0.0015310822,0.038785864],"genre_scores_gemma":[0.17105779,0.002544492,0.7995753,0.0049999068,0.009256136,0.00079465733,0.00004431263,0.0002124339,0.011514922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8004543,0.16017644,0.033653103,0.002862778,0.0014744984,0.0013788701],"domain_scores_gemma":[0.10419723,0.88800657,0.004165207,0.0023065628,0.00038896463,0.000935475],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.4026717,0.0008165222,0.01156311,0.0004123985,0.00016798584,0.00033674965,0.0012556039,0.0018590107,0.0035213393],"category_scores_gemma":[0.962074,0.00048765325,0.0022676555,0.0008057567,0.0011687991,0.00015070062,0.0006011273,0.0030066855,0.00054523395],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063822474,0.0025531084,0.0051820218,0.00020044681,0.00041342844,0.00013985115,0.00003780703,0.0000013317283,0.000029205597,0.52868366,0.042632945,0.41374394],"study_design_scores_gemma":[0.012980587,0.0011439489,0.011955333,0.001866878,0.0006552589,0.0000012878769,0.00010794939,0.00051083317,0.00013436817,0.95934707,0.010688633,0.00060783257],"about_ca_topic_score_codex":0.000017375367,"about_ca_topic_score_gemma":0.000026875912,"teacher_disagreement_score":0.7278301,"about_ca_system_score_codex":0.00013779814,"about_ca_system_score_gemma":0.00071002793,"threshold_uncertainty_score":0.9997575},"labels":[],"label_agreement":null},{"id":"W4411849051","doi":"10.1164/rccm.202504-0809tr","title":"Trial Analysis and Interpretation in Critical Care Using the Evidential (Likelihood) Approach: Rationale and Practical Considerations","year":2025,"lang":"en","type":"article","venue":"American Journal of Respiratory and Critical Care Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Economics; University of Alberta","funders":"National Heart, Lung, and Blood Institute","keywords":"Medicine; Interpretation (philosophy); Intensive care medicine; Evidential reasoning approach; Decision analysis; Statistics","score_opus":0.37970098008537945,"score_gpt":0.5879295760338321,"score_spread":0.20822859594845267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411849051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36815068,0.004274172,0.61533356,0.01073414,0.0005315953,0.0005961416,0.000026891132,0.0000124571,0.00034036234],"genre_scores_gemma":[0.8685962,0.000029766692,0.12946899,0.0015574817,0.00032615237,0.000012047832,5.636145e-7,0.00000794365,8.561923e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99554616,0.0023399675,0.0011926298,0.00028472557,0.0004344711,0.00020201564],"domain_scores_gemma":[0.9342413,0.06447853,0.00021539853,0.00016862038,0.00069054624,0.00020558105],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.0029611888,0.0001664297,0.00091108104,0.00033669264,0.00019257361,0.000086172484,0.000056489025,0.00008994496,0.000046325255],"category_scores_gemma":[0.18380342,0.00011088715,0.00010036891,0.0005248963,0.0028198066,0.00016228876,0.00007063684,0.0005903056,8.857106e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021431526,0.000659097,0.017157359,0.0020203793,0.0013283085,0.0006075955,0.019339085,0.00002449764,0.0007261553,0.836992,0.0006933455,0.09902062],"study_design_scores_gemma":[0.027457139,0.0092566265,0.007988087,0.0013587106,0.015231485,0.00039109687,0.15243363,0.003973743,0.00016256694,0.78077674,0.00033827455,0.0006318735],"about_ca_topic_score_codex":0.00001829996,"about_ca_topic_score_gemma":0.00002761531,"teacher_disagreement_score":0.5004455,"about_ca_system_score_codex":0.000053334523,"about_ca_system_score_gemma":0.00025181918,"threshold_uncertainty_score":0.99989396},"labels":[],"label_agreement":null},{"id":"W4411880349","doi":"10.1186/s13054-025-05515-3","title":"Missing the target in target trial emulation","year":2025,"lang":"en","type":"letter","venue":"Critical Care","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto","funders":"","keywords":"Medicine; Emulation; Intensive care medicine; Missing data; Medical physics; Machine learning; Computer science","score_opus":0.5411079281231422,"score_gpt":0.5948375086651048,"score_spread":0.05372958054196253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411880349","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002771554,0.0004773334,0.11505029,0.86292887,0.0066131367,0.0020365734,0.00068359356,0.00015919998,0.012023296],"genre_scores_gemma":[0.00071911514,0.0000035219095,0.68777514,0.29960555,0.010883008,0.00020416256,0.00010010515,0.00008929712,0.0006201308],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99313706,0.0031784698,0.0015149929,0.0007194108,0.0007924044,0.0006576762],"domain_scores_gemma":[0.8423119,0.1563297,0.00013706119,0.0008182504,0.00032310133,0.00007997719],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0021924204,0.000424159,0.0012638427,0.0001421187,0.00016467216,0.00018085167,0.00062903337,0.0016550565,0.0009976699],"category_scores_gemma":[0.37217492,0.0003088028,0.0004018842,0.0003165139,0.00043683668,0.000051378385,0.00020689325,0.003708165,0.000034093053],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093106204,0.00006786824,0.000013221138,0.002372091,0.000032146527,0.00032319315,0.0002614263,0.0000013654799,0.0000024057636,0.05090378,0.9422454,0.002846039],"study_design_scores_gemma":[0.004203015,0.00009663042,0.0000058184423,0.00046990142,0.00018156282,0.0000014620791,0.000098850134,0.00015135769,0.000048232865,0.85491276,0.13952777,0.00030266124],"about_ca_topic_score_codex":0.000009784986,"about_ca_topic_score_gemma":0.0000015700406,"teacher_disagreement_score":0.80400896,"about_ca_system_score_codex":0.00022300098,"about_ca_system_score_gemma":0.00030071626,"threshold_uncertainty_score":0.9999364},"labels":[],"label_agreement":null},{"id":"W4411932894","doi":"10.1177/09622802251350263","title":"Group sequential analysis of marked point processes: Plasma donation trials","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interim; Donation; Medicine; Interim analysis; Clinical endpoint; Adverse effect; Sample size determination; Computer science; Statistics; Intensive care medicine; Clinical trial; Internal medicine; Mathematics","score_opus":0.7478914177986117,"score_gpt":0.7468351539420226,"score_spread":0.0010562638565890792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411932894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013009451,0.00010153562,0.98453957,0.0016455138,0.00060781575,0.0013311835,0.00038715496,0.000058958987,0.010027318],"genre_scores_gemma":[0.013960501,0.00024419738,0.98477244,0.00014920077,0.00014923819,0.0003753591,0.000028497747,0.000036231744,0.00028435796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89770764,0.085958466,0.007155378,0.0015864267,0.0060719377,0.0015201282],"domain_scores_gemma":[0.20933428,0.7870988,0.00054304354,0.00094657723,0.0014281708,0.00064907223],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2604762,0.00034905612,0.0035989627,0.0025672044,0.00014032745,0.00008393583,0.0012211545,0.00082966476,0.011870182],"category_scores_gemma":[0.962221,0.0002750083,0.00039735314,0.0099653285,0.0021091679,0.00008874768,0.0006912634,0.0022860882,0.000012328015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010603872,0.00069359806,0.00025338324,0.0010829162,0.0010169344,0.000068276066,0.00009115213,0.0000019830447,0.00033404306,0.6376349,0.0017631523,0.35599926],"study_design_scores_gemma":[0.002214394,0.0002535744,0.001730371,0.00054316944,0.0010398556,0.0000012830244,0.00020684583,0.01986921,0.0012275709,0.9719726,0.0007218738,0.00021924083],"about_ca_topic_score_codex":0.00016447129,"about_ca_topic_score_gemma":0.00020351881,"teacher_disagreement_score":0.7017448,"about_ca_system_score_codex":0.00032783448,"about_ca_system_score_gemma":0.0014132732,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W4411984890","doi":"10.1080/01621459.2025.2519814","title":"Adaptive Selection for False Discovery Rate Control Leveraging Symmetry","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Key Research and Development Program of China; Alberta Machine Intelligence Institute","keywords":"False discovery rate; Selection (genetic algorithm); Computer science; Econometrics; Mathematics; Statistics; Artificial intelligence; Biology","score_opus":0.15565189437174692,"score_gpt":0.48701101146231585,"score_spread":0.3313591170905689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411984890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01748965,0.000012860627,0.9776371,0.0029696955,0.0010532244,0.00039882193,0.00024429892,0.0000166158,0.00017773062],"genre_scores_gemma":[0.5642977,0.0000097526745,0.4334573,0.0012139558,0.00036295978,0.000017191369,4.919721e-7,0.00001879214,0.00062186626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957985,0.002036537,0.0012010975,0.00018528705,0.00047764133,0.000300917],"domain_scores_gemma":[0.8849746,0.11167389,0.0025080296,0.00013779938,0.0006365936,0.000069100126],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006111571,0.00016104792,0.00088459364,0.00010636694,0.00017081214,0.00009908145,0.0002655375,0.00007535367,0.000012027891],"category_scores_gemma":[0.2274964,0.00010951173,0.00030753043,0.0005113466,0.00013624945,0.00013995162,0.00004424691,0.0004752165,0.000001972121],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033019609,0.00054846663,0.02958671,0.0001237481,0.002077578,0.000004188356,0.00009583317,0.00016072132,0.0016216732,0.841501,0.06281285,0.05816526],"study_design_scores_gemma":[0.0017174557,0.0003741364,0.034791317,0.00010824745,0.0007555957,0.000002543397,0.00012861706,0.004094847,0.00039395076,0.95716244,0.0003478826,0.00012294811],"about_ca_topic_score_codex":0.000021469185,"about_ca_topic_score_gemma":0.000006111938,"teacher_disagreement_score":0.54680806,"about_ca_system_score_codex":0.0009367063,"about_ca_system_score_gemma":0.00022366224,"threshold_uncertainty_score":0.7790107},"labels":[],"label_agreement":null},{"id":"W4412163746","doi":"10.1158/1557-3265.aimachine-a002","title":"Abstract A002: A Bayesian Machine Learning Approach for Estimating Treatment Effects in Decentralized Clinical Trials","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Clinical trial; Machine learning; Artificial intelligence; Medicine; Computer science; Intensive care medicine; Internal medicine","score_opus":0.882817471872725,"score_gpt":0.7654210037911113,"score_spread":0.11739646808161364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412163746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027578637,0.0017691003,0.9488736,0.0024443802,0.003540399,0.012086065,0.00018954588,0.0002704516,0.0032478373],"genre_scores_gemma":[0.05157616,0.0012413657,0.9413411,0.00022479464,0.0014417833,0.0032298868,0.000017658649,0.00009598385,0.00083127903],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9556712,0.03197445,0.007968022,0.0017902736,0.0010206974,0.0015753951],"domain_scores_gemma":[0.45802543,0.5395575,0.0007419681,0.000785562,0.0003934039,0.00049609336],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16887465,0.0004590536,0.0040396336,0.00036709598,0.0003302974,0.00017451888,0.00080537895,0.0009135966,0.00033825997],"category_scores_gemma":[0.78076416,0.00034464314,0.0013120242,0.0010031423,0.0007982345,0.00007810784,0.0003107585,0.0029441298,0.000016477752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071919076,0.004218631,0.041758288,0.0019419567,0.0007977205,0.000045992834,0.00008887357,0.00024703215,0.00004667021,0.024057187,0.0037631863,0.91584253],"study_design_scores_gemma":[0.030579725,0.0022660815,0.009949397,0.0015420204,0.0004899496,0.000001015329,0.00007512625,0.18502975,0.00022661532,0.76468766,0.0045746635,0.0005780221],"about_ca_topic_score_codex":0.00031710198,"about_ca_topic_score_gemma":0.00015000867,"teacher_disagreement_score":0.91526455,"about_ca_system_score_codex":0.00053241185,"about_ca_system_score_gemma":0.001069316,"threshold_uncertainty_score":0.9999006},"labels":[],"label_agreement":null},{"id":"W4412443540","doi":"10.1016/j.jval.2025.04.1292","title":"MSR141 Reconciling Discrepancies in Results with Different Population-adjusted Indirect Comparison (PAIC) Methods","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Statistics; Econometrics; Mathematics","score_opus":0.6762797987268713,"score_gpt":0.6112923117581431,"score_spread":0.06498748696872814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412443540","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7334126,0.0007801249,0.25269148,0.0054194736,0.0017241122,0.0030225073,0.00013503918,0.000305479,0.00250918],"genre_scores_gemma":[0.27640873,0.000052438394,0.72309417,0.00017407225,0.000055177163,0.00006590251,0.000008074214,0.00002401146,0.00011745758],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.987883,0.0074873175,0.0030041493,0.0006671414,0.00037531304,0.0005831075],"domain_scores_gemma":[0.91370046,0.0848103,0.00066564925,0.00061540323,0.00006719031,0.00014102628],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013947453,0.00027232355,0.0016086077,0.0003961515,0.00009380683,0.000036545443,0.00025243472,0.00020112672,0.000017448334],"category_scores_gemma":[0.09656158,0.00021007411,0.00008057717,0.0010173181,0.00008531064,0.000055507975,0.00009510284,0.00072007364,0.000001928747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030478025,0.0016976291,0.46432412,0.0038646199,0.00016303231,0.000025120215,0.0045518144,0.005784277,0.00003086687,0.3258679,0.0006576828,0.18998516],"study_design_scores_gemma":[0.0034687927,0.00035752344,0.22981332,0.0031808144,0.000038965365,0.0000015446238,0.000514391,0.0355617,0.00030557165,0.72613734,0.00029872704,0.00032131586],"about_ca_topic_score_codex":0.006000277,"about_ca_topic_score_gemma":0.002491762,"teacher_disagreement_score":0.47040266,"about_ca_system_score_codex":0.00061085704,"about_ca_system_score_gemma":0.00024105905,"threshold_uncertainty_score":0.9110485},"labels":[],"label_agreement":null},{"id":"W4412455680","doi":"10.1093/eurheartj/ehaf474","title":"Artificial intelligence in cardiovascular pharmacotherapy: applications and perspectives","year":2025,"lang":"en","type":"review","venue":"European Heart Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Surgical Specialties (Canada)","funders":"","keywords":"Generalizability theory; Medicine; Risk analysis (engineering); Psychological intervention; Certification; Standardization; Health care; Transparency (behavior); Pharmacotherapy; Artificial intelligence; Data science; Computer science","score_opus":0.7164197120694339,"score_gpt":0.6135640606351478,"score_spread":0.1028556514342861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412455680","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6806817e-7,0.82927215,0.16751966,0.0000662493,0.0002478069,0.0007445701,0.000025778982,0.000028894085,0.0020946928],"genre_scores_gemma":[0.0000010109179,0.78512603,0.21355848,0.000029807876,0.001110231,0.000032778313,4.059416e-7,0.000052760006,0.00008851216],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9914445,0.006098821,0.0014033322,0.00047212452,0.00030476952,0.00027641686],"domain_scores_gemma":[0.9815042,0.017518746,0.0002944273,0.00043516056,0.00008418324,0.00016329958],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008920742,0.00031888823,0.0020612893,0.0003073188,0.00013939264,0.00013859819,0.00036036776,0.000108653374,0.00017931548],"category_scores_gemma":[0.012410542,0.0002565792,0.00087289035,0.00045586788,0.00016551107,0.000041152452,0.00013033603,0.0014402487,0.00006539274],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004819425,0.000079964106,8.181498e-7,0.002566608,0.00028134295,0.000051480183,0.00008119619,5.5167516e-7,1.6984299e-7,0.01322856,0.0003540024,0.9833505],"study_design_scores_gemma":[0.00006318941,0.000029787148,0.0000032477917,0.0058951,0.0007061546,0.00020462778,0.0000646706,0.000003906129,7.9268887e-7,0.17470111,0.8180879,0.00023955847],"about_ca_topic_score_codex":6.044879e-7,"about_ca_topic_score_gemma":2.5743384e-7,"teacher_disagreement_score":0.9831109,"about_ca_system_score_codex":0.000095815616,"about_ca_system_score_gemma":0.00018061072,"threshold_uncertainty_score":0.9999886},"labels":[],"label_agreement":null},{"id":"W4412488734","doi":"10.1007/s00428-025-04169-4","title":"Indirect clinical validation for predictive biomarkers in oncology: International Quality Network for Pathology (IQN Path) Position Paper","year":2025,"lang":"en","type":"article","venue":"Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Canadian Light Source (Canada); University of Saskatchewan; Royal University Hospital","funders":"","keywords":"Medical physics; Clinical trial; Medicine; Biomarker; Clinical Practice; Pathology","score_opus":0.34664166566734667,"score_gpt":0.6068853853795204,"score_spread":0.26024371971217375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412488734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14510065,0.00070827844,0.81760544,0.010078657,0.008187069,0.006724437,0.0015763772,0.00048368977,0.009535389],"genre_scores_gemma":[0.23098342,0.0008557171,0.7596581,0.004348673,0.0016574423,0.001580198,0.00070292153,0.000079433376,0.0001340655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9858658,0.007181413,0.0037189529,0.0017099003,0.00042813152,0.0010958568],"domain_scores_gemma":[0.8554884,0.14178073,0.0012517321,0.00088900956,0.00037759158,0.00021252067],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.024654595,0.0006382888,0.0023227993,0.0003767881,0.0002930908,0.00005414503,0.0011107279,0.0012813626,0.00006153296],"category_scores_gemma":[0.16876249,0.0005206216,0.0007672738,0.0006107572,0.0016142321,0.00022416472,0.0005025236,0.001338458,0.000011666837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026075453,0.005400891,0.024911182,0.00094853534,0.005315002,0.00022157132,0.0010326635,0.0004911784,0.010705458,0.55201966,0.057533234,0.31534517],"study_design_scores_gemma":[0.007849885,0.0022983244,0.027804473,0.00033984013,0.00074484956,0.0000042915567,0.0004632703,0.0026209652,0.0009481456,0.95009226,0.006309994,0.0005237087],"about_ca_topic_score_codex":0.00002822844,"about_ca_topic_score_gemma":0.00004055079,"teacher_disagreement_score":0.39807257,"about_ca_system_score_codex":0.0002507305,"about_ca_system_score_gemma":0.00062176166,"threshold_uncertainty_score":0.9997245},"labels":[],"label_agreement":null},{"id":"W4412629587","doi":"10.1093/biomtc/ujaf082","title":"Sparse 2-stage Bayesian meta-analysis for individualized treatments","year":2025,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Bayesian probability; Computer science; Identification (biology); Meta-analysis; Data mining; Machine learning; Econometrics; Artificial intelligence; Medicine; Mathematics; Internal medicine","score_opus":0.8274700279161862,"score_gpt":0.6240568146491524,"score_spread":0.20341321326703377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412629587","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056494056,0.00043853172,0.9920029,0.0003907674,0.0003939816,0.0011257342,0.0020155318,0.00011591619,0.0029516693],"genre_scores_gemma":[0.0055126124,0.000031183223,0.9781676,0.00035087994,0.00004927863,0.00031526355,0.000025085283,0.000027899361,0.015520198],"study_design_codex":"meta_analysis","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968152,0.00055695174,0.0011799572,0.0005687383,0.00049139815,0.00038775732],"domain_scores_gemma":[0.9303925,0.06803736,0.00039221268,0.0008181665,0.00021161023,0.0001481514],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004390157,0.0002848514,0.0021058477,0.0029982878,0.00011650073,0.00009601451,0.00043161566,0.00026193447,0.0011231455],"category_scores_gemma":[0.12923926,0.0002121326,0.0020377159,0.012911589,0.00009251439,0.0000434926,0.00012776181,0.00011109809,0.000015733893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018707271,0.0015127029,0.0028561193,0.00034241998,0.4995585,0.000014180708,0.00006527703,0.000006777908,0.00005435956,0.46100932,0.012645866,0.0217474],"study_design_scores_gemma":[0.0016911285,0.000116367126,0.00066712307,0.0000026037883,0.34457737,1.2952808e-7,0.000018754505,0.00030809428,0.00084859546,0.63726974,0.014268414,0.00023170197],"about_ca_topic_score_codex":0.000019647541,"about_ca_topic_score_gemma":0.000005711332,"teacher_disagreement_score":0.1762604,"about_ca_system_score_codex":0.00009445532,"about_ca_system_score_gemma":0.0000656166,"threshold_uncertainty_score":0.99978995},"labels":[],"label_agreement":null},{"id":"W4412763292","doi":"10.1186/s12874-025-02626-x","title":"Comparing randomized trial designs to estimate treatment effect in rare diseases with longitudinal models: a simulation study showcased by Autosomal Recessive Cerebellar Ataxias using the SARA score","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean","funders":"","keywords":"Randomized controlled trial; Medicine; Cerebellar ataxia; Physical medicine and rehabilitation; Pediatrics; Physical therapy; Ataxia; Internal medicine; Psychiatry","score_opus":0.9042634351777981,"score_gpt":0.7046481815688531,"score_spread":0.19961525360894494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412763292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40244654,0.00013096086,0.5895118,0.00022363677,0.00019448948,0.007381266,0.000020083779,0.000047103087,0.000044091747],"genre_scores_gemma":[0.49848372,0.000013765116,0.4995522,0.0000473023,0.0001725948,0.0016349709,0.000006683492,0.000040339237,0.000048434977],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8401385,0.15332493,0.0019284191,0.0011979014,0.0023129939,0.0010972695],"domain_scores_gemma":[0.22694728,0.77091926,0.00030509685,0.00089491525,0.00035748878,0.0005759459],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08501869,0.00046438805,0.0034148002,0.00046789265,0.00039616085,0.000115240975,0.00081055524,0.00036773938,0.00015192266],"category_scores_gemma":[0.7214521,0.00024662557,0.0002786121,0.0013106064,0.0011692628,0.00008372789,0.0005095638,0.0010417206,0.0000040781283],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9468915,0.0020331144,0.0085285995,0.00035981278,0.000615553,0.0002778784,0.000680179,0.022787062,0.000032798336,0.005649701,0.0001227835,0.012021022],"study_design_scores_gemma":[0.38784403,0.0029683434,0.00027457447,0.0006478675,0.00059304066,0.000003988229,0.00027976328,0.4316381,0.00015044112,0.17538485,0.0000032752341,0.00021175807],"about_ca_topic_score_codex":0.00059546187,"about_ca_topic_score_gemma":0.00079960603,"teacher_disagreement_score":0.6364334,"about_ca_system_score_codex":0.0005664428,"about_ca_system_score_gemma":0.0015069672,"threshold_uncertainty_score":0.9999986},"labels":[],"label_agreement":null},{"id":"W4412957766","doi":"10.1136/bmjopen-2024-097134","title":"Canadian Adaptive Platform Trial of Treatments for COVID in Community Settings (CanTreatCOVID): protocol for a randomised controlled adaptive platform trial of treatments for acute SARS-CoV-2 infection in community settings","year":2025,"lang":"en","type":"article","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ministry of Health and Long Term Care; Thunder Bay Regional Research Institute; NOSM University; Thunder Bay Regional Health Sciences Centre; Sunnybrook Health Science Centre; East Wellington Family Health Team; Manitoba Health; Research Manitoba; University of Saskatchewan; University of Alberta; University Health Network; McMaster University; Access Alliance Multicultural Health and Community Services; Université Laval; Providence Health Care; Humber River Regional Hospital; Université de Montréal; Centre Hospitalier de l’Université de Montréal; Université de Sherbrooke; Impact; South Health Campus; Women's College Hospital; North York General Hospital; St. Michael's Hospital; Queen's University; University of Ottawa; Dalhousie University; University of Manitoba; Jewish General Hospital; Simon Fraser University; Montreal General Hospital; University of Calgary; Institute for Clinical Evaluative Sciences; McGill University; Centre for Addiction and Mental Health; Élisabeth Bruyère Hospital; University of Toronto; Memorial University of Newfoundland; University of British Columbia; Toronto General Hospital; Public Health Ontario","funders":"Canadian Institutes of Health Research; Health Canada; University of Toronto; Public Health Agency; Public Health Agency of Canada","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Randomized controlled trial; 2019-20 coronavirus outbreak; Protocol (science); Pandemic; Trial registration; Sars virus; Alternative medicine; Virology; Outbreak; Infectious disease (medical specialty); Surgery; Internal medicine; Disease; Pathology","score_opus":0.5394323444180716,"score_gpt":0.6056711986177342,"score_spread":0.06623885419966258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412957766","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.123300545,8.7521676e-7,0.013895285,0.00025547337,0.00029096435,0.85616076,0.0044142916,0.000035092584,0.0016466983],"genre_scores_gemma":[0.019354327,0.0000015869492,0.15881212,0.00027874246,0.00007686538,0.8210802,0.00012243997,0.00007010365,0.00020360418],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.991198,0.0032580136,0.0039423183,0.00048002563,0.0003671429,0.00075452134],"domain_scores_gemma":[0.8793773,0.11668033,0.0023115296,0.0009628882,0.000503149,0.00016482014],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.020951536,0.0006201654,0.0043193973,0.0005594749,0.0005219572,0.000090887464,0.0009663171,0.00059759466,0.000012713392],"category_scores_gemma":[0.099058285,0.0005129535,0.0008373825,0.0005279214,0.00023437453,0.00034703768,0.00031297404,0.0006323526,7.2313793e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9774864,0.0060372893,0.00011373041,0.0007434824,0.0030739564,0.0000029826504,0.0017419838,0.000005190531,0.00010152066,0.0046017836,0.001392413,0.004699316],"study_design_scores_gemma":[0.70824945,0.013050886,0.000053851407,0.0010771415,0.0014575508,8.076774e-7,0.0005675354,0.0014952373,0.0037200637,0.26993465,0.000098155506,0.00029466802],"about_ca_topic_score_codex":0.14066018,"about_ca_topic_score_gemma":0.20520787,"teacher_disagreement_score":0.2692369,"about_ca_system_score_codex":0.0018371812,"about_ca_system_score_gemma":0.002583508,"threshold_uncertainty_score":0.9997322},"labels":[],"label_agreement":null},{"id":"W4413114376","doi":"10.1002/pst.70037","title":"Drift Parameter Based Sample Size Determination in Multi‐Stage Bayesian Randomized Clinical Trials","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Bayesian probability; Statistics; Stage (stratigraphy); Randomized controlled trial; Clinical trial; Mathematics; Computer science; Econometrics; Medicine; Internal medicine; Biology","score_opus":0.7611773147160606,"score_gpt":0.6919872169274078,"score_spread":0.06919009778865282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413114376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042133758,0.000051400668,0.99082136,0.00097233517,0.001837047,0.0032715776,0.0018507246,0.00016673206,0.0006074835],"genre_scores_gemma":[0.034520432,0.00012475459,0.96186864,0.0024254564,0.00017467972,0.00039301522,0.000021555717,0.00006589359,0.0004055774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9573543,0.03273736,0.0071592084,0.0010494327,0.0007841587,0.00091555977],"domain_scores_gemma":[0.2717196,0.7261973,0.00081788143,0.0005873442,0.00026404494,0.00041381983],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07151701,0.0005498469,0.0040852726,0.0002453671,0.00012476444,0.00015351154,0.00054959994,0.0005586592,0.0024764547],"category_scores_gemma":[0.9340418,0.000455615,0.0007132413,0.0006175946,0.0009931755,0.00008604765,0.00018335036,0.0013603341,0.00003848404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.050273437,0.0036068864,0.0051969066,0.0012262976,0.00053318345,0.00018842866,0.00008429118,0.000037336296,0.00011472943,0.52447957,0.0037386373,0.4105203],"study_design_scores_gemma":[0.09237625,0.00005159776,0.00033405522,0.00011421032,0.0006203427,4.3568224e-7,0.000010109527,0.36803508,0.0004951521,0.5364073,0.0012465047,0.000308949],"about_ca_topic_score_codex":0.000043868255,"about_ca_topic_score_gemma":0.000035226214,"teacher_disagreement_score":0.86252475,"about_ca_system_score_codex":0.00016877858,"about_ca_system_score_gemma":0.0003129328,"threshold_uncertainty_score":0.99978954},"labels":[],"label_agreement":null},{"id":"W4413301433","doi":"10.1101/2025.08.13.25333581","title":"Group Response Analysis: Clinically Interpretable Longitudinal Responder Analysis Methods Developed Using FDA Data","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Group analysis; Longitudinal data; Group (periodic table); Medicine; Computer science; Data mining; Statistics; Psychology; Mathematics; Chemistry; Social psychology","score_opus":0.7848026658487166,"score_gpt":0.6711754588187829,"score_spread":0.11362720702993367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413301433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06346757,0.0002505474,0.9302394,0.0003124408,0.0018959952,0.00096548075,0.0019747552,0.00030530288,0.00058855733],"genre_scores_gemma":[0.021966696,0.00010089992,0.9753874,0.00032174733,0.0003304822,0.000098933786,0.00019059754,0.00009971702,0.0015035428],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94658655,0.039017204,0.0073873517,0.0043880967,0.0014836179,0.0011372017],"domain_scores_gemma":[0.73090094,0.25437167,0.0028292637,0.010525319,0.0008531033,0.00051968487],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","open_science","research_integrity"],"category_scores_codex":[0.11970784,0.0011678938,0.006694534,0.0029251855,0.00026350163,0.00044086587,0.005900962,0.001711194,0.0015332545],"category_scores_gemma":[0.52772516,0.0010500896,0.002371925,0.008185157,0.0005311526,0.0001911432,0.013071692,0.0031374532,0.000024883231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.048007403,0.0038582056,0.42852446,0.003956624,0.4236788,0.0010638057,0.0013588847,0.0059227454,0.001343122,0.03036321,0.0031906338,0.048732102],"study_design_scores_gemma":[0.0012570344,0.00015744843,0.04476205,0.0008144688,0.16269876,0.0000038311664,0.000087257475,0.2056884,0.00014172739,0.5806694,0.0017984901,0.0019211542],"about_ca_topic_score_codex":0.00014109424,"about_ca_topic_score_gemma":0.00015399797,"teacher_disagreement_score":0.55030614,"about_ca_system_score_codex":0.00037907314,"about_ca_system_score_gemma":0.001301066,"threshold_uncertainty_score":0.9995848},"labels":[],"label_agreement":null},{"id":"W4413330714","doi":"10.21203/rs.3.rs-7291977/v1","title":"Who Benefits? Uncovering Hidden Heterogeneity of Treatment Effects in Adaptive Trials Using Bayesian Methods: A Systematic Review","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; University of Toronto","funders":"","keywords":"Bayesian probability; Econometrics; Computer science; Artificial intelligence; Economics","score_opus":0.7612851861334058,"score_gpt":0.6806110064693837,"score_spread":0.08067417966402213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413330714","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008734324,0.1575326,0.75384223,0.00025076594,0.0014840235,0.07371663,0.0030639877,0.00021361905,0.001161827],"genre_scores_gemma":[0.0023817397,0.01358434,0.98034686,0.0000311179,0.00019258824,0.0032714042,0.000009275652,0.00009283907,0.0000898505],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8910627,0.09782445,0.0065116845,0.001603576,0.0018901168,0.0011075167],"domain_scores_gemma":[0.63527864,0.3591247,0.0019034229,0.0024466,0.0009487036,0.00029790206],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09566698,0.0007755929,0.010592902,0.00089024776,0.00011458126,0.000098097225,0.0010590681,0.0008619373,0.00006623626],"category_scores_gemma":[0.585336,0.00058492646,0.0014956511,0.0012347703,0.00023357321,0.00006180155,0.0019217897,0.0016470031,0.0000053619133],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002575344,0.0004394256,0.00006336708,0.9712157,0.0013053835,0.000048196227,0.00024156108,0.00019117013,0.00005676069,0.015997805,0.00003876168,0.010144316],"study_design_scores_gemma":[0.0009557561,0.00056998007,0.000026550062,0.60222286,0.0015144725,0.000002146147,0.0000752546,0.002986286,0.0025447723,0.3887746,0.0000017992951,0.00032549872],"about_ca_topic_score_codex":0.000642347,"about_ca_topic_score_gemma":0.00010397959,"teacher_disagreement_score":0.48966905,"about_ca_system_score_codex":0.0025088182,"about_ca_system_score_gemma":0.001341236,"threshold_uncertainty_score":0.9996602},"labels":[],"label_agreement":null},{"id":"W4413805698","doi":"10.1186/s12874-025-02652-9","title":"Development of a protocol complexity tool: a framework designed to stimulate discussion and simplify study design","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"AstraZeneca","keywords":"Clinical trial; Protocol (science); Medicine; Computer science; Research design; Medical physics; Statistics; Internal medicine; Alternative medicine; Pathology; Mathematics","score_opus":0.9486650995424512,"score_gpt":0.7577932577158293,"score_spread":0.19087184182662187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413805698","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008653373,0.0000040822842,0.9242758,0.0008634668,0.00013535755,0.065896526,0.0000046955092,0.000057998535,0.000108707565],"genre_scores_gemma":[0.0020242038,0.0000012617651,0.95314467,0.00017050093,0.0000762759,0.044414625,2.9768256e-7,0.00002834154,0.00013984733],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90686,0.08543395,0.0027913672,0.0011146886,0.0027307582,0.0010692235],"domain_scores_gemma":[0.34077075,0.6567873,0.00023514513,0.0008992712,0.000576068,0.00073150726],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17337136,0.0002758893,0.0016435984,0.00045857157,0.00028462207,0.000036266076,0.00090921175,0.00058222155,0.00081251905],"category_scores_gemma":[0.8965813,0.00016672067,0.000089935354,0.0011746127,0.0011032845,0.000029751687,0.0016923631,0.0013280765,0.0000168447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012480471,0.0034923498,0.0025347925,0.0028454803,0.00036662948,0.00006998755,0.0042249663,0.000009640113,0.0020381524,0.33702838,0.002107842,0.6328013],"study_design_scores_gemma":[0.0025200457,0.0012720778,0.005026473,0.000813333,0.000038503,0.0000020374011,0.0007494422,0.00080336165,0.0019046521,0.98610723,0.0005760961,0.00018674663],"about_ca_topic_score_codex":0.000020268313,"about_ca_topic_score_gemma":0.000068332665,"teacher_disagreement_score":0.7232099,"about_ca_system_score_codex":0.00011786363,"about_ca_system_score_gemma":0.0022480665,"threshold_uncertainty_score":0.88965136},"labels":[],"label_agreement":null},{"id":"W4413972648","doi":"10.1016/j.vaccine.2025.127645","title":"Adopting the estimand framework in prophylactic vaccine trials","year":2025,"lang":"en","type":"article","venue":"Vaccine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pfizer (Canada)","funders":"U.S. Food and Drug Administration; National Institutes of Health; European Federation of Pharmaceutical Industries and Associations; GlaxoSmithKline","keywords":"Medicine; Virology","score_opus":0.49796730681477386,"score_gpt":0.5923301963119288,"score_spread":0.09436288949715499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413972648","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05745719,0.000988749,0.9069191,0.023905521,0.003061334,0.0037178255,0.000026052638,0.00029940507,0.0036247747],"genre_scores_gemma":[0.16186729,0.000041625055,0.8361138,0.00077501294,0.0004838854,0.00012476143,5.8429146e-7,0.0000305885,0.0005624239],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949972,0.0020533332,0.0019161344,0.00040709873,0.00025467158,0.0003715871],"domain_scores_gemma":[0.79098666,0.2075256,0.0004720826,0.0008368217,0.00010930179,0.000069545335],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014314806,0.00023687679,0.0012495855,0.0001501031,0.00011179161,0.00007167019,0.00044560703,0.0002322656,0.00052810734],"category_scores_gemma":[0.56314117,0.00013835468,0.00016831094,0.0009406819,0.000014125929,0.000050594015,0.00018699557,0.00076938054,0.000035484623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016616831,0.00069385953,0.009899308,0.0008069047,0.00028131178,0.00005743311,0.00025881568,0.000063167696,0.00028005324,0.74951375,0.012622473,0.22386125],"study_design_scores_gemma":[0.0022612433,0.00009746176,0.00635069,0.0004446448,0.00021678458,0.000002278629,0.0000521748,0.00046814742,0.00042631596,0.9876665,0.0018605618,0.00015323407],"about_ca_topic_score_codex":0.00001713876,"about_ca_topic_score_gemma":0.000015092411,"teacher_disagreement_score":0.5488264,"about_ca_system_score_codex":0.00006315353,"about_ca_system_score_gemma":0.00008074713,"threshold_uncertainty_score":0.5782405},"labels":[],"label_agreement":null},{"id":"W4414062714","doi":"10.1093/jnci/djaf183","title":"Success in oncology phase 3 trials: a small <i>P</i> value or patient value","year":2025,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; McMaster University","funders":"","keywords":"Value (mathematics); Phase (matter); MEDLINE; Patient care","score_opus":0.7535558950252426,"score_gpt":0.669141348257649,"score_spread":0.08441454676759352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414062714","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52529407,0.0022736187,0.2406588,0.081120774,0.10817114,0.005931303,0.0016846405,0.000101351965,0.034764275],"genre_scores_gemma":[0.22655366,0.0006299144,0.75143045,0.015285043,0.0046150973,0.00023132593,0.0000017681089,0.00005244385,0.0012002932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933869,0.0024425085,0.002808546,0.00021014125,0.00091793085,0.0002339701],"domain_scores_gemma":[0.9552935,0.041518737,0.0019555385,0.00019274288,0.00093507336,0.000104461535],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012170534,0.0001887007,0.0011347021,0.00027268595,0.000108452565,0.00004198383,0.0007341399,0.00020704026,0.00015601833],"category_scores_gemma":[0.24818708,0.00010752886,0.00039195464,0.0007407776,0.00021999217,0.00015788965,0.0001594456,0.0007570355,0.0000022465363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009819219,0.0031688511,0.00050868694,0.00033463203,0.0010242949,0.00014122637,0.0005179752,0.008229407,0.0011487864,0.7455143,0.054078538,0.1755141],"study_design_scores_gemma":[0.009006423,0.00036701813,0.00023058528,0.0007931395,0.00030965556,0.00003967202,0.000029404851,0.0006141608,0.003209553,0.9064683,0.07877953,0.00015257756],"about_ca_topic_score_codex":0.00006203349,"about_ca_topic_score_gemma":0.00022679927,"teacher_disagreement_score":0.51077163,"about_ca_system_score_codex":0.001228386,"about_ca_system_score_gemma":0.0035612923,"threshold_uncertainty_score":0.75814575},"labels":[],"label_agreement":null},{"id":"W4414139555","doi":"10.1002/bimj.70072","title":"Estimands for Early‐Phase Dose Optimization Trials in Oncology","year":2025,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Drug Research and Development","funders":"Newcastle University","keywords":"CLARITY; Clinical trial; Function (biology); Phase (matter); Maximum tolerated dose; Confusion","score_opus":0.8107029982460866,"score_gpt":0.7164979095783318,"score_spread":0.09420508866775479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414139555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004841966,0.00014785558,0.9896554,0.0018894846,0.0017096733,0.0007545802,0.000047787024,0.000034511944,0.00091878336],"genre_scores_gemma":[0.012405613,0.00010519475,0.9864566,0.00025306322,0.00051215105,0.00006016881,0.0000017343,0.000019446363,0.0001860319],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99353534,0.0025968945,0.0028276837,0.00029663654,0.00034262612,0.0004008483],"domain_scores_gemma":[0.7468045,0.25130135,0.0009137421,0.0003491179,0.00035325313,0.00027808922],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027189149,0.0001773215,0.0015479228,0.0021127788,0.00011113506,0.00012430623,0.0004526923,0.00039607368,0.00028573384],"category_scores_gemma":[0.72737604,0.00013472092,0.00039052995,0.0034569188,0.00010966862,0.000080806414,0.00011358614,0.00047945903,0.0000059391687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056820167,0.004079643,0.00062823563,0.0001454338,0.00033361258,0.0001060421,0.00006131779,0.00023553448,0.0002982501,0.08018294,0.033772018,0.87447494],"study_design_scores_gemma":[0.016463568,0.0017288495,0.00042389953,0.00011099839,0.0002363744,0.000017102559,0.000016017815,0.011456126,0.0003048043,0.96560097,0.00346821,0.00017309426],"about_ca_topic_score_codex":0.000002670489,"about_ca_topic_score_gemma":4.376635e-7,"teacher_disagreement_score":0.885418,"about_ca_system_score_codex":0.0003241194,"about_ca_system_score_gemma":0.00027551877,"threshold_uncertainty_score":0.942327},"labels":[],"label_agreement":null},{"id":"W4414370371","doi":"10.1093/oncolo/oyaf279","title":"Toxicity-benefit analysis of advanced prostate cancer trials using weighted toxicity scoring","year":2025,"lang":"en","type":"article","venue":"The Oncologist","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Toxicity; Prostate cancer; Clinical trial; Overall survival; Cancer; Radiation therapy","score_opus":0.5622597241237566,"score_gpt":0.6116115389324049,"score_spread":0.049351814808648364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414370371","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90699494,0.0002418527,0.08584509,0.0010839781,0.0010447799,0.0014121331,0.00037217472,0.00010990415,0.0028951643],"genre_scores_gemma":[0.42801446,0.00025100954,0.5697771,0.00043933658,0.00018604998,0.00015840071,0.0000025715333,0.000027119797,0.0011439901],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994768,0.002038736,0.0020398037,0.00042229044,0.00036200616,0.0003691546],"domain_scores_gemma":[0.92289585,0.07482556,0.0012029947,0.0007405232,0.00026666568,0.000068430774],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0119039025,0.00024164791,0.0022549944,0.00023992927,0.0001915009,0.00003818848,0.0005535994,0.00019168813,0.00037483117],"category_scores_gemma":[0.08880988,0.00015082974,0.0005177065,0.002064228,0.00046559318,0.000054233107,0.00025973876,0.0003168031,0.0000021413464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00480352,0.0018134583,0.015255509,0.0009417139,0.014723215,0.000025779153,0.0010106807,0.012768074,0.11031629,0.59064126,0.0012517669,0.24644876],"study_design_scores_gemma":[0.0018026656,0.00017293374,0.002948254,0.00032738372,0.0081418995,3.6765934e-7,0.000305447,0.008199402,0.056655005,0.9208495,0.00031646178,0.0002806841],"about_ca_topic_score_codex":0.00019151055,"about_ca_topic_score_gemma":0.00022727222,"teacher_disagreement_score":0.483932,"about_ca_system_score_codex":0.0003148488,"about_ca_system_score_gemma":0.00020436317,"threshold_uncertainty_score":0.91886544},"labels":[],"label_agreement":null},{"id":"W4414476131","doi":"10.1002/psp4.70115","title":"An Open‐Source Framework for Virtual Bioequivalence Modeling and Clinical Trial Design","year":2025,"lang":"en","type":"article","venue":"CPT Pharmacometrics & Systems Pharmacology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Waterloo","funders":"Food and Drug Administration; U.S. Food and Drug Administration; U.S. Department of Health and Human Services","keywords":"Bioequivalence; Physiologically based pharmacokinetic modelling; In silico; IVIVC; Toolbox; Rework; Inference; In vivo; Benchmark (surveying); Repurposing","score_opus":0.7654397942060153,"score_gpt":0.6792413634340045,"score_spread":0.08619843077201073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414476131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046763137,0.0006305427,0.92118645,0.0003431707,0.022628753,0.007926081,0.00015979771,0.00027576942,0.00008630741],"genre_scores_gemma":[0.33658051,0.0006352081,0.6571993,0.0014384523,0.0025610514,0.0011715012,0.0000046568302,0.000111646164,0.00029766012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9860591,0.0072856527,0.0036042393,0.0015598368,0.0005141166,0.0009770242],"domain_scores_gemma":[0.80157846,0.19559832,0.00089270144,0.00071320694,0.00058325235,0.0006340679],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.027120441,0.00057642505,0.002322923,0.0009677821,0.00044506832,0.0004280152,0.00229975,0.0008425883,0.00015894609],"category_scores_gemma":[0.0862099,0.000544262,0.00025790918,0.0022871124,0.00043001026,0.00033187715,0.0008558065,0.001292904,0.000015311669],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.12737642,0.007847829,0.00034727217,0.0018535012,0.003572741,0.000068466354,0.00020044025,0.006655118,0.005058579,0.65396535,0.04518026,0.14787403],"study_design_scores_gemma":[0.07448085,0.004461715,0.000005531042,0.0001790574,0.0022056445,0.000009285484,0.00013762145,0.46361473,0.0010647689,0.45038345,0.0027319728,0.0007253733],"about_ca_topic_score_codex":0.000031615094,"about_ca_topic_score_gemma":2.44596e-7,"teacher_disagreement_score":0.4569596,"about_ca_system_score_codex":0.00018288358,"about_ca_system_score_gemma":0.0003926244,"threshold_uncertainty_score":0.9997009},"labels":[],"label_agreement":null},{"id":"W4414557720","doi":"10.1016/j.ijrobp.2025.07.1361","title":"Prediction of Severe Early Toxicities with pATM Blood Assay: Results from a Prospective Real-Life Study","year":2025,"lang":"en","type":"article","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alzheimer Society of Canada","funders":"","keywords":"Toxicity; Adverse effect; Common Terminology Criteria for Adverse Events; Clinical endpoint; Cohort; Prospective cohort study; Univariate analysis; Radiation therapy","score_opus":0.16084729468752254,"score_gpt":0.46352955740203117,"score_spread":0.3026822627145086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414557720","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.892754,0.000041269162,0.09962669,0.0008280589,0.002389042,0.0006855585,0.0014653354,0.00005784181,0.0021522052],"genre_scores_gemma":[0.90350217,0.00009948777,0.09475816,0.00015854824,0.0013449211,0.000027042268,0.000019903306,0.000023772081,0.000065991284],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995337,0.0015761368,0.0020284825,0.00035477217,0.0005098419,0.00019377403],"domain_scores_gemma":[0.9711166,0.024363738,0.0025404303,0.00027379778,0.0016068418,0.00009860248],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029138522,0.00023642546,0.00094934757,0.00017474039,0.00006854262,0.00003456079,0.0005338226,0.0003009946,0.000036354762],"category_scores_gemma":[0.029364474,0.00018777986,0.00019124651,0.0002696764,0.00028541614,0.00021551824,0.00010454666,0.00061610935,0.0000035277649],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060622636,0.0045377617,0.7682501,0.000023489662,0.006263166,0.000055344706,0.0029772993,0.0002530997,0.0008709277,0.1870776,0.001307691,0.02232124],"study_design_scores_gemma":[0.0161321,0.0043245633,0.2008369,0.00019950398,0.0007939096,0.000012385219,0.0006601791,0.0003585658,0.0014478039,0.77491313,0.00015030216,0.0001706617],"about_ca_topic_score_codex":0.00011429845,"about_ca_topic_score_gemma":0.000019058296,"teacher_disagreement_score":0.58783555,"about_ca_system_score_codex":0.00037080253,"about_ca_system_score_gemma":0.0007207327,"threshold_uncertainty_score":0.9788116},"labels":[],"label_agreement":null},{"id":"W4414649545","doi":"10.1016/j.ygyno.2025.04.052","title":"Post hoc tipping point and multiple imputation analyses to determine the impact of early censored patients in the ENGOT-EN6-NSGO/GOG-3031/RUBY trial","year":2025,"lang":"en","type":"article","venue":"Gynecologic Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"GlaxoSmithKline","keywords":"Post-hoc analysis; Food and drug administration; Clinical endpoint; Clinical trial; Imputation (statistics); Endometrial cancer; Disease; Tipping point (physics)","score_opus":0.3957069601206963,"score_gpt":0.5835680224617531,"score_spread":0.18786106234105682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414649545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921336,0.000019981188,0.0031695566,0.001030002,0.00050785637,0.0024112992,0.00009258543,0.000027299055,0.0006077863],"genre_scores_gemma":[0.9229116,0.000017234457,0.07615551,0.0006561102,0.00009151477,0.0001303205,0.0000049853206,0.000011657937,0.000021059715],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99411756,0.0035657997,0.0013065155,0.00039394925,0.00021917974,0.0003970096],"domain_scores_gemma":[0.85794497,0.14086714,0.00050090393,0.0003996164,0.00022043157,0.00006693781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004609563,0.00023177773,0.0009629031,0.00020391082,0.00012216638,0.00003688218,0.0004505416,0.00031963657,0.000089181325],"category_scores_gemma":[0.21393739,0.0001221767,0.00021579696,0.000500783,0.0002524871,0.00005339208,0.00023344418,0.00038237506,0.000007046966],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07641981,0.009039699,0.13465098,0.00034740233,0.0014512717,0.00013460293,0.014611026,0.0006113168,0.00592503,0.017648548,0.0060389703,0.73312134],"study_design_scores_gemma":[0.032413878,0.017133748,0.59661096,0.000052333544,0.00031542912,0.0000035203102,0.00092972995,0.0014361487,0.00020032996,0.35053754,0.000103513485,0.00026285177],"about_ca_topic_score_codex":0.00031502446,"about_ca_topic_score_gemma":0.00033723318,"teacher_disagreement_score":0.7328585,"about_ca_system_score_codex":0.00024797634,"about_ca_system_score_gemma":0.00018356019,"threshold_uncertainty_score":0.79268396},"labels":[],"label_agreement":null},{"id":"W4414663835","doi":"10.1186/s41927-025-00563-2","title":"Use of Bayesian techniques in clinical trials for rheumatoid arthritis and systemic sclerosis: a scoping review","year":2025,"lang":"en","type":"review","venue":"BMC Rheumatology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; McGill University Health Centre","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Bayesian probability; Rheumatoid arthritis; Clinical trial; Interim analysis; Sample size determination; Meta-analysis; MEDLINE; Bayesian statistics","score_opus":0.8160651542023729,"score_gpt":0.6417919796778571,"score_spread":0.17427317452451585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414663835","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015483674,0.85404986,0.13043234,0.000024802928,0.0006851808,0.014317282,0.0003571764,0.00011420987,0.00001758227],"genre_scores_gemma":[4.0723694e-7,0.5954869,0.4015237,0.00003386778,0.00002289084,0.0028523928,0.000009749348,0.000061706116,0.000008399134],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9513642,0.02718008,0.019292349,0.0012812791,0.0002849062,0.0005971658],"domain_scores_gemma":[0.5399581,0.45326647,0.0053988853,0.001029018,0.00020042344,0.0001471028],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05323616,0.0007658057,0.02584778,0.000512624,0.000059749404,0.00004777018,0.0005952821,0.0017981246,0.000044864006],"category_scores_gemma":[0.7386513,0.0006203866,0.0020245109,0.0005498302,0.00051478186,0.000079917,0.00036703522,0.00079328136,0.0000038702674],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003330005,0.000072725554,0.000039932253,0.4426335,0.000119631906,0.000001926364,0.0000028721943,3.3010243e-9,3.2127957e-8,0.016873844,0.0008083431,0.53941387],"study_design_scores_gemma":[0.00088791165,0.00013453233,8.632656e-7,0.9411471,0.000765832,0.00017336852,0.0000042755923,0.0000060421626,0.000001541789,0.05206054,0.0043821167,0.0004358647],"about_ca_topic_score_codex":0.000023281815,"about_ca_topic_score_gemma":0.00006605919,"teacher_disagreement_score":0.6854151,"about_ca_system_score_codex":0.0000686161,"about_ca_system_score_gemma":0.0015436372,"threshold_uncertainty_score":0.9996247},"labels":[],"label_agreement":null},{"id":"W4414740356","doi":"10.1093/clinchem/hvaf086.331","title":"A-346 Exploring Clinical Decision Making Cutoffs for the Siemens Serum HCG Assays in Pregnancy","year":2025,"lang":"en","type":"article","venue":"Clinical Chemistry","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Human chorionic gonadotropin; Pregnancy; Chart; Pregnancy test; Cutoff; Trophoblast; Retrospective cohort study; Gonadotropin","score_opus":0.7603317054314243,"score_gpt":0.6529169943358741,"score_spread":0.10741471109555012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414740356","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23353562,0.0014949739,0.7091217,0.0063720937,0.017691646,0.0049424716,0.0003269913,0.00072218,0.025792321],"genre_scores_gemma":[0.27381134,0.0008209775,0.71842414,0.0011970667,0.0027796591,0.00089664065,0.0000037106654,0.00011593871,0.0019505238],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991908,0.0008159933,0.004924919,0.0011611676,0.0004677528,0.0007221769],"domain_scores_gemma":[0.6488917,0.3488249,0.0005722013,0.0013478636,0.00019440173,0.00016899155],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015842214,0.00039090277,0.0015017077,0.000041362233,0.00019343132,0.000092214716,0.0012075262,0.0008284288,0.00024461656],"category_scores_gemma":[0.47997117,0.00029113013,0.00092238106,0.0004520196,0.0005187554,0.00008964099,0.0006895859,0.0017207251,0.000025796226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018985507,0.0020792969,0.086714216,0.0016237729,0.00048322056,0.00006442152,0.00004986384,0.000015236178,0.00006270066,0.029227596,0.022900324,0.8548808],"study_design_scores_gemma":[0.003907313,0.000113655144,0.011512917,0.003938418,0.0003065538,0.000002104521,0.000115070776,0.0017669837,0.0007628315,0.9704465,0.0067344666,0.0003931683],"about_ca_topic_score_codex":9.834578e-7,"about_ca_topic_score_gemma":0.000004830859,"teacher_disagreement_score":0.9412189,"about_ca_system_score_codex":0.000102904065,"about_ca_system_score_gemma":0.00025064952,"threshold_uncertainty_score":0.9999541},"labels":[],"label_agreement":null},{"id":"W4414847741","doi":"10.57264/cer-2025-0029","title":"Estimating per-protocol effects in external comparator analyses using real-world data","year":2025,"lang":"en","type":"review","venue":"Journal of Comparative Effectiveness Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of British Columbia","funders":"","keywords":"Emulation; Protocol (science); Randomized controlled trial; Clinical trial; Estimation; Research design; Comparator","score_opus":0.9569598007759129,"score_gpt":0.8145488453194007,"score_spread":0.14241095545651217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414847741","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003044505,0.4601847,0.41786152,0.000008119915,0.0015393363,0.11869996,0.0002178632,0.00004432052,0.0011397342],"genre_scores_gemma":[0.000061189865,0.08346219,0.9018487,0.0000038102287,0.001504925,0.012943582,0.000006091583,0.00011698508,0.00005257131],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.92521954,0.065600045,0.0045953,0.0010978556,0.002520218,0.0009670315],"domain_scores_gemma":[0.6130826,0.3809762,0.0027847704,0.0014122269,0.0014416386,0.0003025599],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05236287,0.000903824,0.011477893,0.0033605043,0.00028424044,0.00034329624,0.0034737417,0.0003683151,0.00006983357],"category_scores_gemma":[0.09448211,0.0006466719,0.0009070826,0.0041914876,0.0008793617,0.0004087211,0.0017738935,0.0052053737,0.000022693464],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031446698,0.0029458094,0.00062207103,0.35881606,0.0033851082,0.0014261442,0.00018465932,0.0008503123,0.00010320541,0.018571835,0.0014518873,0.6084982],"study_design_scores_gemma":[0.0058819787,0.0018189236,0.00079991,0.5612027,0.0029668235,0.00016493359,0.000086039,0.017660001,0.00020948132,0.39450148,0.013258701,0.0014490295],"about_ca_topic_score_codex":0.00015565843,"about_ca_topic_score_gemma":0.000073569914,"teacher_disagreement_score":0.6070492,"about_ca_system_score_codex":0.0015301104,"about_ca_system_score_gemma":0.0032754666,"threshold_uncertainty_score":0.99959844},"labels":[],"label_agreement":null},{"id":"W4415153955","doi":"10.1002/sim.70269","title":"Specification of Estimands for Complex Disease Processes Using Multistate Models and Utility Functions","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Jackknife resampling; Ranking (information retrieval); Disease; Simplicity; Variance (accounting); Resampling; Clinical trial","score_opus":0.7557390693740194,"score_gpt":0.6269280900231367,"score_spread":0.1288109793508827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415153955","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019012344,0.00013399674,0.9947554,0.00020530337,0.00024688715,0.00076512236,0.0015535849,0.000021031368,0.00041745984],"genre_scores_gemma":[0.1396071,0.000058272017,0.8600328,0.0000533095,0.000059816826,0.000032627126,0.00003669214,0.000012786855,0.00010659417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981097,0.00014914456,0.0010366866,0.00029879133,0.00022486533,0.0001807943],"domain_scores_gemma":[0.95796114,0.040952936,0.00024976442,0.00026940796,0.00046644034,0.000100290956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002272465,0.00013737107,0.00055664044,0.00016057977,0.00006859362,0.0000069984585,0.00010186203,0.00005729771,0.00005030606],"category_scores_gemma":[0.1169391,0.000117859265,0.000018743647,0.00034558895,0.0006086303,0.0000358319,0.000041707393,0.00012466358,1.5717978e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012840286,0.00037408364,0.0028416293,0.0063262545,0.00006920749,0.000006858551,0.0003210811,0.00014652836,0.0002068826,0.943565,0.0074299197,0.037428528],"study_design_scores_gemma":[0.0012690759,0.00006966034,0.004506612,0.00034379325,0.00018096846,2.7818007e-7,0.00011552271,0.2264406,0.000022391072,0.7668666,0.00011479493,0.00006966437],"about_ca_topic_score_codex":0.0000398098,"about_ca_topic_score_gemma":0.00004582336,"teacher_disagreement_score":0.22629407,"about_ca_system_score_codex":0.00003984972,"about_ca_system_score_gemma":0.00012757911,"threshold_uncertainty_score":0.8904993},"labels":[],"label_agreement":null},{"id":"W4415496638","doi":"10.1016/j.fertnstert.2025.10.024","title":"Fragility index analysis for robustness of evidence in randomized controlled trials leading to the US Food and Drug Administration approval of pharmacological therapies for endometriosis","year":2025,"lang":"en","type":"article","venue":"Fertility and Sterility","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Fragility; Food and drug administration; Randomized controlled trial; Endometriosis; Robustness (evolution); Drug","score_opus":0.6195453177350473,"score_gpt":0.5675220349567399,"score_spread":0.05202328277830737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415496638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.558854,0.0003289595,0.43480474,0.00058755913,0.00009833196,0.005130225,0.00018389786,0.0000068204376,0.00000550624],"genre_scores_gemma":[0.93369526,0.000047436155,0.064774536,0.00004788209,0.000020752384,0.0013941162,0.00000139792,0.0000036293454,0.000014988375],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9865503,0.009412556,0.003128726,0.00047755972,0.00023707,0.00019380113],"domain_scores_gemma":[0.46015286,0.53830415,0.0007907846,0.0003335981,0.00035634372,0.00006223572],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09040679,0.00019240212,0.005337068,0.0001861828,0.00008389917,0.00003775617,0.00019257533,0.0001478894,0.000023079123],"category_scores_gemma":[0.6391514,0.00010055065,0.00085571554,0.00058488926,0.00044510895,0.00006463511,0.00008811659,0.00012903007,1.3498501e-8],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9795054,0.00042162638,0.0045098597,0.000951876,0.0025342468,5.691874e-8,0.00037703643,0.000054757147,0.0002892767,0.0008464882,0.000007887131,0.010501472],"study_design_scores_gemma":[0.24910899,0.0009993793,0.2265217,0.0003333571,0.011844388,1.4983566e-7,0.0005327874,0.047072005,0.01063816,0.45262873,0.000016753846,0.00030360866],"about_ca_topic_score_codex":0.000026597834,"about_ca_topic_score_gemma":0.00020622069,"teacher_disagreement_score":0.73039645,"about_ca_system_score_codex":0.00002831987,"about_ca_system_score_gemma":0.00007769375,"threshold_uncertainty_score":0.9366176},"labels":[],"label_agreement":null},{"id":"W4415682896","doi":"10.1093/cid/ciaf587","title":"The Win Ratio Should Be Complemented by Other Win Statistics to Provide a Comprehensive Picture of Relative and Absolute Treatment Effects: The Case Study of the REPRIEVE Trial","year":2025,"lang":"en","type":"article","venue":"Clinical Infectious Diseases","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"University of Queensland","keywords":"Absolute (philosophy); Absolute risk reduction; MEDLINE; Summary statistics; Statistical analysis","score_opus":0.3975277339032623,"score_gpt":0.5791671400738646,"score_spread":0.1816394061706023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415682896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9522019,0.0002127465,0.030834539,0.0015080686,0.0011954731,0.011971146,0.0018934669,0.00006426876,0.000118406635],"genre_scores_gemma":[0.9923293,0.000056389938,0.004417899,0.0017249774,0.00020821152,0.00083378446,0.0000046593523,0.000047826197,0.00037697938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9905706,0.0061614565,0.002132263,0.000520179,0.00035653904,0.0002589784],"domain_scores_gemma":[0.8041672,0.19364531,0.00077863014,0.0009602199,0.00031851267,0.00013012314],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018031447,0.00032199905,0.0011365421,0.00003494923,0.00043826623,0.00006043603,0.00031314278,0.0001430005,0.000024431423],"category_scores_gemma":[0.104274824,0.00015057427,0.00029376964,0.00037030282,0.00097346364,0.000033694694,0.00034351798,0.00039511445,0.0000010568262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.068614475,0.0687859,0.16509786,0.0021191365,0.027016867,0.00052970345,0.015017494,0.0002447733,0.00025398386,0.296507,0.22496049,0.13085231],"study_design_scores_gemma":[0.10115786,0.025449524,0.03409085,0.0005537696,0.009407601,0.000015746195,0.008471961,0.0009769727,0.00030666092,0.81175333,0.007115332,0.0007003681],"about_ca_topic_score_codex":0.00032813536,"about_ca_topic_score_gemma":0.0008546191,"teacher_disagreement_score":0.51524633,"about_ca_system_score_codex":0.00008085095,"about_ca_system_score_gemma":0.00018209606,"threshold_uncertainty_score":0.90327024},"labels":[],"label_agreement":null},{"id":"W4415752840","doi":"10.1016/j.metop.2025.100414","title":"Synthetic target trial emulation and predictive modeling of amylin-pathway therapies for obesity and type 2 diabetes","year":2025,"lang":"en","type":"article","venue":"Metabolism Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Emulation; Type 2 diabetes; Clinical trial; Diabetes mellitus; Confidence interval; Obesity; Interval (graph theory)","score_opus":0.310969882251885,"score_gpt":0.4987228510000103,"score_spread":0.1877529687481253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415752840","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6010563,0.0012327479,0.39216775,0.00024818094,0.00085318374,0.003514262,0.00025595984,0.000028529535,0.0006430835],"genre_scores_gemma":[0.4915598,0.00006512068,0.50802857,0.000045562752,0.000091799026,0.000102677164,0.0000022037198,0.000013961384,0.00009028575],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982944,0.00052813895,0.00059506705,0.0003031256,0.00012712795,0.0001521383],"domain_scores_gemma":[0.9842863,0.015045858,0.00018011939,0.00025313272,0.00018828438,0.00004629707],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003300464,0.00013550978,0.00080538704,0.00006121358,0.00008994761,0.00006714986,0.00020592439,0.00011567748,0.00002950143],"category_scores_gemma":[0.034184787,0.000107258275,0.000056480236,0.00012239775,0.000106722015,0.00010762199,0.00022848202,0.00009507815,3.46646e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.024792287,0.0007869653,0.0015437405,0.0009654776,0.0010287645,5.247163e-7,0.0017494378,0.00036069617,0.002129791,0.9238776,0.00027125786,0.04249344],"study_design_scores_gemma":[0.007925104,0.00014419132,0.0006708971,0.00008582972,0.0002529931,4.9275258e-8,0.00006477715,0.06211719,0.0020517306,0.92639214,0.00019680923,0.00009831618],"about_ca_topic_score_codex":0.00000935959,"about_ca_topic_score_gemma":0.0000012358967,"teacher_disagreement_score":0.11586083,"about_ca_system_score_codex":0.0000072784405,"about_ca_system_score_gemma":0.000055494285,"threshold_uncertainty_score":0.9739507},"labels":[],"label_agreement":null},{"id":"W4415846907","doi":"10.1002/cpdd.1623","title":"What Does an Editor Do in 2025?","year":2025,"lang":"en","type":"editorial","venue":"Clinical Pharmacology in Drug Development","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Publishing; Conversation; Context (archaeology); Clinical trial; Task (project management); Alternative medicine; Clinical pharmacology; Clinical Practice","score_opus":0.30004322525617194,"score_gpt":0.6214337519721888,"score_spread":0.3213905267160168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415846907","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002214307,0.0003060852,0.00023617293,0.0012839393,0.993291,0.001901612,0.000115434756,0.00014746361,0.00050395116],"genre_scores_gemma":[0.000026638743,0.0035966649,0.19875035,0.0010030518,0.7907175,0.0008575447,0.00007715633,0.00010430965,0.004866815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9781719,0.008723741,0.007981012,0.0024853416,0.0013542523,0.0012837726],"domain_scores_gemma":[0.6406134,0.35581917,0.001382977,0.0010545988,0.00054344145,0.00058645115],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.031366833,0.0009943128,0.0039355485,0.00065700395,0.00010904443,0.00018226934,0.0021990053,0.0039809197,0.0017909976],"category_scores_gemma":[0.19660242,0.0008090833,0.00038510148,0.0006935765,0.0007364748,0.0003258113,0.001275818,0.0071917437,0.00019752952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007302776,0.002543357,0.0002935391,0.00058805797,0.00027918938,0.00027052726,0.00048753803,0.0000021655717,0.0000024442675,0.00025285518,0.9740689,0.020481165],"study_design_scores_gemma":[0.0053686546,0.00010215804,0.00019837284,0.001343808,0.00020271853,2.259251e-7,0.00018682869,0.00002065956,0.000102450555,0.1868938,0.8047478,0.0008325136],"about_ca_topic_score_codex":0.000020226216,"about_ca_topic_score_gemma":0.0004274879,"teacher_disagreement_score":0.34709543,"about_ca_system_score_codex":0.0009084,"about_ca_system_score_gemma":0.0040457603,"threshold_uncertainty_score":0.999436},"labels":[],"label_agreement":null},{"id":"W4415938170","doi":"10.1088/2516-1091/ae1c05","title":"Computational modeling and simulation for medical devices: a summary of the 2024 FDA/MDIC Symposium","year":2025,"lang":"en","type":"article","venue":"Progress in Biomedical Engineering","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Credibility; Field (mathematics); Computational model; Modeling and simulation; Panel discussion; Product (mathematics); Authorization; Food and drug administration","score_opus":0.14456353378277925,"score_gpt":0.488932452731929,"score_spread":0.3443689189491497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415938170","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009981281,0.00049459696,0.9867292,0.0013884219,0.0006992,0.0005950157,0.000023256516,0.000043755,0.000045290308],"genre_scores_gemma":[0.4857082,0.000014198399,0.51395184,0.00007594417,0.00010850144,0.0001097043,0.000002802135,0.000015838812,0.00001293886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814045,0.000102109036,0.0008453918,0.00022744958,0.00048344745,0.00020115732],"domain_scores_gemma":[0.9774884,0.022111231,0.000085931446,0.00014595983,0.00007545498,0.00009300099],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022009455,0.00012226585,0.0003635488,0.00012898183,0.00003369683,0.000015349344,0.0002289544,0.00021359662,0.00001586801],"category_scores_gemma":[0.025354972,0.000088414774,0.000073443014,0.0003889842,0.0002070012,0.000030712094,0.000170521,0.00026021132,1.6120615e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046241583,0.0010400497,0.009447176,0.013210805,0.00048998237,0.000016146518,0.0004848089,0.43103483,0.00006969375,0.3717364,0.0005251472,0.17148255],"study_design_scores_gemma":[0.0010164356,0.000022433962,0.0001829856,0.001064239,0.000035263954,8.190481e-7,0.000008988619,0.84547794,0.0000104109395,0.15195882,0.0001525898,0.00006909221],"about_ca_topic_score_codex":0.0000014673182,"about_ca_topic_score_gemma":7.482086e-7,"teacher_disagreement_score":0.47572693,"about_ca_system_score_codex":0.00003587591,"about_ca_system_score_gemma":0.00009488546,"threshold_uncertainty_score":0.9828549},"labels":[],"label_agreement":null},{"id":"W4415940293","doi":"10.1016/j.annonc.2025.08.2935","title":"2319P Landscape of phase III clinical trials in cancer: A cross-sectional analysis","year":2025,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Clinical trial; Phase (matter); Phases of clinical research; MEDLINE","score_opus":0.8638329969577937,"score_gpt":0.768263488987001,"score_spread":0.09556950797079267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415940293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95000833,0.00041659566,0.037938327,0.0019482299,0.0015847965,0.000730584,0.00045161124,0.000045846395,0.0068756505],"genre_scores_gemma":[0.8816368,0.0009692962,0.11572249,0.00083037344,0.0003456279,0.00010789351,0.0000067454102,0.000019337063,0.0003614176],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98609924,0.0067312974,0.0061683957,0.0004307536,0.00028208378,0.00028824547],"domain_scores_gemma":[0.80333173,0.19387954,0.0018061084,0.0003939487,0.00049670483,0.000091944916],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05098938,0.00015247603,0.003791072,0.00053231895,0.000022284585,0.000009325622,0.00033843526,0.00055007904,0.001021895],"category_scores_gemma":[0.29627177,0.0001276307,0.0010710666,0.0012615079,0.0004517733,0.000035575333,0.00012022442,0.00038374268,0.0000021279045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009266528,0.00785077,0.6538387,0.0003095528,0.006020845,0.000026190353,0.00010395651,0.00011331732,0.0002853121,0.10889335,0.015815474,0.197476],"study_design_scores_gemma":[0.016173214,0.002032463,0.14623395,0.00008454722,0.0013002065,7.8081007e-7,0.000039885777,0.0012203588,0.0015267106,0.82693195,0.0042805355,0.0001753924],"about_ca_topic_score_codex":0.00013015144,"about_ca_topic_score_gemma":0.00020644642,"teacher_disagreement_score":0.7180386,"about_ca_system_score_codex":0.00002919749,"about_ca_system_score_gemma":0.0005352869,"threshold_uncertainty_score":0.9998913},"labels":[],"label_agreement":null},{"id":"W4415940703","doi":"10.1016/j.annonc.2025.08.3333","title":"2723P Reverse fragility index (RFI) of systemic therapy trials in soft tissue sarcoma (STS)","year":2025,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Princess Margaret Cancer Centre","funders":"","keywords":"Systemic therapy; Soft tissue sarcoma; Clinical trial; Fragility; Randomized controlled trial; Sarcoma","score_opus":0.7358110313541325,"score_gpt":0.661529090089907,"score_spread":0.07428194126422549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415940703","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6521668,0.004164283,0.3117882,0.009795216,0.0033039548,0.005026811,0.0003138176,0.00013399938,0.0133069195],"genre_scores_gemma":[0.88721544,0.0014547139,0.109651566,0.001190261,0.000126466,0.000061815765,0.0000016562698,0.000022848559,0.00027525768],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882158,0.0074437093,0.0033434404,0.00039094777,0.00027010153,0.0003359951],"domain_scores_gemma":[0.8576032,0.13973577,0.0014213952,0.00072976446,0.00042915047,0.00008070674],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029399388,0.00020393525,0.0031742638,0.00021451578,0.000026181322,0.0000053857116,0.0004757359,0.00059780135,0.0006103054],"category_scores_gemma":[0.23404649,0.00017371998,0.00030980527,0.00041525456,0.00039186398,0.00004045493,0.00013663688,0.00037652635,0.000011270827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004720222,0.0041859304,0.010462436,0.0016793589,0.0007365414,0.000068735375,0.0009275414,0.000043463548,0.009307227,0.1061292,0.03982666,0.8219127],"study_design_scores_gemma":[0.0041339947,0.0012437522,0.0058064233,0.0005359417,0.00006630737,0.0000040864925,0.00020932124,0.00013348208,0.009003729,0.97263956,0.0060633845,0.00015999876],"about_ca_topic_score_codex":0.00021479127,"about_ca_topic_score_gemma":0.000057420606,"teacher_disagreement_score":0.8665104,"about_ca_system_score_codex":0.000047743593,"about_ca_system_score_gemma":0.0003522149,"threshold_uncertainty_score":0.9994376},"labels":[],"label_agreement":null},{"id":"W4415941930","doi":"10.1016/j.annonc.2025.08.2895","title":"2279MO Discontinuation and attrition rates in phase II or phase III first-line randomized clinical trials (RCTs) of solid tumors","year":2025,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Discontinuation; Attrition; Randomized controlled trial; Clinical trial; Phases of clinical research; Cancer","score_opus":0.768843418923632,"score_gpt":0.7129977182229175,"score_spread":0.055845700700714485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415941930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8395521,0.0004563254,0.14149305,0.011742777,0.0010300825,0.0042291246,0.00043528643,0.000041887917,0.0010193367],"genre_scores_gemma":[0.84962076,0.002764267,0.14579742,0.00077335985,0.00032215813,0.00027040037,0.000022501838,0.000025120256,0.00040402147],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.979111,0.012554857,0.0073652887,0.00044351723,0.00022649896,0.00029881689],"domain_scores_gemma":[0.6390716,0.35734105,0.002671039,0.0003526798,0.00044469358,0.00011893284],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07251871,0.00022455925,0.005616134,0.00028888325,0.00005739608,0.000008224742,0.00020040316,0.00042871956,0.0003027393],"category_scores_gemma":[0.61204827,0.0001600627,0.00046697204,0.0003740276,0.00085354043,0.000086760054,0.00014957647,0.00032265592,0.0000014315161],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.42553484,0.01681389,0.000076869306,0.0005072787,0.00063445646,0.00003778383,0.000346082,0.000005277081,0.0010643329,0.05244207,0.0072549796,0.49528214],"study_design_scores_gemma":[0.3863232,0.0064726556,0.0000345883,0.0005198001,0.00039971588,0.0000019293316,0.000081501545,0.001829619,0.008951723,0.59465367,0.00060040894,0.00013118524],"about_ca_topic_score_codex":0.000031046122,"about_ca_topic_score_gemma":0.00007892846,"teacher_disagreement_score":0.5422116,"about_ca_system_score_codex":0.000019968173,"about_ca_system_score_gemma":0.00028084972,"threshold_uncertainty_score":0.9550372},"labels":[],"label_agreement":null},{"id":"W4416060115","doi":"10.1093/jnci/djaf322","title":"De-escalation trials do not always need to be noninferiority: a case for superiority design de-escalation trials in oncology","year":2025,"lang":"en","type":"article","venue":"JNCI Journal of the National Cancer Institute","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Ontario Institute for Cancer Research","funders":"Government of Ontario","keywords":"Compromise; Clinical trial; Disease; Test (biology); Cancer treatment; Clinical study design","score_opus":0.803506148629958,"score_gpt":0.6524075063508564,"score_spread":0.15109864227910152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416060115","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070127144,0.00007574214,0.89326346,0.027252777,0.0058200946,0.0026820013,0.00042569466,0.000021010748,0.0003320938],"genre_scores_gemma":[0.28091875,0.00006141098,0.7127995,0.0035041212,0.0022732692,0.0003027192,0.0000015149991,0.000023984629,0.00011475226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98796433,0.0064643514,0.0040889075,0.0002865242,0.0008328634,0.000363042],"domain_scores_gemma":[0.86735016,0.12812322,0.002340525,0.0002338953,0.0017365662,0.00021561509],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08142265,0.00024322503,0.0019770944,0.0004716736,0.00023446734,0.0001345355,0.00045196296,0.0004163038,0.000092510665],"category_scores_gemma":[0.5557394,0.0001773121,0.0006603846,0.00074289745,0.00013254577,0.00029086642,0.000097290394,0.0006103914,0.0000011603677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031623024,0.0018715148,0.005479869,0.0007591119,0.0022313355,0.00030268222,0.003600731,0.058293555,0.03248761,0.62791455,0.05600824,0.17942779],"study_design_scores_gemma":[0.008918289,0.00043216755,0.0033980964,0.000527315,0.00089902995,0.00025325536,0.00010842098,0.0051864027,0.009121621,0.9499103,0.020957114,0.00028799978],"about_ca_topic_score_codex":0.00010143294,"about_ca_topic_score_gemma":0.00024563572,"teacher_disagreement_score":0.47431678,"about_ca_system_score_codex":0.0028871805,"about_ca_system_score_gemma":0.004310994,"threshold_uncertainty_score":0.9458687},"labels":[],"label_agreement":null},{"id":"W4416257149","doi":"10.1002/pst.70049","title":"Great Wall: A Generalized Dose Optimization Design for Drug Combination Trials Maximizing Survival Benefit","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Advancing Translational Sciences; Ralph W. and Grace M. Showalter Research Trust Fund; National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; Indiana Clinical and Translational Sciences Institute","keywords":"Clinical trial; Modular design; Clinical study design; Maximum tolerated dose; Set (abstract data type); Randomization; Optimal design","score_opus":0.7105486185993154,"score_gpt":0.606923267544355,"score_spread":0.1036253510549604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416257149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015316112,0.00012439316,0.9907375,0.0016448032,0.0020685655,0.003339022,0.0011363853,0.00024779967,0.00054835435],"genre_scores_gemma":[0.0018307318,0.0002723443,0.9950361,0.0008576047,0.00024350904,0.00050244416,0.00008856695,0.000085839594,0.001082815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9920381,0.003348417,0.0025339732,0.00071837846,0.00064931606,0.00071185996],"domain_scores_gemma":[0.83318067,0.16494568,0.0005349164,0.00040254733,0.00064945035,0.00028674625],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.014297856,0.00046415252,0.0017138852,0.00019175066,0.00032165417,0.00020834846,0.00044087516,0.00025690816,0.0008153568],"category_scores_gemma":[0.17915553,0.00042005823,0.0002822408,0.00047684138,0.00021832781,0.00011036002,0.00014683187,0.00040177998,0.000016116837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019963542,0.00050588895,0.000052062303,0.00051504135,0.00038464836,0.000009352721,0.00005265288,0.0041004303,0.00014372908,0.9350118,0.016947659,0.040280387],"study_design_scores_gemma":[0.006591571,0.00008043539,0.000023242248,0.00007590482,0.00094271306,9.2798626e-7,0.000010484402,0.34201205,0.0014786478,0.64663,0.0018638221,0.00029020393],"about_ca_topic_score_codex":0.00001445199,"about_ca_topic_score_gemma":0.0000038295393,"teacher_disagreement_score":0.3379116,"about_ca_system_score_codex":0.00024265384,"about_ca_system_score_gemma":0.00015711243,"threshold_uncertainty_score":0.9998251},"labels":[],"label_agreement":null},{"id":"W4416391724","doi":"10.1016/j.annonc.2025.09.076","title":"LBA64 Safety and performance of a multi-cancer early detection (MCED) test in an intended-use population: Initial results from the registrational PATHFINDER II study","year":2025,"lang":"en","type":"article","venue":"Annals of Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"","keywords":"Pathfinder; Test (biology); Test site","score_opus":0.6448445048999395,"score_gpt":0.6030298954929485,"score_spread":0.041814609406991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416391724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99555904,0.000018522667,0.0022166884,0.0009316077,0.00021956018,0.0005662087,0.00030980032,0.000013575194,0.00016498615],"genre_scores_gemma":[0.96536636,0.00005484801,0.03418508,0.00020627838,0.00009193108,0.00003629426,0.0000055237415,0.0000076579745,0.000046026904],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972117,0.00091638975,0.0012717168,0.00028325917,0.00017982401,0.0001371225],"domain_scores_gemma":[0.9683989,0.030426417,0.0005106033,0.00030776006,0.0003216336,0.000034680048],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002654003,0.000114269824,0.00050954416,0.0000717951,0.00008575395,0.0000111518975,0.00016129125,0.00018449941,0.00002217751],"category_scores_gemma":[0.045862924,0.000087136286,0.000044016324,0.00021879743,0.00021402935,0.00013435408,0.00010921436,0.00027421175,3.4081583e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.017672585,0.0067542987,0.5210181,0.00010563667,0.0002911151,0.00001399588,0.0045912885,0.000089696194,0.00075707346,0.011150386,0.0003245837,0.43723127],"study_design_scores_gemma":[0.0036546998,0.004146077,0.9274267,0.00010380748,0.00005520053,6.6860787e-7,0.000273866,0.0017439529,0.00054056535,0.061896794,0.00007418866,0.00008346236],"about_ca_topic_score_codex":0.0009527961,"about_ca_topic_score_gemma":0.003735879,"teacher_disagreement_score":0.4371478,"about_ca_system_score_codex":0.000030338619,"about_ca_system_score_gemma":0.00011197514,"threshold_uncertainty_score":0.9621742},"labels":[],"label_agreement":null},{"id":"W4416425153","doi":"10.1016/j.tmrv.2025.150935","title":"A Practical Review of Adaptive Platform Trials","year":2025,"lang":"en","type":"review","venue":"Transfusion Medicine Reviews","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Sunnybrook Health Science Centre","funders":"","keywords":"Bayesian probability; Randomized controlled trial; Clinical trial; Psychological intervention; Randomization; Protocol (science); Adaptive design; Coronavirus disease 2019 (COVID-19); Pandemic","score_opus":0.9123074522640604,"score_gpt":0.7161383739664361,"score_spread":0.1961690782976243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416425153","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.278044e-9,0.8691444,0.10655011,0.00064418226,0.0012106324,0.013611731,0.00019527416,0.000066705674,0.008576999],"genre_scores_gemma":[7.632984e-11,0.6866635,0.3108249,0.00047759723,0.00064601144,0.00083877245,0.000023158,0.000062542415,0.0004635083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95774436,0.020700496,0.018322317,0.00121681,0.0014429962,0.00057301554],"domain_scores_gemma":[0.6608111,0.32990912,0.006501079,0.0019844756,0.00040903417,0.00038515913],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08340504,0.0012125795,0.036169957,0.000407442,0.00007217126,0.0000072055045,0.0008400519,0.00091948465,0.0071950452],"category_scores_gemma":[0.6908552,0.0006384291,0.004331402,0.0017755546,0.00049059145,0.000072832976,0.00013450041,0.0018310017,0.00011906407],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021528744,0.00008791693,1.0417891e-8,0.40836352,0.00016233794,0.000008637542,0.000008363674,1.8131338e-10,7.01431e-8,0.022251721,0.07449745,0.49459845],"study_design_scores_gemma":[0.00042054322,0.0002408479,7.746612e-9,0.46060342,0.014275613,0.000023779743,0.0000041683916,2.3181782e-7,3.6259598e-7,0.034816407,0.4893809,0.00023373468],"about_ca_topic_score_codex":0.000022283088,"about_ca_topic_score_gemma":0.0000055688615,"teacher_disagreement_score":0.6074502,"about_ca_system_score_codex":0.0001325125,"about_ca_system_score_gemma":0.0010853588,"threshold_uncertainty_score":0.9996067},"labels":[],"label_agreement":null},{"id":"W4416524812","doi":"10.1016/b978-0-323-90509-1.00011-4","title":"Sample size calculation","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary","funders":"","keywords":"Sample size determination; Sample (material); Key (lock); Large sample; Statistical analysis","score_opus":0.3028094312677775,"score_gpt":0.48777460147445406,"score_spread":0.18496517020667658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416524812","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.656579e-7,0.00007892949,0.012261847,0.000107537664,0.001126769,0.0009571376,0.00041184007,0.00017474727,0.98488045],"genre_scores_gemma":[0.000003910414,0.000016436572,0.4292116,0.00028449378,0.00042717994,0.000028934828,0.0000034344805,0.00006015009,0.5699639],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969284,0.00023201373,0.0013786058,0.0006254348,0.0005259444,0.00030959942],"domain_scores_gemma":[0.8865634,0.11171545,0.00048981834,0.000913001,0.00018109352,0.0001371904],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017135963,0.00047817468,0.0013059694,0.00009419462,0.00009595666,0.000047334393,0.00036229097,0.00079349946,0.0020283428],"category_scores_gemma":[0.10496081,0.0004359594,0.00048284617,0.000018000455,0.00019432601,0.00001581823,0.00022590571,0.0007449061,0.00015339379],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016576656,0.0000067064907,8.280616e-7,0.00018475196,0.00009707321,0.000006751251,0.000013659681,3.584923e-8,0.0000016787358,0.42684045,0.0016862011,0.5711453],"study_design_scores_gemma":[0.0002219177,0.000026037998,0.0000030879876,0.00045064892,0.0002686434,9.699809e-7,5.0257614e-7,0.000009986308,0.000012846946,0.5755052,0.42326486,0.00023533434],"about_ca_topic_score_codex":5.960974e-7,"about_ca_topic_score_gemma":0.000005381497,"teacher_disagreement_score":0.57091,"about_ca_system_score_codex":0.00012814147,"about_ca_system_score_gemma":0.00016941392,"threshold_uncertainty_score":0.9998092},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4416524834","doi":"10.1016/b978-0-323-90509-1.00020-5","title":"Correlation","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Waterloo","funders":"","keywords":"Correlation; Context (archaeology); Measure (data warehouse); Outcome (game theory); Relation (database)","score_opus":0.3092028071510501,"score_gpt":0.48504396379255144,"score_spread":0.17584115664150135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416524834","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9721013e-7,0.0001285144,0.010409161,0.00007370229,0.0018143543,0.00080198044,0.00011495056,0.00016232838,0.98649484],"genre_scores_gemma":[0.0000021437227,0.000025492283,0.26528293,0.00025516882,0.00044506017,0.000026328675,0.0000042542174,0.00006282468,0.7338958],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99745095,0.00017718902,0.0011888886,0.0005140458,0.00043075572,0.00023818579],"domain_scores_gemma":[0.9721825,0.026222566,0.0005069254,0.0008158953,0.00015907263,0.00011299873],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015125705,0.00040331855,0.0010823696,0.0001299625,0.0000756787,0.000034796103,0.00031947787,0.0007910364,0.0015332069],"category_scores_gemma":[0.0196285,0.0003674081,0.00037730444,0.000013197135,0.00017589945,0.0000140729635,0.00018262325,0.00085076754,0.00039088383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011985531,0.000004535023,3.9922585e-7,0.00012016289,0.000068108966,0.000008218995,0.000010293287,4.082686e-8,3.6009155e-7,0.46095425,0.0026057456,0.5362159],"study_design_scores_gemma":[0.00017178708,0.000024386112,8.697582e-7,0.00056145835,0.00024495198,0.0000013933752,5.2237243e-7,0.000015467853,0.0000040229347,0.55168355,0.44710556,0.00018600389],"about_ca_topic_score_codex":6.9131495e-8,"about_ca_topic_score_gemma":0.00000201368,"teacher_disagreement_score":0.5360299,"about_ca_system_score_codex":0.000097812735,"about_ca_system_score_gemma":0.00014512135,"threshold_uncertainty_score":0.9998778},"labels":[],"label_agreement":null},{"id":"W4416526465","doi":"10.1016/b978-0-323-90509-1.00023-0","title":"Continuous variable analyses: t-test, Mann–Whitney U test, and Wilcoxon signed-rank test","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Wilcoxon signed-rank test; Nonparametric statistics; Parametric statistics; Statistical hypothesis testing; Test (biology); Population; Variable (mathematics)","score_opus":0.22698329963221686,"score_gpt":0.4622624510964926,"score_spread":0.23527915146427575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416526465","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023027062,0.00084565964,0.0050205574,0.00013543051,0.0006406148,0.0020025377,0.0014196477,0.00032870978,0.98960453],"genre_scores_gemma":[0.000029897428,0.0001490523,0.32222873,0.0006193471,0.0006641134,0.00010075713,0.000013871106,0.00017814293,0.6760161],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99369824,0.0003500412,0.002720784,0.0015602187,0.0008564982,0.0008142395],"domain_scores_gemma":[0.8407994,0.15552738,0.0011241212,0.0016513518,0.000461246,0.00043653397],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034669214,0.0012360422,0.0034961724,0.00035476006,0.00025078628,0.00024153224,0.0008286643,0.0014096795,0.0016634568],"category_scores_gemma":[0.13150029,0.0011068352,0.00053386996,0.00009578166,0.000702003,0.000062121486,0.0006341084,0.001560469,0.00015462711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062976054,0.00023603503,0.000089638765,0.0018704843,0.0006941258,0.00021646635,0.000075124975,1.9683193e-7,0.0002710953,0.18403272,0.010814554,0.8016366],"study_design_scores_gemma":[0.0010207022,0.00040948886,0.0000079115825,0.0023043677,0.0019839555,0.00002233582,0.000007965692,0.00004869488,0.00010724396,0.7151757,0.2780667,0.00084495277],"about_ca_topic_score_codex":0.0000029176492,"about_ca_topic_score_gemma":0.000009496724,"teacher_disagreement_score":0.8007916,"about_ca_system_score_codex":0.00015095252,"about_ca_system_score_gemma":0.00039262287,"threshold_uncertainty_score":0.9998867},"labels":[],"label_agreement":null},{"id":"W4416538899","doi":"10.2337/dc25-1508","title":"The Role of Adaptive and Innovative Trial Designs in Diabetes Research: A Scoping Review","year":2025,"lang":"en","type":"article","venue":"Diabetes Care","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Leicester Biomedical Research Centre; National Health and Medical Research Council; Medical Research Council; Diabetes Victoria; MTPConnect; Servier; Nestlé Health Science; Deakin University; Diabetes Australia; British Heart Foundation; Novo Nordisk; Daiichi-Sankyo; National Institute for Health and Care Research; Diabetes Canada; Sanofi; Amgen; Pfizer; AstraZeneca; Eli Lilly and Company","keywords":"Incentive; Diabetes mellitus; Protocol (science); Research design; Clinical trial; MEDLINE","score_opus":0.6309787262186826,"score_gpt":0.6005206558920146,"score_spread":0.03045807032666792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416538899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69535494,0.2534658,0.0011622063,0.0019998997,0.0011984631,0.022760527,0.00041938416,0.00014201371,0.02349679],"genre_scores_gemma":[0.7619117,0.0073123015,0.22695494,0.00075917237,0.00026608643,0.002642456,0.000006357551,0.00007604924,0.000070976974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99526846,0.002779175,0.0009408018,0.0002901431,0.00033154237,0.00038988437],"domain_scores_gemma":[0.8704249,0.12829444,0.00019613573,0.00036544772,0.0006778421,0.00004117718],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0078853415,0.00013463454,0.00075849064,0.00013300365,0.000116845236,0.000030242989,0.0002809668,0.00010667464,0.000013951802],"category_scores_gemma":[0.20645912,0.000093481125,0.00006458808,0.0012541063,0.00048934453,0.000040506122,0.00025308586,0.00041251202,0.0000040528116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018344532,0.00024341448,0.031714257,0.021127747,0.00032279667,0.0000027447213,0.0016642093,4.203697e-7,0.0011941574,0.53071404,0.0021841447,0.4089976],"study_design_scores_gemma":[0.003878226,0.00031269842,0.00038658569,0.047316197,0.0000505494,9.935265e-9,0.0014069681,0.000039140188,0.010732627,0.9356676,0.00009202953,0.00011741354],"about_ca_topic_score_codex":0.0000027633268,"about_ca_topic_score_gemma":0.000013302557,"teacher_disagreement_score":0.4088802,"about_ca_system_score_codex":0.00005487607,"about_ca_system_score_gemma":0.00020160593,"threshold_uncertainty_score":0.8002252},"labels":[],"label_agreement":null},{"id":"W4416593520","doi":"10.1007/s43441-025-00893-w","title":"In Silico Clinical Trials in Drug Development: A Systematic Review","year":2025,"lang":"en","type":"article","venue":"Therapeutic Innovation & Regulatory Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Clinical trial; Context (archaeology); In silico; Drug development; Drug; Systematic review; MEDLINE; Pharmacy; Drug trial","score_opus":0.6504858736111147,"score_gpt":0.6425682271148281,"score_spread":0.007917646496286568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416593520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7097721,0.01511165,0.19883324,0.01664024,0.011102709,0.033492487,0.000021236767,0.0006820579,0.014344302],"genre_scores_gemma":[0.63312566,0.00040628668,0.33857012,0.023956602,0.00016064242,0.0009616463,0.0000019913653,0.000054254422,0.0027627714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9812841,0.0073543447,0.009055832,0.00077296916,0.0010265312,0.0005062596],"domain_scores_gemma":[0.8874733,0.10630365,0.0030758483,0.0019429307,0.001079502,0.00012479827],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23868011,0.00024943205,0.0024772526,0.0010536371,0.00012096909,0.000067990135,0.0009135078,0.00015601378,0.00009580382],"category_scores_gemma":[0.3220279,0.00019477915,0.00012378024,0.008746468,0.00074929366,0.00028492455,0.00014720639,0.00049488666,0.000036519144],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048388716,0.00028959863,0.0011187552,0.03760734,0.00004168796,0.0000044976136,0.00022239336,8.7410086e-7,0.0005424976,0.9477448,0.0004440721,0.011935129],"study_design_scores_gemma":[0.0012870998,0.000024347491,0.008717921,0.056804877,0.00011038391,0.0000021644028,0.00007797642,0.00025673572,0.0012790051,0.93089026,0.00025203673,0.00029721876],"about_ca_topic_score_codex":0.0000040729983,"about_ca_topic_score_gemma":0.000012475153,"teacher_disagreement_score":0.13973689,"about_ca_system_score_codex":0.00033103878,"about_ca_system_score_gemma":0.0013073175,"threshold_uncertainty_score":0.79428625},"labels":[],"label_agreement":null},{"id":"W4416605431","doi":"10.1186/s13063-025-09291-x","title":"Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; SickKids Foundation; Institute for Clinical Evaluative Sciences; Public Health Ontario; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Groupe canadien de recherche en soins intensifs; National Sanitarium Association","keywords":"Bayesian probability; Clinical trial; Equity (law); Bayes' theorem; Bayesian statistics; MEDLINE; Research design; Bayesian inference","score_opus":0.7178661278879936,"score_gpt":0.6388013046769554,"score_spread":0.07906482321103825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416605431","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009294756,0.04713152,0.9123366,0.00014824295,0.0016457095,0.028472787,0.00028574775,0.00012929435,0.00055533904],"genre_scores_gemma":[0.0035896995,0.0027718828,0.9921546,0.00019116716,0.00015592232,0.0010216318,0.0000014337406,0.000054269745,0.00005936823],"study_design_codex":"systematic_review","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9148016,0.07194892,0.011271217,0.0008670759,0.00053324667,0.0005779482],"domain_scores_gemma":[0.51292473,0.48123422,0.0041554035,0.0013142515,0.0002131992,0.00015816574],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1054339,0.00054728414,0.013630695,0.0003395569,0.00006195327,0.00004307637,0.00043043977,0.0003242667,0.000072411196],"category_scores_gemma":[0.69310504,0.0003777072,0.0013637735,0.00087851647,0.00009610973,0.00008594276,0.00016101495,0.00021015228,0.000005005078],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020316623,0.0010935339,0.00012225047,0.7501651,0.0058671953,0.00004166793,0.0003633623,0.00013889649,0.004368815,0.17494702,0.00019505608,0.0606654],"study_design_scores_gemma":[0.0056613856,0.0006008755,0.000029092747,0.3035052,0.009465612,0.0000036640517,0.00004635522,0.00081571855,0.035610165,0.6438549,0.000005629406,0.0004013705],"about_ca_topic_score_codex":0.00013279967,"about_ca_topic_score_gemma":0.000027025133,"teacher_disagreement_score":0.58767116,"about_ca_system_score_codex":0.0006327593,"about_ca_system_score_gemma":0.00030390956,"threshold_uncertainty_score":0.9998675},"labels":[],"label_agreement":null},{"id":"W4416799561","doi":"10.1136/bmjopen-2025-111418","title":"Comparison of intention-to-treat and per-protocol results in non-inferiority trials: a methodological review protocol","year":2025,"lang":"en","type":"review","venue":"BMJ Open","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Protocol (science); Research ethics; Health services research; Systematic review; MEDLINE; Register (sociolinguistics); Research design","score_opus":0.9570146823012856,"score_gpt":0.8138797967877078,"score_spread":0.14313488551357778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416799561","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.702893e-9,0.027298601,0.009934803,0.00020099578,0.0001168844,0.95483786,0.0004247403,0.000029375986,0.0071567227],"genre_scores_gemma":[1.0674527e-9,0.074951135,0.40320376,0.000059372524,0.000057751688,0.52137136,0.0000059778486,0.000024987876,0.0003256746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9345495,0.048032977,0.014534657,0.001583221,0.0007818668,0.0005177527],"domain_scores_gemma":[0.6754065,0.3152979,0.0062522343,0.0022837757,0.00043957887,0.00031997266],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12823121,0.0007764761,0.019752134,0.00028164315,0.00006221809,0.00014212163,0.001814161,0.0008580895,0.00046508305],"category_scores_gemma":[0.7654327,0.0004929962,0.0010279128,0.0009716501,0.00019194362,0.00008075483,0.002827627,0.0009796682,0.00003525479],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012132826,0.0003716248,0.0000083100995,0.3844548,0.000074836884,0.000008171214,0.000019720597,1.5128654e-8,1.83682e-7,0.0020125757,0.00931477,0.6025217],"study_design_scores_gemma":[0.0037965646,0.0006903591,0.000013103045,0.40408856,0.0012368428,0.0000062783793,0.000013023025,0.000004631947,0.0000043834007,0.07187348,0.5177606,0.0005122018],"about_ca_topic_score_codex":0.000073340096,"about_ca_topic_score_gemma":0.000034514553,"teacher_disagreement_score":0.63720155,"about_ca_system_score_codex":0.00015275154,"about_ca_system_score_gemma":0.0008260443,"threshold_uncertainty_score":0.99975216},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"protocol","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4416910352","doi":"10.1016/j.cmi.2025.11.027","title":"Comparing different methods for analysing hierarchical composite endpoints: two illustrative case studies with post hoc analyses of the BALANCE (Bacteraemia Antibiotic Length Actually Needed for Clinical Effectiveness) and CAMERA2 (Combination Antibiotics for methicillin-resistant Staphylococcus aureus) randomized clinical trials","year":2025,"lang":"en","type":"article","venue":"Clinical Microbiology and Infection","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"Health Research Council of New Zealand; National Health and Medical Research Council; Canadian Institutes of Health Research; University of Melbourne; University of Toronto; National Medical Research Council; Ontario Ministry of Health and Long-Term Care","keywords":"Post hoc; Balance (ability); Antibiotics; Post-hoc analysis; Antibacterial agent","score_opus":0.49272558850458437,"score_gpt":0.631085238800257,"score_spread":0.13835965029567265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416910352","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54873174,0.00032542748,0.44540647,0.0003025346,0.0010803597,0.0039256853,0.00019538624,0.000029083578,0.000003337906],"genre_scores_gemma":[0.7277362,0.0009166995,0.2707143,0.00027933862,0.0002233782,0.000065338274,0.000028831591,0.000029125604,0.0000067739716],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9495688,0.04271855,0.0060373656,0.0011520269,0.000085904925,0.00043736413],"domain_scores_gemma":[0.5040507,0.49207717,0.002286249,0.00040487593,0.0010623174,0.00011872364],"candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.083614476,0.0005653626,0.006992361,0.00021692872,0.00055690255,0.00007421001,0.00021863078,0.0008843237,0.0000020865932],"category_scores_gemma":[0.3910193,0.00032516167,0.0017608823,0.0003309875,0.003962522,0.00009309784,0.00022899211,0.0010797092,1.0714513e-7],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5030146,0.0058427714,0.08746845,0.0068592187,0.038682114,0.000011333163,0.0004973229,0.00006392147,0.17212924,0.07419376,0.00028147385,0.11095579],"study_design_scores_gemma":[0.3849096,0.015337417,0.044781752,0.0039746757,0.034507904,0.000053316387,0.00071118923,0.02492136,0.06500153,0.42414585,0.0001275641,0.0015278375],"about_ca_topic_score_codex":0.000020123063,"about_ca_topic_score_gemma":0.00007950238,"teacher_disagreement_score":0.4493586,"about_ca_system_score_codex":0.0000729479,"about_ca_system_score_gemma":0.00017310848,"threshold_uncertainty_score":0.99992007},"labels":[],"label_agreement":null},{"id":"W4416919420","doi":"10.1016/j.cjca.2025.11.042","title":"Outcome Monitoring and Intermediate End Points for Gene Therapy","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Genetic enhancement; Outcome (game theory); Multidisciplinary approach; Disease; Clinical trial; Set (abstract data type); End point; Principal (computer security)","score_opus":0.46273815727827944,"score_gpt":0.5422132878777125,"score_spread":0.07947513059943306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416919420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36532968,0.0016363591,0.6141864,0.0028190764,0.012533554,0.00058206497,0.00016316368,0.000013608456,0.0027360974],"genre_scores_gemma":[0.6926962,0.00016557438,0.30506924,0.00022713408,0.001717462,0.0000096667345,2.2035663e-7,0.000016701078,0.00009776987],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985383,0.00034593293,0.00069829775,0.00011548686,0.000056898483,0.00024508897],"domain_scores_gemma":[0.9858156,0.013396888,0.0001839101,0.00014117234,0.00018272577,0.00027974413],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002428524,0.000098763696,0.00070033665,0.00018442502,0.000056299505,0.000020470594,0.0001850948,0.00014105113,0.000011403342],"category_scores_gemma":[0.035439853,0.000080112855,0.00017065486,0.000060578215,0.00018045962,0.000025862375,0.000013993326,0.00022273214,7.5966517e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064377923,0.000010288699,0.37322658,0.00028475848,0.002175743,0.00030957474,0.0003928351,0.000022879662,0.001453707,0.10792815,0.017945657,0.49560603],"study_design_scores_gemma":[0.0016779109,0.00022252803,0.03604746,0.00006117386,0.00012511197,0.000056781737,0.000054919,0.000005133151,0.00097271544,0.9457008,0.0149749825,0.000100430996],"about_ca_topic_score_codex":0.000027751033,"about_ca_topic_score_gemma":0.00002810973,"teacher_disagreement_score":0.8377727,"about_ca_system_score_codex":0.00007288367,"about_ca_system_score_gemma":0.00030968527,"threshold_uncertainty_score":0.97268504},"labels":[],"label_agreement":null},{"id":"W4416990044","doi":"10.1007/s40262-025-01602-4","title":"Guidance for External Evaluation and Selection of Population Pharmacokinetic Models for Precision Dosing","year":2025,"lang":"en","type":"article","venue":"Clinical Pharmacokinetics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Dosing; Selection (genetic algorithm); Population; Key (lock); Model selection; Clinical trial","score_opus":0.6026922687554581,"score_gpt":0.6569799012189769,"score_spread":0.054287632463518753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416990044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08364405,0.0003202528,0.91070575,0.00023308262,0.0014816074,0.003243953,0.000091151735,0.000054612316,0.00022554953],"genre_scores_gemma":[0.3680148,0.00016643647,0.6307947,0.00020144881,0.00044442527,0.00023745008,0.0000063697853,0.000028861534,0.00010549378],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99554914,0.00086519093,0.0023440912,0.0005709361,0.00039757564,0.0002730639],"domain_scores_gemma":[0.9439886,0.05402952,0.00071591267,0.0002040386,0.00095225906,0.00010961705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010139697,0.00022087622,0.00074455794,0.00012643758,0.000107179345,0.00003261564,0.00020970943,0.00023387794,0.000050228682],"category_scores_gemma":[0.06352926,0.00020961254,0.0002623373,0.0002553589,0.00014576956,0.00010679954,0.00008594224,0.00023442006,4.1309121e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030641095,0.00074310886,0.002254671,0.0014965812,0.00023575348,2.073648e-7,0.000034864246,0.004144603,0.01392503,0.053088423,0.006874636,0.914138],"study_design_scores_gemma":[0.004001602,0.00020231589,0.0017168561,0.00022995022,0.0007115264,4.3546962e-7,0.0000024059325,0.44597226,0.0044022156,0.54235893,0.00029146747,0.000110027664],"about_ca_topic_score_codex":0.0000029788441,"about_ca_topic_score_gemma":0.000001066876,"teacher_disagreement_score":0.914028,"about_ca_system_score_codex":0.00006283191,"about_ca_system_score_gemma":0.00006758883,"threshold_uncertainty_score":0.944359},"labels":[],"label_agreement":null},{"id":"W4417048830","doi":"10.1016/j.ajog.2025.12.023","title":"Toward equitable biomarker-driven trials in gynecologic oncology research","year":2025,"lang":"en","type":"article","venue":"American Journal of Obstetrics and Gynecology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Gynecologic oncology; Gynecologic cancer; Clinical trial; MEDLINE; Gynecologic surgical procedures","score_opus":0.7084108962848776,"score_gpt":0.6238441236922959,"score_spread":0.08456677259258172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417048830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8884383,0.003481066,0.056462046,0.015958257,0.012233481,0.0018283005,0.00005501331,0.000047764966,0.021495795],"genre_scores_gemma":[0.6885097,0.0016438623,0.30908266,0.00047769505,0.000075240205,0.00002558001,3.0605304e-7,0.000017769122,0.00016719961],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.981493,0.0133882575,0.0034177029,0.0003961031,0.00044825597,0.0008566691],"domain_scores_gemma":[0.2557103,0.74132013,0.0016702451,0.00030036434,0.0007720092,0.00022690788],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.052559912,0.00021059433,0.0030590743,0.0017235425,0.00011657928,0.000049856128,0.000603897,0.00033316482,0.00023400201],"category_scores_gemma":[0.87029254,0.0001614399,0.00026144876,0.0027639952,0.0012255536,0.00007274657,0.0004293858,0.0012341776,0.0000066800353],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036410143,0.00084385334,0.010216919,0.00010161338,0.0003275683,0.0007040764,0.0002573833,0.000008415306,0.00033251662,0.102292,0.00614052,0.87841105],"study_design_scores_gemma":[0.0040605217,0.0052783517,0.010904888,0.00009663423,0.00017968882,0.000043552125,0.002011123,0.00017792496,0.00009278561,0.95383006,0.023125151,0.00019929171],"about_ca_topic_score_codex":0.000022280132,"about_ca_topic_score_gemma":0.00001695236,"teacher_disagreement_score":0.87821174,"about_ca_system_score_codex":0.00061832665,"about_ca_system_score_gemma":0.0008415433,"threshold_uncertainty_score":0.9755889},"labels":[],"label_agreement":null},{"id":"W4417187360","doi":"10.1186/s13063-025-09315-6","title":"An efficient single-arm Bayesian adaptive trial algorithm to evaluate de-intensified oncologic treatment","year":2025,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; University Health Network; Children's Hospital of Western Ontario; London Health Sciences Centre; Western University; Princess Margaret Cancer Centre","funders":"National Cancer Institute; Children’s Oncology Group","keywords":"Leverage (statistics); Bayesian probability; Interim; Sensitivity (control systems); Clinical trial; Computerized adaptive testing; MEDLINE","score_opus":0.7645082156280925,"score_gpt":0.6364320608410957,"score_spread":0.12807615478699674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417187360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017312815,0.000039478913,0.96328324,0.0012299395,0.004038246,0.008431409,0.00021335267,0.00033339614,0.0051181125],"genre_scores_gemma":[0.0376734,0.000009187385,0.9585615,0.0008323996,0.0012319292,0.0008681116,0.0000040134937,0.000047979265,0.0007715114],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98378223,0.011174743,0.0028234937,0.00092159706,0.00057835877,0.0007195529],"domain_scores_gemma":[0.8783434,0.11915632,0.0006624966,0.0010045968,0.00038850305,0.00044467015],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.027930818,0.00046463404,0.0027729475,0.00025449708,0.00016597386,0.00012091258,0.00045802063,0.00039371647,0.00068529183],"category_scores_gemma":[0.26255706,0.00033418578,0.0005647506,0.00053699146,0.00014358519,0.000031043142,0.00010705407,0.00023629214,0.00010182322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.100973755,0.010745756,0.0000024381327,0.000037417234,0.0008799362,0.00009311181,0.00063704984,0.00040117363,0.002239533,0.0847938,0.004098037,0.795098],"study_design_scores_gemma":[0.07297854,0.02314359,0.000020257738,0.00016788823,0.0015462118,0.0000033273382,0.00032948825,0.015116335,0.013115827,0.8720645,0.0010415005,0.0004725762],"about_ca_topic_score_codex":0.000057912996,"about_ca_topic_score_gemma":0.000013808354,"teacher_disagreement_score":0.7946254,"about_ca_system_score_codex":0.0009982726,"about_ca_system_score_gemma":0.0005054756,"threshold_uncertainty_score":0.999911},"labels":[],"label_agreement":null},{"id":"W4417311632","doi":"10.1038/s41698-025-01231-x","title":"Benchmarking progression-free survival ratio as primary endpoint in precision oncology clinical trials","year":2025,"lang":"en","type":"article","venue":"npj Precision Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Cancer Institute","keywords":"Censoring (clinical trials); Sample size determination; Clinical trial; Benchmarking; Clinical endpoint; Survival analysis; Progression-free survival; Correlation","score_opus":0.6552909208156281,"score_gpt":0.6898935354422623,"score_spread":0.034602614626634165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417311632","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060258444,0.00089386944,0.6064929,0.014299895,0.042852692,0.01194842,0.0002146689,0.0006290539,0.26241007],"genre_scores_gemma":[0.009862271,0.00089371577,0.98321044,0.002095479,0.0017785308,0.00064954546,0.000023853683,0.00008222294,0.0014039107],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91826093,0.063289665,0.012896077,0.0024149066,0.001824931,0.0013134838],"domain_scores_gemma":[0.43942186,0.55554193,0.002251476,0.0018912358,0.00047837457,0.0004151213],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.14682135,0.00060583744,0.0053511756,0.0006690356,0.00021859269,0.00009208074,0.0017204612,0.0026418106,0.0027492899],"category_scores_gemma":[0.73258454,0.00047353934,0.00083998346,0.0009936922,0.00064045377,0.00018450567,0.0021428184,0.0024412344,0.00016951619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0066771023,0.0026501706,0.0018571317,0.000101550635,0.00014572736,0.00019722534,0.00014177135,0.000006085631,0.00038398828,0.07452884,0.03391885,0.87939155],"study_design_scores_gemma":[0.010507924,0.003352854,0.008498046,0.0006407902,0.00024067536,0.000016132906,0.00010174809,0.000638385,0.0004899161,0.88089585,0.09421265,0.00040504965],"about_ca_topic_score_codex":0.000025415786,"about_ca_topic_score_gemma":0.00015600372,"teacher_disagreement_score":0.87898654,"about_ca_system_score_codex":0.001227702,"about_ca_system_score_gemma":0.0025987949,"threshold_uncertainty_score":0.99986017},"labels":[],"label_agreement":null},{"id":"W4417479690","doi":"10.1016/j.jval.2025.09.3474","title":"MSR197 The Effects of Pooling Treatment Effects Targeting Treatment Policy and Hypothetical Estimands With Rank-Preserving Structural Failure Time Model in Oncology Aggregate-Level Meta-Analyses","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McGill University","funders":"","keywords":"Pooling; Clinical trial; Randomized controlled trial; Event (particle physics); Treatment effect; Cancer treatment","score_opus":0.5258736131249707,"score_gpt":0.5693965461418977,"score_spread":0.043522933016927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417479690","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.942586,0.0037120222,0.04003205,0.008261439,0.00017537689,0.0047455183,0.00008975385,0.00007715317,0.00032067],"genre_scores_gemma":[0.44884086,0.00017430221,0.55041724,0.00018348986,0.0000537443,0.00020226196,0.0000018396789,0.000030082227,0.00009615013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9932574,0.00396322,0.001352582,0.00054318376,0.00029647918,0.00058711896],"domain_scores_gemma":[0.88694465,0.11192117,0.00044503028,0.00048677405,0.000055934066,0.00014642891],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028171088,0.00040313418,0.0022826868,0.00031387812,0.00012657593,0.000028239145,0.00023628815,0.00019330734,0.000010315384],"category_scores_gemma":[0.04215293,0.00020911955,0.00022458335,0.0005552155,0.00023474015,0.000047518264,0.00012240114,0.00029244018,9.069728e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0067826062,0.005174921,0.0057993857,0.021023596,0.019175164,0.0005958469,0.019571668,0.2347197,0.0063097663,0.42629415,0.00039624772,0.25415695],"study_design_scores_gemma":[0.006328258,0.002924494,0.00056576036,0.00079966336,0.002207324,0.000010339092,0.000077388424,0.3803654,0.004133831,0.6023383,0.000013872925,0.00023537278],"about_ca_topic_score_codex":0.0038833932,"about_ca_topic_score_gemma":0.00020321461,"teacher_disagreement_score":0.5103852,"about_ca_system_score_codex":0.0008139994,"about_ca_system_score_gemma":0.0007628653,"threshold_uncertainty_score":0.96591544},"labels":[],"label_agreement":null},{"id":"W4417479737","doi":"10.1016/j.jval.2025.09.3466","title":"MSR187 Simulation-Guided Trial Planning of a Cluster Randomized Trial With Probabilistic Covariate-Constrained Randomization for Vaccine Coverage","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Simon Fraser University","funders":"","keywords":"Randomization; Covariate; Cluster randomised controlled trial; Cluster (spacecraft); Randomized controlled trial; Sample size determination; Probabilistic logic; Outcome (game theory)","score_opus":0.4089605287641479,"score_gpt":0.5466162763627133,"score_spread":0.13765574759856536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417479737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031608645,0.00003385367,0.94069105,0.00061386375,0.0013571684,0.025233813,0.00007900206,0.00006154444,0.00032106088],"genre_scores_gemma":[0.34058794,0.000013002222,0.65692014,0.00035569834,0.0004698048,0.0014712112,0.000021722843,0.000045575503,0.0001148753],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9893821,0.0055303895,0.00387385,0.0004699206,0.00036506949,0.000378665],"domain_scores_gemma":[0.6913544,0.30638626,0.0013781771,0.00039666108,0.0003877663,0.00009673017],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0240595,0.00026061482,0.0027596443,0.00027126048,0.000091725524,0.00003269783,0.00017378615,0.00021529617,0.00004581621],"category_scores_gemma":[0.44424233,0.00019398952,0.00026122874,0.00050946634,0.00011251224,0.000059838883,0.00003625395,0.00023914772,5.4090395e-7],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7574896,0.0003489073,0.0000086073605,0.0010057393,0.000117614276,7.903606e-7,0.00019942396,0.1564763,0.0000010162572,0.083826296,0.00013361368,0.00039207598],"study_design_scores_gemma":[0.4968893,0.0005946754,0.0000016572238,0.00050045067,0.000118175696,1.9781429e-7,0.000007721662,0.15797365,0.0000064803253,0.34381214,0.000013397853,0.00008214832],"about_ca_topic_score_codex":0.00012724608,"about_ca_topic_score_gemma":0.0000056299014,"teacher_disagreement_score":0.42018282,"about_ca_system_score_codex":0.00016597123,"about_ca_system_score_gemma":0.00092035753,"threshold_uncertainty_score":0.8338591},"labels":[],"label_agreement":null},{"id":"W4417480163","doi":"10.1016/j.jval.2025.09.3322","title":"MSR31 Applying Simulation-Guided Trial Design Principles to Prospectively Plan Target Trial Emulation of a Cluster Randomized Trial for Vaccine Coverage","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University; Simon Fraser University","funders":"","keywords":"Emulation; Randomized controlled trial; Cluster randomised controlled trial; Design elements and principles; Cluster (spacecraft); Vaccine trial","score_opus":0.6018879378595969,"score_gpt":0.568326293465835,"score_spread":0.03356164439376197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417480163","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04042508,0.000024420855,0.89087737,0.0006896066,0.0022900912,0.06541191,0.00010330433,0.00007064409,0.00010758818],"genre_scores_gemma":[0.122619286,0.000011282537,0.8707574,0.00031979656,0.0010520706,0.005027187,0.000010257041,0.00004859761,0.00015414557],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9863321,0.0070772166,0.0048900233,0.00066028844,0.0005483278,0.00049199635],"domain_scores_gemma":[0.75599223,0.24169514,0.0014416106,0.00046281048,0.000257225,0.00015098396],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034106445,0.0003032931,0.0027580492,0.0003967423,0.00013535378,0.00004533688,0.00025932855,0.00027718127,0.000036767713],"category_scores_gemma":[0.3755703,0.00025888407,0.0003794991,0.0005735954,0.000045063716,0.00007535012,0.000087200286,0.00027683095,0.0000021333894],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8127009,0.00055475323,0.000007415199,0.00048110264,0.000088461034,4.5847008e-7,0.00025686927,0.12670207,0.0000062420063,0.058126897,0.00022613503,0.0008486407],"study_design_scores_gemma":[0.48697862,0.0014139484,0.0000057356306,0.0002007633,0.000050880535,7.1580594e-8,0.0000069133725,0.14091417,0.000051790208,0.37019736,0.00007822668,0.00010152955],"about_ca_topic_score_codex":0.00015420327,"about_ca_topic_score_gemma":0.000005437516,"teacher_disagreement_score":0.34146386,"about_ca_system_score_codex":0.00037214055,"about_ca_system_score_gemma":0.0008547372,"threshold_uncertainty_score":0.99998635},"labels":[],"label_agreement":null},{"id":"W4417480751","doi":"10.1016/j.jval.2025.09.525","title":"EE141 Comparing Alternative Extrapolation Methods Using Standard Partitioned Survival Model Functionality in the Presence of Converging Survival Data: A Case Study in Renal Cell Carcinoma","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thermo Fisher Scientific (Canada)","funders":"","keywords":"Extrapolation; Renal cell carcinoma; Survival analysis; Parametric statistics; Equivalence (formal languages); Overall survival; Cell survival","score_opus":0.8253920294109419,"score_gpt":0.6337543514233877,"score_spread":0.19163767798755427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417480751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5217125,0.000038181137,0.4767876,0.000091671725,0.00031934606,0.0008611377,0.00009580288,0.000007555103,0.00008621753],"genre_scores_gemma":[0.6576937,0.0000054330785,0.34220514,0.000022527873,0.0000348314,0.00002381456,0.0000033297688,0.000008644031,0.0000026173943],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97772366,0.018279446,0.0023171934,0.00063247717,0.0006533798,0.00039386595],"domain_scores_gemma":[0.9408438,0.05766417,0.00054679846,0.00076065806,0.00012459724,0.000059926315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.044016518,0.00017812506,0.000914677,0.00024388656,0.00010540051,0.000030085317,0.0004010333,0.000078560486,0.000008179079],"category_scores_gemma":[0.020098994,0.00015452356,0.000047342062,0.00080787373,0.00012062184,0.0001635251,0.0002499076,0.00057374174,1.4334779e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014387941,0.002489047,0.4546526,0.0017649474,0.00006568366,0.0002939857,0.013361344,0.42866483,0.00013107006,0.09479851,0.000033321314,0.002305862],"study_design_scores_gemma":[0.0019775166,0.00009402181,0.010535121,0.0002121891,0.000025666644,0.0000044933367,0.0037791815,0.72628814,0.00005917803,0.25693023,0.0000011411495,0.00009311843],"about_ca_topic_score_codex":0.023117935,"about_ca_topic_score_gemma":0.0028444063,"teacher_disagreement_score":0.4441175,"about_ca_system_score_codex":0.0003770894,"about_ca_system_score_gemma":0.0006146168,"threshold_uncertainty_score":0.9881551},"labels":[],"label_agreement":null},{"id":"W59313137","doi":"10.22237/jmasm/1051747560","title":"Analyzing Group by Time Effects in Longitudinal Two-Group Randomized Trial Designs With Missing Data","year":2003,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Missing data; Mathematics; Statistics; Group (periodic table); Type I and type II errors; Repeated measures design; Range (aeronautics); Sampling (signal processing); Econometrics; Computer science","score_opus":0.38854215717426166,"score_gpt":0.5491069104777841,"score_spread":0.1605647533035225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W59313137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074917456,0.00036236914,0.995031,0.000068740665,0.00040711171,0.0018277913,0.000098081015,0.00003879035,0.0014169234],"genre_scores_gemma":[0.016593829,0.000027404705,0.98280084,0.000078842764,0.0002892714,0.00006174002,0.000011095959,0.00011564225,0.000021338356],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9747809,0.018182943,0.003967767,0.0009635491,0.0012178817,0.00088694884],"domain_scores_gemma":[0.7181144,0.27873024,0.0016133987,0.0008611025,0.00014991529,0.00053098006],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05959051,0.0006159254,0.0042992197,0.00030348508,0.00013858912,0.00019557183,0.00093401014,0.00031196422,0.00030411943],"category_scores_gemma":[0.20861292,0.0004358858,0.0002558943,0.0005325646,0.0006440616,0.00021560016,0.00017575764,0.001533926,0.000007629254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.43614414,0.0014203512,0.000020952097,0.0002635494,0.00079308526,0.00028106535,0.00008208694,0.000036400303,0.008021179,0.34770146,0.0008790628,0.20435667],"study_design_scores_gemma":[0.33023423,0.0005548889,0.000008615436,0.00018896363,0.0009979068,0.000053315896,0.00000830236,0.014246365,0.00039737675,0.6529147,0.00004593328,0.00034940647],"about_ca_topic_score_codex":0.0000060521443,"about_ca_topic_score_gemma":0.0000021890548,"teacher_disagreement_score":0.30521324,"about_ca_system_score_codex":0.00019040219,"about_ca_system_score_gemma":0.00020541632,"threshold_uncertainty_score":0.99980927},"labels":[],"label_agreement":null},{"id":"W608898764","doi":"10.2307/3316023","title":"Bayesian randomized clinical trials: A decision‐theoretic sequential design","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Randomization; Gynecology; Humanities; Medicine; Randomized controlled trial; Philosophy; Surgery; Biology","score_opus":0.6461465458887752,"score_gpt":0.5830920886938148,"score_spread":0.06305445719496039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W608898764","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027169276,0.00018319338,0.99303204,0.0005129683,0.0042105294,0.0008954286,0.00050799915,0.0000161,0.00037006816],"genre_scores_gemma":[0.039889082,0.00017463775,0.9582162,0.00037971095,0.001211146,0.0000105719,0.0000018754002,0.000071170434,0.00004560987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9753652,0.015519907,0.007365275,0.00034055763,0.0007505318,0.00065853645],"domain_scores_gemma":[0.57888395,0.41376764,0.0031848252,0.0005493281,0.0011167141,0.0024975426],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1096335,0.00035272853,0.0037192288,0.00040509595,0.0001848497,0.00019157203,0.0006898813,0.0003980755,0.0014763016],"category_scores_gemma":[0.8190778,0.00026548165,0.0008937124,0.00030033317,0.0014604639,0.00007769364,0.000028329398,0.0010540844,0.000044936558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012508848,0.00010933936,0.000029534458,0.00005259546,0.00054974825,0.0016177796,0.00022918389,0.00025006183,0.0000036161134,0.89699996,0.011868784,0.07578058],"study_design_scores_gemma":[0.07505898,0.00039211244,0.000014930853,0.0003240422,0.0010958731,0.0001952939,0.000055041597,0.00072764605,0.000041380947,0.9213851,0.0004476997,0.0002618605],"about_ca_topic_score_codex":0.0003190158,"about_ca_topic_score_gemma":0.0010825994,"teacher_disagreement_score":0.7094443,"about_ca_system_score_codex":0.00032433085,"about_ca_system_score_gemma":0.00537719,"threshold_uncertainty_score":0.99997973},"labels":[],"label_agreement":null},{"id":"W67613939","doi":"","title":"Open Source on Trial","year":2007,"lang":"en","type":"article","venue":"˜The œopen source business resource","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Open source; Computer science; Operating system; Software","score_opus":0.47204800520696216,"score_gpt":0.5370595000900733,"score_spread":0.06501149488311114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W67613939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037792105,0.000062690335,0.67824924,0.0043812906,0.0017201405,0.01096721,0.00006212772,0.00060700526,0.26615816],"genre_scores_gemma":[0.19700976,0.000027001159,0.5488248,0.0233274,0.011892182,0.0011961835,0.000042859323,0.0015171388,0.2161627],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916683,0.002141072,0.0022277045,0.001330999,0.0013765539,0.0012553572],"domain_scores_gemma":[0.9290632,0.06605172,0.0011335276,0.0029110352,0.00038905928,0.0004514765],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021164266,0.00070491625,0.0016560976,0.00018240557,0.00091438054,0.0015309512,0.008045143,0.0005149854,0.0013404652],"category_scores_gemma":[0.045574784,0.00048626921,0.000299417,0.0015823588,0.00064141635,0.00023276651,0.0049522496,0.00087490754,0.00067628897],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13898832,0.0035510312,0.00022847712,0.00025228795,0.0005597182,0.0001706395,0.0019750579,0.00040208487,0.00022658636,0.09383421,0.18050395,0.5793076],"study_design_scores_gemma":[0.032108787,0.0004303449,0.0007111074,0.00026548884,0.00020956359,0.000030842966,0.000612765,0.00017543584,0.00018201221,0.14762057,0.81685656,0.0007965152],"about_ca_topic_score_codex":0.00041715836,"about_ca_topic_score_gemma":0.00011279028,"teacher_disagreement_score":0.6363526,"about_ca_system_score_codex":0.0001738766,"about_ca_system_score_gemma":0.0001779009,"threshold_uncertainty_score":0.9997589},"labels":[],"label_agreement":null},{"id":"W6901745268","doi":"10.60692/pgsq7-edg58","title":"Bayesian Optimal Phase II Design for Randomized Clinical Trials","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Frequentist inference; Bayesian probability; Flexibility (engineering); Interim analysis; Protocol (science); Randomized controlled trial; Interim; Table (database); Clinical trial","score_opus":0.6961878066735211,"score_gpt":0.5551210901413203,"score_spread":0.14106671653220082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901745268","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035649564,0.0000022375632,0.98446333,0.00014549875,0.0025926377,0.0071583064,0.0010724047,0.0003353632,0.0006652577],"genre_scores_gemma":[0.3543799,1.4229146e-7,0.64142406,0.00025048575,0.00043045642,0.0032609396,0.000014610268,0.000030793075,0.00020862665],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.96967024,0.020932803,0.007799302,0.00035963728,0.0007803051,0.00045772118],"domain_scores_gemma":[0.9346295,0.06113222,0.0030085177,0.0006835191,0.00029625476,0.0002499686],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14647596,0.00031277718,0.0030195983,0.00024037989,0.0006363709,0.00014740055,0.00044990057,0.00021338728,0.00054738275],"category_scores_gemma":[0.17647418,0.00023524417,0.001109466,0.00024571104,0.00013064883,0.00026140985,0.00025192663,0.00035434478,0.00007247006],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.646068,0.00044028595,0.000215543,0.0026515748,0.0031476372,0.000024400364,0.07084277,0.0023212382,0.0000028887669,0.19402793,0.03438856,0.04586916],"study_design_scores_gemma":[0.6797086,0.0023804086,0.0000054558554,0.0001561597,0.0015421604,0.000049983068,0.008625243,0.27930832,0.00023209491,0.02518013,0.0020019778,0.0008094628],"about_ca_topic_score_codex":7.2337474e-7,"about_ca_topic_score_gemma":4.9322515e-9,"teacher_disagreement_score":0.3508149,"about_ca_system_score_codex":0.0001395436,"about_ca_system_score_gemma":0.00014057626,"threshold_uncertainty_score":0.95929784},"labels":[],"label_agreement":null},{"id":"W6901983075","doi":"10.6084/m9.figshare.13173941","title":"Additional file 2 of Guidance for conducting feasibility and pilot studies for implementation trials","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"","keywords":"File format; Troubleshooting; Table (database); Key (lock); Data collection","score_opus":0.9734835577151113,"score_gpt":0.69863126972866,"score_spread":0.27485228798645134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901983075","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014284952,0.000055907854,0.00055931933,0.00017817956,0.000031163057,0.0016855985,0.9974169,0.00002548362,0.000033151515],"genre_scores_gemma":[0.00013824365,7.503762e-7,0.7700248,0.00017519135,0.00038676194,0.0043398733,0.2248997,0.000014184279,0.000020520187],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983545,0.00029466764,0.0008793664,0.00023751575,0.00011816034,0.00011582193],"domain_scores_gemma":[0.5115023,0.48714927,0.00071549177,0.00010692637,0.000464573,0.00006141109],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007866511,0.0000924556,0.00060989155,0.00001053977,0.000060278242,0.000011902244,0.00007445083,0.000037445447,0.89855343],"category_scores_gemma":[0.8946956,0.00007877784,0.000110807756,0.000053703516,0.0000194518,0.000046616595,0.000058741025,0.000044508517,0.000012554738],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012358022,0.000018683182,5.518768e-7,0.0014235198,0.00006534954,9.4004164e-8,0.00006683109,6.290348e-8,0.000042132928,0.00045111464,0.9943391,0.003468993],"study_design_scores_gemma":[0.0030634545,0.0013032801,0.00013082761,0.0020108088,0.00011188455,4.892032e-7,0.00063834916,0.00016537891,0.0030587842,0.76650155,0.2227922,0.00022299823],"about_ca_topic_score_codex":1.6574344e-7,"about_ca_topic_score_gemma":0.0000016055911,"teacher_disagreement_score":0.89854085,"about_ca_system_score_codex":0.000018298817,"about_ca_system_score_gemma":0.000051028816,"threshold_uncertainty_score":0.3212467},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W6901992341","doi":"10.6084/m9.figshare.13031627","title":"Additional file 1 of Correction to: Cluster identification, selection, and description in Cluster randomized crossover trials: the PREP-IT trials","year":2020,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cluster (spacecraft); Crossover; Cluster analysis; Field (mathematics)","score_opus":0.6141473959595923,"score_gpt":0.5554244649261547,"score_spread":0.05872293103343762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901992341","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00628547,0.000051854255,0.55532634,0.021575106,0.004732632,0.040496342,0.3604019,0.000036034686,0.011094327],"genre_scores_gemma":[0.005162719,0.000012920064,0.9756062,0.0015730785,0.0010699604,0.0039816056,0.0018176744,0.000052565738,0.010723296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9854972,0.010197522,0.0032863743,0.0004837246,0.00036643175,0.0001687805],"domain_scores_gemma":[0.52941865,0.4679193,0.0018247208,0.00030470453,0.00039474524,0.00013791029],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028236696,0.0001662664,0.0016572557,0.000068034366,0.000102074846,0.0003061876,0.00029351164,0.00013903127,0.5450746],"category_scores_gemma":[0.7958893,0.00011090991,0.00022318249,0.000388501,0.00014861971,0.00022860059,0.0001751318,0.00022439007,0.0002102595],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.035679284,0.00007914529,0.000001979224,0.000018958805,0.000085930034,2.5160207e-7,0.0006684316,0.000026353295,0.000103665545,0.00010299779,0.9485792,0.014653823],"study_design_scores_gemma":[0.2129431,0.0005393711,0.00046815313,0.0013858548,0.0011886389,0.000019074352,0.0011055788,0.028314376,0.0038643887,0.3200012,0.42938575,0.0007844892],"about_ca_topic_score_codex":0.000019284138,"about_ca_topic_score_gemma":0.00011605384,"teacher_disagreement_score":0.76765263,"about_ca_system_score_codex":0.000044456352,"about_ca_system_score_gemma":0.000120451026,"threshold_uncertainty_score":0.97863317},"labels":[],"label_agreement":null},{"id":"W6901996792","doi":"10.6084/m9.figshare.27173670.v1","title":"Additional file 1 of Adaptive designs in clinical trials: a systematic review-part I","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital Research Institute of Manitoba; SickKids Foundation; George & Fay Yee Centre for Healthcare Innovation; University of Toronto; University of Calgary; University of Manitoba; Hospital for Sick Children; University of British Columbia","funders":"","keywords":"Adaptive design; Key (lock); Scheme (mathematics); Matching (statistics)","score_opus":0.9175016093535353,"score_gpt":0.6560205158156046,"score_spread":0.2614810935379307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901996792","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6497215e-8,0.0014855581,0.00016629296,0.000043087537,0.00013797158,0.0018849655,0.99344003,0.000081651015,0.0027603954],"genre_scores_gemma":[0.000007708044,0.00010368287,0.49852547,0.0005700741,0.0010024747,0.016355265,0.48136318,0.00009257415,0.0019795783],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9874081,0.007276334,0.00423435,0.00040476024,0.0004606823,0.00021579686],"domain_scores_gemma":[0.14464942,0.8535474,0.0009532851,0.0004977056,0.00021814254,0.00013407231],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008477778,0.00019549091,0.0024474212,0.000089703,0.000017084512,0.000027299013,0.00030701733,0.00022745681,0.99583936],"category_scores_gemma":[0.9617351,0.00014390748,0.0006718094,0.0004248535,0.000030220534,0.000065146174,0.000102254504,0.0004695904,0.005598573],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014243022,0.0000791194,1.4258423e-8,0.14780119,0.00009255703,0.000034887595,0.000006446669,6.545986e-8,6.4984874e-8,0.000799634,0.8505621,0.0006096828],"study_design_scores_gemma":[0.00016470558,0.00012175486,0.0000046381424,0.80632985,0.00020364505,0.00000636546,0.0000129186865,0.0005520291,0.000003232939,0.13561247,0.056831814,0.00015657386],"about_ca_topic_score_codex":3.1499758e-7,"about_ca_topic_score_gemma":0.0000016756194,"teacher_disagreement_score":0.9902408,"about_ca_system_score_codex":0.00004804847,"about_ca_system_score_gemma":0.0002856894,"threshold_uncertainty_score":0.99517566},"labels":[],"label_agreement":null},{"id":"W6902046467","doi":"10.6084/m9.figshare.16822645","title":"Additional file 2 of Confidence interval of risk difference by different statistical methods and its impact on the study conclusion in antibiotic non-inferiority trials","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; University Health Network; Queen's University","funders":"","keywords":"Confidence interval; Interval (graph theory); Statistical analysis; Antibiotics; Interval data; Clinical trial","score_opus":0.46184954047280846,"score_gpt":0.5839566755569755,"score_spread":0.12210713508416704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902046467","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015675783,0.000024414874,0.0010156331,0.000015737336,0.00004795185,0.00077737885,0.982346,0.000009689393,0.000087393826],"genre_scores_gemma":[0.68234086,0.000019990885,0.19716151,0.00007229087,0.00014696165,0.0004884108,0.119630255,0.000054555694,0.00008518889],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9904275,0.0071409508,0.0013805126,0.00039350239,0.00045072788,0.00020682235],"domain_scores_gemma":[0.3802479,0.6181877,0.0008060749,0.00037176543,0.0002773923,0.00010912525],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020795236,0.00023939132,0.0014709628,0.00004549686,0.00005266753,0.000029484663,0.00025694357,0.00013889186,0.9072284],"category_scores_gemma":[0.80711573,0.00014182265,0.00016508951,0.0001835957,0.00006239429,0.000027715041,0.00038710528,0.00045881368,0.000028206461],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033302372,0.0015212616,0.00013785639,0.00041975165,0.00016802184,0.000024584355,0.0002710529,5.131409e-7,0.00073020835,0.0008610458,0.98409694,0.011435754],"study_design_scores_gemma":[0.0049227956,0.003557505,0.5246161,0.022209844,0.00041328414,0.000011704725,0.0009647113,0.006450442,0.02607231,0.40919188,0.0006966815,0.00089271757],"about_ca_topic_score_codex":0.000010619008,"about_ca_topic_score_gemma":0.000008631322,"teacher_disagreement_score":0.9834002,"about_ca_system_score_codex":0.00004241394,"about_ca_system_score_gemma":0.00015015416,"threshold_uncertainty_score":0.57833594},"labels":[],"label_agreement":null},{"id":"W6902060615","doi":"10.6084/m9.figshare.23632746","title":"Additional file 9 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Bar (unit); Dosing; Bar chart; Table (database); Diagram; Calibration","score_opus":0.8319963453932503,"score_gpt":0.6024880844721656,"score_spread":0.22950826092108467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902060615","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002627462,0.000006506183,0.000045431894,0.00005303128,0.000039061368,0.001589562,0.9954508,0.00003979859,0.0001483806],"genre_scores_gemma":[0.0058909804,7.191938e-7,0.807591,0.00005016627,0.00019130301,0.004815303,0.18093874,0.00005490942,0.00046689133],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750865,0.00050529925,0.00128137,0.00023227153,0.00029538843,0.00017701137],"domain_scores_gemma":[0.6231398,0.3757215,0.0005901602,0.00021006499,0.00027728456,0.00006118316],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015549732,0.00013156574,0.00072383136,0.000072435374,0.00013010611,0.000014856369,0.00015266838,0.000081602724,0.81034607],"category_scores_gemma":[0.644848,0.00009154843,0.00012856745,0.00022431496,0.000052919808,0.0000143612615,0.00014302297,0.00011420717,0.00012936936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009920148,0.00023304137,0.0000029662028,0.00016836911,0.00013113083,0.0000052504206,0.00020270165,3.7818378e-7,0.00003230281,0.0002095921,0.9927561,0.006158931],"study_design_scores_gemma":[0.026190251,0.0034566342,0.034018666,0.018557,0.0009266103,0.00002340472,0.0037007493,0.0019407622,0.0025683085,0.31525168,0.59202427,0.0013416914],"about_ca_topic_score_codex":4.604131e-7,"about_ca_topic_score_gemma":0.0000031339796,"teacher_disagreement_score":0.814512,"about_ca_system_score_codex":0.000011639658,"about_ca_system_score_gemma":0.00022042716,"threshold_uncertainty_score":0.37332365},"labels":[],"label_agreement":null},{"id":"W6902068573","doi":"10.6084/m9.figshare.17056754","title":"Additional file 1 of On clinical trial fragility due to patients lost to follow up","year":2021,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Fragility; Clinical trial; MEDLINE; Fragility fracture","score_opus":0.6898962469456295,"score_gpt":0.6071808759547955,"score_spread":0.08271537099083393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902068573","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06199547,3.7523589e-7,0.0019250605,0.00037775846,0.0019814211,0.0023254626,0.8840521,0.0000032410135,0.04733911],"genre_scores_gemma":[0.00039982903,1.9121671e-7,0.98922986,0.00052278984,0.00046085982,0.00021975896,0.0027733117,0.000021784406,0.0063715903],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959024,0.0012118756,0.0015130735,0.000613254,0.0005333255,0.00022603088],"domain_scores_gemma":[0.83695865,0.16141562,0.0002772536,0.0006566024,0.00037466545,0.00031721068],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021475384,0.00015433978,0.00089321827,0.000033513734,0.00004555287,0.000057385776,0.0004974424,0.00019239513,0.936174],"category_scores_gemma":[0.59090316,0.00013888505,0.00023768803,0.0002590095,0.00006727825,0.00004292082,0.0005534203,0.00025407318,0.0056508672],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007274327,0.0013064189,0.0000183767,0.0000068223067,0.000049122245,0.00001528028,0.00002856054,2.2202615e-7,0.0000012858308,0.0002981622,0.8724982,0.118503205],"study_design_scores_gemma":[0.022884844,0.003367107,0.004025085,0.0004992901,0.0000815119,0.0000010668002,0.000038304664,0.00000827371,0.0007061666,0.14601842,0.8220097,0.0003602388],"about_ca_topic_score_codex":0.0000036034207,"about_ca_topic_score_gemma":0.00003103854,"teacher_disagreement_score":0.9873048,"about_ca_system_score_codex":0.00003872697,"about_ca_system_score_gemma":0.00026522743,"threshold_uncertainty_score":0.9951233},"labels":[],"label_agreement":null},{"id":"W6902093946","doi":"10.6084/m9.figshare.23632731","title":"Additional file 4 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Delphi; Key (lock); Development (topology); Delphi method; Phase (matter)","score_opus":0.833429272486276,"score_gpt":0.6029794275569275,"score_spread":0.2304498449293485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902093946","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026161997,0.000006503862,0.00004542174,0.000052649906,0.000039053568,0.0015902461,0.9954618,0.00003979281,0.00014832859],"genre_scores_gemma":[0.0059472863,7.17644e-7,0.80659175,0.00005003243,0.00019093795,0.004841196,0.18186234,0.000054831136,0.00046090464],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750906,0.0005048703,0.001281415,0.0002322734,0.0002953908,0.00017700756],"domain_scores_gemma":[0.62336165,0.37550324,0.00058949227,0.00020989754,0.00027460328,0.00006110508],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015544744,0.00013156254,0.0007238172,0.00007243709,0.00013009677,0.000014860274,0.00015284095,0.000081615544,0.81100225],"category_scores_gemma":[0.64389557,0.00009155299,0.0001285612,0.00022425129,0.000052917647,0.000014360016,0.0001430786,0.00011422807,0.00012973793],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010080269,0.00023302734,0.0000029747464,0.00016830135,0.00013112588,0.000005250749,0.00020256554,3.727286e-7,0.000032077525,0.00021375758,0.9926939,0.0062158215],"study_design_scores_gemma":[0.026200859,0.0035016176,0.033785444,0.018523755,0.00092569797,0.000023384859,0.0036967793,0.0019386107,0.0025449176,0.31501234,0.592506,0.0013406303],"about_ca_topic_score_codex":4.657189e-7,"about_ca_topic_score_gemma":0.0000031296183,"teacher_disagreement_score":0.81359947,"about_ca_system_score_codex":0.000011638008,"about_ca_system_score_gemma":0.00022020453,"threshold_uncertainty_score":0.37334228},"labels":[],"label_agreement":null},{"id":"W6902160453","doi":"10.6084/m9.figshare.23632728.v1","title":"Additional file 3 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Protocol (science); Phase (matter); File format; Key (lock)","score_opus":0.8323473328243262,"score_gpt":0.6024961044540303,"score_spread":0.2298512283702958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902160453","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026283828,0.000006479002,0.000045125536,0.000052743126,0.000039409446,0.0015886977,0.99545074,0.00003973413,0.00014870912],"genre_scores_gemma":[0.0058016907,7.182017e-7,0.8066702,0.000050015704,0.00019306254,0.004844585,0.18190673,0.000054887616,0.0004781449],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975095,0.00050494046,0.0012809538,0.00023225087,0.00029541133,0.00017698796],"domain_scores_gemma":[0.6225244,0.37633163,0.00059135526,0.00021048356,0.00028084675,0.0000613055],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015532017,0.00013155318,0.0007236427,0.00007240267,0.00013003065,0.000014852197,0.00015272613,0.000081608494,0.81363213],"category_scores_gemma":[0.64718777,0.00009153522,0.00012855102,0.00022428056,0.000052907933,0.000014357871,0.00014302287,0.00011423168,0.00013250143],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009961987,0.00023262121,0.000002964322,0.00016945112,0.00013096239,0.0000052257233,0.0002021082,3.7765255e-7,0.000032547723,0.00020583057,0.99270517,0.0062131207],"study_design_scores_gemma":[0.025752505,0.0033691097,0.032912653,0.018089144,0.00089926575,0.000022651502,0.0036076386,0.0018910358,0.002544689,0.30527666,0.60432255,0.0013120748],"about_ca_topic_score_codex":4.6998267e-7,"about_ca_topic_score_gemma":0.0000031165516,"teacher_disagreement_score":0.813544,"about_ca_system_score_codex":0.000011683951,"about_ca_system_score_gemma":0.00022105097,"threshold_uncertainty_score":0.3732698},"labels":[],"label_agreement":null},{"id":"W6902216532","doi":"10.6084/m9.figshare.26749925","title":"Additional file 1 of Hypothesis testing and sample size considerations for the test-negative design","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Gilead Sciences (Canada)","funders":"","keywords":"Sample size determination; Statistical hypothesis testing; Sample (material); Statistical analysis; Design of experiments; Statistical power","score_opus":0.7991971054752205,"score_gpt":0.5456773893075642,"score_spread":0.25351971616765634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902216532","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016514789,0.000004673282,0.03109697,0.0005460843,0.0000558026,0.001501341,0.9628448,0.0000053979043,0.003928429],"genre_scores_gemma":[0.00020984726,7.1512414e-7,0.9983021,0.00004584949,0.000092573246,0.00067162624,0.000007380078,0.000014635655,0.0006552707],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990037,0.00020714058,0.00037854945,0.00020354254,0.00010589452,0.00010114728],"domain_scores_gemma":[0.0063959686,0.9931801,0.00011031255,0.00014647687,0.0001302961,0.000036839425],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011775299,0.00008170222,0.00023133916,0.000014547435,0.00013631479,0.00015439365,0.00011834019,0.00004748899,0.73226523],"category_scores_gemma":[0.98298347,0.000054704095,0.000041275507,0.00010730836,0.0001894724,0.00005069261,0.00008047625,0.000083717576,0.000041151998],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012792892,0.0000418802,7.7894003e-7,0.000025914549,0.00006453894,0.0000016683366,0.00010690279,0.0000019055079,0.00005705283,0.0005673875,0.91712,0.081999205],"study_design_scores_gemma":[0.00014035396,0.00010488929,0.000068353234,0.00023727343,0.00009197356,0.000005093948,0.00008246963,0.0030289688,0.0008608553,0.99082714,0.004482478,0.00007017214],"about_ca_topic_score_codex":0.000007706052,"about_ca_topic_score_gemma":0.000008203375,"teacher_disagreement_score":0.99297297,"about_ca_system_score_codex":0.000010645285,"about_ca_system_score_gemma":0.00017870402,"threshold_uncertainty_score":0.2679795},"labels":[],"label_agreement":null},{"id":"W6902320358","doi":"10.6084/m9.figshare.26693443","title":"Additional file 3 of Trials that turn from retrospectively registered to prospectively registered: a cohort study of “retroactively prospective” clinical trial registration using history data","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Clinical trial; Cohort study; Cohort; Retrospective cohort study; Patient data","score_opus":0.8939182581846759,"score_gpt":0.5951802511582628,"score_spread":0.29873800702641307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902320358","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015528396,0.000071545124,0.0006670099,0.0000249671,0.0008688262,0.008085498,0.9861487,0.00019570511,0.002384899],"genre_scores_gemma":[0.047096692,0.0000060263965,0.62076545,0.00008766063,0.005165936,0.007315966,0.3165316,0.0003858863,0.0026448106],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9872364,0.003640991,0.0045344834,0.0022913779,0.001868894,0.00042788638],"domain_scores_gemma":[0.62587345,0.35450134,0.011737103,0.0053889854,0.001932869,0.00056628045],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058833924,0.00056311657,0.0031516945,0.00028724354,0.000091910566,0.00011662257,0.0013226346,0.00051225646,0.82402843],"category_scores_gemma":[0.79428685,0.0005069164,0.00060166925,0.00061256776,0.00016366364,0.0005041142,0.0007744859,0.00095399085,0.0001663806],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010467574,0.0016492347,0.0001926092,0.0003159637,0.001114783,0.000050909297,0.0003152181,5.38996e-7,0.000026534879,0.00025352303,0.98454493,0.0010681739],"study_design_scores_gemma":[0.06620364,0.01855534,0.36742797,0.04104233,0.004303612,0.00004726421,0.0015789417,0.0030541203,0.00046208143,0.28362963,0.20998004,0.0037150243],"about_ca_topic_score_codex":0.00015271368,"about_ca_topic_score_gemma":0.00011086869,"teacher_disagreement_score":0.8238621,"about_ca_system_score_codex":0.0010262502,"about_ca_system_score_gemma":0.0012338774,"threshold_uncertainty_score":0.9997382},"labels":[],"label_agreement":null},{"id":"W6902350275","doi":"10.6084/m9.figshare.26749925.v1","title":"Additional file 1 of Hypothesis testing and sample size considerations for the test-negative design","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Gilead Sciences (Canada)","funders":"","keywords":"Sample size determination; Statistical hypothesis testing; Sample (material); Statistical analysis; Design of experiments; Statistical power","score_opus":0.808745824011418,"score_gpt":0.5108620845299195,"score_spread":0.2978837394814985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902350275","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1439742e-7,0.0000062365784,0.00076404127,0.00014860208,0.00001741375,0.0005510645,0.99797326,0.00005501279,0.0004842558],"genre_scores_gemma":[0.000055071872,2.7727856e-7,0.9956624,0.00010572619,0.00016618561,0.0026241343,0.0012104659,0.000020581094,0.00015516067],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991377,0.00014266647,0.00031691077,0.0001719644,0.00012148593,0.00010927178],"domain_scores_gemma":[0.0012662435,0.99824846,0.00010551619,0.00013235926,0.00020991122,0.000037519454],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002518472,0.000088735076,0.00019284886,0.000016906493,0.00012110417,0.00006241594,0.000067024484,0.0000589992,0.9828245],"category_scores_gemma":[0.9978479,0.000060921513,0.00006121734,0.000117279524,0.000039704068,0.000031229672,0.000042655614,0.00010040678,0.00010563209],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003081482,0.000016200465,9.031285e-8,0.0001838473,0.000033963253,0.000001287552,0.000027302414,0.0000015687478,0.0000058169744,0.00015695345,0.9947349,0.004834979],"study_design_scores_gemma":[0.00007790576,0.00007031921,0.000106376705,0.001787705,0.000038226754,0.0000044857184,0.000020550287,0.004096048,0.00021245335,0.9875785,0.0059346473,0.00007277839],"about_ca_topic_score_codex":0.0000013733826,"about_ca_topic_score_gemma":0.000001830238,"teacher_disagreement_score":0.99810576,"about_ca_system_score_codex":0.0000112906655,"about_ca_system_score_gemma":0.0001358338,"threshold_uncertainty_score":0.24843073},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W6902409931","doi":"10.6084/m9.figshare.26608248","title":"Additional file 1 of Power and sample size calculation for incremental net benefit in cost effectiveness analyses with applications to trials conducted by the Canadian Cancer Trials Group","year":2024,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; University of Toronto; Queen's University; Cancer Care Ontario; Sunnybrook Health Science Centre","funders":"","keywords":"Sample size determination; Cost effectiveness; Sample (material); Power (physics); Clinical trial; Statistical power","score_opus":0.6434768039651223,"score_gpt":0.610085346982012,"score_spread":0.0333914569831103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902409931","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031759646,0.000033040993,0.014375733,0.00026212572,0.00006018638,0.0075312485,0.9742512,0.000002351542,0.00030811553],"genre_scores_gemma":[0.022729035,0.0000027495282,0.9516448,0.000102747144,0.00013473081,0.01730297,0.007857525,0.000034678174,0.00019080858],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99730814,0.0011372903,0.0008734863,0.00033178634,0.00018541423,0.000163905],"domain_scores_gemma":[0.64408755,0.3553836,0.00020031723,0.00014000664,0.00009252457,0.00009596096],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065715928,0.00012996336,0.00082721596,0.00007342342,0.00010002642,0.0001571623,0.0001836971,0.00009165802,0.2541042],"category_scores_gemma":[0.16171163,0.00008289983,0.000075315496,0.0003677883,0.00009391466,0.00007194533,0.00004808639,0.00009302875,0.0000071801283],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016406238,0.00022593931,0.000077650744,0.00016361834,0.0009741932,0.000002262002,0.00026282054,0.00005489316,0.003353962,0.0072892993,0.79318106,0.1927737],"study_design_scores_gemma":[0.006392098,0.0007517386,0.006154875,0.0020734426,0.0012848903,0.0000047763883,0.00037943348,0.0009076378,0.0074766045,0.36462328,0.60923034,0.000720863],"about_ca_topic_score_codex":0.01727696,"about_ca_topic_score_gemma":0.12221313,"teacher_disagreement_score":0.9663937,"about_ca_system_score_codex":0.0001652794,"about_ca_system_score_gemma":0.00033098814,"threshold_uncertainty_score":0.98926705},"labels":[],"label_agreement":null},{"id":"W6907950096","doi":"10.25384/sage.22010449","title":"sj-docx-1-ctj-10.1177_17407745221149222 – Supplemental material for A hybrid automated event adjudication system for clinical trials","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute; McMaster University","funders":"","keywords":"Adjudication; Event (particle physics); Clinical trial; Event data","score_opus":0.782974641663131,"score_gpt":0.6665223528253421,"score_spread":0.11645228883778891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6907950096","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039673964,0.00043525628,0.58964366,0.0030665125,0.010668136,0.00911478,0.38116905,0.0018354097,0.00009981183],"genre_scores_gemma":[0.019688431,0.0017608866,0.9526347,0.0002926267,0.010022169,0.0016292556,0.012918247,0.00032425582,0.00072942814],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98343396,0.005978615,0.0074686,0.0011884936,0.0009614889,0.00096882787],"domain_scores_gemma":[0.8682268,0.12563686,0.0031033584,0.0021621492,0.00038635998,0.0004844408],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.111242205,0.00046604016,0.0026849294,0.0002508077,0.00038297617,0.0003739456,0.001898435,0.00034854058,0.012329473],"category_scores_gemma":[0.30202836,0.00038514362,0.00079016417,0.00039263078,0.0001478694,0.00035402935,0.00088377245,0.00038093564,0.00025830924],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015624326,0.0003903718,0.000044741868,0.0007698875,0.00080313574,0.00003667755,0.000024802892,0.000002038748,0.0012230745,0.0012933913,0.90394837,0.08990107],"study_design_scores_gemma":[0.036942743,0.002783602,0.00095681875,0.005429908,0.0055041886,0.00021681217,0.0008982429,0.11761194,0.009961283,0.64457035,0.173107,0.002017132],"about_ca_topic_score_codex":0.000010840136,"about_ca_topic_score_gemma":0.0000052420414,"teacher_disagreement_score":0.7308414,"about_ca_system_score_codex":0.00017583233,"about_ca_system_score_gemma":0.00029318137,"threshold_uncertainty_score":0.99986005},"labels":[],"label_agreement":null},{"id":"W6920472379","doi":"10.60692/aresz-9k152","title":"Bayesian Optimal Phase II Design for Randomized Clinical Trials","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Frequentist inference; Bayesian probability; Flexibility (engineering); Interim analysis; Protocol (science); Randomized controlled trial; Interim; Table (database); Clinical trial","score_opus":0.6961878066735211,"score_gpt":0.5551210901413203,"score_spread":0.14106671653220082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920472379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035649564,0.0000022375632,0.98446333,0.00014549875,0.0025926377,0.0071583064,0.0010724047,0.0003353632,0.0006652577],"genre_scores_gemma":[0.3543799,1.4229146e-7,0.64142406,0.00025048575,0.00043045642,0.0032609396,0.000014610268,0.000030793075,0.00020862665],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.96967024,0.020932803,0.007799302,0.00035963728,0.0007803051,0.00045772118],"domain_scores_gemma":[0.9346295,0.06113222,0.0030085177,0.0006835191,0.00029625476,0.0002499686],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14647596,0.00031277718,0.0030195983,0.00024037989,0.0006363709,0.00014740055,0.00044990057,0.00021338728,0.00054738275],"category_scores_gemma":[0.17647418,0.00023524417,0.001109466,0.00024571104,0.00013064883,0.00026140985,0.00025192663,0.00035434478,0.00007247006],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.646068,0.00044028595,0.000215543,0.0026515748,0.0031476372,0.000024400364,0.07084277,0.0023212382,0.0000028887669,0.19402793,0.03438856,0.04586916],"study_design_scores_gemma":[0.6797086,0.0023804086,0.0000054558554,0.0001561597,0.0015421604,0.000049983068,0.008625243,0.27930832,0.00023209491,0.02518013,0.0020019778,0.0008094628],"about_ca_topic_score_codex":7.2337474e-7,"about_ca_topic_score_gemma":4.9322515e-9,"teacher_disagreement_score":0.3508149,"about_ca_system_score_codex":0.0001395436,"about_ca_system_score_gemma":0.00014057626,"threshold_uncertainty_score":0.95929784},"labels":[],"label_agreement":null},{"id":"W6920549791","doi":"10.6084/m9.figshare.13031627.v1","title":"Additional file 1 of Correction to: Cluster identification, selection, and description in Cluster randomized crossover trials: the PREP-IT trials","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cluster (spacecraft); Crossover; Cluster analysis; Field (mathematics)","score_opus":0.6196506493216412,"score_gpt":0.5245333096316499,"score_spread":0.09511733968999125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920549791","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018476672,0.000012911484,0.005290271,0.0014414449,0.0003226467,0.003189787,0.98931086,0.000049151455,0.00036443849],"genre_scores_gemma":[0.005215894,0.000016344136,0.43910077,0.010794536,0.0054903883,0.03862046,0.4906499,0.00022150388,0.009890165],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98901355,0.0073021105,0.002719938,0.00039798897,0.00039415623,0.00017223158],"domain_scores_gemma":[0.26572177,0.7310399,0.0020636213,0.00032294294,0.0006867682,0.00016501642],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007879496,0.00017793402,0.0014378948,0.0000768852,0.0000913195,0.00013849046,0.00018013686,0.00016515389,0.9363851],"category_scores_gemma":[0.9506869,0.000121164776,0.00031148572,0.00041785592,0.000039285525,0.0001507852,0.000101977246,0.00026305974,0.00047849547],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013267294,0.000044135984,4.5416823e-7,0.0001179204,0.00006187776,2.5643297e-7,0.00023210031,0.000028558514,0.000018418687,0.000052902513,0.98459953,0.0015765389],"study_design_scores_gemma":[0.12375365,0.00037190103,0.0007471687,0.0073299385,0.0005346638,0.000016416976,0.00029810905,0.036083993,0.0011570288,0.2496558,0.5792677,0.00078363984],"about_ca_topic_score_codex":0.000004674327,"about_ca_topic_score_gemma":0.000034217563,"teacher_disagreement_score":0.9428074,"about_ca_system_score_codex":0.000046297002,"about_ca_system_score_gemma":0.00009570365,"threshold_uncertainty_score":0.6150251},"labels":[],"label_agreement":null},{"id":"W6920562733","doi":"10.6084/m9.figshare.19793292","title":"Additional file 1 of Evaluation of statistical approaches for association testing in noisy drug screening data","year":2022,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Université du Québec à Montréal; University of Toronto; University Health Network","funders":"","keywords":"Association (psychology); Screening test; Statistical analysis; Statistical hypothesis testing","score_opus":0.8950764574806416,"score_gpt":0.6048455537779277,"score_spread":0.29023090370271387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920562733","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006489558,0.000002191275,0.033675756,0.00005071503,0.000048292008,0.0011673695,0.9602517,0.0000011475271,0.0041539003],"genre_scores_gemma":[0.0016568863,4.0919755e-8,0.9669694,0.0000055433943,0.000048184418,0.00064444856,0.030442826,0.0000121778785,0.00022051953],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964281,0.0014050584,0.00087405083,0.00031754797,0.0008340966,0.00014118715],"domain_scores_gemma":[0.69242096,0.3061066,0.00084137503,0.00035032973,0.00024949215,0.00003123505],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015367164,0.00007263415,0.00037835343,0.000050927498,0.00006501657,0.000019712303,0.00044897682,0.00004170072,0.5647131],"category_scores_gemma":[0.5628826,0.0000771323,0.00002719197,0.0002257251,0.00003874241,0.000099047254,0.0006384277,0.00015740767,0.0000051378083],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009811146,0.00036102172,0.00009853269,0.000043010037,0.00005360217,5.9711897e-7,0.00012169157,0.00021966315,0.000010829199,0.0013744717,0.6691401,0.3284784],"study_design_scores_gemma":[0.0020936462,0.00017224858,0.0023984632,0.00023900536,0.00026670334,0.0000014242444,0.00082612416,0.41704607,0.00010233107,0.5587699,0.017883055,0.00020107148],"about_ca_topic_score_codex":0.000017003642,"about_ca_topic_score_gemma":0.000025836755,"teacher_disagreement_score":0.93329364,"about_ca_system_score_codex":0.00011136136,"about_ca_system_score_gemma":0.00028971894,"threshold_uncertainty_score":0.5325983},"labels":[],"label_agreement":null},{"id":"W6920671261","doi":"10.6084/m9.figshare.16822642","title":"Additional file 1 of Confidence interval of risk difference by different statistical methods and its impact on the study conclusion in antibiotic non-inferiority trials","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; University Health Network; Queen's University","funders":"","keywords":"Confidence interval; Interval (graph theory); Statistical analysis; Antibiotics; Interval data; Clinical trial","score_opus":0.4703599247224805,"score_gpt":0.5846481298855969,"score_spread":0.11428820516311639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920671261","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015766587,0.000024066929,0.0010353402,0.000015807635,0.00004769479,0.00077847944,0.9822367,0.000009689772,0.00008563636],"genre_scores_gemma":[0.68261945,0.000019313808,0.19864622,0.000071484894,0.00014343193,0.00049142324,0.11787065,0.000054017662,0.000083995415],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99042577,0.007142877,0.0013799169,0.00039375396,0.00045081458,0.00020688405],"domain_scores_gemma":[0.37695587,0.6214785,0.0008056203,0.00037266014,0.0002781356,0.00010921438],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002089708,0.0002394594,0.0014706412,0.000045523517,0.000052664076,0.000029427552,0.00025707152,0.00013889115,0.90865034],"category_scores_gemma":[0.80880076,0.00014186412,0.00016511808,0.0001837234,0.00006239506,0.000027698068,0.00038715394,0.00045890812,0.000028478327],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003320711,0.0015099627,0.0001407919,0.00041316604,0.00016672391,0.000023812672,0.0002687586,5.0700265e-7,0.0007477643,0.0008411809,0.9844827,0.011072538],"study_design_scores_gemma":[0.004869353,0.0035398812,0.52917457,0.022349156,0.00041263472,0.000011625415,0.0009689238,0.006458036,0.026091788,0.4045636,0.0006703489,0.0008900986],"about_ca_topic_score_codex":0.000010524213,"about_ca_topic_score_gemma":0.000008585892,"teacher_disagreement_score":0.9838124,"about_ca_system_score_codex":0.000042403077,"about_ca_system_score_gemma":0.0001507542,"threshold_uncertainty_score":0.57850504},"labels":[],"label_agreement":null},{"id":"W6920759399","doi":"10.6084/m9.figshare.16900735","title":"Additional file 1 of A comparison of the Food and Drug Administration’s and Health Canada’s regulatory decisions about failed confirmatory trials for oncology drugs: an observational study","year":2021,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University; University of Toronto; University Health Network","funders":"","keywords":"Observational study; Confirmatory factor analysis; Drug; Clinical trial; Table (database); MEDLINE","score_opus":0.8427006086704912,"score_gpt":0.6311781503436248,"score_spread":0.21152245832686645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920759399","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122127764,0.000088712964,0.0006619454,0.0028279964,0.0003200641,0.004446913,0.8686697,0.0000022150075,0.00085470406],"genre_scores_gemma":[0.11341862,0.0000024023625,0.8828086,0.00021318982,0.00009165819,0.00049066456,0.0025472417,0.00001663685,0.0004109896],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952242,0.0021770825,0.0017764131,0.000314767,0.00037781204,0.00012972613],"domain_scores_gemma":[0.82388335,0.1740518,0.001203382,0.00035088652,0.00037616727,0.00013439415],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0050201304,0.00011456803,0.0010912152,0.000020735912,0.0001599203,0.00003531332,0.0002415182,0.00007452944,0.08756357],"category_scores_gemma":[0.12039911,0.00008815357,0.00006181859,0.0000865933,0.00017041208,0.00006262343,0.00016376772,0.00011893911,4.2481645e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020433699,0.0009559003,0.00029493362,0.00004394513,0.00015730235,8.7582737e-7,0.0010582459,8.594239e-7,0.000008148958,0.0051388256,0.9509148,0.041221824],"study_design_scores_gemma":[0.00978736,0.0033972543,0.108191386,0.0011197719,0.00046723898,0.0000122435695,0.029953826,0.0005257332,0.0016632888,0.2211054,0.6232687,0.0005077727],"about_ca_topic_score_codex":0.0007183587,"about_ca_topic_score_gemma":0.17359819,"teacher_disagreement_score":0.88214666,"about_ca_system_score_codex":0.00007464433,"about_ca_system_score_gemma":0.0069784876,"threshold_uncertainty_score":0.998651},"labels":[],"label_agreement":null},{"id":"W6920837855","doi":"10.6084/m9.figshare.16822642.v1","title":"Additional file 1 of Confidence interval of risk difference by different statistical methods and its impact on the study conclusion in antibiotic non-inferiority trials","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; University Health Network; Queen's University","funders":"","keywords":"Confidence interval; Interval (graph theory); Statistical analysis; Antibiotics; Interval data; Clinical trial","score_opus":0.4703599247224805,"score_gpt":0.5846481298855969,"score_spread":0.11428820516311639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920837855","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015766587,0.000024066929,0.0010353402,0.000015807635,0.00004769479,0.00077847944,0.9822367,0.000009689772,0.00008563636],"genre_scores_gemma":[0.68261945,0.000019313808,0.19864622,0.000071484894,0.00014343193,0.00049142324,0.11787065,0.000054017662,0.000083995415],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99042577,0.007142877,0.0013799169,0.00039375396,0.00045081458,0.00020688405],"domain_scores_gemma":[0.37695587,0.6214785,0.0008056203,0.00037266014,0.0002781356,0.00010921438],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002089708,0.0002394594,0.0014706412,0.000045523517,0.000052664076,0.000029427552,0.00025707152,0.00013889115,0.90865034],"category_scores_gemma":[0.80880076,0.00014186412,0.00016511808,0.0001837234,0.00006239506,0.000027698068,0.00038715394,0.00045890812,0.000028478327],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003320711,0.0015099627,0.0001407919,0.00041316604,0.00016672391,0.000023812672,0.0002687586,5.0700265e-7,0.0007477643,0.0008411809,0.9844827,0.011072538],"study_design_scores_gemma":[0.004869353,0.0035398812,0.52917457,0.022349156,0.00041263472,0.000011625415,0.0009689238,0.006458036,0.026091788,0.4045636,0.0006703489,0.0008900986],"about_ca_topic_score_codex":0.000010524213,"about_ca_topic_score_gemma":0.000008585892,"teacher_disagreement_score":0.9838124,"about_ca_system_score_codex":0.000042403077,"about_ca_system_score_gemma":0.0001507542,"threshold_uncertainty_score":0.57850504},"labels":[],"label_agreement":null},{"id":"W6920899151","doi":"10.6084/m9.figshare.26735643.v1","title":"Additional file 1 of Accounting for center-level effects in multicenter randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Population Health Research Institute; McMaster University","funders":"","keywords":"Table (database); Randomized controlled trial; Calibration; Data collection","score_opus":0.5269972240537086,"score_gpt":0.5390080990832374,"score_spread":0.0120108750295288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920899151","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018433967,0.000052149368,0.0012080028,0.000035798275,0.00025992014,0.0046838336,0.9926664,0.000059319704,0.0010327228],"genre_scores_gemma":[0.00018921866,9.333273e-7,0.5908674,0.00010693622,0.0006192078,0.027689597,0.37980783,0.00005066183,0.00066820637],"study_design_codex":"not_applicable","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9949606,0.0020617289,0.002153679,0.0002934088,0.00029102288,0.00023958221],"domain_scores_gemma":[0.13865618,0.8603238,0.00062036084,0.00016586097,0.00018288342,0.000050914878],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004512067,0.0001955325,0.0034850386,0.00013773571,0.000022689655,0.00006474272,0.00017043272,0.0001684738,0.9785453],"category_scores_gemma":[0.9646778,0.00013023485,0.0012456722,0.00013004235,0.000020934354,0.000066962995,0.00006789547,0.0001859635,0.00039799852],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015218711,0.00010792947,7.101386e-8,0.0019805154,0.00029001167,0.0000070068995,0.000020106996,3.2696968e-7,0.000005274377,0.00079630606,0.97829384,0.0032799041],"study_design_scores_gemma":[0.42019993,0.00007335334,0.000019467623,0.051917072,0.00033820508,0.0000017179744,0.000013335092,0.015550496,0.0001906773,0.3997256,0.11165311,0.00031704732],"about_ca_topic_score_codex":5.3820486e-7,"about_ca_topic_score_gemma":0.0000016182985,"teacher_disagreement_score":0.9781473,"about_ca_system_score_codex":0.000033737233,"about_ca_system_score_gemma":0.000093370145,"threshold_uncertainty_score":0.53108233},"labels":[],"label_agreement":null},{"id":"W6920910932","doi":"10.6084/m9.figshare.12799225.v1","title":"Additional file 1 of Cluster identification, selection, and description in cluster randomized crossover trials: the PREP-IT trials","year":2020,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Cluster (spacecraft); Crossover; Field (mathematics); Cluster analysis","score_opus":0.6730572175693899,"score_gpt":0.5629274517943299,"score_spread":0.11012976577505995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920910932","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005167094,0.00010739908,0.23571229,0.023949306,0.0012939563,0.034010608,0.6860762,0.000027266016,0.013655866],"genre_scores_gemma":[0.0029317248,0.000017907067,0.98580337,0.0009959697,0.0007236261,0.0025004407,0.0018215938,0.00004103129,0.0051643127],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98273176,0.012454557,0.0037789543,0.0004721534,0.00038629174,0.00017626984],"domain_scores_gemma":[0.4500338,0.5468785,0.0022865052,0.00034107474,0.00034426965,0.0001158488],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03339874,0.00016745958,0.0018934888,0.0000502705,0.000090859205,0.0003041337,0.00035671945,0.0001708786,0.6943169],"category_scores_gemma":[0.7768495,0.00010617441,0.0002541882,0.00027993743,0.00025351578,0.00023963324,0.00019628859,0.00022408785,0.00016782922],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031985883,0.000089411726,0.000001698982,0.00003227166,0.00012669644,4.2975947e-7,0.0005534513,0.000007120686,0.000071901435,0.0004111622,0.9584193,0.008300631],"study_design_scores_gemma":[0.17374623,0.00017076777,0.00015306477,0.0005674255,0.00076403975,0.000007949726,0.00044256926,0.008419043,0.0012982412,0.567076,0.24695328,0.00040133108],"about_ca_topic_score_codex":0.000008739403,"about_ca_topic_score_gemma":0.00004244162,"teacher_disagreement_score":0.7500911,"about_ca_system_score_codex":0.000028360959,"about_ca_system_score_gemma":0.00012961302,"threshold_uncertainty_score":0.9953194},"labels":[],"label_agreement":null},{"id":"W6920945089","doi":"10.6084/m9.figshare.23632752","title":"Additional file 11 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Delphi; Development (topology); Delphi method; Tree (set theory); Diagram","score_opus":0.8328310564941064,"score_gpt":0.6025784693116346,"score_spread":0.23025258718247177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920945089","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069390405,0.0000073204073,0.00006392373,0.00006661832,0.00004725399,0.0016952599,0.9910349,0.000041994484,0.00010365366],"genre_scores_gemma":[0.014457903,9.374332e-7,0.8625646,0.000061058585,0.00023038466,0.004529104,0.1176269,0.0000666828,0.0004623968],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740124,0.0005302853,0.0013315792,0.00024289572,0.0003085673,0.00018543318],"domain_scores_gemma":[0.6728924,0.32591325,0.00061098294,0.0002245812,0.0002928643,0.00006591384],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017792725,0.00013794325,0.0007531847,0.00007560036,0.00013496206,0.000015642767,0.0001597544,0.00008498818,0.6139765],"category_scores_gemma":[0.58555454,0.00009638092,0.00013346657,0.00022894569,0.000055142664,0.00001537773,0.00014882759,0.00010743252,0.00009754591],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009083401,0.00026663128,0.000008937091,0.00019230835,0.0001225374,0.000006149614,0.00023758615,5.114881e-7,0.00004036019,0.00036446002,0.993931,0.0047386843],"study_design_scores_gemma":[0.03663641,0.003843112,0.058516327,0.020299083,0.0012663719,0.000030241994,0.004903695,0.0023860452,0.0040660347,0.36907357,0.4972911,0.0016880233],"about_ca_topic_score_codex":8.354859e-7,"about_ca_topic_score_gemma":0.000007011021,"teacher_disagreement_score":0.873408,"about_ca_system_score_codex":0.00001228965,"about_ca_system_score_gemma":0.00021707483,"threshold_uncertainty_score":0.41793653},"labels":[],"label_agreement":null},{"id":"W6920965766","doi":"10.6084/m9.figshare.26693443.v1","title":"Additional file 3 of Trials that turn from retrospectively registered to prospectively registered: a cohort study of “retroactively prospective” clinical trial registration using history data","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Clinical trial; Cohort study; Cohort; Retrospective cohort study; Patient data","score_opus":0.8939182581846759,"score_gpt":0.5951802511582628,"score_spread":0.29873800702641307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920965766","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015528396,0.000071545124,0.0006670099,0.0000249671,0.0008688262,0.008085498,0.9861487,0.00019570511,0.002384899],"genre_scores_gemma":[0.047096692,0.0000060263965,0.62076545,0.00008766063,0.005165936,0.007315966,0.3165316,0.0003858863,0.0026448106],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9872364,0.003640991,0.0045344834,0.0022913779,0.001868894,0.00042788638],"domain_scores_gemma":[0.62587345,0.35450134,0.011737103,0.0053889854,0.001932869,0.00056628045],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058833924,0.00056311657,0.0031516945,0.00028724354,0.000091910566,0.00011662257,0.0013226346,0.00051225646,0.82402843],"category_scores_gemma":[0.79428685,0.0005069164,0.00060166925,0.00061256776,0.00016366364,0.0005041142,0.0007744859,0.00095399085,0.0001663806],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010467574,0.0016492347,0.0001926092,0.0003159637,0.001114783,0.000050909297,0.0003152181,5.38996e-7,0.000026534879,0.00025352303,0.98454493,0.0010681739],"study_design_scores_gemma":[0.06620364,0.01855534,0.36742797,0.04104233,0.004303612,0.00004726421,0.0015789417,0.0030541203,0.00046208143,0.28362963,0.20998004,0.0037150243],"about_ca_topic_score_codex":0.00015271368,"about_ca_topic_score_gemma":0.00011086869,"teacher_disagreement_score":0.8238621,"about_ca_system_score_codex":0.0010262502,"about_ca_system_score_gemma":0.0012338774,"threshold_uncertainty_score":0.9997382},"labels":[],"label_agreement":null},{"id":"W6921059687","doi":"10.6084/m9.figshare.14451051","title":"Additional file 1 of Intention-to-treat analysis may be more conservative than per protocol analysis in antibiotic non-inferiority trials: a systematic review","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; McMaster University; Juravinski Cancer Centre","funders":"","keywords":"Protocol (science); Antibiotics; MEDLINE; Data collection; Protocol analysis","score_opus":0.5621384658236344,"score_gpt":0.5747946818366167,"score_spread":0.01265621601298239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921059687","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004588158,0.00003100905,0.00036385062,0.00017372804,0.000011056107,0.034687817,0.9642399,0.000030946172,0.00045711495],"genre_scores_gemma":[0.00010874432,0.0000038793564,0.21634246,0.00075425603,0.000060312108,0.2094243,0.57215047,0.00004096815,0.0011146299],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9913864,0.003944068,0.0030470102,0.0006340802,0.00070118404,0.00028725484],"domain_scores_gemma":[0.79035956,0.20465314,0.0019725938,0.0011837602,0.0016052269,0.00022574005],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022062163,0.00033001043,0.0047197817,0.00045968918,0.000052143856,0.000056525758,0.00035982096,0.00019901627,0.97220886],"category_scores_gemma":[0.7776001,0.00025942933,0.0016816892,0.004816505,0.000037673904,0.000083063074,0.00021853198,0.00028078523,0.0004476859],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003636226,0.0003261313,0.0000804522,0.14652866,0.0029324368,0.000042720265,0.000058643996,0.0000027395681,0.0000035883102,0.000034380046,0.8499271,0.000026736261],"study_design_scores_gemma":[0.0015837777,0.00020747188,0.0111411465,0.9451888,0.027980186,0.000008501602,0.00046074443,0.0020197297,0.00039747666,0.0068276897,0.0032017718,0.0009826685],"about_ca_topic_score_codex":0.000017319397,"about_ca_topic_score_gemma":0.000115854076,"teacher_disagreement_score":0.97176117,"about_ca_system_score_codex":0.00011786058,"about_ca_system_score_gemma":0.0003499999,"threshold_uncertainty_score":0.9999858},"labels":[],"label_agreement":null},{"id":"W6921107056","doi":"10.6084/m9.figshare.26693437","title":"Additional file 1 of Trials that turn from retrospectively registered to prospectively registered: a cohort study of “retroactively prospective” clinical trial registration using history data","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Clinical trial; Table (database); Cohort; Cohort study; Retrospective cohort study; Data collection","score_opus":0.8955052973751,"score_gpt":0.5956874186779625,"score_spread":0.2998178786971375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921107056","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015438242,0.00007124755,0.00066398625,0.00002505476,0.00086230814,0.008084362,0.9861797,0.0001958688,0.002373664],"genre_scores_gemma":[0.046336185,0.000005913341,0.6203476,0.000087022985,0.0050800024,0.0073648565,0.31781068,0.00038286942,0.0025848353],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9872358,0.0036433935,0.0045325393,0.002291957,0.0018684405,0.00042787552],"domain_scores_gemma":[0.62389946,0.35648572,0.011734365,0.0053946455,0.0019195429,0.00056625454],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058854492,0.00056317804,0.0031514456,0.00028731793,0.0000919167,0.00011643706,0.0013232796,0.0005122902,0.8268139],"category_scores_gemma":[0.7943209,0.00050701655,0.00060169905,0.000612744,0.00016365462,0.0005038136,0.0007749201,0.000954142,0.00016498295],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01041542,0.0016491965,0.00019233103,0.00031172254,0.0011150624,0.000050418275,0.00031508194,5.386521e-7,0.000026473102,0.00025465974,0.98461336,0.0010557288],"study_design_scores_gemma":[0.065678075,0.018624065,0.37003747,0.041217197,0.0043451935,0.00004773396,0.0015889253,0.0030583313,0.0004556372,0.28375015,0.20747282,0.00372443],"about_ca_topic_score_codex":0.00015138254,"about_ca_topic_score_gemma":0.0001102878,"teacher_disagreement_score":0.8266489,"about_ca_system_score_codex":0.0010231058,"about_ca_system_score_gemma":0.001233349,"threshold_uncertainty_score":0.99973816},"labels":[],"label_agreement":null},{"id":"W6921162853","doi":"10.6084/m9.figshare.23632722","title":"Additional file 2 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Development (topology); Data flow diagram; Diagram; Flow (mathematics)","score_opus":0.8301276040917855,"score_gpt":0.6024223961486928,"score_spread":0.2277052079430928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6921162853","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025908633,0.0000065482577,0.000043887045,0.000052714597,0.000039254355,0.0015856923,0.9954901,0.00003977165,0.00015120221],"genre_scores_gemma":[0.0056562945,7.2839435e-7,0.8026663,0.000050171966,0.00019411798,0.0048537776,0.18605223,0.000054938624,0.00047141497],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975094,0.00050526246,0.0012809501,0.00023217773,0.00029527477,0.00017693559],"domain_scores_gemma":[0.62403166,0.3748279,0.00059153116,0.00021019619,0.00027745316,0.00006124327],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015453573,0.00013152978,0.0007237463,0.0000723794,0.00013005167,0.000014853659,0.00015273818,0.00008161605,0.81456786],"category_scores_gemma":[0.6444429,0.00009152876,0.00012853426,0.00022418918,0.00005290336,0.000014356549,0.00014310802,0.00011422891,0.00012962737],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098372475,0.00023243036,0.0000028625577,0.00016791422,0.00013094643,0.0000052998566,0.00020207226,3.7899352e-7,0.000031298317,0.00021062937,0.9926303,0.0062875054],"study_design_scores_gemma":[0.025283916,0.0033367695,0.032213982,0.017702375,0.0008941544,0.00002266424,0.003547677,0.0018542482,0.0024462736,0.3033393,0.6080641,0.0012945096],"about_ca_topic_score_codex":4.6933658e-7,"about_ca_topic_score_gemma":0.0000031136176,"teacher_disagreement_score":0.8144382,"about_ca_system_score_codex":0.000011640236,"about_ca_system_score_gemma":0.00021993289,"threshold_uncertainty_score":0.37324345},"labels":[],"label_agreement":null},{"id":"W6925066981","doi":"10.17605/osf.io/t9f3y","title":"TORONTO: A Monte Carlo Simulation Study to Evaluate the Statistical Properties of a Smoothed Non-Parametric Bootstrap Point Estimator and Corresponding Non-Parametric Bootstrap Confidence Interval Estimators in Post-Selection Inference Problems in Case-Control Sampling Designs in the L1 Penalized Logit Model","year":2022,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Monte Carlo method; Estimator; Confidence interval; Point estimation; Inference; Statistical inference; Sampling (signal processing); Interval estimation; Interval (graph theory)","score_opus":0.37806610701661064,"score_gpt":0.49645671350330983,"score_spread":0.11839060648669919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925066981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6237907,0.0000038049045,0.37017524,0.00005755835,0.00007721325,0.005677177,0.00004312975,0.000026755013,0.00014845267],"genre_scores_gemma":[0.9206535,0.000004421371,0.077124886,0.00006383578,0.000011090549,0.0020168985,7.654364e-7,0.000046865916,0.00007771254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98648745,0.0075176214,0.002552044,0.001703916,0.0010824928,0.00065646385],"domain_scores_gemma":[0.93317056,0.06397966,0.00068895036,0.0016406919,0.0003393024,0.00018081587],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03796306,0.000472633,0.0012423017,0.0006437014,0.000250577,0.00020376679,0.0010712845,0.00015009908,0.0032879226],"category_scores_gemma":[0.1901225,0.0003662719,0.00013471075,0.0014546723,0.00025512403,0.0002930751,0.0008917016,0.0011624767,0.00021756053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027179206,0.0018174221,0.035861697,0.00023180904,0.00011923635,0.00009069231,0.014992233,0.93773144,0.0011284484,0.0010206001,0.000010634257,0.004277867],"study_design_scores_gemma":[0.003085809,0.00011862545,0.04259903,0.00024474045,0.00018961167,0.000063492436,0.0043127183,0.90810865,0.00014928619,0.0407706,5.779146e-7,0.00035683787],"about_ca_topic_score_codex":0.005839458,"about_ca_topic_score_gemma":0.002110056,"teacher_disagreement_score":0.29686287,"about_ca_system_score_codex":0.0007664835,"about_ca_system_score_gemma":0.0003986467,"threshold_uncertainty_score":0.99987894},"labels":[],"label_agreement":null},{"id":"W6926003003","doi":"10.20383/103.01216","title":"Catchment Attributes and MEteorology for Large-Sample SPATially distributed analysis (CAMELS-SPAT): Streamflow observations, forcing data and geospatial data for hydrologic studies across North America","year":2025,"lang":"en","type":"dataset","venue":"Federated Research Data Repository","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Geospatial analysis; Streamflow; Data set; Shapefile; Forcing (mathematics); Hydrological modelling; Drainage basin; Structural basin","score_opus":0.674288906206791,"score_gpt":0.5969620838648094,"score_spread":0.07732682234198163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926003003","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027806705,0.0014630655,0.30034736,0.0007045626,0.00047349863,0.0030430525,0.6936268,0.00006310707,4.6146812e-7],"genre_scores_gemma":[0.000102433994,0.00281747,0.2580163,0.00011642405,0.0005538864,0.00064816093,0.7376749,0.00003545396,0.000035007888],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865014,0.003937321,0.002603999,0.00411583,0.0011683434,0.0016731209],"domain_scores_gemma":[0.7685883,0.21652216,0.0013066197,0.011078101,0.0020806047,0.0004242084],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.017047768,0.0008120351,0.0031755415,0.00037724807,0.0028841018,0.0010584631,0.005926442,0.00082426006,0.00001225522],"category_scores_gemma":[0.41103923,0.0006929688,0.0001381283,0.0013357946,0.0009503359,0.0006123792,0.022557534,0.0014270575,6.158738e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094757264,0.00051469536,0.001017247,0.0025758047,0.008872189,0.000046682653,0.000039965922,0.000023066346,0.000008016686,0.000056485682,0.9842902,0.0016080816],"study_design_scores_gemma":[0.0045334054,0.0015500586,0.000418448,0.00043639736,0.011469085,0.000010475,0.0009003222,0.25678143,0.000040542214,0.014274726,0.70825976,0.0013253454],"about_ca_topic_score_codex":0.0030758115,"about_ca_topic_score_gemma":0.017423032,"teacher_disagreement_score":0.39399147,"about_ca_system_score_codex":0.00021759175,"about_ca_system_score_gemma":0.000933768,"threshold_uncertainty_score":0.99997854},"labels":[],"label_agreement":null},{"id":"W6926308733","doi":"10.25318/3310076201-eng","title":"Canadian Business Counts, without employees, June 2024","year":2024,"lang":"en","type":"dataset","venue":"Statistics Canada Dissemination","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Business failure; Census; Feature (linguistics)","score_opus":0.11071859367913721,"score_gpt":0.4616052425059286,"score_spread":0.3508866488267914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926308733","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.5235691e-7,0.000103818005,0.004299019,0.00033243975,0.010501725,0.00038288548,0.9834631,0.00003426283,0.00088229845],"genre_scores_gemma":[0.0000033200004,0.00014196627,0.070100375,0.00014623963,0.0005893281,0.000056166038,0.9157604,0.00008831889,0.01311389],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99718034,0.00017977254,0.0008149607,0.00050759193,0.0008718058,0.00044553386],"domain_scores_gemma":[0.9896896,0.008581723,0.0002596416,0.0005939692,0.0004912244,0.00038387498],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00073144835,0.0003942491,0.0006537022,0.00021900362,0.000104005456,0.00014058001,0.00039166602,0.00036945232,0.0056716898],"category_scores_gemma":[0.03894299,0.000384928,0.000037798425,0.00048512363,0.00008156076,0.000025968457,0.00006401297,0.0006416128,0.00073098385],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048179745,0.000020277688,0.0000021887731,0.00088409916,0.00007666886,0.00023580175,0.000004710317,2.0125202e-7,2.073275e-7,0.009461366,0.98711616,0.0021935091],"study_design_scores_gemma":[0.00006204049,0.000012680568,0.0000555431,0.00041307334,0.00039454576,0.000006473667,0.00001353712,0.000019892761,0.0000015740605,0.15351762,0.8451333,0.00036973486],"about_ca_topic_score_codex":0.6300794,"about_ca_topic_score_gemma":0.99039763,"teacher_disagreement_score":0.36031824,"about_ca_system_score_codex":0.001210729,"about_ca_system_score_gemma":0.0037036913,"threshold_uncertainty_score":0.9998603},"labels":[],"label_agreement":null},{"id":"W6926371380","doi":"10.22008/fk2/cs5lka/abpfkm","title":"c50ac4.rtl","year":2021,"lang":"en","type":"dataset","venue":"Geological Survey of Denmark and Greenland (GEUS)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Apotex Pharmachem (Canada)","funders":"","keywords":"Process (computing); Identification (biology); Product (mathematics)","score_opus":0.49016086826801203,"score_gpt":0.5021642668041167,"score_spread":0.012003398536104715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926371380","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032210585,0.0008741824,0.0017246723,0.000115965944,0.00077995507,0.00043732123,0.9925485,0.000025616091,0.00027273243],"genre_scores_gemma":[0.00079459907,0.0046101087,0.16588517,0.0006148633,0.00087765127,0.000074243246,0.82596684,0.00006721551,0.0011093302],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9907336,0.005279571,0.0017178536,0.0009776349,0.0006967191,0.00059458],"domain_scores_gemma":[0.90063673,0.09695699,0.0007241134,0.0009864798,0.0003586845,0.00033701502],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009772222,0.00058113714,0.002638053,0.00009761955,0.00011724082,0.000056399444,0.00068098103,0.0013990271,0.0062872693],"category_scores_gemma":[0.190172,0.00040893775,0.00028441765,0.00036383592,0.0007100239,0.00003338851,0.0008430165,0.0010501996,0.00010822823],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003128011,0.00034362735,0.011401448,0.0005374265,0.0002459,0.00016386296,0.0000031724944,2.4382786e-7,9.949432e-7,0.00024290626,0.98044777,0.0062998384],"study_design_scores_gemma":[0.0023797418,0.00091796974,0.2753948,0.0004952053,0.0007470746,0.000071412534,0.000011869106,0.000020693265,0.000016086835,0.40168285,0.31697065,0.0012916453],"about_ca_topic_score_codex":0.0011088373,"about_ca_topic_score_gemma":0.0011104442,"teacher_disagreement_score":0.6634771,"about_ca_system_score_codex":0.000018647639,"about_ca_system_score_gemma":0.0001105889,"threshold_uncertainty_score":0.99989736},"labels":[],"label_agreement":null},{"id":"W6929646734","doi":"10.5061/dryad.ph02r","title":"Data from: Reduced mycorrhizal responsiveness leads to increased competitive tolerance in an invasive exotic plant","year":2016,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Competition (biology); Invasive species; Introduced species; Biota; Centaurea; Range (aeronautics); Native plant; Symbiosis","score_opus":0.36098151687366736,"score_gpt":0.4635438775579016,"score_spread":0.10256236068423424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929646734","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061945643,0.00011358195,0.0020128407,0.000097106575,0.00089810306,0.001048669,0.93376106,0.00007997544,0.000043032705],"genre_scores_gemma":[0.0010873189,0.00070907164,0.07774682,0.00071217126,0.0016102325,0.000072727235,0.9179496,0.00009834242,0.000013705097],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9882933,0.00559292,0.0017376785,0.0027737075,0.00069319323,0.00090921787],"domain_scores_gemma":[0.8835338,0.10771684,0.00073725625,0.007311896,0.00008962586,0.0006106094],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0051468536,0.00086612237,0.002137635,0.0002837157,0.00022465436,0.0002541788,0.0077933013,0.00045325383,0.0002064511],"category_scores_gemma":[0.018605843,0.00070513773,0.000060142607,0.00040008558,0.00026160505,0.0005138393,0.006876121,0.0010963221,0.00009162084],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008987588,0.0008800491,0.0022158676,0.0030146434,0.00043232687,0.0014716646,0.00093918043,0.000037241116,0.00095676206,0.0005346385,0.97733635,0.0031936655],"study_design_scores_gemma":[0.014981021,0.0025158415,0.061844762,0.115812,0.004617342,0.00027989908,0.00257176,0.04563799,0.0002906889,0.28769264,0.45253313,0.011222932],"about_ca_topic_score_codex":0.0022246717,"about_ca_topic_score_gemma":0.03356102,"teacher_disagreement_score":0.5248032,"about_ca_system_score_codex":0.00007966396,"about_ca_system_score_gemma":0.00032053632,"threshold_uncertainty_score":0.99954},"labels":[],"label_agreement":null},{"id":"W6930028805","doi":"10.5061/dryad.djh9w0vx9","title":"Data from: Mate fidelity improves survival and breeding propensity of a long-lived bird","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Mating; Mate choice; Reproductive success; Animal sexual behaviour; Fidelity; Cooperative breeding; Sexual selection; Mating system","score_opus":0.6529299646902322,"score_gpt":0.48102253582412596,"score_spread":0.17190742886610627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930028805","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041068293,0.000030771153,0.007545617,0.00023811925,0.0002702841,0.0008623871,0.98965657,0.00040013035,0.00058542326],"genre_scores_gemma":[0.0004356564,0.00040887046,0.034972217,0.00008769253,0.0005580001,6.733902e-8,0.961862,0.0016260154,0.00004947275],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947533,0.0020628397,0.0010618513,0.001040921,0.00072580494,0.00035526804],"domain_scores_gemma":[0.9930783,0.0034454793,0.0007294231,0.001788177,0.00065278163,0.00030582512],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0044160564,0.00031199976,0.00095956284,0.00011936291,0.0006135088,0.00054265454,0.0027330664,0.00026068315,0.006407971],"category_scores_gemma":[0.12044549,0.00029562233,0.00007025378,0.0003467173,0.00048711663,0.00017767434,0.009632475,0.0008261523,0.0025041304],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024884808,0.00015071536,0.0000012885245,0.00090736954,0.00018948565,0.000034529454,0.0000514489,1.0610856e-7,0.00059335295,0.0003000207,0.98575103,0.011771801],"study_design_scores_gemma":[0.00090499624,0.0003902887,0.00035895567,0.00026862058,0.00031671076,0.000017412473,0.00007620361,0.00019328493,0.00010491627,0.016441852,0.9805362,0.00039052975],"about_ca_topic_score_codex":0.00018306718,"about_ca_topic_score_gemma":0.0000052144987,"teacher_disagreement_score":0.116029434,"about_ca_system_score_codex":0.00006093929,"about_ca_system_score_gemma":0.000013080686,"threshold_uncertainty_score":0.9999496},"labels":[],"label_agreement":null},{"id":"W6930086686","doi":"10.5281/zenodo.11756340","title":"pre calculus 12 textbook pdf bc","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Filter (signal processing); Limiting; Subject (documents); Population","score_opus":0.33765175215630694,"score_gpt":0.4620366955888531,"score_spread":0.12438494343254614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930086686","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019186587,0.00018653292,0.038688798,0.00027814545,0.0006279863,0.0009990756,0.00096118404,0.0025568218,0.95569956],"genre_scores_gemma":[0.000036549667,0.0001433266,0.0491613,0.00012206667,0.001252105,1.7286158e-7,0.00026934658,0.01849257,0.93052256],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959361,0.0012857789,0.0006817952,0.0008597878,0.00071246695,0.0005240683],"domain_scores_gemma":[0.99705344,0.001034895,0.0003021821,0.001065838,0.00022947196,0.00031416657],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021641676,0.0003656884,0.0006212723,0.0003597494,0.000439915,0.0007204401,0.0014012884,0.00042440504,0.39285704],"category_scores_gemma":[0.030251807,0.0003435232,0.00018514179,0.00037707872,0.00035547782,0.000048808266,0.0018092787,0.0008848873,0.2191502],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031705265,0.00010763764,6.142164e-8,0.0006812107,0.0001661319,0.000047689566,0.00014159933,2.1657489e-7,0.00003448137,0.056389183,0.8992056,0.04319443],"study_design_scores_gemma":[0.00036053415,0.00016208571,0.0000022780257,0.00044662086,0.00013289598,0.000038662594,0.000034322533,0.000045861307,0.000026559617,0.09849728,0.8999278,0.00032509264],"about_ca_topic_score_codex":0.000022291253,"about_ca_topic_score_gemma":9.2003387e-7,"teacher_disagreement_score":0.17370684,"about_ca_system_score_codex":0.00016693179,"about_ca_system_score_gemma":0.000007769583,"threshold_uncertainty_score":0.99990165},"labels":[],"label_agreement":null},{"id":"W6930245077","doi":"10.5281/zenodo.11810618","title":"understanding canadian business 11th edition pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Work (physics); Government (linguistics); Headline; Gloom","score_opus":0.5738663899843082,"score_gpt":0.4472729811135459,"score_spread":0.12659340887076226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930245077","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.375989e-7,0.00005588785,0.10734858,0.00074544345,0.00104472,0.00057180104,0.0014022789,0.0011174089,0.8877133],"genre_scores_gemma":[0.0006923031,0.00034106642,0.058308367,0.00032681407,0.0043939343,2.1554123e-7,0.0016633162,0.030891998,0.903382],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971854,0.00074386585,0.00045486374,0.0006110995,0.0005111916,0.0004935519],"domain_scores_gemma":[0.9978881,0.00063356914,0.0002038633,0.00059858727,0.00027776507,0.0003981467],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018586612,0.00026720573,0.00041824047,0.00068739994,0.00064675737,0.00080329215,0.0008138739,0.0003483014,0.26549947],"category_scores_gemma":[0.024361908,0.0002719021,0.000086510496,0.00081636116,0.0002429134,0.000058390342,0.00053108204,0.0005898359,0.08915676],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009200159,0.000031263524,4.3797733e-8,0.00045831728,0.00008780478,0.000044606986,0.00006136806,3.6111268e-7,0.000008934111,0.1296516,0.86574876,0.0038977517],"study_design_scores_gemma":[0.00020111297,0.000043802003,0.0000023582145,0.00044942388,0.00007595228,0.000028983746,0.00007272452,0.000024340325,0.000003864806,0.23286353,0.76601046,0.00022343281],"about_ca_topic_score_codex":0.0008410674,"about_ca_topic_score_gemma":0.00013996524,"teacher_disagreement_score":0.17634271,"about_ca_system_score_codex":0.0007219946,"about_ca_system_score_gemma":0.000020819096,"threshold_uncertainty_score":0.9999733},"labels":[],"label_agreement":null},{"id":"W6930251460","doi":"10.5281/zenodo.12101550","title":"Iso 2339 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Filter (signal processing); Limiting; Field (mathematics); Term (time)","score_opus":0.3856794262446551,"score_gpt":0.4716026149749306,"score_spread":0.08592318873027549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930251460","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014479598,0.00019073808,0.026616985,0.00040478862,0.00071302004,0.000685524,0.0009464705,0.0023793015,0.96806175],"genre_scores_gemma":[0.000031357235,0.00017394811,0.08049184,0.00014501711,0.0013281342,8.2265785e-8,0.00025909403,0.020016087,0.89755446],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99648327,0.0011202084,0.000588904,0.0007530183,0.000608064,0.0004465558],"domain_scores_gemma":[0.99728817,0.0010143805,0.0002632417,0.00095228746,0.00022862821,0.0002533243],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0022315248,0.00030785037,0.0005461267,0.00037671882,0.0003951225,0.0007025534,0.0013095128,0.00035811958,0.4703497],"category_scores_gemma":[0.036513142,0.00029364933,0.0001597828,0.0005021353,0.00029708096,0.00003924327,0.0015590559,0.0007708821,0.34170094],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018243738,0.000088116816,2.4236932e-8,0.00052299857,0.0001334664,0.000036385474,0.000079780184,7.97081e-8,0.00003362679,0.07880478,0.88681906,0.033463445],"study_design_scores_gemma":[0.00026552205,0.000114451825,7.754586e-7,0.00031689205,0.000090868176,0.00003155369,0.00003220795,0.000016751039,0.000019687126,0.19171488,0.8071482,0.0002481672],"about_ca_topic_score_codex":0.000008556853,"about_ca_topic_score_gemma":2.797483e-7,"teacher_disagreement_score":0.12864876,"about_ca_system_score_codex":0.00011893088,"about_ca_system_score_gemma":0.000004701524,"threshold_uncertainty_score":0.99995154},"labels":[],"label_agreement":null},{"id":"W6930259438","doi":"10.5281/zenodo.11682389","title":"Audi lieferzeiten pdf","year":2024,"lang":"de","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Order (exchange); Passenger transport; Context (archaeology); Work (physics)","score_opus":0.3352038029212054,"score_gpt":0.44882948358148045,"score_spread":0.11362568066027506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930259438","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010043538,0.0008690041,0.032565784,0.0011807076,0.0020689096,0.001554248,0.002313506,0.0017997626,0.957638],"genre_scores_gemma":[0.00019876496,0.0011640235,0.079574764,0.000403575,0.004155528,2.0062214e-7,0.0010684514,0.027158424,0.88627625],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99159884,0.0031224282,0.0014726047,0.0015794017,0.0012127946,0.0010139416],"domain_scores_gemma":[0.9935509,0.0025905608,0.00060917967,0.0018073912,0.000795239,0.0006467518],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005298486,0.0006896421,0.0011620091,0.000640047,0.0012570184,0.0023167557,0.0026996373,0.0007807763,0.683518],"category_scores_gemma":[0.07607274,0.00067962665,0.00039169446,0.0010910853,0.00072457345,0.0000984222,0.0040705544,0.0018630576,0.8471959],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008965,0.0003172837,9.5206595e-8,0.0014606455,0.00057620707,0.000120821926,0.00039837626,0.0000011473531,0.0001395193,0.065071106,0.86513376,0.066691406],"study_design_scores_gemma":[0.00067296973,0.00042046496,0.000005386849,0.000966673,0.00045910536,0.00006481036,0.00010907797,0.00012475488,0.00004562406,0.13361958,0.86290926,0.00060231355],"about_ca_topic_score_codex":0.000008193848,"about_ca_topic_score_gemma":1.6829253e-7,"teacher_disagreement_score":0.16367796,"about_ca_system_score_codex":0.00035498236,"about_ca_system_score_gemma":0.000014180187,"threshold_uncertainty_score":0.9995655},"labels":[],"label_agreement":null},{"id":"W6930336795","doi":"10.5281/zenodo.13799947","title":"Global climate change below 2°C avoids large end century increases in burned area in Canada","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Environment and Climate Change Canada","funders":"","keywords":"Climate change; Climate model; Global warming; Global change; Greenhouse gas; Land use; General Circulation Model; Projection (relational algebra)","score_opus":0.2613149954855941,"score_gpt":0.4179108965158886,"score_spread":0.15659590103029447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930336795","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063901755,0.0011305863,0.000869001,0.0004412407,0.0007800268,0.002007823,0.018878782,0.001035935,0.9742176],"genre_scores_gemma":[0.33140796,0.03507913,0.22338341,0.0075872857,0.015592885,0.000017679627,0.017394261,0.19216035,0.17737703],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955014,0.0015487754,0.00075889414,0.0007460763,0.0006690527,0.00077582797],"domain_scores_gemma":[0.9978639,0.0008622703,0.00025223155,0.00064154976,0.00012082928,0.00025920497],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023745617,0.0003428436,0.00068766304,0.0003557531,0.00018737007,0.00026730518,0.0009922074,0.00025384207,0.050229356],"category_scores_gemma":[0.020259323,0.0003439212,0.00007707249,0.0010576698,0.00011285327,0.000058133934,0.0016894065,0.000630857,0.0027560382],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010470112,0.00032753896,0.00007253989,0.0010880835,0.0000764252,0.0005163749,0.00014314376,4.1513672e-7,0.0000034131194,0.066279426,0.8998143,0.03157365],"study_design_scores_gemma":[0.0010543579,0.00008434867,0.00054654083,0.0011989574,0.000050477996,0.00003128003,0.00023097635,0.00009872368,0.0000021762094,0.037224367,0.959066,0.00041184627],"about_ca_topic_score_codex":0.09164859,"about_ca_topic_score_gemma":0.05871874,"teacher_disagreement_score":0.79684055,"about_ca_system_score_codex":0.0011851457,"about_ca_system_score_gemma":0.000039346374,"threshold_uncertainty_score":0.9999013},"labels":[],"label_agreement":null},{"id":"W6930626648","doi":"10.5281/zenodo.12669938","title":"BundleAdjustmentModels.jl: Julia repository of bundle adjustment problems","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Bundle; Calculus (dental); Set (abstract data type); Sequence (biology)","score_opus":0.32537922959809507,"score_gpt":0.4292610397571606,"score_spread":0.10388181015906556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930626648","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009333736,0.0010677897,0.022021841,0.0001720112,0.0010008939,0.0014929491,0.0010863785,0.001803662,0.9713451],"genre_scores_gemma":[0.0004306499,0.0006310701,0.13187018,0.00008917208,0.0015772362,7.5153025e-7,0.00041445432,0.024634315,0.8403522],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99578273,0.001140544,0.0009906004,0.0008296622,0.0008118611,0.00044461282],"domain_scores_gemma":[0.99702454,0.00065489335,0.0005915007,0.0011320852,0.0003593277,0.00023768474],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018304872,0.0003647805,0.00074646896,0.00037366588,0.00031601117,0.0002698091,0.0012316232,0.00036366063,0.029352682],"category_scores_gemma":[0.008130938,0.00034334662,0.0002050612,0.0004607623,0.0004077504,0.000051414103,0.0014243838,0.0006167593,0.009455593],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003546177,0.00048120035,6.9354044e-8,0.0020489125,0.00030958978,0.0000133804515,0.00025531076,0.000002923255,0.00023859901,0.06746548,0.91615796,0.012991088],"study_design_scores_gemma":[0.00046307218,0.000492586,0.0000019842428,0.00089071057,0.00024091211,0.000039612354,0.00005824993,0.000086097534,0.00017483877,0.10031238,0.89693755,0.00030198172],"about_ca_topic_score_codex":0.00003030621,"about_ca_topic_score_gemma":3.7544865e-7,"teacher_disagreement_score":0.13099296,"about_ca_system_score_codex":0.000212951,"about_ca_system_score_gemma":0.00000998084,"threshold_uncertainty_score":0.99990183},"labels":[],"label_agreement":null},{"id":"W6930710279","doi":"10.5281/zenodo.12575776","title":"PDF EPUB Download Lore Olympus: Volume One by Full Book","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Afterlife; Pilgrim; Creatures; Publishing; Ruler; Painting; Politics","score_opus":0.25672500973011897,"score_gpt":0.41993683371668894,"score_spread":0.16321182398656997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930710279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023275071,0.0021612581,0.48531964,0.010682105,0.0015102173,0.0024499665,0.004417239,0.0067965654,0.4843355],"genre_scores_gemma":[0.06627864,0.0041347584,0.57436746,0.006254689,0.0071132635,0.0000029079886,0.007185423,0.023545768,0.31111708],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962716,0.0011401928,0.0006985104,0.0006915353,0.00066707603,0.0005311048],"domain_scores_gemma":[0.99655634,0.0018955006,0.00012424882,0.0006870253,0.0004103879,0.00032647344],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029085795,0.00022943638,0.00038642276,0.00017494113,0.00087317755,0.0011103742,0.0010436613,0.00017029575,0.18026458],"category_scores_gemma":[0.028150272,0.00022619934,0.00012998533,0.00061120826,0.0003342143,0.00025444358,0.001028447,0.00057852484,0.09351562],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000720713,0.00018725415,2.7482025e-7,0.00025928929,0.00012346561,0.000028979268,0.00026024246,8.919425e-7,0.002997024,0.020287026,0.87605596,0.099727534],"study_design_scores_gemma":[0.0004351563,0.000335169,0.000009132321,0.00013076302,0.000079850535,0.000050694696,0.000064306296,0.00041217208,0.0005715117,0.06305875,0.9346005,0.00025204144],"about_ca_topic_score_codex":0.0000049211035,"about_ca_topic_score_gemma":8.9293025e-8,"teacher_disagreement_score":0.17321841,"about_ca_system_score_codex":0.00018016662,"about_ca_system_score_gemma":0.00000798389,"threshold_uncertainty_score":0.99992657},"labels":[],"label_agreement":null},{"id":"W6930719539","doi":"10.5281/zenodo.15736581","title":"Genetic and phenotypic characterization of phages from the BASEL phage collection","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Escherichia coli; Bacteriophage; Host (biology); Bacterial virus; Phage typing; Phenotype; Selection (genetic algorithm); Genetic diversity","score_opus":0.2163956017084941,"score_gpt":0.41267086766781313,"score_spread":0.19627526595931905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930719539","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007401762,0.000058839894,0.02298768,0.00026750125,0.00032611616,0.00089680357,0.9737147,0.00015772396,0.00085045164],"genre_scores_gemma":[0.00043828625,0.0011868824,0.017133184,0.00024489986,0.0005611278,3.571246e-7,0.9792761,0.0006462834,0.0005128466],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961262,0.0020647384,0.0006935316,0.00048307667,0.00041220817,0.00022024744],"domain_scores_gemma":[0.9942588,0.0039350125,0.0004750528,0.00079157896,0.00044978788,0.000089743226],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015891105,0.00021703943,0.00045459447,0.0001491795,0.00095072447,0.0003296551,0.0009446831,0.00021180772,0.00884396],"category_scores_gemma":[0.03642527,0.00018276565,0.00006923299,0.00051574863,0.00028671135,0.00006259402,0.0010634842,0.0004536825,0.0001526714],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008294895,0.00013247489,5.0812343e-7,0.00029258837,0.000112925285,0.0000035044095,0.00011057686,3.0349165e-7,0.00084780424,0.000663196,0.97185737,0.025895828],"study_design_scores_gemma":[0.0006041417,0.00014930965,0.00057567464,0.00019884355,0.0002566233,0.000007011455,0.000038145383,0.00008149758,0.00024553758,0.015646465,0.98201907,0.00017767547],"about_ca_topic_score_codex":0.000043266653,"about_ca_topic_score_gemma":8.631129e-7,"teacher_disagreement_score":0.03483616,"about_ca_system_score_codex":0.000071263654,"about_ca_system_score_gemma":0.000010542102,"threshold_uncertainty_score":0.9920621},"labels":[],"label_agreement":null},{"id":"W6930815823","doi":"10.5281/zenodo.15732270","title":"Fig. 7 in Methods for estimating and modelling spruce budworm development rates at constant temperatures","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"","keywords":"Spruce budworm; Constant (computer programming); Larva; Instar; Head (geology); Choristoneura fumiferana","score_opus":0.3888862844555556,"score_gpt":0.4971070617485492,"score_spread":0.10822077729299356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930815823","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005332979,0.0006212569,0.87274003,0.00013001477,0.00026296594,0.0012950153,0.0003131661,0.00042543473,0.12415877],"genre_scores_gemma":[0.00004380658,0.00014566458,0.9715665,0.00005632932,0.00019732639,4.8136434e-7,0.00034060492,0.003982262,0.023667047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964539,0.0013839697,0.000765026,0.00070117635,0.00027994506,0.00041602753],"domain_scores_gemma":[0.9947133,0.0040256856,0.00035376922,0.0004284365,0.00030369568,0.00017508499],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004184119,0.0002972,0.00067357445,0.00026160147,0.0007122861,0.00042636247,0.0005001982,0.00024712566,0.011794677],"category_scores_gemma":[0.037162468,0.000290012,0.00006472879,0.00031133922,0.00019471765,0.000034467022,0.0011538707,0.00042651597,0.000119662785],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028266053,0.0003688575,0.0000024624537,0.0047109094,0.00046991115,0.00008106076,0.0021609373,0.0001395316,0.0024149152,0.084038496,0.54303634,0.3622939],"study_design_scores_gemma":[0.0008295017,0.00007551544,0.0000020944003,0.0011589555,0.000046630546,0.000058782793,0.00011041744,0.010980619,0.00057460775,0.041083433,0.9446548,0.00042461365],"about_ca_topic_score_codex":0.0000074109316,"about_ca_topic_score_gemma":0.0000014932893,"teacher_disagreement_score":0.40161848,"about_ca_system_score_codex":0.00019877299,"about_ca_system_score_gemma":0.000016156,"threshold_uncertainty_score":0.9999552},"labels":[],"label_agreement":null},{"id":"W6930846329","doi":"10.5281/zenodo.4114490","title":"OpenAIRE Week: General Assembly: Building Open Science Gateways to open and linked research outcomes","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Research Institute for the Advancement of Women","funders":"European Commission","keywords":"Session (web analytics); Linked data; Citizen science; Open science; Open research; Open data","score_opus":0.7162172825056304,"score_gpt":0.5659494321013087,"score_spread":0.15026785040432178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930846329","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31494105,0.00008178294,0.12476361,0.09649876,0.0008614192,0.018701507,0.0011261157,0.0023262396,0.44069952],"genre_scores_gemma":[0.31260788,0.0000520797,0.68124956,0.0023432968,0.0004182973,0.0000012535531,0.000039545877,0.0018981334,0.0013899106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939823,0.0022067605,0.0006958776,0.0011699084,0.0011510329,0.00079410715],"domain_scores_gemma":[0.9939779,0.0025926402,0.00016372473,0.0009072077,0.0013337518,0.0010247768],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.016540335,0.00021580709,0.0005698511,0.00026219932,0.0038168102,0.006552448,0.008571242,0.000098723736,0.0041234675],"category_scores_gemma":[0.17104168,0.00019756281,0.00004586356,0.0020076497,0.0006880041,0.0007081336,0.032903258,0.00066926953,0.002331386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045564224,0.00037437864,0.000042898388,0.00018513777,0.00008634964,0.000055392495,0.0023126125,0.000013347497,0.03253459,0.61937505,0.22263037,0.121934205],"study_design_scores_gemma":[0.0035426735,0.0023202202,0.0037222756,0.00026251024,0.00005672267,0.000050760653,0.0010706856,0.0022582768,0.0060737436,0.30009395,0.67966896,0.00087923417],"about_ca_topic_score_codex":0.000060523213,"about_ca_topic_score_gemma":5.7094223e-7,"teacher_disagreement_score":0.55648595,"about_ca_system_score_codex":0.00019879162,"about_ca_system_score_gemma":0.000039454888,"threshold_uncertainty_score":0.9984454},"labels":[],"label_agreement":null},{"id":"W6930880758","doi":"10.5281/zenodo.15477555","title":"ZIP-Modified Bell Inequality","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nortel (Canada)","funders":"","keywords":"Quantum correlation; Bell's theorem; Local hidden variable theory; Quantum; Ideal (ethics); Limit (mathematics); Bell state; Inequality; Bell test experiments","score_opus":0.5043490908496174,"score_gpt":0.5066275383683124,"score_spread":0.0022784475186949926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930880758","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007975579,0.00003376316,0.48188105,0.0019526819,0.0004403431,0.0008667522,0.00035789565,0.0014973037,0.50499463],"genre_scores_gemma":[0.685447,0.00012300028,0.2968522,0.0017839357,0.0007214555,3.1937182e-7,0.00041188352,0.0033954396,0.011264792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99642646,0.001738264,0.00064206135,0.00045893595,0.0003765575,0.00035769943],"domain_scores_gemma":[0.99542284,0.0029465598,0.0001580483,0.00075547665,0.00055955007,0.00015755478],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0043062465,0.00015237553,0.0003351773,0.00016967872,0.0011793973,0.00037517402,0.0010224952,0.00012294896,0.010077141],"category_scores_gemma":[0.08664013,0.00014923146,0.00008974686,0.0006715642,0.00023341256,0.00008982434,0.0012909217,0.00038954415,0.002678614],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001249279,0.00026894643,0.0000033706576,0.0002014183,0.00007376989,0.00000759027,0.0002038858,0.0000040953755,0.00089756324,0.64954686,0.21889353,0.129774],"study_design_scores_gemma":[0.0007621625,0.00010616155,0.00025841824,0.000059023365,0.000038455924,0.000006065637,0.00007101027,0.00022331545,0.00070505205,0.53823483,0.45938316,0.00015230454],"about_ca_topic_score_codex":0.0000071565587,"about_ca_topic_score_gemma":1.3852156e-7,"teacher_disagreement_score":0.6774714,"about_ca_system_score_codex":0.00012202422,"about_ca_system_score_gemma":0.000005812685,"threshold_uncertainty_score":0.9980979},"labels":[],"label_agreement":null},{"id":"W6930936221","doi":"10.5281/zenodo.14941604","title":"Type-Preserving Flat Closure Optimization Artifact","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artifact (error); Closure (psychology); Minification; Smoothing","score_opus":0.34366489224614194,"score_gpt":0.45532597714698647,"score_spread":0.11166108490084453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930936221","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000032551914,0.0000832124,0.19844268,0.00028582852,0.00048213062,0.00072065217,0.00051979366,0.0016411934,0.7978213],"genre_scores_gemma":[0.00011224246,0.00045771612,0.4250662,0.0002128703,0.0010744479,1.3542969e-7,0.0010754747,0.013402929,0.558598],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99627405,0.0015055992,0.00060954294,0.00066054234,0.0005394103,0.00041085872],"domain_scores_gemma":[0.9963556,0.0014308755,0.00038033555,0.0010574742,0.00058792473,0.00018779804],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018964533,0.00029845117,0.00054203783,0.0003869797,0.0006889084,0.0005231203,0.0013868049,0.0004109281,0.19746551],"category_scores_gemma":[0.06642363,0.00030111626,0.00011801586,0.0006986577,0.00017002523,0.00006928471,0.0015958342,0.000590942,0.0060940064],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051136907,0.00007392111,5.050917e-7,0.0003548902,0.0001366233,0.000009969579,0.00004826868,0.000051178053,0.000033215394,0.025410064,0.9512275,0.022602731],"study_design_scores_gemma":[0.00046236574,0.00011503717,0.000004066052,0.00038513396,0.00010224148,0.000008302237,0.000028177708,0.0007189776,0.00005236514,0.03871569,0.9591186,0.00028903206],"about_ca_topic_score_codex":0.000015908625,"about_ca_topic_score_gemma":4.7427002e-7,"teacher_disagreement_score":0.23922327,"about_ca_system_score_codex":0.00012640453,"about_ca_system_score_gemma":0.0000120730065,"threshold_uncertainty_score":0.9999441},"labels":[],"label_agreement":null},{"id":"W6931046752","doi":"10.5281/zenodo.3739228","title":"Teaching the \"Information Creation as a Process\" Framework through Video Gaming","year":2020,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Game art design; Game Developer; Storytelling; Narrative; CLIPS; Video game design; Order (exchange); Video game development","score_opus":0.26083421483935076,"score_gpt":0.4715572620399705,"score_spread":0.21072304720061974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931046752","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004798854,0.00003385111,0.33310518,0.0015316787,0.00019104069,0.00093063695,0.00023834818,0.0013201162,0.6626444],"genre_scores_gemma":[0.0036283494,0.0005058757,0.8475132,0.005287996,0.005840612,0.0000022500292,0.0021638358,0.027694782,0.10736309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99600416,0.0016564074,0.0007119684,0.0004519114,0.0008116513,0.00036389192],"domain_scores_gemma":[0.9954495,0.0026605334,0.00070758973,0.000757067,0.00027345048,0.0001518891],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002354569,0.0002960644,0.00044445033,0.00014745732,0.0014412453,0.00090608606,0.0013997299,0.00034625156,0.03719188],"category_scores_gemma":[0.13021792,0.00023838574,0.00011448191,0.00046195678,0.0002472492,0.0002681248,0.0008034596,0.0012897673,0.01105308],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051599713,0.000058634534,1.1945835e-7,0.00048170527,0.00009769713,0.0000042327038,0.0031210796,0.0000025118052,0.000011843457,0.23969063,0.6695592,0.08692078],"study_design_scores_gemma":[0.00023313938,0.00012039369,0.00000187917,0.0003608452,0.00007164288,0.000018429131,0.0004481571,0.000113577546,0.000022684138,0.2688417,0.7295739,0.00019361761],"about_ca_topic_score_codex":0.000039076484,"about_ca_topic_score_gemma":1.9203912e-7,"teacher_disagreement_score":0.5552813,"about_ca_system_score_codex":0.00011365388,"about_ca_system_score_gemma":0.000010198177,"threshold_uncertainty_score":0.99985874},"labels":[],"label_agreement":null},{"id":"W6931103969","doi":"10.5281/zenodo.4304369","title":"Online Supplement --- What Makes Effective Leadership in Agile Software Development Teams?","year":2020,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Volvo (Canada)","funders":"","keywords":"Agile software development; Software development; Software; Lean software development; Agile usability engineering; Software development process","score_opus":0.4822167320290053,"score_gpt":0.44381576277352663,"score_spread":0.038400969255478645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931103969","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027307848,0.0021267405,0.34510648,0.012428926,0.0035693273,0.021994794,0.010988817,0.0133164255,0.5901954],"genre_scores_gemma":[0.0004027727,0.00057887717,0.8893927,0.0012786922,0.0014384349,0.0000013703008,0.0047113243,0.023595734,0.0786001],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99523646,0.0018945695,0.0007705891,0.00081826455,0.00069263164,0.00058750395],"domain_scores_gemma":[0.99647766,0.002123773,0.0003670387,0.0005756554,0.00018466807,0.00027122724],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020225768,0.00037687144,0.00070711924,0.00035836824,0.00037713713,0.0005529326,0.0011503263,0.0002895791,0.078069575],"category_scores_gemma":[0.038018104,0.00037428024,0.00009711178,0.000518868,0.00021213593,0.0001015315,0.0013181571,0.0008019832,0.0054746806],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007090344,0.00040058017,0.000001713468,0.0008825029,0.0001286432,0.00004558373,0.0007968469,8.0494084e-7,0.000025487956,0.0025863347,0.7313289,0.26373172],"study_design_scores_gemma":[0.0010711331,0.00022969901,0.000062270214,0.0010814319,0.00004268473,0.000010248648,0.0009928503,0.000013165218,0.00016009258,0.008479153,0.9874585,0.00039873226],"about_ca_topic_score_codex":0.000011685817,"about_ca_topic_score_gemma":0.0000069072244,"teacher_disagreement_score":0.5442862,"about_ca_system_score_codex":0.00037593962,"about_ca_system_score_gemma":0.000014519518,"threshold_uncertainty_score":0.9998709},"labels":[],"label_agreement":null},{"id":"W6931190694","doi":"10.5281/zenodo.4155146","title":"Assistir O Mensageiro do Último Dia (2020) Dublado Filme Online Grátis lam","year":2020,"lang":"pt","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Limiting; Context (archaeology); Quality (philosophy); Population; Field (mathematics)","score_opus":0.4170330933449991,"score_gpt":0.4476373901411062,"score_spread":0.0306042967961071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931190694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018581375,0.0020737038,0.48864108,0.088877656,0.0051770983,0.011059165,0.053466,0.011617864,0.32050607],"genre_scores_gemma":[0.3592733,0.0039433558,0.55984426,0.009941339,0.011485436,9.923396e-7,0.00747227,0.02810919,0.019929882],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9899956,0.0041767773,0.001807788,0.0015355853,0.0013873463,0.0010968829],"domain_scores_gemma":[0.9908907,0.0043902295,0.00073799735,0.0014033532,0.0012787291,0.0012989839],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003617071,0.00062543654,0.0011669763,0.00018678253,0.002074256,0.0017226308,0.002703126,0.00043948326,0.12433067],"category_scores_gemma":[0.15009645,0.0006498514,0.0003434785,0.0015274601,0.0006234443,0.00026507207,0.00407628,0.0015824055,0.032653343],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050768466,0.0010855866,0.00000598615,0.0009640098,0.00044385638,0.00036657625,0.002141999,0.00002049423,0.0018576133,0.021388486,0.7946249,0.17659281],"study_design_scores_gemma":[0.002722827,0.0014913882,0.00074021774,0.0003164535,0.00039521753,0.000103181475,0.0008018265,0.0031708232,0.0003470182,0.01555919,0.9734419,0.0009099747],"about_ca_topic_score_codex":0.000008184835,"about_ca_topic_score_gemma":4.0394747e-7,"teacher_disagreement_score":0.34069192,"about_ca_system_score_codex":0.00027582818,"about_ca_system_score_gemma":0.00002299586,"threshold_uncertainty_score":0.9995953},"labels":[],"label_agreement":null},{"id":"W6931281899","doi":"10.5281/zenodo.4947387","title":"FIGURE 6 in Ascetoaxinus quatsinoensis sp. et gen. nov. (Bivalvia: Thyasiroidea) from Vancouver Island, with notes on Conchocele Gabb, 1866, and Channelaxinus Valentich-Scott &amp; Coan, 2012","year":2014,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal British Columbia Museum","funders":"","keywords":"Section (typography); Transverse plane; Line drawings; Presentation (obstetrics)","score_opus":0.21284986966633232,"score_gpt":0.3955751240037545,"score_spread":0.18272525433742218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931281899","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002249864,0.00068400556,0.11527855,0.0015526109,0.0013270789,0.003712596,0.009107643,0.0019313714,0.8641563],"genre_scores_gemma":[0.029231075,0.0032332593,0.40029314,0.0040586623,0.005930556,0.0000041235253,0.00642896,0.054195866,0.49662435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99419737,0.0023667957,0.0007851613,0.0011047665,0.0009085994,0.00063732953],"domain_scores_gemma":[0.99239784,0.005130301,0.000633022,0.0011344315,0.00037743774,0.0003269615],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002503383,0.0005718437,0.0010934455,0.00042660398,0.0003908401,0.0005936106,0.00092125824,0.00057064573,0.048258398],"category_scores_gemma":[0.02946365,0.0004919327,0.00011205571,0.000444917,0.0004453411,0.00013066179,0.00079624006,0.0012395801,0.005705511],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000346354,0.00028059917,0.000013398537,0.00032103359,0.00022769725,0.000049465052,0.00037827395,0.0000051164825,0.00008369797,0.0053273104,0.980178,0.012789036],"study_design_scores_gemma":[0.0030229848,0.0005427013,0.00027338573,0.0009307181,0.00017356173,0.000020290337,0.00007793119,0.00007530977,0.00007449207,0.020446943,0.9737091,0.0006525772],"about_ca_topic_score_codex":0.00021209687,"about_ca_topic_score_gemma":0.0003177486,"teacher_disagreement_score":0.36753193,"about_ca_system_score_codex":0.0001429586,"about_ca_system_score_gemma":0.000014426734,"threshold_uncertainty_score":0.99975324},"labels":[],"label_agreement":null},{"id":"W6931297151","doi":"10.5281/zenodo.6015839","title":"DocNow/twarc: v2.9.3","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Alberta Library; University of Alberta","funders":"","keywords":"Sample (material); Identification (biology); Term (time); Troubleshooting; Context (archaeology)","score_opus":0.4404557448974252,"score_gpt":0.4755809593202749,"score_spread":0.03512521442284966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931297151","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000048935663,0.00009630466,0.016221698,0.0003533968,0.00050933205,0.00092350965,0.0013375517,0.002741158,0.9778122],"genre_scores_gemma":[0.000083728875,0.00037407398,0.17793088,0.00046322835,0.0018461761,4.264833e-7,0.0015778632,0.040441714,0.77728194],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948159,0.0023604701,0.0006330546,0.00077837467,0.00089220266,0.0005200086],"domain_scores_gemma":[0.9959903,0.001828974,0.0004500811,0.0012248933,0.00022707568,0.00027872808],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002989382,0.0003200705,0.0006058429,0.00040230947,0.0009272312,0.00041449512,0.001999302,0.00025694573,0.80363065],"category_scores_gemma":[0.049715493,0.0003293288,0.00016443888,0.0005922501,0.0003011249,0.00004721657,0.002914118,0.00092579133,0.01772549],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035152832,0.00016111485,2.1080905e-7,0.00020669181,0.00010910725,0.00003146118,0.00009481488,4.0493637e-7,0.000023267137,0.066695645,0.8800434,0.05259876],"study_design_scores_gemma":[0.0005532559,0.00019668163,0.00000398359,0.000073735086,0.00006771618,0.000042041567,0.000069011345,0.00001273998,0.000010172473,0.08133725,0.91731346,0.00031993567],"about_ca_topic_score_codex":0.000015645646,"about_ca_topic_score_gemma":3.89389e-7,"teacher_disagreement_score":0.7859051,"about_ca_system_score_codex":0.00022892392,"about_ca_system_score_gemma":0.0000067878436,"threshold_uncertainty_score":0.9999159},"labels":[],"label_agreement":null},{"id":"W6931300398","doi":"10.5281/zenodo.3800156","title":"Vedalia Beetles and Cyanide","year":2018,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Locust; Bureaucracy; Scale (ratio); Agriculture; Work (physics)","score_opus":0.44979956802221294,"score_gpt":0.47847756932019275,"score_spread":0.028678001297979816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931300398","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.117969416,0.00010313719,0.29712704,0.0027137196,0.0010353813,0.0017486112,0.00081692135,0.0032963892,0.5751894],"genre_scores_gemma":[0.5387615,0.00010435137,0.45378423,0.00054484355,0.0015592233,7.7562014e-8,0.000088179906,0.0028653773,0.0022922424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799085,0.00073229504,0.0003525817,0.00035868477,0.00028514146,0.00028044163],"domain_scores_gemma":[0.99757147,0.0012665628,0.0001112096,0.0004122332,0.0004503726,0.00018817425],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021664032,0.00011553019,0.00021175109,0.00008809483,0.0011353001,0.00036286865,0.000518096,0.000077665325,0.014731618],"category_scores_gemma":[0.045259815,0.00010966831,0.000035992634,0.00025662812,0.0005090749,0.00009014916,0.0008772134,0.00019526694,0.004343648],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015495051,0.00018732772,0.0000092268665,0.0001388619,0.000079071244,0.000015592357,0.0008750789,1.8276515e-7,0.007916994,0.4284944,0.30048048,0.26164785],"study_design_scores_gemma":[0.0005233331,0.0003842911,0.0004325263,0.000039220504,0.000029054321,0.00006576735,0.00010736058,0.000111674,0.0010985794,0.33969572,0.65735114,0.0001613393],"about_ca_topic_score_codex":0.0000042795527,"about_ca_topic_score_gemma":1.8792491e-7,"teacher_disagreement_score":0.57289714,"about_ca_system_score_codex":0.000042077652,"about_ca_system_score_gemma":0.0000018921323,"threshold_uncertainty_score":0.9964316},"labels":[],"label_agreement":null},{"id":"W6931315368","doi":"10.5281/zenodo.5145817","title":"FIG. 22. — Caudal PVL 4170 in Osteological revision of the holotype of the Middle Jurassic sauropod dinosaur Patagosaurus fariasi Bonaparte, 1979 (Sauropoda: Cetiosauridae)","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Tyrrell Museum","funders":"","keywords":"Osteology; Holotype; Dorsum; Sauropoda; Paratype","score_opus":0.31296423955062763,"score_gpt":0.4025845927049904,"score_spread":0.08962035315436279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931315368","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015295013,0.0014594907,0.006318825,0.0044725244,0.0031445906,0.006852993,0.00631387,0.0010401108,0.95510256],"genre_scores_gemma":[0.36931583,0.0043244623,0.16439793,0.0019145175,0.004691785,0.0000029046048,0.0025723318,0.038042214,0.41473803],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99126244,0.004969343,0.0013544167,0.00079428445,0.001113433,0.0005060888],"domain_scores_gemma":[0.99419457,0.002079001,0.001179754,0.0018902197,0.0005123572,0.00014407173],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027098486,0.00040299675,0.0010338522,0.00021549576,0.00044655398,0.0001382438,0.0025745996,0.0004887192,0.038229067],"category_scores_gemma":[0.061075352,0.0002680439,0.00034524998,0.0012520408,0.0009634652,0.000044024033,0.0034990516,0.0011472875,0.00033692823],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000208842,0.0011013395,0.00009096931,0.0018565041,0.00023783221,0.000050930885,0.00054934365,0.0000072538082,0.0021245526,0.057644118,0.8881426,0.047985725],"study_design_scores_gemma":[0.0014619079,0.0003521303,0.002761852,0.0021499372,0.00017185614,0.000047863297,0.0001721965,0.000047610072,0.00079500384,0.019552762,0.9720383,0.00044857824],"about_ca_topic_score_codex":0.00005249439,"about_ca_topic_score_gemma":0.000006149592,"teacher_disagreement_score":0.54036456,"about_ca_system_score_codex":0.00013742287,"about_ca_system_score_gemma":0.000031585372,"threshold_uncertainty_score":0.9999772},"labels":[],"label_agreement":null},{"id":"W6931348401","doi":"10.5281/zenodo.5221775","title":"FIGURE 21. Metapterodectes toxostomae. A in Feather mites of the subfamily Pterodectinae (Acariformes: Proctophyllodidae) from passerines and kingfishers in Canada","year":2021,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Subfamily; Feather; Holotype; Taxonomy (biology); Key (lock)","score_opus":0.19052315942252632,"score_gpt":0.36890928913410037,"score_spread":0.17838612971157405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931348401","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19737375,0.0032316416,0.0019917355,0.0023208186,0.0015075495,0.005906855,0.004520341,0.0007245799,0.7824227],"genre_scores_gemma":[0.5512675,0.002428207,0.22810806,0.001852109,0.0016068215,0.0000058552178,0.0014704058,0.037994992,0.17526606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666274,0.0013315737,0.0006512834,0.00056685245,0.00046828773,0.00031928412],"domain_scores_gemma":[0.9969001,0.0017732757,0.00038574962,0.0006631136,0.0001835681,0.00009420348],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009814694,0.00026859916,0.0006719907,0.00018273816,0.00014582084,0.00015973611,0.0008705582,0.00018561013,0.015104008],"category_scores_gemma":[0.023368476,0.00021722092,0.00007180881,0.00057951774,0.00016606742,0.00003961737,0.00091387396,0.00053599465,0.00002950359],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004076745,0.00085586944,0.0071285805,0.0038649396,0.0010854595,0.00018893661,0.0031437345,0.000012307477,0.0037033814,0.009912149,0.8344643,0.13523266],"study_design_scores_gemma":[0.0020780254,0.00015854806,0.035310365,0.002319795,0.00015780386,0.000018615905,0.0011578373,0.000129979,0.00075333455,0.026976168,0.9302442,0.0006953144],"about_ca_topic_score_codex":0.107391745,"about_ca_topic_score_gemma":0.05185486,"teacher_disagreement_score":0.6071567,"about_ca_system_score_codex":0.00019796102,"about_ca_system_score_gemma":0.000046930767,"threshold_uncertainty_score":0.98579633},"labels":[],"label_agreement":null},{"id":"W6931413362","doi":"10.5281/zenodo.7007909","title":"aspuru-guzik-group/chemspyd: Release for Zenodo sync","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"sync; Synchronization (alternating current); Noise (video); Signal processing; SIGNAL (programming language)","score_opus":0.3635039971971465,"score_gpt":0.4499592019786952,"score_spread":0.08645520478154872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931413362","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011031525,0.00020267381,0.106626645,0.00046423177,0.00083051686,0.002647572,0.005225882,0.0031512056,0.88084024],"genre_scores_gemma":[0.00022205105,0.00045998968,0.39182097,0.0007442395,0.0029198402,0.000002572465,0.005648307,0.055605967,0.5425761],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943378,0.0018925817,0.0009403096,0.0011455509,0.000927059,0.0007567092],"domain_scores_gemma":[0.993747,0.0032059064,0.0007203895,0.0015430019,0.0003591315,0.00042458822],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0037123773,0.00048273077,0.000901056,0.00045727848,0.0016386276,0.00056479184,0.0023325058,0.00041580142,0.36235157],"category_scores_gemma":[0.066912636,0.00051096897,0.00031095167,0.00060181256,0.00034855457,0.000075607204,0.0025274626,0.000952541,0.0074475887],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014999781,0.00032089153,1.2523743e-7,0.00055652315,0.00019405036,0.00002547569,0.00012037916,9.346797e-7,0.000092742746,0.07656252,0.8566282,0.06534816],"study_design_scores_gemma":[0.0012382246,0.00048607012,0.0000023025768,0.00013267013,0.00016480325,0.000045341356,0.00012589523,0.00008449188,0.000033552325,0.075752206,0.92142683,0.0005076245],"about_ca_topic_score_codex":0.000017754404,"about_ca_topic_score_gemma":5.714991e-7,"teacher_disagreement_score":0.35490397,"about_ca_system_score_codex":0.00035253842,"about_ca_system_score_gemma":0.0000099137815,"threshold_uncertainty_score":0.99973416},"labels":[],"label_agreement":null},{"id":"W6931419688","doi":"10.5281/zenodo.3950570","title":"Nepal","year":2008,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Government (linguistics); Table (database); Encyclopedia; Scope (computer science)","score_opus":0.5757890665546646,"score_gpt":0.4767792007640074,"score_spread":0.09900986579065713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931419688","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039814204,0.00005091631,0.29478964,0.0016096089,0.0006218295,0.0011856215,0.00047371193,0.003379367,0.6580751],"genre_scores_gemma":[0.36371785,0.00019058849,0.6245458,0.0006541327,0.0012744406,1.0575189e-7,0.00023200203,0.0048397942,0.0045452947],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975569,0.0008930474,0.0004268985,0.0003586569,0.0004277282,0.0003367493],"domain_scores_gemma":[0.997231,0.001513334,0.00012250924,0.00051978,0.0004024574,0.00021092239],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017027692,0.00012529382,0.0002463681,0.00010362447,0.0016412772,0.00016616698,0.00079587783,0.00008566629,0.02540965],"category_scores_gemma":[0.049414366,0.00012149021,0.00007783016,0.00037305072,0.00031302456,0.00009842486,0.0007390694,0.00030619025,0.008907368],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020700111,0.0003660564,0.0000058372752,0.000085798325,0.000073570605,0.00009096811,0.0007564945,0.000002723164,0.0011311417,0.23167072,0.62747705,0.13813262],"study_design_scores_gemma":[0.00078924675,0.00029763166,0.00031156506,0.00002219327,0.000020023062,0.00023172174,0.000063431085,0.00013220975,0.00038393977,0.17383623,0.8237197,0.0001921272],"about_ca_topic_score_codex":0.0000028865443,"about_ca_topic_score_gemma":3.2464833e-8,"teacher_disagreement_score":0.6535298,"about_ca_system_score_codex":0.000071769944,"about_ca_system_score_gemma":0.0000031373058,"threshold_uncertainty_score":0.99965847},"labels":[],"label_agreement":null},{"id":"W6931465784","doi":"10.5281/zenodo.5357335","title":"Figs 1-3 in Two new species of Cryptophagus HERBST, 1792 (Coleoptera: Cryptophagidae) from New Mexico (United States of America)","year":2017,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Assemblage (archaeology); Holotype; Table (database); Natural (archaeology); Key (lock)","score_opus":0.2746866463519568,"score_gpt":0.4352374647944343,"score_spread":0.16055081844247754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931465784","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053448125,0.0006786718,0.11975634,0.0005564855,0.00051888794,0.0016693333,0.0047467495,0.00076372875,0.87077534],"genre_scores_gemma":[0.0012696112,0.0018261741,0.56210476,0.00024507885,0.0015923968,2.4005539e-7,0.0027550126,0.01113678,0.41906995],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99596196,0.0011977279,0.0010142406,0.00065236137,0.0007381263,0.00043558574],"domain_scores_gemma":[0.993997,0.0024965007,0.0014092617,0.0013985747,0.00036060976,0.00033807036],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009877752,0.00038017647,0.0011922879,0.00068977865,0.00021971935,0.00024591692,0.0020264508,0.00023094164,0.12002117],"category_scores_gemma":[0.0322192,0.0003840794,0.00017109209,0.0006466552,0.00053494226,0.000090928275,0.001244639,0.00057089713,0.0016497893],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001696489,0.0002416064,0.000011460762,0.0002637136,0.0002125574,0.000024335284,0.0005482944,0.000010862345,0.0002445994,0.005812363,0.9302562,0.06220437],"study_design_scores_gemma":[0.002053063,0.00024554617,0.00029877987,0.00088436523,0.00008432597,0.000002541552,0.00011164945,0.00012009837,0.0006735495,0.10489153,0.8903,0.0003345808],"about_ca_topic_score_codex":0.0028192983,"about_ca_topic_score_gemma":0.000017474404,"teacher_disagreement_score":0.4517054,"about_ca_system_score_codex":0.00010753818,"about_ca_system_score_gemma":0.000027753613,"threshold_uncertainty_score":0.9998611},"labels":[],"label_agreement":null},{"id":"W6931493193","doi":"10.5281/zenodo.5311891","title":"FIGURES 62–68 in Revision of New World Leptocera Olivier (Diptera, Sphaeroceridae)","year":2009,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ridiculous; Key (lock)","score_opus":0.30189238108869787,"score_gpt":0.4488681526319528,"score_spread":0.14697577154325492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931493193","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040829946,0.00059980183,0.016420871,0.00034871313,0.00024511147,0.0012859834,0.00035854275,0.0006824342,0.9800177],"genre_scores_gemma":[0.0007643035,0.0012605775,0.19933613,0.00034641987,0.0014630869,7.109073e-8,0.00036677322,0.011915211,0.78454745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958539,0.0012372427,0.0010685864,0.0006703419,0.00070506975,0.0004648443],"domain_scores_gemma":[0.9967607,0.0011538098,0.0006374553,0.0009280648,0.00024893074,0.00027100474],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021792902,0.00034742945,0.0009061074,0.00071107055,0.00021384715,0.0002350634,0.0013217882,0.00028842382,0.18777238],"category_scores_gemma":[0.028007485,0.00033937552,0.0001547434,0.00092278316,0.00019130851,0.00008761157,0.00075752503,0.00069093093,0.00506089],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007208953,0.00015303814,0.0000010176761,0.0003883917,0.000040630945,0.000014086414,0.00012281141,9.947371e-7,0.000052942054,0.009787745,0.741417,0.24794924],"study_design_scores_gemma":[0.0009018986,0.00018548983,0.000065001615,0.0014188276,0.00004895575,0.000008695191,0.000016739215,0.00001623098,0.00009040814,0.03266582,0.9642802,0.00030177168],"about_ca_topic_score_codex":0.000044305536,"about_ca_topic_score_gemma":0.0000038220774,"teacher_disagreement_score":0.24764746,"about_ca_system_score_codex":0.00013288205,"about_ca_system_score_gemma":0.000013163797,"threshold_uncertainty_score":0.9999058},"labels":[],"label_agreement":null},{"id":"W6931513852","doi":"10.5281/zenodo.6448021","title":"Opportunities for cross-disciplinary interoperability in SSH research data management","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canarie","funders":"","keywords":"Interoperability; Data collection; Data management; Vocabulary; Work (physics); Domain (mathematical analysis)","score_opus":0.8702764985652749,"score_gpt":0.587724648389847,"score_spread":0.28255185017542794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931513852","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18472323,0.00032132815,0.15498114,0.018244216,0.0027409617,0.018756527,0.028455561,0.0036859517,0.5880911],"genre_scores_gemma":[0.6052893,0.0003776387,0.3617529,0.00064238574,0.0009615071,0.000013689965,0.006065953,0.006332333,0.018564302],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99267757,0.0041488227,0.0008032626,0.00087057886,0.00090611994,0.0005936737],"domain_scores_gemma":[0.993132,0.004046813,0.00014693668,0.0018753132,0.0006082543,0.00019066595],"candidate_categories":["metaresearch","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024623219,0.00015408458,0.00032513615,0.00036129527,0.0029660154,0.00058808207,0.0034566042,0.000058672136,0.015557325],"category_scores_gemma":[0.03279305,0.00016144285,0.000061405546,0.0006856124,0.0005273773,0.00022958747,0.015671063,0.0007583473,0.00033107956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012935008,0.00157976,0.000025932997,0.0011656989,0.00012764109,0.00014290653,0.0016533132,0.000044909746,0.00019124748,0.24333228,0.53887093,0.21157189],"study_design_scores_gemma":[0.0013530991,0.0006219855,0.00040699745,0.00006437437,0.000020315072,0.00002559538,0.004116282,0.001353332,0.000032405398,0.28512233,0.706662,0.00022129135],"about_ca_topic_score_codex":0.00000646099,"about_ca_topic_score_gemma":5.991169e-7,"teacher_disagreement_score":0.5695268,"about_ca_system_score_codex":0.0004009073,"about_ca_system_score_gemma":0.0000101437,"threshold_uncertainty_score":0.99833196},"labels":[],"label_agreement":null},{"id":"W6931523210","doi":"10.5281/zenodo.5970661","title":"CliMA/Oceananigans.jl: v0.69.5","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"NetCDF; Solver; Problem solver; Fast Fourier transform; Key (lock)","score_opus":0.43001744088515403,"score_gpt":0.46930075386810904,"score_spread":0.03928331298295501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931523210","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010198193,0.000106906155,0.013665957,0.0004926436,0.0006038937,0.0010368631,0.002016056,0.002741881,0.9793256],"genre_scores_gemma":[0.00019626942,0.0005300993,0.1436067,0.00063230196,0.0020652758,4.175064e-7,0.0019245154,0.04338623,0.8076582],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942227,0.0024766596,0.00077636517,0.00090305443,0.0010008137,0.0006204049],"domain_scores_gemma":[0.995683,0.0018025396,0.00054212665,0.0013638258,0.00028403263,0.0003244507],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003452644,0.00038138515,0.0007218272,0.00042651515,0.001336553,0.00048802316,0.0022002608,0.00031066133,0.5849826],"category_scores_gemma":[0.047450665,0.0003949585,0.00019967766,0.0006954136,0.00033554484,0.00005695455,0.0028204003,0.0010492174,0.017091574],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004345875,0.00019793407,5.41281e-7,0.00024060156,0.0001350544,0.000043365886,0.00012294536,4.4927398e-7,0.000030106772,0.06726814,0.8995477,0.032369696],"study_design_scores_gemma":[0.0006471749,0.0002477511,0.0000071489735,0.00008655021,0.00009596392,0.000039414197,0.00012418539,0.000020127454,0.000014842386,0.05992074,0.93840563,0.00039048964],"about_ca_topic_score_codex":0.000017066654,"about_ca_topic_score_gemma":5.550255e-7,"teacher_disagreement_score":0.567891,"about_ca_system_score_codex":0.00026292316,"about_ca_system_score_gemma":0.000008929792,"threshold_uncertainty_score":0.9999636},"labels":[],"label_agreement":null},{"id":"W6931787817","doi":"10.5281/zenodo.7686551","title":"StanJulia/Stan.jl: v10.3.1","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Summit Pacific College","funders":"","keywords":"Process (computing); Work (physics); Identification (biology); Product (mathematics)","score_opus":0.5052548320101375,"score_gpt":0.49057314255154366,"score_spread":0.014681689458593883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931787817","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005348187,0.00006450469,0.03178752,0.00038288685,0.0007529605,0.001024,0.0024575295,0.008304932,0.95522034],"genre_scores_gemma":[0.00010316153,0.0006543472,0.11872675,0.00021008977,0.0021606875,2.3370228e-7,0.0005416764,0.07731386,0.8002892],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955157,0.0014672261,0.00073077955,0.00081092614,0.000864542,0.000610836],"domain_scores_gemma":[0.99514717,0.002508294,0.00045544564,0.001194637,0.0003679312,0.00032653133],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0030936277,0.0003617983,0.0006837583,0.0004190882,0.0007409021,0.00052725215,0.00163593,0.00040547125,0.15600847],"category_scores_gemma":[0.06917999,0.00036069567,0.00016615691,0.0007573009,0.00034608573,0.000060683506,0.0016039719,0.00073812075,0.05388002],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003599436,0.00010068902,1.6822585e-7,0.00023467244,0.00013209188,0.000039268652,0.00008442939,2.4236e-7,0.000029390529,0.06651035,0.87540704,0.05742569],"study_design_scores_gemma":[0.00053832156,0.0001679005,0.00000773452,0.00026453123,0.00007276763,0.000016052862,0.00006152105,0.0000184294,0.000023326196,0.09317587,0.9053104,0.00034312412],"about_ca_topic_score_codex":0.00001953287,"about_ca_topic_score_gemma":0.0000018632405,"teacher_disagreement_score":0.15493113,"about_ca_system_score_codex":0.00020891479,"about_ca_system_score_gemma":0.000007064275,"threshold_uncertainty_score":0.9998845},"labels":[],"label_agreement":null},{"id":"W6931860553","doi":"10.5683/sp3/iglsq8","title":"Appearance of the ‘FOCAL Population Survey Tool (English)’ in Qualtrics","year":2023,"lang":"en","type":"dataset","venue":"Borealis","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Population; Survey research; Epidemiology; Survey methodology; Survey data collection; Statistical survey","score_opus":0.5053706873098643,"score_gpt":0.5421093214401878,"score_spread":0.03673863413032341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931860553","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014254519,0.00001954688,0.0006169213,0.00003767842,0.0012160327,0.00066474406,0.99722475,0.000041207142,0.000036565565],"genre_scores_gemma":[0.0000552697,0.00012786457,0.013563712,0.00006152432,0.0004593632,0.0000579264,0.9855832,0.000056126686,0.000035003104],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99361855,0.003205649,0.0017106987,0.00041635148,0.000749914,0.00029884273],"domain_scores_gemma":[0.95017505,0.04729939,0.0008390939,0.0014115288,0.00022232288,0.00005263076],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009489809,0.00026403213,0.0010621503,0.00013601618,0.000037290174,0.00002583434,0.0008322049,0.0006194411,0.000016376378],"category_scores_gemma":[0.46845436,0.00019171213,0.00019581258,0.0008492818,0.0001342545,0.000031393793,0.00026623174,0.00071264,0.000015665473],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059277918,0.00010576493,0.0009431745,0.00045555705,0.000025945958,0.0000043748005,0.000016861703,0.0000054613147,1.1292529e-7,0.0024059583,0.9953128,0.00066468667],"study_design_scores_gemma":[0.0010848107,0.00009043653,0.29126793,0.0011358461,0.00018558076,8.1442187e-7,0.000019566174,0.000072834206,0.000009240332,0.58151776,0.12405519,0.000560001],"about_ca_topic_score_codex":0.0698074,"about_ca_topic_score_gemma":0.04985484,"teacher_disagreement_score":0.8712576,"about_ca_system_score_codex":0.000088566914,"about_ca_system_score_gemma":0.00009685082,"threshold_uncertainty_score":0.9674828},"labels":[],"label_agreement":null},{"id":"W6939185456","doi":"10.6084/m9.figshare.12502811.v1","title":"Additional file 1 of Stakeholder perspectives on adaptive clinical trials: a scoping review","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; BC Children's Hospital","funders":"","keywords":"Table (database); Inclusion (mineral); Stakeholder; Key (lock); Table of contents","score_opus":0.9600789659525235,"score_gpt":0.6698040416597687,"score_spread":0.2902749242927548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939185456","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.3766386e-8,0.000591281,0.00014718172,0.0002923029,0.000033247157,0.0012400832,0.99348056,0.00006757189,0.0041476907],"genre_scores_gemma":[0.000010013526,0.00016056283,0.6121504,0.0037415302,0.0018560217,0.0025522253,0.37934005,0.00007312718,0.00011606193],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99359876,0.003330922,0.001947892,0.00047936113,0.00046084617,0.00018224563],"domain_scores_gemma":[0.24261637,0.7545326,0.0016229483,0.00043574473,0.00049202895,0.00030030173],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017926457,0.00018811837,0.0015678733,0.000024014362,0.000037035024,0.000013214128,0.0002699668,0.00015800347,0.9980463],"category_scores_gemma":[0.9601046,0.0001505473,0.0005363516,0.0002248303,0.000043608998,0.00004749433,0.000115920455,0.0004517761,0.0026597548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008750577,0.00012337934,2.9896388e-8,0.002748465,0.00007196439,0.000007646934,0.000041125335,1.5966951e-7,1.0750255e-7,0.00066013134,0.9905372,0.0057222443],"study_design_scores_gemma":[0.00097637455,0.0011184079,0.000030263767,0.83652073,0.00013773183,0.000001804674,0.0002388873,0.00017053628,0.000015890228,0.05136252,0.109028384,0.00039849462],"about_ca_topic_score_codex":1.0480951e-7,"about_ca_topic_score_gemma":2.5282418e-7,"teacher_disagreement_score":0.99538654,"about_ca_system_score_codex":0.000021371681,"about_ca_system_score_gemma":0.00026588116,"threshold_uncertainty_score":0.9981168},"labels":[],"label_agreement":null},{"id":"W6939563658","doi":"10.6084/m9.figshare.16822645.v1","title":"Additional file 2 of Confidence interval of risk difference by different statistical methods and its impact on the study conclusion in antibiotic non-inferiority trials","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University; University Health Network; Queen's University","funders":"","keywords":"Confidence interval; Interval (graph theory); Statistical analysis; Antibiotics; Interval data; Clinical trial","score_opus":0.46184954047280846,"score_gpt":0.5839566755569755,"score_spread":0.12210713508416704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939563658","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015675783,0.000024414874,0.0010156331,0.000015737336,0.00004795185,0.00077737885,0.982346,0.000009689393,0.000087393826],"genre_scores_gemma":[0.68234086,0.000019990885,0.19716151,0.00007229087,0.00014696165,0.0004884108,0.119630255,0.000054555694,0.00008518889],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9904275,0.0071409508,0.0013805126,0.00039350239,0.00045072788,0.00020682235],"domain_scores_gemma":[0.3802479,0.6181877,0.0008060749,0.00037176543,0.0002773923,0.00010912525],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020795236,0.00023939132,0.0014709628,0.00004549686,0.00005266753,0.000029484663,0.00025694357,0.00013889186,0.9072284],"category_scores_gemma":[0.80711573,0.00014182265,0.00016508951,0.0001835957,0.00006239429,0.000027715041,0.00038710528,0.00045881368,0.000028206461],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033302372,0.0015212616,0.00013785639,0.00041975165,0.00016802184,0.000024584355,0.0002710529,5.131409e-7,0.00073020835,0.0008610458,0.98409694,0.011435754],"study_design_scores_gemma":[0.0049227956,0.003557505,0.5246161,0.022209844,0.00041328414,0.000011704725,0.0009647113,0.006450442,0.02607231,0.40919188,0.0006966815,0.00089271757],"about_ca_topic_score_codex":0.000010619008,"about_ca_topic_score_gemma":0.000008631322,"teacher_disagreement_score":0.9834002,"about_ca_system_score_codex":0.00004241394,"about_ca_system_score_gemma":0.00015015416,"threshold_uncertainty_score":0.57833594},"labels":[],"label_agreement":null},{"id":"W6939591959","doi":"10.6084/m9.figshare.23632749","title":"Additional file 10 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Phase (matter); Set (abstract data type); File format","score_opus":0.8219686074653252,"score_gpt":0.5985845190346615,"score_spread":0.2233840884306637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939591959","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042358343,0.000008037161,0.00004671737,0.000059166305,0.000040897543,0.001634305,0.9937438,0.00004142515,0.00018982559],"genre_scores_gemma":[0.009288399,9.464316e-7,0.8510368,0.000055401215,0.00024258225,0.0047376514,0.13346283,0.00006956888,0.0011058233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742925,0.0005222759,0.0013175723,0.0002413961,0.0003071101,0.00018241619],"domain_scores_gemma":[0.66433483,0.33443287,0.00061448925,0.00022712108,0.00032468242,0.00006597819],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017690596,0.0001369275,0.00074416935,0.00007473838,0.00013285343,0.000015853448,0.00015868111,0.00008637696,0.7774371],"category_scores_gemma":[0.6132596,0.0000956745,0.00013241856,0.00022648195,0.000054887998,0.000015095065,0.00014792559,0.000111046924,0.00017370106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013710992,0.00025500308,0.0000028785557,0.00018031523,0.00013917284,0.000005443614,0.00019952121,3.9242147e-7,0.000036942365,0.0002463064,0.99261034,0.0061865575],"study_design_scores_gemma":[0.030315328,0.004005419,0.027969694,0.016039638,0.0010428248,0.00002246805,0.0033817678,0.0020651359,0.003204789,0.34593675,0.56461567,0.0014005224],"about_ca_topic_score_codex":4.807624e-7,"about_ca_topic_score_gemma":0.000003242904,"teacher_disagreement_score":0.86028093,"about_ca_system_score_codex":0.000012235979,"about_ca_system_score_gemma":0.0002216257,"threshold_uncertainty_score":0.39014927},"labels":[],"label_agreement":null},{"id":"W6939655804","doi":"10.6084/m9.figshare.20968241.v1","title":"Additional file 1 of Overestimation of benefit when clinical trials stop early: a simulation study","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Table (database); Clinical trial; Relative risk; Absolute risk reduction; Reduction (mathematics); Statistical analysis","score_opus":0.8336163245398001,"score_gpt":0.6369848996935964,"score_spread":0.19663142484620366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939655804","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030858067,0.0000029617397,0.00016582437,0.0000090503045,0.000081360165,0.0010959695,0.99758625,0.000036544916,0.0007134427],"genre_scores_gemma":[0.023925152,1.2421086e-7,0.39476636,0.00006393462,0.00045859875,0.003208021,0.57683504,0.000056300218,0.00068645994],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9931522,0.0031685992,0.0024533612,0.00029562853,0.00079454156,0.0001356741],"domain_scores_gemma":[0.4256821,0.5713421,0.0020998865,0.00044252418,0.00035485122,0.00007852404],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034552515,0.00012959242,0.000990458,0.00008121421,0.00007771933,0.000012115199,0.0002788547,0.00010137489,0.9972709],"category_scores_gemma":[0.8004976,0.00012343221,0.0003220236,0.0001874616,0.00001894631,0.00006441247,0.00029204926,0.00029931878,0.00017641857],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018970262,0.00088769296,0.000014462383,0.00009439328,0.000094990224,0.0000024642102,0.00013401477,0.0004193264,7.9802464e-7,0.00024779123,0.9872954,0.010619001],"study_design_scores_gemma":[0.0033853257,0.002793073,0.023322405,0.0015610475,0.00024175206,0.0000014249283,0.00033554906,0.01930368,0.00002372592,0.8898441,0.058789745,0.00039817847],"about_ca_topic_score_codex":0.0000027062615,"about_ca_topic_score_gemma":0.000001063615,"teacher_disagreement_score":0.99709445,"about_ca_system_score_codex":0.00003871229,"about_ca_system_score_gemma":0.00012457043,"threshold_uncertainty_score":0.503342},"labels":[],"label_agreement":null},{"id":"W6939773735","doi":"10.6084/m9.figshare.27173673","title":"Additional file 2 of Adaptive designs in clinical trials: a systematic review-part I","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital Research Institute of Manitoba; SickKids Foundation; George & Fay Yee Centre for Healthcare Innovation; University of Toronto; University of Calgary; University of Manitoba; Hospital for Sick Children; University of British Columbia","funders":"","keywords":"Adaptive design; Key (lock); Scheme (mathematics); Matching (statistics)","score_opus":0.9141425953467399,"score_gpt":0.655190547230821,"score_spread":0.2589520481159189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939773735","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6301512e-8,0.0015108696,0.00016243284,0.00004284225,0.00013881832,0.001881111,0.99335474,0.00008161882,0.0028275168],"genre_scores_gemma":[0.000007635485,0.00010750115,0.4929063,0.0005747698,0.0010267803,0.01615117,0.4871298,0.00009319077,0.0020028476],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9874079,0.007274449,0.0042368206,0.00040447564,0.00046060584,0.00021573355],"domain_scores_gemma":[0.14709647,0.85109913,0.0009554112,0.000497038,0.00021777855,0.00013414836],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008428414,0.00019542404,0.0024480643,0.00008963982,0.00001708586,0.00002736276,0.00030683354,0.00022745822,0.9957537],"category_scores_gemma":[0.96125144,0.00014385687,0.0006716697,0.00042449834,0.000030220084,0.000065194195,0.00010223903,0.00046947412,0.005534695],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014135459,0.00007895673,1.3749091e-8,0.14875112,0.00009240008,0.00003585454,0.0000064415144,6.568614e-8,6.246059e-8,0.0008133784,0.8495806,0.0006269507],"study_design_scores_gemma":[0.00016600807,0.00012184204,0.0000045602874,0.8030302,0.00020296047,0.000006384071,0.000012783723,0.00054835534,0.0000032130295,0.13666743,0.05907994,0.00015630398],"about_ca_topic_score_codex":3.184139e-7,"about_ca_topic_score_gemma":0.0000016862908,"teacher_disagreement_score":0.990219,"about_ca_system_score_codex":0.000048063277,"about_ca_system_score_gemma":0.00028432222,"threshold_uncertainty_score":0.9952396},"labels":[{"model":"gemma","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W6945460143","doi":"10.25384/sage.23916435","title":"sj-docx-2-msj-10.1177_13524585231189673 – Supplemental material for Assessing heterogeneity of treatment effect in multiple sclerosis trials","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Multiple sclerosis; Treatment effect; Clinical trial; Randomized controlled trial; Fingolimod; MEDLINE","score_opus":0.8044893180181177,"score_gpt":0.6094999466314407,"score_spread":0.19498937138667705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945460143","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81501055,0.0004253317,0.035681423,0.00050411926,0.002564204,0.004508122,0.14109562,0.00016378675,0.000046858582],"genre_scores_gemma":[0.31534317,0.0018425636,0.6781199,0.0000664875,0.0017719726,0.0004744318,0.0020945566,0.00018721826,0.00009967059],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99002934,0.0046184678,0.0033443442,0.00073115504,0.0005717387,0.0007049824],"domain_scores_gemma":[0.90079623,0.09622923,0.0013155037,0.001365559,0.00009021313,0.00020328209],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030935967,0.00042033655,0.002472585,0.0002924503,0.0001660702,0.00024732054,0.0009419352,0.0002321887,0.008681346],"category_scores_gemma":[0.13233821,0.0003060071,0.00046293708,0.00046353592,0.00012664765,0.0003833296,0.0006328762,0.00020105949,0.00003624277],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041774684,0.0018718698,0.014627186,0.0012388657,0.0019369597,0.00013736544,0.00026656178,0.000031614698,0.2912327,0.00013915468,0.045149762,0.6391905],"study_design_scores_gemma":[0.059334002,0.00573549,0.019045401,0.006947626,0.0032744706,0.0000353989,0.0005356007,0.0076521533,0.64148086,0.24979511,0.004357638,0.0018062624],"about_ca_topic_score_codex":0.000091092195,"about_ca_topic_score_gemma":0.000087593646,"teacher_disagreement_score":0.6424385,"about_ca_system_score_codex":0.00023010238,"about_ca_system_score_gemma":0.0001318192,"threshold_uncertainty_score":0.9999392},"labels":[],"label_agreement":null},{"id":"W6945633622","doi":"10.25384/sage.23916432.v1","title":"sj-docx-1-msj-10.1177_13524585231189673 – Supplemental material for Assessing heterogeneity of treatment effect in multiple sclerosis trials","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Multiple sclerosis; Treatment effect; Clinical trial; Randomized controlled trial; Fingolimod; MEDLINE","score_opus":0.809807904840611,"score_gpt":0.5879156561892993,"score_spread":0.22189224865131174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945633622","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16581933,0.000013552973,0.000126428,0.00005510367,0.0005019706,0.0033822258,0.8298418,0.00017849838,0.000081082806],"genre_scores_gemma":[0.542156,0.000014150246,0.31445092,0.00006945617,0.0014812673,0.008660113,0.13266538,0.0002847141,0.00021798896],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9948367,0.0019325704,0.0018068687,0.0005443917,0.00032957684,0.00054988754],"domain_scores_gemma":[0.8821353,0.116535,0.0006440359,0.00045657993,0.000103926664,0.00012519216],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003512444,0.00036938436,0.001809043,0.00017606936,0.000097710705,0.000103708066,0.0002935488,0.00024689024,0.15696143],"category_scores_gemma":[0.2273876,0.00028473703,0.0005894295,0.0003548802,0.000027940294,0.00010916378,0.00019246321,0.00009894629,0.0003215824],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039049645,0.0016580719,0.0029126445,0.006426392,0.0010931346,0.00007849446,0.00039009945,0.00006291199,0.06624638,0.00036192389,0.81502527,0.101839714],"study_design_scores_gemma":[0.024277601,0.0032804937,0.0067291637,0.0048211263,0.00049949036,0.00000330182,0.00011742315,0.002339433,0.89558375,0.052154593,0.009175846,0.0010177653],"about_ca_topic_score_codex":0.000024493838,"about_ca_topic_score_gemma":0.000038041515,"teacher_disagreement_score":0.82933736,"about_ca_system_score_codex":0.0002381067,"about_ca_system_score_gemma":0.00009093952,"threshold_uncertainty_score":0.9999605},"labels":[],"label_agreement":null},{"id":"W6946054690","doi":"10.25384/sage.21078004","title":"sj-pdf-1-ctj-10.1177_17407745221118366 – Supplemental material for A Bayesian adaptive design for clinical trials of rare efficacy outcomes with multiple definitions","year":2022,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; McMaster University; University of Toronto","funders":"","keywords":"Adaptive design; Clinical trial; Bayesian probability; Research design; Clinical study design; MEDLINE","score_opus":0.8467833716984642,"score_gpt":0.6163678694703746,"score_spread":0.2304155022280896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946054690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056318083,0.00013448572,0.7441213,0.0008648419,0.000961366,0.0048506223,0.2484066,0.00004938929,0.000048188514],"genre_scores_gemma":[0.010665868,0.00020146261,0.98524004,0.00023053377,0.0006598196,0.0010136176,0.0016855547,0.00012360855,0.00017946953],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9833299,0.008768151,0.005424383,0.00089359,0.00090602116,0.00067794736],"domain_scores_gemma":[0.6685814,0.3259176,0.0031704085,0.0016615288,0.00031852565,0.00035052796],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05514707,0.00044264356,0.0029596474,0.00018801095,0.00058423687,0.00013309202,0.001690257,0.00019555012,0.051499333],"category_scores_gemma":[0.286614,0.00033825365,0.0007817022,0.00026845903,0.00026858697,0.00025222354,0.0009228015,0.00056315213,0.000010687422],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.067259595,0.011817476,0.0032389704,0.0007882013,0.0088670375,0.00015866944,0.00062664034,0.00013074676,0.001441947,0.012962805,0.7522114,0.14049652],"study_design_scores_gemma":[0.06441035,0.009939913,0.0012926676,0.0009572078,0.005215151,0.000101416146,0.0022933036,0.0056669414,0.0021129462,0.88955975,0.017085958,0.001364412],"about_ca_topic_score_codex":0.000012396925,"about_ca_topic_score_gemma":0.000019127194,"teacher_disagreement_score":0.8765969,"about_ca_system_score_codex":0.00009343196,"about_ca_system_score_gemma":0.0004226453,"threshold_uncertainty_score":0.99990696},"labels":[],"label_agreement":null},{"id":"W6957596443","doi":"10.60692/2a5sz-qtv42","title":"Deep historical borrowing framework to prospectively and simultaneously synthesize control information in confirmatory clinical trials with multiple endpoints","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Prior probability; Bayesian probability; Prior information; Posterior probability; Clinical trial; Sample size determination; Bayes' theorem; Reliability (semiconductor); Statistical power; Statistical hypothesis testing","score_opus":0.33495010488497234,"score_gpt":0.4375995612269564,"score_spread":0.10264945634198408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957596443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12655897,0.0000038671874,0.86772645,0.00025137098,0.0010076319,0.0035447965,0.00029689237,0.0002709284,0.00033907915],"genre_scores_gemma":[0.85615224,1.7418462e-7,0.14233857,0.00063093536,0.000121496196,0.0007184611,0.0000026618338,0.00002261633,0.000012872943],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896781,0.0040961164,0.004541958,0.00032393888,0.0009218733,0.00043800232],"domain_scores_gemma":[0.9689746,0.028152408,0.0017489073,0.00051401573,0.0002913336,0.0003187332],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019739214,0.00033986845,0.0016979051,0.00040762208,0.0002692325,0.00014916313,0.00030325074,0.00026354162,0.00007305317],"category_scores_gemma":[0.12538111,0.00027140428,0.00017189421,0.00042517463,0.00005818393,0.0006642023,0.00016945027,0.0007316212,0.00009587495],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027225073,0.00022344073,0.6586623,0.0036820325,0.00097507634,0.00015580062,0.23163766,0.0074215983,0.000003981192,0.042202096,0.0009566538,0.026854288],"study_design_scores_gemma":[0.10444611,0.008359462,0.23013407,0.0051307846,0.0022582312,0.0011861229,0.16951865,0.42966002,0.0003148222,0.029471956,0.012012636,0.0075071477],"about_ca_topic_score_codex":0.000014329236,"about_ca_topic_score_gemma":8.5507025e-7,"teacher_disagreement_score":0.7295932,"about_ca_system_score_codex":0.0009486481,"about_ca_system_score_gemma":0.000110771885,"threshold_uncertainty_score":0.99997383},"labels":[],"label_agreement":null},{"id":"W6957758445","doi":"10.60692/edrx5-44d34","title":"Deep historical borrowing framework to prospectively and simultaneously synthesize control information in confirmatory clinical trials with multiple endpoints","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Prior probability; Bayesian probability; Prior information; Posterior probability; Clinical trial; Sample size determination; Bayes' theorem; Reliability (semiconductor); Statistical power; Statistical hypothesis testing","score_opus":0.33495010488497234,"score_gpt":0.4375995612269564,"score_spread":0.10264945634198408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957758445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12655897,0.0000038671874,0.86772645,0.00025137098,0.0010076319,0.0035447965,0.00029689237,0.0002709284,0.00033907915],"genre_scores_gemma":[0.85615224,1.7418462e-7,0.14233857,0.00063093536,0.000121496196,0.0007184611,0.0000026618338,0.00002261633,0.000012872943],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896781,0.0040961164,0.004541958,0.00032393888,0.0009218733,0.00043800232],"domain_scores_gemma":[0.9689746,0.028152408,0.0017489073,0.00051401573,0.0002913336,0.0003187332],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019739214,0.00033986845,0.0016979051,0.00040762208,0.0002692325,0.00014916313,0.00030325074,0.00026354162,0.00007305317],"category_scores_gemma":[0.12538111,0.00027140428,0.00017189421,0.00042517463,0.00005818393,0.0006642023,0.00016945027,0.0007316212,0.00009587495],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027225073,0.00022344073,0.6586623,0.0036820325,0.00097507634,0.00015580062,0.23163766,0.0074215983,0.000003981192,0.042202096,0.0009566538,0.026854288],"study_design_scores_gemma":[0.10444611,0.008359462,0.23013407,0.0051307846,0.0022582312,0.0011861229,0.16951865,0.42966002,0.0003148222,0.029471956,0.012012636,0.0075071477],"about_ca_topic_score_codex":0.000014329236,"about_ca_topic_score_gemma":8.5507025e-7,"teacher_disagreement_score":0.7295932,"about_ca_system_score_codex":0.0009486481,"about_ca_system_score_gemma":0.000110771885,"threshold_uncertainty_score":0.99997383},"labels":[],"label_agreement":null},{"id":"W6957839776","doi":"10.60692/wgy36-8ea31","title":"What is a randomization test?","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Randomization; Permutation (music); Terminology; Conditional independence; Meaning (existential); Resampling; Restricted randomization; Construct (python library)","score_opus":0.4363852204703797,"score_gpt":0.45040036667264827,"score_spread":0.014015146202268569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957839776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079706356,0.0000033643994,0.89922285,0.0008537776,0.006077252,0.002631388,0.00046317183,0.002841303,0.008200546],"genre_scores_gemma":[0.92259485,0.0000025775619,0.07482553,0.0006276082,0.00034006604,0.00027029382,0.000013144091,0.000036140667,0.0012897837],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754894,0.00027876298,0.0012871496,0.0001598935,0.0004659409,0.00025933527],"domain_scores_gemma":[0.9954036,0.003348642,0.00046273743,0.0004525845,0.00022855497,0.0001038801],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0031067564,0.00016763055,0.00046812333,0.00023812402,0.00010880868,0.00038221502,0.00018012233,0.0001662504,0.00014226181],"category_scores_gemma":[0.012853603,0.00013018091,0.00012720266,0.00059353217,0.000035646844,0.00090567744,0.000074941796,0.00010341964,0.00503693],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027031293,0.000052332023,0.0791138,0.013442881,0.0009223568,0.000064080596,0.62429255,0.00022750064,0.000014854265,0.12328542,0.0976256,0.058255468],"study_design_scores_gemma":[0.12654743,0.0011090132,0.044692114,0.0121595785,0.0018223182,0.0002468343,0.25479224,0.26663613,0.011444258,0.26339293,0.011117535,0.0060396157],"about_ca_topic_score_codex":5.282384e-7,"about_ca_topic_score_gemma":1.3791442e-8,"teacher_disagreement_score":0.8428885,"about_ca_system_score_codex":0.000061187064,"about_ca_system_score_gemma":0.000024156996,"threshold_uncertainty_score":0.9957378},"labels":[],"label_agreement":null},{"id":"W6958057553","doi":"10.6084/m9.figshare.23632746.v1","title":"Additional file 9 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Bar (unit); Dosing; Bar chart; Table (database); Diagram; Calibration","score_opus":0.8319963453932503,"score_gpt":0.6024880844721656,"score_spread":0.22950826092108467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958057553","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002627462,0.000006506183,0.000045431894,0.00005303128,0.000039061368,0.001589562,0.9954508,0.00003979859,0.0001483806],"genre_scores_gemma":[0.0058909804,7.191938e-7,0.807591,0.00005016627,0.00019130301,0.004815303,0.18093874,0.00005490942,0.00046689133],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750865,0.00050529925,0.00128137,0.00023227153,0.00029538843,0.00017701137],"domain_scores_gemma":[0.6231398,0.3757215,0.0005901602,0.00021006499,0.00027728456,0.00006118316],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015549732,0.00013156574,0.00072383136,0.000072435374,0.00013010611,0.000014856369,0.00015266838,0.000081602724,0.81034607],"category_scores_gemma":[0.644848,0.00009154843,0.00012856745,0.00022431496,0.000052919808,0.0000143612615,0.00014302297,0.00011420717,0.00012936936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009920148,0.00023304137,0.0000029662028,0.00016836911,0.00013113083,0.0000052504206,0.00020270165,3.7818378e-7,0.00003230281,0.0002095921,0.9927561,0.006158931],"study_design_scores_gemma":[0.026190251,0.0034566342,0.034018666,0.018557,0.0009266103,0.00002340472,0.0037007493,0.0019407622,0.0025683085,0.31525168,0.59202427,0.0013416914],"about_ca_topic_score_codex":4.604131e-7,"about_ca_topic_score_gemma":0.0000031339796,"teacher_disagreement_score":0.814512,"about_ca_system_score_codex":0.000011639658,"about_ca_system_score_gemma":0.00022042716,"threshold_uncertainty_score":0.37332365},"labels":[],"label_agreement":null},{"id":"W6958061606","doi":"10.6084/m9.figshare.13173938","title":"Additional file 1 of Guidance for conducting feasibility and pilot studies for implementation trials","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"","keywords":"Key (lock); Troubleshooting; File format; Data collection; Component (thermodynamics)","score_opus":0.9745450350473516,"score_gpt":0.6993810002162266,"score_spread":0.27516403483112495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958061606","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001439016,0.000054969783,0.00057253515,0.00017918702,0.000030971893,0.0016889535,0.9974011,0.000025492296,0.00003236302],"genre_scores_gemma":[0.00014017559,7.270308e-7,0.7715799,0.00017453953,0.0003793185,0.0044143125,0.22327647,0.000014153567,0.000020372925],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835455,0.00029477128,0.0008789337,0.00023770401,0.00011819064,0.00011586635],"domain_scores_gemma":[0.50685763,0.49179244,0.0007150658,0.00010724386,0.00046610413,0.000061476254],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007912801,0.00009248714,0.0006097315,0.000010547176,0.000060273505,0.000011874599,0.0000744953,0.000037445217,0.9003982],"category_scores_gemma":[0.8959164,0.00007880547,0.00011083074,0.00005374833,0.000019452089,0.000046582358,0.000058749887,0.00004451951,0.000012700009],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012437963,0.000018700806,5.7162396e-7,0.0014106648,0.00006538764,9.137502e-8,0.000066810266,6.261794e-8,0.0000437818,0.00044301877,0.9944563,0.0033702545],"study_design_scores_gemma":[0.003079541,0.001319501,0.00013480638,0.002063479,0.00011373911,4.942046e-7,0.0006535612,0.00016867626,0.0031181918,0.77174914,0.21737258,0.00022632367],"about_ca_topic_score_codex":1.6397047e-7,"about_ca_topic_score_gemma":0.0000015954608,"teacher_disagreement_score":0.9003855,"about_ca_system_score_codex":0.000018293196,"about_ca_system_score_gemma":0.00005127351,"threshold_uncertainty_score":0.32135937},"labels":[],"label_agreement":null},{"id":"W6958062577","doi":"10.6084/m9.figshare.26608248.v1","title":"Additional file 1 of Power and sample size calculation for incremental net benefit in cost effectiveness analyses with applications to trials conducted by the Canadian Cancer Trials Group","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; University of Toronto; Queen's University; Cancer Care Ontario; Sunnybrook Health Science Centre","funders":"","keywords":"Sample size determination; Cost effectiveness; Sample (material); Power (physics); Clinical trial; Statistical power","score_opus":0.6565058055922895,"score_gpt":0.5852538498568018,"score_spread":0.0712519557354877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958062577","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061178034,0.000055811204,0.0009940017,0.000111848385,0.000027808795,0.004001264,0.9946606,0.000018404364,0.000069085494],"genre_scores_gemma":[0.010942482,0.0000018080075,0.26377454,0.00029007226,0.00030420363,0.072382025,0.6521555,0.00006481775,0.000084548126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997712,0.00085464073,0.0007601893,0.00029047017,0.00020743298,0.00017526503],"domain_scores_gemma":[0.5209819,0.47841415,0.00020989201,0.00013946915,0.0001484846,0.000106090665],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019123687,0.00013982547,0.00071970734,0.00008345414,0.00009161258,0.00007676698,0.00011742929,0.000110282956,0.7910944],"category_scores_gemma":[0.4637844,0.00009105106,0.000104045896,0.00039626853,0.000026455105,0.000049482445,0.000029252833,0.00010957234,0.000015684],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013293381,0.000027501974,0.0000036108993,0.00022999947,0.00014843191,4.874012e-7,0.00002307793,0.000012344118,0.00013584827,0.000780083,0.99357134,0.004934345],"study_design_scores_gemma":[0.0035107078,0.00048393203,0.007722226,0.01021735,0.00052035716,0.0000038171042,0.000111203335,0.0010463323,0.002140955,0.2659297,0.7076502,0.00066327426],"about_ca_topic_score_codex":0.0042235777,"about_ca_topic_score_gemma":0.04048655,"teacher_disagreement_score":0.79107875,"about_ca_system_score_codex":0.0001748063,"about_ca_system_score_gemma":0.0002661236,"threshold_uncertainty_score":0.97702205},"labels":[],"label_agreement":null},{"id":"W6958146462","doi":"10.6084/m9.figshare.13173938.v1","title":"Additional file 1 of Guidance for conducting feasibility and pilot studies for implementation trials","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"","keywords":"Key (lock); Troubleshooting; File format; Data collection; Component (thermodynamics)","score_opus":0.9745450350473516,"score_gpt":0.6993810002162266,"score_spread":0.27516403483112495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958146462","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001439016,0.000054969783,0.00057253515,0.00017918702,0.000030971893,0.0016889535,0.9974011,0.000025492296,0.00003236302],"genre_scores_gemma":[0.00014017559,7.270308e-7,0.7715799,0.00017453953,0.0003793185,0.0044143125,0.22327647,0.000014153567,0.000020372925],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835455,0.00029477128,0.0008789337,0.00023770401,0.00011819064,0.00011586635],"domain_scores_gemma":[0.50685763,0.49179244,0.0007150658,0.00010724386,0.00046610413,0.000061476254],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007912801,0.00009248714,0.0006097315,0.000010547176,0.000060273505,0.000011874599,0.0000744953,0.000037445217,0.9003982],"category_scores_gemma":[0.8959164,0.00007880547,0.00011083074,0.00005374833,0.000019452089,0.000046582358,0.000058749887,0.00004451951,0.000012700009],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012437963,0.000018700806,5.7162396e-7,0.0014106648,0.00006538764,9.137502e-8,0.000066810266,6.261794e-8,0.0000437818,0.00044301877,0.9944563,0.0033702545],"study_design_scores_gemma":[0.003079541,0.001319501,0.00013480638,0.002063479,0.00011373911,4.942046e-7,0.0006535612,0.00016867626,0.0031181918,0.77174914,0.21737258,0.00022632367],"about_ca_topic_score_codex":1.6397047e-7,"about_ca_topic_score_gemma":0.0000015954608,"teacher_disagreement_score":0.9003855,"about_ca_system_score_codex":0.000018293196,"about_ca_system_score_gemma":0.00005127351,"threshold_uncertainty_score":0.32135937},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"not_applicable","genre":"dataset","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W6958211345","doi":"10.6084/m9.figshare.17056754.v1","title":"Additional file 1 of On clinical trial fragility due to patients lost to follow up","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Fragility; Clinical trial; MEDLINE; Fragility fracture","score_opus":0.7080002190339147,"score_gpt":0.5759471338519853,"score_spread":0.13205308518192949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958211345","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040647553,4.957244e-7,0.000048116373,0.00009402151,0.00055304216,0.00077861233,0.9924033,0.000031022344,0.0056848917],"genre_scores_gemma":[0.00013814968,9.521133e-8,0.45393813,0.0016885456,0.0010918829,0.0011612471,0.53988343,0.00004167676,0.002056814],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964541,0.00085206446,0.0012859685,0.00053083344,0.00062618894,0.0002508243],"domain_scores_gemma":[0.7231271,0.2747857,0.00030628205,0.0006840854,0.0007193173,0.00037745936],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00045327964,0.0001725048,0.0007610863,0.000040958148,0.000041612646,0.000023716626,0.00028993335,0.00024268814,0.9967384],"category_scores_gemma":[0.9011817,0.0001600708,0.00035905646,0.00029649647,0.000013975442,0.000027436932,0.0003023871,0.00031107085,0.015453987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024814804,0.0007141154,0.0000029791097,0.000066812994,0.000035660796,0.000016839938,0.0000103033435,2.67514e-7,1.8453363e-7,0.00013789107,0.9865562,0.009977315],"study_design_scores_gemma":[0.010890875,0.0018933419,0.0052407943,0.0032198029,0.00002749561,7.957553e-7,0.000008094921,0.000008850861,0.00014945205,0.0897252,0.8885196,0.0003157302],"about_ca_topic_score_codex":6.2592164e-7,"about_ca_topic_score_gemma":0.000007206472,"teacher_disagreement_score":0.9812844,"about_ca_system_score_codex":0.000042659216,"about_ca_system_score_gemma":0.00020782772,"threshold_uncertainty_score":0.9853126},"labels":[],"label_agreement":null},{"id":"W6958250352","doi":"10.6084/m9.figshare.20968244","title":"Additional file 2 of Overestimation of benefit when clinical trials stop early: a simulation study","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Clinical trial; Table (database); MEDLINE; Data collection","score_opus":0.8277903316685217,"score_gpt":0.6361785578634089,"score_spread":0.19161177380511274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958250352","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030642256,0.00000301011,0.00016215797,0.000009001616,0.00008184098,0.0010938878,0.9975771,0.000036533125,0.00073006196],"genre_scores_gemma":[0.023671368,1.2833938e-7,0.3896877,0.00006432031,0.0004683543,0.0031637712,0.5821949,0.00005655535,0.000692901],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99315196,0.0031678192,0.002454735,0.00029543086,0.00079441775,0.00013563645],"domain_scores_gemma":[0.4299701,0.5670546,0.0021015941,0.00044137848,0.00035382196,0.00007846357],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034359538,0.00012955011,0.0009907067,0.000081159626,0.00007772517,0.000012142194,0.0002786954,0.00010137549,0.9972172],"category_scores_gemma":[0.7984992,0.0001233908,0.00032195967,0.00018731202,0.00001894604,0.00006445778,0.0002920071,0.00029924806,0.00017448692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018870962,0.0008877117,0.000013996747,0.00009530544,0.000095024894,0.0000025343697,0.00013417852,0.00042154448,7.699441e-7,0.0002523573,0.98698324,0.010924616],"study_design_scores_gemma":[0.0033859347,0.0027745662,0.022783283,0.0015308111,0.00023921659,0.0000014184684,0.00032977728,0.019041467,0.000023414223,0.8888419,0.060653564,0.0003946204],"about_ca_topic_score_codex":0.0000027342626,"about_ca_topic_score_gemma":0.0000010700779,"teacher_disagreement_score":0.9970427,"about_ca_system_score_codex":0.000038723672,"about_ca_system_score_gemma":0.00012400141,"threshold_uncertainty_score":0.50317305},"labels":[],"label_agreement":null},{"id":"W6958271950","doi":"10.6084/m9.figshare.26693437.v1","title":"Additional file 1 of Trials that turn from retrospectively registered to prospectively registered: a cohort study of “retroactively prospective” clinical trial registration using history data","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Clinical trial; Table (database); Cohort; Cohort study; Retrospective cohort study; Data collection","score_opus":0.8955052973751,"score_gpt":0.5956874186779625,"score_spread":0.2998178786971375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958271950","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015438242,0.00007124755,0.00066398625,0.00002505476,0.00086230814,0.008084362,0.9861797,0.0001958688,0.002373664],"genre_scores_gemma":[0.046336185,0.000005913341,0.6203476,0.000087022985,0.0050800024,0.0073648565,0.31781068,0.00038286942,0.0025848353],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9872358,0.0036433935,0.0045325393,0.002291957,0.0018684405,0.00042787552],"domain_scores_gemma":[0.62389946,0.35648572,0.011734365,0.0053946455,0.0019195429,0.00056625454],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0058854492,0.00056317804,0.0031514456,0.00028731793,0.0000919167,0.00011643706,0.0013232796,0.0005122902,0.8268139],"category_scores_gemma":[0.7943209,0.00050701655,0.00060169905,0.000612744,0.00016365462,0.0005038136,0.0007749201,0.000954142,0.00016498295],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01041542,0.0016491965,0.00019233103,0.00031172254,0.0011150624,0.000050418275,0.00031508194,5.386521e-7,0.000026473102,0.00025465974,0.98461336,0.0010557288],"study_design_scores_gemma":[0.065678075,0.018624065,0.37003747,0.041217197,0.0043451935,0.00004773396,0.0015889253,0.0030583313,0.0004556372,0.28375015,0.20747282,0.00372443],"about_ca_topic_score_codex":0.00015138254,"about_ca_topic_score_gemma":0.0001102878,"teacher_disagreement_score":0.8266489,"about_ca_system_score_codex":0.0010231058,"about_ca_system_score_gemma":0.001233349,"threshold_uncertainty_score":0.99973816},"labels":[],"label_agreement":null},{"id":"W6958290170","doi":"10.6084/m9.figshare.23632716.v1","title":"Additional file 1 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Phase (matter); Expert system; File format","score_opus":0.8352761008364948,"score_gpt":0.6031552918435796,"score_spread":0.2321208089929152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958290170","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026083023,0.0000064434507,0.00004485563,0.000052985466,0.00003902004,0.0015883672,0.9954725,0.00003977691,0.00014778347],"genre_scores_gemma":[0.005682919,7.0114305e-7,0.80552953,0.000049580445,0.00018901034,0.004891424,0.18313815,0.000054370772,0.0004643344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750954,0.0005054247,0.0012803432,0.00023234876,0.00029534308,0.0001769977],"domain_scores_gemma":[0.62091285,0.37794647,0.0005907295,0.00021061672,0.00027809368,0.00006125579],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015539186,0.00013157207,0.0007235673,0.00007242733,0.00013004204,0.000014821146,0.00015282416,0.00008161557,0.81745446],"category_scores_gemma":[0.6472503,0.00009155901,0.00012855939,0.00022436545,0.0000529041,0.000014346613,0.00014312836,0.0001142555,0.00013104017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009891579,0.00023250472,0.0000029572989,0.00016638852,0.00013094391,0.00000515713,0.00020189813,3.7715768e-7,0.000032432836,0.00020694692,0.9928058,0.0061156754],"study_design_scores_gemma":[0.02571126,0.0034160218,0.033529107,0.018354503,0.0009189099,0.00002315455,0.0036704096,0.001911523,0.0025206439,0.30818656,0.6004296,0.0013282981],"about_ca_topic_score_codex":4.6460408e-7,"about_ca_topic_score_gemma":0.000003095102,"teacher_disagreement_score":0.8173234,"about_ca_system_score_codex":0.000011636867,"about_ca_system_score_gemma":0.0002209264,"threshold_uncertainty_score":0.37336683},"labels":[],"label_agreement":null},{"id":"W6958325757","doi":"10.6084/m9.figshare.20267219","title":"Additional file 1 of Risk and benefit for umbrella trials in oncology: a systematic review and meta-analysis","year":2022,"lang":"en","type":"article","venue":"Open MIND","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Table (database); Glossary; Randomized controlled trial; Risk assessment; Key (lock)","score_opus":0.7912938527940113,"score_gpt":0.6181167373624348,"score_spread":0.17317711543157654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958325757","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027336102,0.0024985198,0.0008228165,0.00023479945,0.000016179945,0.004457982,0.9910641,9.49628e-7,0.0008773433],"genre_scores_gemma":[0.00003310642,0.00013904789,0.9899617,0.0001563281,0.000012401769,0.0067525012,0.0013967393,0.000012790336,0.0015353775],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99336845,0.003735428,0.0022084904,0.00034703655,0.00022013164,0.00012048391],"domain_scores_gemma":[0.57271725,0.4254467,0.0014383642,0.0002758226,0.00006822032,0.00005363217],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02223739,0.00012794559,0.0056265593,0.0001029057,0.000073028204,0.000028573262,0.00026640703,0.00006106627,0.8218219],"category_scores_gemma":[0.40649498,0.00009270324,0.00057388813,0.00035767577,0.000066095745,0.00003148457,0.00032990944,0.00014567235,0.000007845889],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003297023,0.00086032884,0.0000026589273,0.060629155,0.10670553,0.000014490338,0.00036927738,0.000009056975,0.0000018838014,0.0063894996,0.8172909,0.00739754],"study_design_scores_gemma":[0.00082788075,0.00025557663,0.000009499098,0.0009169826,0.5577229,0.0000066547154,0.00017518051,0.00013623595,0.000004938864,0.4234884,0.016281096,0.00017465567],"about_ca_topic_score_codex":0.000010754498,"about_ca_topic_score_gemma":0.000051673727,"teacher_disagreement_score":0.98966736,"about_ca_system_score_codex":0.00003149784,"about_ca_system_score_gemma":0.000056053654,"threshold_uncertainty_score":0.770708},"labels":[],"label_agreement":null},{"id":"W6958359120","doi":"10.6084/m9.figshare.23632728","title":"Additional file 3 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Protocol (science); Phase (matter); File format; Key (lock)","score_opus":0.8323473328243262,"score_gpt":0.6024961044540303,"score_spread":0.2298512283702958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958359120","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026283828,0.000006479002,0.000045125536,0.000052743126,0.000039409446,0.0015886977,0.99545074,0.00003973413,0.00014870912],"genre_scores_gemma":[0.0058016907,7.182017e-7,0.8066702,0.000050015704,0.00019306254,0.004844585,0.18190673,0.000054887616,0.0004781449],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975095,0.00050494046,0.0012809538,0.00023225087,0.00029541133,0.00017698796],"domain_scores_gemma":[0.6225244,0.37633163,0.00059135526,0.00021048356,0.00028084675,0.0000613055],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015532017,0.00013155318,0.0007236427,0.00007240267,0.00013003065,0.000014852197,0.00015272613,0.000081608494,0.81363213],"category_scores_gemma":[0.64718777,0.00009153522,0.00012855102,0.00022428056,0.000052907933,0.000014357871,0.00014302287,0.00011423168,0.00013250143],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009961987,0.00023262121,0.000002964322,0.00016945112,0.00013096239,0.0000052257233,0.0002021082,3.7765255e-7,0.000032547723,0.00020583057,0.99270517,0.0062131207],"study_design_scores_gemma":[0.025752505,0.0033691097,0.032912653,0.018089144,0.00089926575,0.000022651502,0.0036076386,0.0018910358,0.002544689,0.30527666,0.60432255,0.0013120748],"about_ca_topic_score_codex":4.6998267e-7,"about_ca_topic_score_gemma":0.0000031165516,"teacher_disagreement_score":0.813544,"about_ca_system_score_codex":0.000011683951,"about_ca_system_score_gemma":0.00022105097,"threshold_uncertainty_score":0.3732698},"labels":[],"label_agreement":null},{"id":"W6958529562","doi":"10.6084/m9.figshare.13173941.v1","title":"Additional file 2 of Guidance for conducting feasibility and pilot studies for implementation trials","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Victoria","funders":"","keywords":"File format; Troubleshooting; Table (database); Key (lock); Data collection","score_opus":0.9734835577151113,"score_gpt":0.69863126972866,"score_spread":0.27485228798645134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958529562","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014284952,0.000055907854,0.00055931933,0.00017817956,0.000031163057,0.0016855985,0.9974169,0.00002548362,0.000033151515],"genre_scores_gemma":[0.00013824365,7.503762e-7,0.7700248,0.00017519135,0.00038676194,0.0043398733,0.2248997,0.000014184279,0.000020520187],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983545,0.00029466764,0.0008793664,0.00023751575,0.00011816034,0.00011582193],"domain_scores_gemma":[0.5115023,0.48714927,0.00071549177,0.00010692637,0.000464573,0.00006141109],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007866511,0.0000924556,0.00060989155,0.00001053977,0.000060278242,0.000011902244,0.00007445083,0.000037445447,0.89855343],"category_scores_gemma":[0.8946956,0.00007877784,0.000110807756,0.000053703516,0.0000194518,0.000046616595,0.000058741025,0.000044508517,0.000012554738],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012358022,0.000018683182,5.518768e-7,0.0014235198,0.00006534954,9.4004164e-8,0.00006683109,6.290348e-8,0.000042132928,0.00045111464,0.9943391,0.003468993],"study_design_scores_gemma":[0.0030634545,0.0013032801,0.00013082761,0.0020108088,0.00011188455,4.892032e-7,0.00063834916,0.00016537891,0.0030587842,0.76650155,0.2227922,0.00022299823],"about_ca_topic_score_codex":1.6574344e-7,"about_ca_topic_score_gemma":0.0000016055911,"teacher_disagreement_score":0.89854085,"about_ca_system_score_codex":0.000018298817,"about_ca_system_score_gemma":0.000051028816,"threshold_uncertainty_score":0.3212467},"labels":[],"label_agreement":null},{"id":"W6958650153","doi":"10.6084/m9.figshare.23632722.v1","title":"Additional file 2 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Development (topology); Data flow diagram; Diagram; Flow (mathematics)","score_opus":0.8301276040917855,"score_gpt":0.6024223961486928,"score_spread":0.2277052079430928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958650153","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025908633,0.0000065482577,0.000043887045,0.000052714597,0.000039254355,0.0015856923,0.9954901,0.00003977165,0.00015120221],"genre_scores_gemma":[0.0056562945,7.2839435e-7,0.8026663,0.000050171966,0.00019411798,0.0048537776,0.18605223,0.000054938624,0.00047141497],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975094,0.00050526246,0.0012809501,0.00023217773,0.00029527477,0.00017693559],"domain_scores_gemma":[0.62403166,0.3748279,0.00059153116,0.00021019619,0.00027745316,0.00006124327],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015453573,0.00013152978,0.0007237463,0.0000723794,0.00013005167,0.000014853659,0.00015273818,0.00008161605,0.81456786],"category_scores_gemma":[0.6444429,0.00009152876,0.00012853426,0.00022418918,0.00005290336,0.000014356549,0.00014310802,0.00011422891,0.00012962737],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098372475,0.00023243036,0.0000028625577,0.00016791422,0.00013094643,0.0000052998566,0.00020207226,3.7899352e-7,0.000031298317,0.00021062937,0.9926303,0.0062875054],"study_design_scores_gemma":[0.025283916,0.0033367695,0.032213982,0.017702375,0.0008941544,0.00002266424,0.003547677,0.0018542482,0.0024462736,0.3033393,0.6080641,0.0012945096],"about_ca_topic_score_codex":4.6933658e-7,"about_ca_topic_score_gemma":0.0000031136176,"teacher_disagreement_score":0.8144382,"about_ca_system_score_codex":0.000011640236,"about_ca_system_score_gemma":0.00021993289,"threshold_uncertainty_score":0.37324345},"labels":[],"label_agreement":null},{"id":"W6963996213","doi":"10.25384/sage.23916432","title":"sj-docx-1-msj-10.1177_13524585231189673 – Supplemental material for Assessing heterogeneity of treatment effect in multiple sclerosis trials","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Multiple sclerosis; Treatment effect; Clinical trial; Randomized controlled trial; Fingolimod; MEDLINE","score_opus":0.8045023425764544,"score_gpt":0.6095039208997886,"score_spread":0.1949984216766658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6963996213","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8142953,0.0004186769,0.034663994,0.0004948732,0.0025243645,0.0044332077,0.14296263,0.00016160401,0.000045333145],"genre_scores_gemma":[0.31284145,0.0018541907,0.6805958,0.000066398025,0.0017652304,0.00046360886,0.002129577,0.00018658626,0.000097125994],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99003917,0.0046142363,0.0033410164,0.0007303898,0.0005709785,0.00070421904],"domain_scores_gemma":[0.90099406,0.0960346,0.0013144688,0.0013639062,0.00008986523,0.00020309922],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03065671,0.00042008012,0.0024702041,0.0002922946,0.00016556912,0.00024647152,0.0009416447,0.00023202322,0.008655898],"category_scores_gemma":[0.13082737,0.00030585282,0.00046273848,0.00046319573,0.00012658001,0.00038291997,0.00063297496,0.00020129699,0.00003599091],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004133819,0.0018877396,0.014732966,0.0012366999,0.0019271056,0.00013822102,0.00026577845,0.00003141179,0.29441595,0.00013216227,0.045330886,0.6357673],"study_design_scores_gemma":[0.060623467,0.0058049355,0.019693043,0.0071012382,0.0033332782,0.000037005837,0.0005541389,0.0077636437,0.63595176,0.25286284,0.0044359807,0.0018386522],"about_ca_topic_score_codex":0.00008946329,"about_ca_topic_score_gemma":0.00008823663,"teacher_disagreement_score":0.64593184,"about_ca_system_score_codex":0.00022991339,"about_ca_system_score_gemma":0.00013118636,"threshold_uncertainty_score":0.9999394},"labels":[],"label_agreement":null},{"id":"W6969384008","doi":"10.5281/zenodo.858835","title":"D5.2 - Report On System Integration And Application Implementation","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Parkinson Canada","funders":"European Commission","keywords":"Deliverable; Software; System integration; Work (physics); Software system; Current (fluid)","score_opus":0.40149042390769996,"score_gpt":0.5169286495282288,"score_spread":0.11543822562052886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969384008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030354887,0.00001320662,0.7668602,0.0020026623,0.00046802434,0.0023326143,0.0003736052,0.0014534107,0.1961414],"genre_scores_gemma":[0.9506069,0.000020759731,0.04776235,0.000053335512,0.00031486707,4.5157432e-7,0.00028766095,0.0007143109,0.00023938114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980272,0.00051419786,0.000493105,0.00042380116,0.000348082,0.00019358478],"domain_scores_gemma":[0.9975437,0.00058898755,0.00048371108,0.00087602256,0.00038512272,0.00012245183],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.003139824,0.00011941987,0.00020380296,0.00008923412,0.0025856157,0.0008389523,0.0005401609,0.00007453601,0.00090998044],"category_scores_gemma":[0.019229127,0.00011269383,0.000037588085,0.00008477994,0.00016702646,0.00017614239,0.00046854472,0.00019345713,0.00072353997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006700419,0.00006679697,0.000010998602,0.00010320609,0.000028068338,0.000015900227,0.00018989357,7.056295e-7,0.0013603002,0.46495852,0.018370394,0.5148282],"study_design_scores_gemma":[0.0037189068,0.0012613903,0.012431254,0.00039892108,0.000211327,0.00069743214,0.002714789,0.0025634808,0.007421095,0.3697723,0.5979629,0.0008462195],"about_ca_topic_score_codex":0.000020849398,"about_ca_topic_score_gemma":6.1431825e-7,"teacher_disagreement_score":0.920252,"about_ca_system_score_codex":0.00013399846,"about_ca_system_score_gemma":0.0000025049899,"threshold_uncertainty_score":0.9987129},"labels":[],"label_agreement":null},{"id":"W6976898610","doi":"10.6084/m9.figshare.19980","title":"Health Care Utilization by Canadian Women-7","year":2011,"lang":"en","type":"other","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health care; MEDLINE; Public health; Health services; Health policy","score_opus":0.6963407803405149,"score_gpt":0.5606089527768968,"score_spread":0.13573182756361812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976898610","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8551987e-8,0.00067322777,0.00004967272,0.00003135715,0.0001930571,0.0005177136,0.58629185,0.00016404278,0.41207904],"genre_scores_gemma":[0.000011903976,0.0000660051,0.1920505,0.0028351732,0.0013142482,0.0011283953,0.14960265,0.0019550154,0.6510361],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980126,0.00035870806,0.00045684728,0.0004067817,0.00023319348,0.00053187204],"domain_scores_gemma":[0.99523705,0.0030626,0.0004345234,0.00056885666,0.00007691186,0.0006200553],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00019676755,0.0002819226,0.0007145117,0.00014848118,0.00005476479,0.000027954451,0.00035362333,0.00058067054,0.87397134],"category_scores_gemma":[0.061525542,0.0002717637,0.00007629348,0.00014109032,0.000011714546,0.000012442233,0.00005647582,0.00029775835,0.0052507287],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019993481,0.000013183792,5.1780125e-7,0.0011404083,0.000028453267,0.0000042069555,0.00020660412,2.0546405e-9,1.362243e-8,0.0005782144,0.98347837,0.014548005],"study_design_scores_gemma":[0.00018223206,0.000055620418,0.0000031940665,0.002566801,0.000008535565,6.203538e-7,0.00005451607,5.906723e-7,0.0000032369476,0.023804765,0.9730629,0.00025700819],"about_ca_topic_score_codex":0.005982864,"about_ca_topic_score_gemma":0.02854656,"teacher_disagreement_score":0.86872065,"about_ca_system_score_codex":0.0004398203,"about_ca_system_score_gemma":0.00069152634,"threshold_uncertainty_score":0.9999735},"labels":[],"label_agreement":null},{"id":"W6976973099","doi":"10.6084/m9.figshare.23632716","title":"Additional file 1 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Phase (matter); Expert system; File format","score_opus":0.8352761008364948,"score_gpt":0.6031552918435796,"score_spread":0.2321208089929152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976973099","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026083023,0.0000064434507,0.00004485563,0.000052985466,0.00003902004,0.0015883672,0.9954725,0.00003977691,0.00014778347],"genre_scores_gemma":[0.005682919,7.0114305e-7,0.80552953,0.000049580445,0.00018901034,0.004891424,0.18313815,0.000054370772,0.0004643344],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750954,0.0005054247,0.0012803432,0.00023234876,0.00029534308,0.0001769977],"domain_scores_gemma":[0.62091285,0.37794647,0.0005907295,0.00021061672,0.00027809368,0.00006125579],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015539186,0.00013157207,0.0007235673,0.00007242733,0.00013004204,0.000014821146,0.00015282416,0.00008161557,0.81745446],"category_scores_gemma":[0.6472503,0.00009155901,0.00012855939,0.00022436545,0.0000529041,0.000014346613,0.00014312836,0.0001142555,0.00013104017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009891579,0.00023250472,0.0000029572989,0.00016638852,0.00013094391,0.00000515713,0.00020189813,3.7715768e-7,0.000032432836,0.00020694692,0.9928058,0.0061156754],"study_design_scores_gemma":[0.02571126,0.0034160218,0.033529107,0.018354503,0.0009189099,0.00002315455,0.0036704096,0.001911523,0.0025206439,0.30818656,0.6004296,0.0013282981],"about_ca_topic_score_codex":4.6460408e-7,"about_ca_topic_score_gemma":0.000003095102,"teacher_disagreement_score":0.8173234,"about_ca_system_score_codex":0.000011636867,"about_ca_system_score_gemma":0.0002209264,"threshold_uncertainty_score":0.37336683},"labels":[],"label_agreement":null},{"id":"W6977085202","doi":"10.6084/m9.figshare.27173670","title":"Additional file 1 of Adaptive designs in clinical trials: a systematic review-part I","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital Research Institute of Manitoba; SickKids Foundation; George & Fay Yee Centre for Healthcare Innovation; University of Toronto; University of Calgary; University of Manitoba; Hospital for Sick Children; University of British Columbia","funders":"","keywords":"Adaptive design; Key (lock); Scheme (mathematics); Matching (statistics)","score_opus":0.9175016093535353,"score_gpt":0.6560205158156046,"score_spread":0.2614810935379307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977085202","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6497215e-8,0.0014855581,0.00016629296,0.000043087537,0.00013797158,0.0018849655,0.99344003,0.000081651015,0.0027603954],"genre_scores_gemma":[0.000007708044,0.00010368287,0.49852547,0.0005700741,0.0010024747,0.016355265,0.48136318,0.00009257415,0.0019795783],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9874081,0.007276334,0.00423435,0.00040476024,0.0004606823,0.00021579686],"domain_scores_gemma":[0.14464942,0.8535474,0.0009532851,0.0004977056,0.00021814254,0.00013407231],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008477778,0.00019549091,0.0024474212,0.000089703,0.000017084512,0.000027299013,0.00030701733,0.00022745681,0.99583936],"category_scores_gemma":[0.9617351,0.00014390748,0.0006718094,0.0004248535,0.000030220534,0.000065146174,0.000102254504,0.0004695904,0.005598573],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014243022,0.0000791194,1.4258423e-8,0.14780119,0.00009255703,0.000034887595,0.000006446669,6.545986e-8,6.4984874e-8,0.000799634,0.8505621,0.0006096828],"study_design_scores_gemma":[0.00016470558,0.00012175486,0.0000046381424,0.80632985,0.00020364505,0.00000636546,0.0000129186865,0.0005520291,0.000003232939,0.13561247,0.056831814,0.00015657386],"about_ca_topic_score_codex":3.1499758e-7,"about_ca_topic_score_gemma":0.0000016756194,"teacher_disagreement_score":0.9902408,"about_ca_system_score_codex":0.00004804847,"about_ca_system_score_gemma":0.0002856894,"threshold_uncertainty_score":0.99517566},"labels":[],"label_agreement":null},{"id":"W6977176236","doi":"10.6084/m9.figshare.12502811","title":"Additional file 1 of Stakeholder perspectives on adaptive clinical trials: a scoping review","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; BC Children's Hospital","funders":"","keywords":"Table (database); Inclusion (mineral); Stakeholder; Key (lock); Table of contents","score_opus":0.9600789659525235,"score_gpt":0.6698040416597687,"score_spread":0.2902749242927548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977176236","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.3766386e-8,0.000591281,0.00014718172,0.0002923029,0.000033247157,0.0012400832,0.99348056,0.00006757189,0.0041476907],"genre_scores_gemma":[0.000010013526,0.00016056283,0.6121504,0.0037415302,0.0018560217,0.0025522253,0.37934005,0.00007312718,0.00011606193],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.99359876,0.003330922,0.001947892,0.00047936113,0.00046084617,0.00018224563],"domain_scores_gemma":[0.24261637,0.7545326,0.0016229483,0.00043574473,0.00049202895,0.00030030173],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017926457,0.00018811837,0.0015678733,0.000024014362,0.000037035024,0.000013214128,0.0002699668,0.00015800347,0.9980463],"category_scores_gemma":[0.9601046,0.0001505473,0.0005363516,0.0002248303,0.000043608998,0.00004749433,0.000115920455,0.0004517761,0.0026597548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008750577,0.00012337934,2.9896388e-8,0.002748465,0.00007196439,0.000007646934,0.000041125335,1.5966951e-7,1.0750255e-7,0.00066013134,0.9905372,0.0057222443],"study_design_scores_gemma":[0.00097637455,0.0011184079,0.000030263767,0.83652073,0.00013773183,0.000001804674,0.0002388873,0.00017053628,0.000015890228,0.05136252,0.109028384,0.00039849462],"about_ca_topic_score_codex":1.0480951e-7,"about_ca_topic_score_gemma":2.5282418e-7,"teacher_disagreement_score":0.99538654,"about_ca_system_score_codex":0.000021371681,"about_ca_system_score_gemma":0.00026588116,"threshold_uncertainty_score":0.9981168},"labels":[],"label_agreement":null},{"id":"W6977183773","doi":"10.6084/m9.figshare.20968244.v1","title":"Additional file 2 of Overestimation of benefit when clinical trials stop early: a simulation study","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Clinical trial; Table (database); MEDLINE; Data collection","score_opus":0.8277903316685217,"score_gpt":0.6361785578634089,"score_spread":0.19161177380511274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977183773","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030642256,0.00000301011,0.00016215797,0.000009001616,0.00008184098,0.0010938878,0.9975771,0.000036533125,0.00073006196],"genre_scores_gemma":[0.023671368,1.2833938e-7,0.3896877,0.00006432031,0.0004683543,0.0031637712,0.5821949,0.00005655535,0.000692901],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99315196,0.0031678192,0.002454735,0.00029543086,0.00079441775,0.00013563645],"domain_scores_gemma":[0.4299701,0.5670546,0.0021015941,0.00044137848,0.00035382196,0.00007846357],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034359538,0.00012955011,0.0009907067,0.000081159626,0.00007772517,0.000012142194,0.0002786954,0.00010137549,0.9972172],"category_scores_gemma":[0.7984992,0.0001233908,0.00032195967,0.00018731202,0.00001894604,0.00006445778,0.0002920071,0.00029924806,0.00017448692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018870962,0.0008877117,0.000013996747,0.00009530544,0.000095024894,0.0000025343697,0.00013417852,0.00042154448,7.699441e-7,0.0002523573,0.98698324,0.010924616],"study_design_scores_gemma":[0.0033859347,0.0027745662,0.022783283,0.0015308111,0.00023921659,0.0000014184684,0.00032977728,0.019041467,0.000023414223,0.8888419,0.060653564,0.0003946204],"about_ca_topic_score_codex":0.0000027342626,"about_ca_topic_score_gemma":0.0000010700779,"teacher_disagreement_score":0.9970427,"about_ca_system_score_codex":0.000038723672,"about_ca_system_score_gemma":0.00012400141,"threshold_uncertainty_score":0.50317305},"labels":[],"label_agreement":null},{"id":"W6977303959","doi":"10.6084/m9.figshare.14451051.v1","title":"Additional file 1 of Intention-to-treat analysis may be more conservative than per protocol analysis in antibiotic non-inferiority trials: a systematic review","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; McMaster University; Juravinski Cancer Centre","funders":"","keywords":"Protocol (science); Antibiotics; MEDLINE; Data collection; Protocol analysis","score_opus":0.5621384658236344,"score_gpt":0.5747946818366167,"score_spread":0.01265621601298239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977303959","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004588158,0.00003100905,0.00036385062,0.00017372804,0.000011056107,0.034687817,0.9642399,0.000030946172,0.00045711495],"genre_scores_gemma":[0.00010874432,0.0000038793564,0.21634246,0.00075425603,0.000060312108,0.2094243,0.57215047,0.00004096815,0.0011146299],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9913864,0.003944068,0.0030470102,0.0006340802,0.00070118404,0.00028725484],"domain_scores_gemma":[0.79035956,0.20465314,0.0019725938,0.0011837602,0.0016052269,0.00022574005],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022062163,0.00033001043,0.0047197817,0.00045968918,0.000052143856,0.000056525758,0.00035982096,0.00019901627,0.97220886],"category_scores_gemma":[0.7776001,0.00025942933,0.0016816892,0.004816505,0.000037673904,0.000083063074,0.00021853198,0.00028078523,0.0004476859],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003636226,0.0003261313,0.0000804522,0.14652866,0.0029324368,0.000042720265,0.000058643996,0.0000027395681,0.0000035883102,0.000034380046,0.8499271,0.000026736261],"study_design_scores_gemma":[0.0015837777,0.00020747188,0.0111411465,0.9451888,0.027980186,0.000008501602,0.00046074443,0.0020197297,0.00039747666,0.0068276897,0.0032017718,0.0009826685],"about_ca_topic_score_codex":0.000017319397,"about_ca_topic_score_gemma":0.000115854076,"teacher_disagreement_score":0.97176117,"about_ca_system_score_codex":0.00011786058,"about_ca_system_score_gemma":0.0003499999,"threshold_uncertainty_score":0.9999858},"labels":[],"label_agreement":null},{"id":"W6977307993","doi":"10.6084/m9.figshare.23632734","title":"Additional file 5 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Phase (matter); Statistical analysis; File format","score_opus":0.832161337517509,"score_gpt":0.60257189033934,"score_spread":0.22958944717816898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977307993","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026291532,0.000006496035,0.000045279383,0.00005294076,0.000039057333,0.0015899555,0.99544924,0.000039797316,0.00014807134],"genre_scores_gemma":[0.005891569,7.180323e-7,0.80706024,0.00005009469,0.00019107613,0.004843808,0.18144293,0.00005487216,0.00046470296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975086,0.0005053077,0.0012813802,0.00023230504,0.0002954103,0.00017700403],"domain_scores_gemma":[0.6238636,0.37499982,0.000589112,0.00020973335,0.0002767157,0.000061074876],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015552733,0.00013157586,0.00072394416,0.000072434115,0.0001301029,0.000014853566,0.00015278219,0.00008161959,0.8109599],"category_scores_gemma":[0.6448359,0.00009155473,0.00012857893,0.00022432522,0.000052917912,0.000014359994,0.00014308601,0.0001142418,0.00012884644],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009917625,0.00023298462,0.0000029634837,0.0001683058,0.00013109251,0.0000052491237,0.00020240198,3.7735788e-7,0.00003231477,0.00021381838,0.9926873,0.0062240325],"study_design_scores_gemma":[0.026351476,0.0034759196,0.03457303,0.018655442,0.0009319298,0.000023535988,0.0037222106,0.0019368593,0.0025813875,0.31533596,0.5910629,0.0013493444],"about_ca_topic_score_codex":4.700434e-7,"about_ca_topic_score_gemma":0.0000031411128,"teacher_disagreement_score":0.8140063,"about_ca_system_score_codex":0.00001164061,"about_ca_system_score_gemma":0.00022045748,"threshold_uncertainty_score":0.37334937},"labels":[],"label_agreement":null},{"id":"W6977319103","doi":"10.6084/m9.figshare.23632740.v1","title":"Additional file 7 of Development of consensus-driven SPIRIT and CONSORT extensions for early phase dose-finding trials: the DEFINE study","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Development (topology); Phase (matter); File format; Key (lock)","score_opus":0.8320903105681303,"score_gpt":0.6025135330286536,"score_spread":0.2295767775394767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977319103","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002628307,0.0000065012473,0.000045342353,0.000052960226,0.00003906442,0.0015897631,0.9954502,0.000039798386,0.0001480769],"genre_scores_gemma":[0.00586372,7.186589e-7,0.8060912,0.00005004288,0.00019090064,0.004834242,0.18245004,0.00005482254,0.00046430566],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99750865,0.00050518586,0.0012814028,0.00023233015,0.0002954145,0.00017703701],"domain_scores_gemma":[0.6237709,0.37509173,0.0005894658,0.00020987669,0.00027693505,0.000061119914],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015552432,0.0001315855,0.0007239527,0.000072439216,0.00013010601,0.000014861429,0.00015279936,0.00008161748,0.80872744],"category_scores_gemma":[0.6423791,0.00009156389,0.00012857169,0.00022432697,0.000052925967,0.0000143618145,0.00014309734,0.000114251896,0.00012912287],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099241144,0.00023318197,0.000002963197,0.00016995247,0.00013121766,0.0000052539626,0.00020284709,3.7828107e-7,0.000032424614,0.00021342654,0.9926449,0.0062641995],"study_design_scores_gemma":[0.026192766,0.003460661,0.033652678,0.01872704,0.00092631363,0.00002338866,0.0036971474,0.0019383047,0.0025768834,0.3149497,0.5925137,0.0013414102],"about_ca_topic_score_codex":4.703402e-7,"about_ca_topic_score_gemma":0.0000031425593,"teacher_disagreement_score":0.81300014,"about_ca_system_score_codex":0.000011642667,"about_ca_system_score_gemma":0.0002205299,"threshold_uncertainty_score":0.37338668},"labels":[],"label_agreement":null},{"id":"W6981444991","doi":"","title":"Effets d'un gradient hydrique expérimental sur la xylogénèse des semis de quatre espèces de conifères","year":2021,"lang":"fr","type":"other","venue":"Archipelago (Université du Québec à Montréal)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Semis; Environmental factor; Zea mays; Forest regeneration; Natural regeneration","score_opus":0.0511340784209909,"score_gpt":0.31277496457358983,"score_spread":0.26164088615259895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981444991","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85662526,0.016602773,0.07261738,0.001914346,0.00075318903,0.0013482108,0.00046531172,0.00027613904,0.049397405],"genre_scores_gemma":[0.18842903,0.005867695,0.74893427,0.00059133355,0.0009894513,0.00007833473,0.00006113139,0.0007771043,0.054271676],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9893338,0.0060453154,0.001148488,0.001334825,0.0006784515,0.001459122],"domain_scores_gemma":[0.93349147,0.063212015,0.000857885,0.0011817822,0.00018545707,0.0010713654],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027219786,0.0011576492,0.0021072547,0.0003310988,0.00060117966,0.00015658596,0.0012673242,0.0011475009,0.023491692],"category_scores_gemma":[0.021370586,0.0012449287,0.0010517332,0.00043076745,0.0018960627,0.00013525678,0.0010160571,0.0014566487,0.0002104959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002009481,0.006875583,0.020661036,0.0056034485,0.007814967,0.02166148,0.25189695,0.00028349453,0.008640809,0.17051508,0.029648464,0.47438923],"study_design_scores_gemma":[0.015835501,0.001835766,0.028236264,0.008698994,0.0059322156,0.0022489948,0.0378937,0.007510014,0.007448786,0.7325229,0.14662482,0.005212036],"about_ca_topic_score_codex":0.1731185,"about_ca_topic_score_gemma":0.3096303,"teacher_disagreement_score":0.67631686,"about_ca_system_score_codex":0.0017211383,"about_ca_system_score_gemma":0.0016575868,"threshold_uncertainty_score":0.9990001},"labels":[],"label_agreement":null},{"id":"W6981778971","doi":"","title":"Federal fiscal snapshot. Impact on and response to snapshot from Canadian Federation of Independent Business. Dan Kelly. President/CEO CFIB","year":2020,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Snapshot (computer storage); Government (linguistics); Fiscal year","score_opus":0.05959140602414402,"score_gpt":0.33605880476056393,"score_spread":0.2764673987364199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981778971","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027360276,0.000048627342,0.000025651423,0.00090109603,0.00041059547,0.0013244656,0.0020412712,0.000067839675,0.9924444],"genre_scores_gemma":[0.016577045,0.00010333181,0.09501316,0.0012470298,0.0006875691,0.000059346687,0.0006558159,0.0003740513,0.88528264],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99583316,0.0008124258,0.0016169673,0.00045678814,0.00084908557,0.00043155128],"domain_scores_gemma":[0.99028754,0.0072992574,0.0009796862,0.0005609497,0.00022245396,0.0006500945],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011537996,0.0005753067,0.0012598954,0.00019612513,0.00010644076,0.0001573662,0.00040595018,0.00075258827,0.2309716],"category_scores_gemma":[0.020011792,0.0005159507,0.0002179369,0.00003053359,0.0001566383,8.0268046e-7,0.00014961725,0.0004898907,0.0006665786],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002370468,0.00006885515,0.000028669812,0.00040016827,0.00017775528,0.00004402512,0.00025797967,0.00010224979,0.0000066513294,0.0001597833,0.9954477,0.0009357137],"study_design_scores_gemma":[0.0012938265,0.000734897,0.0012266461,0.0007408032,0.00014460432,0.000019216328,0.00009881798,0.000044040764,0.00007907854,0.0021217295,0.9929521,0.0005442319],"about_ca_topic_score_codex":0.09979586,"about_ca_topic_score_gemma":0.0514753,"teacher_disagreement_score":0.23030503,"about_ca_system_score_codex":0.00019587265,"about_ca_system_score_gemma":0.00024030889,"threshold_uncertainty_score":0.9997292},"labels":[],"label_agreement":null},{"id":"W6983749278","doi":"","title":"Novel Bayesian approaches for the planning and monitoring phases of clinical studies","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Janssen Pharmaceuticals; Sanofi Pasteur; Massachusetts Institute of Technology; Massachusetts General Hospital; Sanofi; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Bill and Melinda Gates Foundation","keywords":"Bayesian probability; Bayesian inference; Feature (linguistics); Bayes estimator; Bayesian network","score_opus":0.7687956781585763,"score_gpt":0.5821880011586853,"score_spread":0.186607676999891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6983749278","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9429435,0.0061227623,0.0014068428,0.000118476644,0.024789825,0.008701476,0.008310777,0.0010355384,0.006570758],"genre_scores_gemma":[0.27951685,0.0014829113,0.71225315,0.000054519227,0.0011055038,0.001196668,0.000077769284,0.00056182593,0.0037507885],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933806,0.00083771977,0.0032690817,0.0011213165,0.00079591456,0.0005953635],"domain_scores_gemma":[0.83171946,0.16537371,0.001592133,0.00069490593,0.00042933502,0.00019044334],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011904992,0.0006900808,0.0024493423,0.00019199321,0.0008394894,0.00005864306,0.0007095607,0.00091651606,0.000011608309],"category_scores_gemma":[0.29230866,0.0005183497,0.0006728375,0.0003821267,0.00032492843,0.00015924948,0.00024362892,0.0015336261,0.0000047754647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013258903,0.0006025212,0.00025759495,0.004589288,0.003613227,0.000019341676,0.000089176516,0.000022862007,0.0011996572,0.28058508,0.00003184311,0.70766354],"study_design_scores_gemma":[0.002442352,0.00043334023,0.0014994584,0.002702302,0.0020737587,0.0000073536216,0.004813996,0.00017080107,0.011238322,0.972776,0.0010559983,0.00078634557],"about_ca_topic_score_codex":0.000021706572,"about_ca_topic_score_gemma":0.000037409238,"teacher_disagreement_score":0.7108463,"about_ca_system_score_codex":0.00009413266,"about_ca_system_score_gemma":0.00005159568,"threshold_uncertainty_score":0.99972683},"labels":[],"label_agreement":null},{"id":"W6989526962","doi":"","title":"Bolton discrepancy in a selected Canadian population","year":2008,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Population; MEDLINE; Incidence (geometry); Statistical analysis","score_opus":0.1719777575927202,"score_gpt":0.39263538369298445,"score_spread":0.22065762610026426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6989526962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859966,0.000047266985,0.0006980049,0.0002956826,0.0006600068,0.0007854323,0.00017194575,0.00008054826,0.01126453],"genre_scores_gemma":[0.53125787,0.00039045388,0.46137145,0.000029289804,0.00022177392,0.0000029297053,0.00078178727,0.00013172833,0.005812722],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99812317,0.0004220779,0.00034593657,0.00040186264,0.00036985648,0.00033712122],"domain_scores_gemma":[0.9963011,0.0024645247,0.0004616174,0.00036036095,0.00022271385,0.0001896832],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047902105,0.00023652447,0.00079430704,0.0005024965,0.00014497167,0.000010107486,0.0003378211,0.00058071635,0.00006592467],"category_scores_gemma":[0.008121095,0.00031253276,0.00014861976,0.00062151573,0.000056158147,0.00009053817,0.000027748185,0.00048745243,0.000028912998],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039299736,0.0019739473,0.6768829,0.006441448,0.0013178705,0.002758131,0.008538801,0.00003633239,0.00053279335,0.1701062,0.076368056,0.051113542],"study_design_scores_gemma":[0.0008116931,0.00008185948,0.8921325,0.00044538747,0.0001614422,0.0000028569305,0.003608746,0.00015292122,0.000033804477,0.101672314,0.0005234738,0.00037299254],"about_ca_topic_score_codex":0.41241738,"about_ca_topic_score_gemma":0.9967626,"teacher_disagreement_score":0.5843452,"about_ca_system_score_codex":0.0004647145,"about_ca_system_score_gemma":0.00033445042,"threshold_uncertainty_score":0.99993265},"labels":[],"label_agreement":null},{"id":"W6990598074","doi":"","title":"Dose-Response Vol 11, no 1, Front Matter","year":2007,"lang":"en","type":"article","venue":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Massachusetts Amherst; Université de Namur; University of Ottawa; Jiangsu University; University of Rochester; Arizona State University; University of Missouri; Florida International University; University of Miami; AstraZeneca","keywords":"Focus (optics); Nonlinear system; Front (military); Current (fluid); Medical journal","score_opus":0.1722818568170727,"score_gpt":0.4040675713135632,"score_spread":0.2317857144964905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990598074","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49602902,0.00024811283,0.4362882,0.0049242233,0.004867736,0.0026343581,0.0004766499,0.0009115309,0.053620152],"genre_scores_gemma":[0.19547306,0.000031334795,0.78231806,0.00064309477,0.00053006224,0.000002591181,0.000011763531,0.00018023951,0.020809777],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928365,0.0021195456,0.0012178659,0.0011546651,0.001399817,0.0012716027],"domain_scores_gemma":[0.9714961,0.024169039,0.0010157109,0.0016479687,0.0009060969,0.0007650995],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014548065,0.0006606137,0.0014543791,0.0004940422,0.0005438709,0.00011131137,0.0015730824,0.00096944754,0.018101452],"category_scores_gemma":[0.024091113,0.00074266474,0.0007296263,0.0006772221,0.0009550001,0.000756418,0.00054482,0.0014474394,0.0032050915],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.034429885,0.0036438792,0.09727812,0.001134747,0.0022698636,0.0017272402,0.0051339376,0.000051662282,0.013681881,0.019668533,0.8012447,0.01973556],"study_design_scores_gemma":[0.031796377,0.0024956786,0.23561814,0.0021475647,0.002935058,0.00007914074,0.01753817,0.0008196359,0.0028365573,0.30412295,0.39324147,0.0063692513],"about_ca_topic_score_codex":0.00016213229,"about_ca_topic_score_gemma":0.00022429872,"teacher_disagreement_score":0.40800324,"about_ca_system_score_codex":0.0005260899,"about_ca_system_score_gemma":0.00017988587,"threshold_uncertainty_score":0.9995024},"labels":[],"label_agreement":null},{"id":"W6991833884","doi":"","title":"Instruments à lecture directe et analyse de l'air en temps réel","year":2021,"lang":"fr","type":"article","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut de recherche Robert-Sauvé en santé et en sécurité du travail","funders":"","keywords":"Measure (data warehouse); Product (mathematics); Context (archaeology); Focus (optics); Set (abstract data type)","score_opus":0.3376313662404418,"score_gpt":0.5475002428149328,"score_spread":0.209868876574491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991833884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03337474,0.0012230888,0.87170523,0.027734654,0.003628555,0.0004920883,0.00036964146,0.00022583861,0.06124615],"genre_scores_gemma":[0.021292856,0.0006871259,0.9348863,0.004984299,0.000601012,0.000023014418,0.000008687439,0.000075759584,0.037440963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99037015,0.006399336,0.001300747,0.0006859167,0.0005262028,0.00071767205],"domain_scores_gemma":[0.9427199,0.055476632,0.0002651548,0.00084369356,0.00026710297,0.00042756344],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005072294,0.0003964227,0.0011380027,0.00007049453,0.000092291986,0.000112949776,0.0003412143,0.00069911685,0.012753724],"category_scores_gemma":[0.19960293,0.00036077687,0.00041964903,0.00065841665,0.00019487346,0.000106475156,0.00036971492,0.00093319564,0.0005062708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001140858,0.0018616768,0.0069821673,0.0011508449,0.0017487227,0.0005868425,0.0012985687,0.00009297143,0.0026911923,0.62469745,0.021168472,0.337607],"study_design_scores_gemma":[0.0012707019,0.00009155062,0.0027577737,0.00040935478,0.0007908005,0.00006759025,0.0001900359,0.0014380793,0.028575737,0.9385346,0.025436988,0.00043679203],"about_ca_topic_score_codex":0.00025648793,"about_ca_topic_score_gemma":0.00050847273,"teacher_disagreement_score":0.3371702,"about_ca_system_score_codex":0.00026592976,"about_ca_system_score_gemma":0.000572498,"threshold_uncertainty_score":0.9998844},"labels":[],"label_agreement":null},{"id":"W6991850732","doi":"","title":"The Implementation and Feasibility of the Supporting Physical Activity in the Childcare Environment (SPACE) Intervention: A Process Evaluation","year":2018,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Attendance; Intervention (counseling); Physical activity; Schedule; Descriptive statistics; Process (computing); Program evaluation","score_opus":0.5531496796362214,"score_gpt":0.587005985084389,"score_spread":0.033856305448167534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991850732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963654,0.0000072113594,0.0014352563,0.00064599956,0.00011124075,0.0013395948,0.000026896201,0.000013306927,0.000055087898],"genre_scores_gemma":[0.9995223,0.0000047743283,0.00029286847,0.000029059049,0.00008567135,0.00000825763,0.0000011830971,0.000011760688,0.000044108037],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9950614,0.003293728,0.00036759654,0.0003605329,0.0006768168,0.00023992646],"domain_scores_gemma":[0.99429953,0.0043596067,0.0005659433,0.0005844763,0.00014131992,0.000049140566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006305107,0.00016038367,0.0002562155,0.00004854197,0.00032937303,0.00009595147,0.00058258476,0.00006921451,0.000023006076],"category_scores_gemma":[0.0035071862,0.000096489464,0.00013063349,0.00026751758,0.00046897144,0.00033763505,0.0003024512,0.000395097,0.0000036620377],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015617645,0.00028582555,0.9826649,0.00008691285,0.000037890262,0.0000022104289,0.0023292631,0.0000010181652,0.00017971327,0.0013548293,3.4968335e-7,0.0129009215],"study_design_scores_gemma":[0.0011443436,0.00018174452,0.9163459,0.00009645176,0.00016349269,0.0000032949515,0.0031803641,0.000007117648,0.0032585594,0.075504445,0.000011999484,0.000102272286],"about_ca_topic_score_codex":0.000005034939,"about_ca_topic_score_gemma":0.00090638094,"teacher_disagreement_score":0.074149616,"about_ca_system_score_codex":0.00015863228,"about_ca_system_score_gemma":0.000054740667,"threshold_uncertainty_score":0.4198683},"labels":[],"label_agreement":null},{"id":"W6992630466","doi":"","title":"Mexican Witness: Bittersweet Harvest","year":2013,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Event (particle physics); Immigration; Quarter (Canadian coin); Latin Americans","score_opus":0.08057004495590041,"score_gpt":0.3392723441497592,"score_spread":0.2587022991938588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992630466","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009866618,0.00007100944,0.00007530338,0.00025268414,0.00075968873,0.0009456182,0.00039653457,0.0003514576,0.99713784],"genre_scores_gemma":[0.000023489507,0.000099469165,0.18182744,0.0003764917,0.00041527406,0.00005091199,0.000033222703,0.00024694327,0.8169268],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99642086,0.0004401537,0.0016418323,0.00034307782,0.0007050169,0.00044904073],"domain_scores_gemma":[0.99089086,0.0063456027,0.001472361,0.0008326287,0.00020336403,0.00025515867],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010080317,0.00053177465,0.0012192046,0.00010546892,0.000054993186,0.00008537179,0.00063213723,0.0007860252,0.7131134],"category_scores_gemma":[0.01193424,0.00047166142,0.00030109964,0.000012859108,0.00045253243,2.1077504e-7,0.00017628756,0.0004978745,0.026837632],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046535275,0.00008479012,0.0000012403478,0.0010693241,0.00014231066,0.00001246953,0.000046895268,0.0000030991246,1.9798048e-7,0.0040335315,0.9920829,0.00247672],"study_design_scores_gemma":[0.0007144286,0.00015778256,0.000003845499,0.0005809686,0.0001656179,0.000023524166,0.00005292169,0.000010857433,0.000010145838,0.012336407,0.9854499,0.0004935719],"about_ca_topic_score_codex":0.0025532593,"about_ca_topic_score_gemma":0.00030682,"teacher_disagreement_score":0.6862758,"about_ca_system_score_codex":0.000050026556,"about_ca_system_score_gemma":0.000038459602,"threshold_uncertainty_score":0.9997735},"labels":[],"label_agreement":null},{"id":"W7000584010","doi":"","title":"Fool¿s gold, lost treasures, and the randomized clinical trial","year":2013,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Randomized controlled trial; Clinical trial; Clinical endpoint; Randomization; N of 1 trial; Gold standard (test)","score_opus":0.23338819384226103,"score_gpt":0.4268122910467322,"score_spread":0.19342409720447115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000584010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5741323,0.0019557646,0.040314905,0.030508772,0.0062839566,0.035091937,0.0068109874,0.0024086994,0.30249265],"genre_scores_gemma":[0.6397328,0.000483288,0.33481756,0.0059225676,0.0048970017,0.0013243633,0.00011800832,0.0005072551,0.012197184],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9872585,0.007180297,0.0032701243,0.0008338833,0.0007838701,0.0006733326],"domain_scores_gemma":[0.7920901,0.2055283,0.00071115105,0.0009598103,0.000102390855,0.00060821965],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012387022,0.00054382446,0.0024580646,0.00009619957,0.00014958813,0.0023275136,0.00088418747,0.0005048937,0.0023717931],"category_scores_gemma":[0.33196193,0.00030536752,0.0010739588,0.00034034724,0.0021710838,0.0015634156,0.0005767943,0.0013056577,0.0036609336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.5041852,0.00084533414,0.0018577643,0.00010488323,0.0006315692,0.00002309171,0.000023881132,1.09025265e-7,0.0000020038115,0.3657285,0.039732892,0.08686479],"study_design_scores_gemma":[0.33526632,0.00013499374,0.00010818375,0.00005656757,0.00017171566,0.000006433016,0.000010105563,0.00010549957,0.0000174069,0.6540193,0.009831163,0.00027229535],"about_ca_topic_score_codex":0.000006560568,"about_ca_topic_score_gemma":5.7378634e-7,"teacher_disagreement_score":0.3195749,"about_ca_system_score_codex":0.00001962513,"about_ca_system_score_gemma":0.00013619718,"threshold_uncertainty_score":0.99993986},"labels":[],"label_agreement":null},{"id":"W7014010608","doi":"","title":"OPTIMIZED ADAPTIVE ENRICHMENT DESIGNS FOR MULTI-ARM TRIALS: LEARNING WHICH SUBPOPULATIONS BENEFIT FROM DIFFERENT TREATMENTS","year":2018,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Sample size determination; Adaptive design; Type I and type II errors; Sample (material); Disjoint sets; Adaptive control; Computerized adaptive testing; Interim analysis","score_opus":0.8219072492581264,"score_gpt":0.6271974068010037,"score_spread":0.19470984245712275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7014010608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005644624,0.000027327611,0.9850083,0.000092547074,0.00052442536,0.0037142541,0.0043718945,0.000070139,0.0005465119],"genre_scores_gemma":[0.06781724,0.0001407403,0.92925215,0.000008031409,0.00036372436,0.00080512045,0.00015215135,0.00006658682,0.001394232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990072,0.0056994343,0.0018078283,0.00074673374,0.0009939797,0.0006800272],"domain_scores_gemma":[0.80710214,0.1896021,0.00069747417,0.00043189246,0.0018513502,0.0003150165],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006932391,0.00033326633,0.0013633431,0.00056411454,0.0009023541,0.00008553618,0.00034198267,0.0001948274,0.0005891737],"category_scores_gemma":[0.26612014,0.0002786685,0.00026207475,0.0007866484,0.00060825,0.0000528723,0.00020969893,0.0005657766,0.000022175876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.061054848,0.01690121,0.0049689873,0.00071950455,0.009847881,0.000030144522,0.013958499,0.00102008,0.0313544,0.6592631,0.044683423,0.15619797],"study_design_scores_gemma":[0.006831061,0.0049772644,0.0032304307,0.00016245985,0.00034286478,7.232444e-7,0.00041807897,0.13971092,0.008136091,0.8358158,0.00012002999,0.00025430924],"about_ca_topic_score_codex":0.00042665875,"about_ca_topic_score_gemma":0.00042917108,"teacher_disagreement_score":0.25918773,"about_ca_system_score_codex":0.00037541808,"about_ca_system_score_gemma":0.00027009047,"threshold_uncertainty_score":0.99996656},"labels":[],"label_agreement":null},{"id":"W7015017619","doi":"","title":"Response adaptive designs for clinical trials with continuous outcomes","year":2013,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Adaptive design; Randomization; Clinical trial; Research design; Clinical study design; Statistical power; Power (physics); Sequential analysis; Design of experiments","score_opus":0.6383076151992558,"score_gpt":0.5326649859393171,"score_spread":0.10564262925993873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015017619","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50916886,0.00010198612,0.4731486,0.0016300833,0.0026714173,0.009225676,0.0011917682,0.00029339475,0.00256821],"genre_scores_gemma":[0.0059722355,0.000089640685,0.98068845,0.00006160584,0.00018721259,0.000017790719,0.00004558814,0.00011287449,0.0128246145],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9897404,0.0072951335,0.0012250965,0.00073263224,0.0006052808,0.00040149153],"domain_scores_gemma":[0.7682212,0.22728486,0.0027035172,0.00068817934,0.0008718508,0.00023037946],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019853767,0.00046985876,0.003807755,0.00022357804,0.0001942355,0.00003653389,0.00068980514,0.0009894599,0.00010178757],"category_scores_gemma":[0.16301689,0.00042553653,0.0010312356,0.00017713883,0.00034162283,0.00011580001,0.00007299373,0.00061278394,0.000060836897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.33860818,0.004000479,0.022399845,0.0031452065,0.013252333,0.0003762747,0.0023664904,0.000005962369,0.00076358835,0.14384586,0.41249487,0.058740947],"study_design_scores_gemma":[0.028925324,0.012138761,0.25302595,0.0025090487,0.0118616875,0.000006988689,0.102474965,0.00038875642,0.00074611173,0.57530224,0.009799305,0.0028208424],"about_ca_topic_score_codex":0.0001920542,"about_ca_topic_score_gemma":0.013162648,"teacher_disagreement_score":0.5075398,"about_ca_system_score_codex":0.00010929022,"about_ca_system_score_gemma":0.00035552122,"threshold_uncertainty_score":0.99981964},"labels":[],"label_agreement":null},{"id":"W7015230952","doi":"","title":"On the statistical analysis of functional data arising from designed experiments","year":2012,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Test statistic; Permutation (music); Resampling; Robustness (evolution); Statistical hypothesis testing; Factorial; Context (archaeology); Statistic","score_opus":0.5094606217933688,"score_gpt":0.4613210311063714,"score_spread":0.04813959068699741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015230952","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4026893,0.000072850475,0.58740556,0.00016910433,0.0010126366,0.0005493029,0.004833148,0.000042541265,0.0032255475],"genre_scores_gemma":[0.37111664,0.000032142387,0.6251612,0.000034959136,0.00018598948,0.0000013434535,0.0028336758,0.000057045447,0.00057704013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9971705,0.0009189746,0.0004037436,0.0004711083,0.00082400144,0.00021169252],"domain_scores_gemma":[0.9536198,0.044068284,0.00085493864,0.0011801939,0.0001806798,0.00009614389],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015082946,0.00023559338,0.0010184144,0.00023545699,0.00015720978,0.000015548736,0.0008656339,0.00032278107,0.0012557923],"category_scores_gemma":[0.012548691,0.00021914858,0.00022422713,0.00040702434,0.00019870543,0.00008915917,0.00019975788,0.00035786178,0.000032384043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008391792,0.004145296,0.017997576,0.0008935829,0.037908673,0.00007557785,0.0029185964,0.00010256681,0.008074527,0.78967035,0.11639669,0.013424765],"study_design_scores_gemma":[0.0014143279,0.00022824747,0.5702242,0.00041692474,0.0234661,2.4869342e-7,0.024596956,0.003281428,0.0009597382,0.37451053,0.00023080058,0.00067048654],"about_ca_topic_score_codex":0.0009493442,"about_ca_topic_score_gemma":0.017660594,"teacher_disagreement_score":0.55222666,"about_ca_system_score_codex":0.00008016348,"about_ca_system_score_gemma":0.00008039072,"threshold_uncertainty_score":0.9996572},"labels":[],"label_agreement":null},{"id":"W7024350063","doi":"","title":"Rhetoric and Settler Inertia: Strategies of Canadian Decolonization","year":2019,"lang":"en","type":"article","venue":"Digital Commons - CSUMB (California State University, Monterey Bay)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rhetoric; Decolonization; Indigenous; Colonialism; Kingdom","score_opus":0.13441892854491386,"score_gpt":0.35330652910292837,"score_spread":0.2188876005580145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024350063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91984826,0.00002453496,0.012269318,0.00045804554,0.00027229637,0.0006418082,0.004629227,0.00010076125,0.06175576],"genre_scores_gemma":[0.98399353,0.000036559,0.014808976,0.000035533656,0.000017995077,8.580404e-7,0.0000428862,0.00003480138,0.0010288715],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99832827,0.00021076505,0.0004917055,0.000350566,0.00024107954,0.0003776011],"domain_scores_gemma":[0.9948234,0.0039733755,0.00024175868,0.00041385862,0.00021073401,0.00033687454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003507499,0.00023812217,0.0005583789,0.0005104014,0.00009840749,0.00014337778,0.0003407562,0.00015249006,0.00015777902],"category_scores_gemma":[0.0020910713,0.00024032492,0.000106151754,0.0006236315,0.00020923585,0.00043488914,0.00024010995,0.00023526355,0.00006421306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081517384,0.00078447285,0.5231062,0.0009456994,0.0008107097,0.00027373782,0.0011574934,0.00016538099,0.00015225126,0.44360396,0.0142582385,0.0139267035],"study_design_scores_gemma":[0.0048777987,0.0009664778,0.057801146,0.00038868317,0.00031289624,0.000023729219,0.0031024588,0.0023159138,0.00022005918,0.87519944,0.05353046,0.0012609251],"about_ca_topic_score_codex":0.00339688,"about_ca_topic_score_gemma":0.03507487,"teacher_disagreement_score":0.46530503,"about_ca_system_score_codex":0.0001554158,"about_ca_system_score_gemma":0.00017850232,"threshold_uncertainty_score":0.9825325},"labels":[],"label_agreement":null},{"id":"W7025285267","doi":"","title":"Utility comparisons naturalized","year":2006,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"","keywords":"Assertion; Proposition; Nothing; Metaphysics; Worry; Philosophy of science; Meaning (existential)","score_opus":0.28914056662929893,"score_gpt":0.4407403858934052,"score_spread":0.15159981926410626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025285267","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68908083,0.00043235923,0.077952646,0.0012249799,0.005982567,0.0028694223,0.0013175533,0.0007762776,0.22036338],"genre_scores_gemma":[0.06421263,0.000059433518,0.92086035,0.000019339413,0.00019907863,8.0031907e-7,0.0002684672,0.00007196564,0.014307946],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997597,0.0006278227,0.0004144587,0.00048489796,0.00057694974,0.00029891904],"domain_scores_gemma":[0.989236,0.008846496,0.000860003,0.00062386243,0.00032041833,0.00011325067],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008674032,0.00031278186,0.001262423,0.00015378992,0.00018451364,0.000018541372,0.00062516227,0.00068322354,0.00017656012],"category_scores_gemma":[0.0060687596,0.0003775902,0.0004330098,0.00025400583,0.00020894187,0.00006850031,0.000095480274,0.0007056586,0.00006820983],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002650883,0.0014515088,0.016063761,0.003955254,0.0009384522,0.00016805835,0.00039018193,0.0000031087586,0.00044999164,0.14858042,0.8162092,0.009139177],"study_design_scores_gemma":[0.0033978675,0.0001815503,0.3633885,0.0007782229,0.0018149602,0.000002637564,0.012881353,0.00058528135,0.0007902545,0.588234,0.026823541,0.0011218175],"about_ca_topic_score_codex":0.001631278,"about_ca_topic_score_gemma":0.2304232,"teacher_disagreement_score":0.8429077,"about_ca_system_score_codex":0.00007509417,"about_ca_system_score_gemma":0.000105309264,"threshold_uncertainty_score":0.9998676},"labels":[],"label_agreement":null},{"id":"W7065495365","doi":"","title":"Estimating multinomial cell probabilities using normalized beta kernels","year":2010,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"BETA (programming language); Multinomial distribution; Beta distribution; Bayesian probability; Measure (data warehouse)","score_opus":0.23898401376487788,"score_gpt":0.41458288020447087,"score_spread":0.175598866439593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7065495365","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95414776,0.000021130796,0.03468805,0.000058015958,0.0023571984,0.0010099143,0.00017786863,0.00014156457,0.007398486],"genre_scores_gemma":[0.016704177,0.0000068035833,0.9812095,0.000006348134,0.00034120568,0.0000010998881,0.000040977287,0.0000740281,0.0016158276],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973438,0.0005273829,0.0005686867,0.0005809569,0.0005750403,0.00040416134],"domain_scores_gemma":[0.9881274,0.009279394,0.0013825336,0.00064567855,0.0004079971,0.00015699978],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001523358,0.00040780887,0.0012688258,0.00018955751,0.00030758255,0.000042039796,0.00068850355,0.0008992043,0.00015306448],"category_scores_gemma":[0.008657715,0.0005017583,0.000409337,0.00017556037,0.00027696392,0.00015573115,0.00017770249,0.0009958729,0.000032677275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.023786718,0.0137283085,0.06010287,0.15546314,0.006958749,0.0017112159,0.06009506,0.0020646763,0.2958741,0.2481185,0.030323748,0.101772904],"study_design_scores_gemma":[0.010962268,0.0006756528,0.017963085,0.0033676515,0.005306917,0.000017305347,0.060329836,0.03721218,0.022134766,0.83746845,0.0008987726,0.0036630959],"about_ca_topic_score_codex":0.0015018579,"about_ca_topic_score_gemma":0.044728693,"teacher_disagreement_score":0.94652146,"about_ca_system_score_codex":0.00013723133,"about_ca_system_score_gemma":0.00022260364,"threshold_uncertainty_score":0.9997434},"labels":[],"label_agreement":null},{"id":"W7084039312","doi":"10.5281/zenodo.17242782","title":"CANADA 🇨🇦, AUSTRALIA 🇦🇺,UK 🇬🇧 WORK VISAS AVAILABLE CALL OR WHATSAPP MR PETER OBENDE ON ☎(08143870581).","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics)","score_opus":0.3707503818119267,"score_gpt":0.43682678163969746,"score_spread":0.06607639982777075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084039312","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014166688,0.00004166921,0.004777104,0.0004771217,0.0009947467,0.0012228298,0.0026167512,0.00089584786,0.9889598],"genre_scores_gemma":[0.00025596615,0.000106177664,0.037127063,0.0005758832,0.0007182747,3.0109763e-7,0.00037563703,0.00625565,0.9545851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99473435,0.0015569779,0.00086604164,0.0010263472,0.0010334236,0.0007828339],"domain_scores_gemma":[0.994497,0.0027475385,0.00045599986,0.0014183368,0.00046133014,0.00041978154],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017776212,0.00051034393,0.00084260415,0.00033626292,0.0007001768,0.0006792143,0.0018327323,0.00043531702,0.48679683],"category_scores_gemma":[0.043152805,0.00045202122,0.0001371014,0.00074849237,0.00024638922,0.000048371832,0.0012164932,0.0010293358,0.028130569],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000218097,0.00014117622,0.0000011172314,0.00036522665,0.00020817657,0.000097895485,0.000029516763,0.0000014832386,0.000013734755,0.0147139095,0.976026,0.00818367],"study_design_scores_gemma":[0.00074664387,0.00022381647,0.0000151638915,0.000761056,0.00011306303,0.000012318702,0.000018686189,0.000008155746,0.00006902583,0.0060237567,0.9915363,0.0004719985],"about_ca_topic_score_codex":0.010055153,"about_ca_topic_score_gemma":0.0013497656,"teacher_disagreement_score":0.45866624,"about_ca_system_score_codex":0.0005480698,"about_ca_system_score_gemma":0.000091535745,"threshold_uncertainty_score":0.9997932},"labels":[],"label_agreement":null},{"id":"W7087452629","doi":"10.17613/g4ntc-3sr03","title":"join the illuminati and become rich+27633832074,UK,USA,SOUTH AFRICA","year":2025,"lang":"en","type":"article","venue":"Knowledge Commons (Lakehead University)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Order (exchange); Variety (cybernetics); Power (physics); MAGIC (telescope); Notice; Poverty; Great power; Work (physics)","score_opus":0.28816887523649953,"score_gpt":0.42223082058062245,"score_spread":0.1340619453441229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7087452629","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13164541,0.0006528717,0.060507327,0.0025959755,0.0013160456,0.0011271056,0.00020024415,0.00026749494,0.80168754],"genre_scores_gemma":[0.9198603,0.0000057827556,0.020603662,0.000024259773,0.00011134814,0.0000064916667,0.0000018373321,0.00003229554,0.05935401],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969167,0.0013932438,0.00051338965,0.00050917413,0.00020715395,0.00046034087],"domain_scores_gemma":[0.9652414,0.033205703,0.00018565834,0.0009176054,0.000255762,0.00019388026],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015849161,0.00031215113,0.00070257316,0.00040792182,0.000576803,0.00007315747,0.0008654109,0.00021937345,0.00034146282],"category_scores_gemma":[0.016115725,0.00025446387,0.0001812952,0.0015103333,0.00083547924,0.000078390076,0.0008657357,0.0006315617,0.00011868659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008952588,0.00031002195,0.011395093,0.00016275576,0.00019306167,0.000051703704,0.0019785492,3.537242e-7,0.00003072394,0.9553233,0.02230479,0.00816013],"study_design_scores_gemma":[0.0027272163,0.00018191474,0.022647098,0.0003562522,0.0007853408,0.0000069350763,0.0011492424,0.00014165204,0.00021298607,0.63116354,0.34002322,0.000604622],"about_ca_topic_score_codex":0.000008402947,"about_ca_topic_score_gemma":0.004117008,"teacher_disagreement_score":0.7882149,"about_ca_system_score_codex":0.00015357675,"about_ca_system_score_gemma":0.00014920428,"threshold_uncertainty_score":0.99999076},"labels":[],"label_agreement":null},{"id":"W71138283","doi":"10.1023/a:1014464505261","title":"Information Tools for Exploratory Data Analysis in Population Pharmacokinetics","year":2001,"lang":"en","type":"article","venue":"Journal of Pharmacokinetics and Pharmacodynamics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Exploratory data analysis; Covariate; Computer science; Context (archaeology); Population; Statistical graphics; Data science; Data mining; Medical physics; Statistics; Econometrics; Medicine; Machine learning; Mathematics; Geography; Environmental health","score_opus":0.44772367363832377,"score_gpt":0.5524062716429492,"score_spread":0.10468259800462543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W71138283","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3698601,0.0003194638,0.62175685,0.0004906582,0.005692329,0.000845994,0.00081985584,0.00003589041,0.00017883016],"genre_scores_gemma":[0.65163857,0.004730757,0.34044498,0.00044688873,0.0025402766,0.000018092685,0.0001177413,0.00004580628,0.000016915259],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99611807,0.00042238686,0.00228666,0.00023320159,0.000588124,0.00035154703],"domain_scores_gemma":[0.9842838,0.013183314,0.0013327037,0.00037231905,0.0005674834,0.00026038],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0050168745,0.0002798018,0.0008759574,0.0006559201,0.0000751073,0.00018684448,0.00067783205,0.00014509649,0.00007772968],"category_scores_gemma":[0.009805835,0.0002552127,0.00019879603,0.0009712436,0.000076268065,0.0013689839,0.00019788262,0.00053825625,0.0000010942094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008198136,0.0027665615,0.047596164,0.0019652501,0.007130429,0.00023361419,0.0021087942,0.023007134,0.013347229,0.021639755,0.03688536,0.8351216],"study_design_scores_gemma":[0.011188667,0.00032034234,0.0043095923,0.000104676794,0.0064318413,0.000054728334,0.00023200118,0.80854046,0.00065820274,0.13487674,0.03259524,0.0006875272],"about_ca_topic_score_codex":0.000006322486,"about_ca_topic_score_gemma":0.0000063600132,"teacher_disagreement_score":0.83443403,"about_ca_system_score_codex":0.00008154393,"about_ca_system_score_gemma":0.000064674256,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W7116688526","doi":"10.1200/po-25-00507","title":"Master Protocol Design With Hybrid Control for Efficient Early-Phase Trial Consolidation","year":2025,"lang":"en","type":"article","venue":"JCO Precision Oncology","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Protocol (science); Consolidation (business); Control (management); Hybrid system; Bayesian probability; Control system","score_opus":0.5109775295074659,"score_gpt":0.6108634696134609,"score_spread":0.09988594010599505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116688526","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025202972,0.0000012341997,0.83409685,0.0005379752,0.00074292405,0.16050352,0.000065576,0.00007980875,0.001451813],"genre_scores_gemma":[0.010151039,2.8200017e-7,0.8002053,0.0004226485,0.0002631888,0.1882428,0.0000018279048,0.000030502808,0.0006824465],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948176,0.0024724961,0.0014379256,0.0005654692,0.0003278017,0.00037868],"domain_scores_gemma":[0.870138,0.12839814,0.00051399943,0.0004671239,0.00037057823,0.0001121705],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0071098823,0.00023789491,0.0010261326,0.00016033924,0.00012566804,0.00005913107,0.00029929867,0.0002778498,0.00034897125],"category_scores_gemma":[0.08103342,0.00016636336,0.00015403154,0.00017929912,0.00019786262,0.000039787785,0.00007613523,0.00026739185,0.000035929097],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6082537,0.004277406,0.000013204995,0.00017852653,0.00024028926,0.000031033018,0.00007939844,0.00018582902,0.0005541914,0.05660319,0.025760887,0.30382237],"study_design_scores_gemma":[0.32249096,0.015583454,0.0000146630855,0.00016249408,0.0002985418,0.0000063005814,0.000014817139,0.011113655,0.004905131,0.6168429,0.028327417,0.00023965944],"about_ca_topic_score_codex":0.0000012745711,"about_ca_topic_score_gemma":9.4874673e-7,"teacher_disagreement_score":0.56023973,"about_ca_system_score_codex":0.00018030909,"about_ca_system_score_gemma":0.00045468024,"threshold_uncertainty_score":0.92670745},"labels":[],"label_agreement":null},{"id":"W7116732864","doi":"10.2139/ssrn.5937835","title":"Adaptive versus Fixed Designs in Confirmatory Clinical Trials: Centering the Choice on Ethics","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Adaptive design; Matching (statistics); Research design; Process (computing); Engineering design process; Clinical study design; Construct (python library); Adaptation (eye)","score_opus":0.8886305187440243,"score_gpt":0.6777312076702561,"score_spread":0.21089931107376825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116732864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009304811,0.0029183321,0.9342521,0.010437051,0.029891744,0.004968853,0.00032797444,0.000258102,0.007641039],"genre_scores_gemma":[0.38385856,0.085855864,0.49205106,0.0059843226,0.025779435,0.0010212071,0.000025692538,0.00072250684,0.004701337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93892354,0.049318068,0.006226843,0.0010621496,0.0013110059,0.0031584243],"domain_scores_gemma":[0.35089934,0.6434798,0.0035002052,0.0014022267,0.00044253154,0.00027588895],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.2090066,0.00066680956,0.002824511,0.00026860563,0.00034403094,0.00017547816,0.0018397282,0.0018628745,0.00009464974],"category_scores_gemma":[0.6090799,0.0004673469,0.0013156999,0.0002663634,0.0003979791,0.000052656498,0.0007798272,0.046521552,0.000026097927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00533759,0.0005661333,0.0001947421,0.00017551219,0.0021732347,0.000026168931,0.00032455093,0.00018423866,0.0000039266056,0.9354872,0.00093949697,0.054587197],"study_design_scores_gemma":[0.005628149,0.00090223143,0.00013436061,0.0013831413,0.00064783427,0.0000129309965,0.0008127871,0.00076420186,0.000021290629,0.9882214,0.0010490955,0.00042257016],"about_ca_topic_score_codex":0.00006741519,"about_ca_topic_score_gemma":0.0007370512,"teacher_disagreement_score":0.59416175,"about_ca_system_score_codex":0.0022075106,"about_ca_system_score_gemma":0.011402665,"threshold_uncertainty_score":0.99977785},"labels":[],"label_agreement":null},{"id":"W7117115668","doi":"10.3390/stats9010001","title":"A Proportional Hazards Mixture Cure Model for Subgroup Analysis: Inferential Method and an Application to Colon Cancer Data","year":2025,"lang":"en","type":"article","venue":"Stats","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Levamisole; Cure rate; Colorectal cancer; Proportional hazards model; Cancer; Mixture model; Maximum likelihood","score_opus":0.4864509021177346,"score_gpt":0.6537123222113409,"score_spread":0.16726142009360628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117115668","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032212336,0.000031662104,0.9901848,0.0011524041,0.0001301793,0.0013087202,0.0038563358,0.00005172691,0.00006295944],"genre_scores_gemma":[0.034176815,0.000014061987,0.96410406,0.0003498952,0.00015911841,0.0006452684,0.00020636148,0.000016930542,0.00032748864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980416,0.00028090863,0.00057724764,0.0006415588,0.0002514833,0.0002071431],"domain_scores_gemma":[0.99415255,0.004539355,0.0001778579,0.0007444232,0.00025357396,0.00013222851],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024208608,0.00014996932,0.00051701313,0.00012872601,0.00009578479,0.000054071385,0.00033682864,0.00015159567,0.000040747196],"category_scores_gemma":[0.009016977,0.0001289291,0.00006644255,0.00046348898,0.00004987945,0.00009616176,0.00021244705,0.00014357138,7.9550404e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009465462,0.00049614446,0.0010517874,0.00061882514,0.0015129189,0.0000010419297,0.0004323133,0.0021137875,0.0015861361,0.75728756,0.021119108,0.21283385],"study_design_scores_gemma":[0.00035404076,0.000036570324,0.0003630393,0.000017420056,0.0009966388,8.966399e-8,0.000010424975,0.41760796,0.00012990834,0.5798044,0.0005863996,0.000093082665],"about_ca_topic_score_codex":0.000046047953,"about_ca_topic_score_gemma":0.0006292964,"teacher_disagreement_score":0.41549417,"about_ca_system_score_codex":0.00004247276,"about_ca_system_score_gemma":0.00022509888,"threshold_uncertainty_score":0.9993305},"labels":[],"label_agreement":null},{"id":"W7117654090","doi":"10.6084/m9.figshare.30969710","title":"Additional file 3 of Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Bayesian inference; Bayesian statistics; Key (lock); Statistical model","score_opus":0.5519478193213218,"score_gpt":0.5565899054538088,"score_spread":0.004642086132487067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117654090","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003632763,0.015122968,0.0030689742,0.000009121664,0.0001468778,0.008268716,0.9729826,0.000023162354,0.00037393946],"genre_scores_gemma":[0.000039341823,0.00029586317,0.9083549,0.00012278903,0.00012240156,0.007213335,0.08367219,0.00007636177,0.000102813385],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9732549,0.01763828,0.00708525,0.00086557446,0.0006165413,0.0005394221],"domain_scores_gemma":[0.40043622,0.59253365,0.00504865,0.0011848161,0.0006120445,0.00018465084],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047925306,0.00075157895,0.009341769,0.00035605588,0.00007717129,0.000039588922,0.0005910805,0.00053287426,0.879951],"category_scores_gemma":[0.84763217,0.00063415896,0.0015977285,0.0012501308,0.00006388562,0.00012403622,0.00041760295,0.00035852968,0.00008960512],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015516498,0.0004723165,4.0105218e-7,0.76148194,0.001705307,0.000017369997,0.000056960624,0.000051094947,0.000013412414,0.00043407347,0.22611606,0.009495907],"study_design_scores_gemma":[0.0012633539,0.00062938244,0.000022628496,0.9560905,0.002692487,0.0000043584005,0.00003109093,0.0042313966,0.0020476608,0.03227116,0.00032225053,0.00039369284],"about_ca_topic_score_codex":0.000020570178,"about_ca_topic_score_gemma":0.00001649157,"teacher_disagreement_score":0.90528595,"about_ca_system_score_codex":0.000848492,"about_ca_system_score_gemma":0.0010176544,"threshold_uncertainty_score":0.99961096},"labels":[],"label_agreement":null},{"id":"W7117703714","doi":"10.6084/m9.figshare.30969704.v1","title":"Additional file 1 of Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Feature selection; Bayesian inference; Key (lock); Feature (linguistics)","score_opus":0.5567253635126055,"score_gpt":0.5572036937736271,"score_spread":0.00047833026102162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117703714","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003606255,0.015045661,0.003051625,0.00000916342,0.00014548992,0.008268093,0.97308147,0.000023189428,0.00037173132],"genre_scores_gemma":[0.00003876493,0.00029058655,0.9072605,0.0001223995,0.00012054783,0.00731896,0.08467171,0.00007606642,0.000100464924],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9732457,0.017651858,0.0070809834,0.0008658039,0.0006163152,0.0005393737],"domain_scores_gemma":[0.3988532,0.59412575,0.0050444007,0.0011857576,0.0006063433,0.00018453953],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047946665,0.00075168343,0.009340835,0.00035617332,0.00007717784,0.000039508734,0.00059144787,0.000532919,0.88252735],"category_scores_gemma":[0.84766644,0.00063431857,0.0015978292,0.0012505886,0.00006388113,0.00012394201,0.00041790126,0.00035860206,0.0000886475],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015388451,0.00047141983,3.9956586e-7,0.75435525,0.00170266,0.00001712481,0.000056822817,0.000050957926,0.000013347644,0.0004357368,0.23340385,0.009338559],"study_design_scores_gemma":[0.0012466512,0.0006304217,0.000022770302,0.9562165,0.002717278,0.0000044001517,0.000031245738,0.0042258925,0.0020052947,0.03218955,0.0003162292,0.0003937554],"about_ca_topic_score_codex":0.000020342066,"about_ca_topic_score_gemma":0.000016381591,"teacher_disagreement_score":0.9042089,"about_ca_system_score_codex":0.0008451818,"about_ca_system_score_gemma":0.0010170992,"threshold_uncertainty_score":0.9996108},"labels":[],"label_agreement":null},{"id":"W7117711590","doi":"10.6084/m9.figshare.30969707.v1","title":"Additional file 2 of Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Missing data; Bayesian inference; Key (lock); Bayesian statistics","score_opus":0.5481439583913437,"score_gpt":0.556499015349742,"score_spread":0.008355056958398333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117711590","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035819503,0.015275311,0.0029872216,0.00000911579,0.00014630027,0.008252681,0.9729226,0.000023180764,0.00037996465],"genre_scores_gemma":[0.00003833491,0.0002995461,0.9066066,0.00012300325,0.00012289251,0.0072173607,0.085414656,0.000076332835,0.00010128125],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.97324544,0.01764865,0.007085094,0.00086529384,0.00061625335,0.0005392571],"domain_scores_gemma":[0.4024787,0.5905023,0.0050474373,0.0011826309,0.0006045638,0.00018437281],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004769154,0.00075144955,0.009343053,0.00035594503,0.00007718338,0.0000395927,0.0005911257,0.00053292204,0.88058233],"category_scores_gemma":[0.84612453,0.00063411565,0.001597527,0.0012496378,0.000063880274,0.00012402516,0.00041784372,0.00035852124,0.000087721324],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015305658,0.00047124614,3.8713492e-7,0.75719523,0.0017025927,0.000017582755,0.000056866964,0.00005119521,0.000012894264,0.0004432197,0.230304,0.009591694],"study_design_scores_gemma":[0.001257294,0.0006316779,0.000022452201,0.95592546,0.0027126078,0.000004417777,0.000030989977,0.004205995,0.0019967426,0.03248998,0.00032871845,0.00039366484],"about_ca_topic_score_codex":0.000020542782,"about_ca_topic_score_gemma":0.000016476526,"teacher_disagreement_score":0.90361935,"about_ca_system_score_codex":0.0008454187,"about_ca_system_score_gemma":0.001012671,"threshold_uncertainty_score":0.999611},"labels":[],"label_agreement":null},{"id":"W7117731703","doi":"10.6084/m9.figshare.30969707","title":"Additional file 2 of Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Missing data; Bayesian inference; Key (lock); Bayesian statistics","score_opus":0.5481439583913437,"score_gpt":0.556499015349742,"score_spread":0.008355056958398333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117731703","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035819503,0.015275311,0.0029872216,0.00000911579,0.00014630027,0.008252681,0.9729226,0.000023180764,0.00037996465],"genre_scores_gemma":[0.00003833491,0.0002995461,0.9066066,0.00012300325,0.00012289251,0.0072173607,0.085414656,0.000076332835,0.00010128125],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.97324544,0.01764865,0.007085094,0.00086529384,0.00061625335,0.0005392571],"domain_scores_gemma":[0.4024787,0.5905023,0.0050474373,0.0011826309,0.0006045638,0.00018437281],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004769154,0.00075144955,0.009343053,0.00035594503,0.00007718338,0.0000395927,0.0005911257,0.00053292204,0.88058233],"category_scores_gemma":[0.84612453,0.00063411565,0.001597527,0.0012496378,0.000063880274,0.00012402516,0.00041784372,0.00035852124,0.000087721324],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015305658,0.00047124614,3.8713492e-7,0.75719523,0.0017025927,0.000017582755,0.000056866964,0.00005119521,0.000012894264,0.0004432197,0.230304,0.009591694],"study_design_scores_gemma":[0.001257294,0.0006316779,0.000022452201,0.95592546,0.0027126078,0.000004417777,0.000030989977,0.004205995,0.0019967426,0.03248998,0.00032871845,0.00039366484],"about_ca_topic_score_codex":0.000020542782,"about_ca_topic_score_gemma":0.000016476526,"teacher_disagreement_score":0.90361935,"about_ca_system_score_codex":0.0008454187,"about_ca_system_score_gemma":0.001012671,"threshold_uncertainty_score":0.999611},"labels":[],"label_agreement":null},{"id":"W7117775314","doi":"10.6084/m9.figshare.30969710.v1","title":"Additional file 3 of Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Bayesian inference; Bayesian statistics; Key (lock); Statistical model","score_opus":0.5519478193213218,"score_gpt":0.5565899054538088,"score_spread":0.004642086132487067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117775314","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003632763,0.015122968,0.0030689742,0.000009121664,0.0001468778,0.008268716,0.9729826,0.000023162354,0.00037393946],"genre_scores_gemma":[0.000039341823,0.00029586317,0.9083549,0.00012278903,0.00012240156,0.007213335,0.08367219,0.00007636177,0.000102813385],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9732549,0.01763828,0.00708525,0.00086557446,0.0006165413,0.0005394221],"domain_scores_gemma":[0.40043622,0.59253365,0.00504865,0.0011848161,0.0006120445,0.00018465084],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047925306,0.00075157895,0.009341769,0.00035605588,0.00007717129,0.000039588922,0.0005910805,0.00053287426,0.879951],"category_scores_gemma":[0.84763217,0.00063415896,0.0015977285,0.0012501308,0.00006388562,0.00012403622,0.00041760295,0.00035852968,0.00008960512],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015516498,0.0004723165,4.0105218e-7,0.76148194,0.001705307,0.000017369997,0.000056960624,0.000051094947,0.000013412414,0.00043407347,0.22611606,0.009495907],"study_design_scores_gemma":[0.0012633539,0.00062938244,0.000022628496,0.9560905,0.002692487,0.0000043584005,0.00003109093,0.0042313966,0.0020476608,0.03227116,0.00032225053,0.00039369284],"about_ca_topic_score_codex":0.000020570178,"about_ca_topic_score_gemma":0.00001649157,"teacher_disagreement_score":0.90528595,"about_ca_system_score_codex":0.000848492,"about_ca_system_score_gemma":0.0010176544,"threshold_uncertainty_score":0.99961096},"labels":[],"label_agreement":null},{"id":"W7117781331","doi":"10.6084/m9.figshare.30969704","title":"Additional file 1 of Who benefits? Uncovering hidden heterogeneity of treatment effects in adaptive trials using Bayesian methods: a systematic review","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Bayesian probability; Feature selection; Bayesian inference; Key (lock); Feature (linguistics)","score_opus":0.5567253635126055,"score_gpt":0.5572036937736271,"score_spread":0.00047833026102162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117781331","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003606255,0.015045661,0.003051625,0.00000916342,0.00014548992,0.008268093,0.97308147,0.000023189428,0.00037173132],"genre_scores_gemma":[0.00003876493,0.00029058655,0.9072605,0.0001223995,0.00012054783,0.00731896,0.08467171,0.00007606642,0.000100464924],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9732457,0.017651858,0.0070809834,0.0008658039,0.0006163152,0.0005393737],"domain_scores_gemma":[0.3988532,0.59412575,0.0050444007,0.0011857576,0.0006063433,0.00018453953],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047946665,0.00075168343,0.009340835,0.00035617332,0.00007717784,0.000039508734,0.00059144787,0.000532919,0.88252735],"category_scores_gemma":[0.84766644,0.00063431857,0.0015978292,0.0012505886,0.00006388113,0.00012394201,0.00041790126,0.00035860206,0.0000886475],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015388451,0.00047141983,3.9956586e-7,0.75435525,0.00170266,0.00001712481,0.000056822817,0.000050957926,0.000013347644,0.0004357368,0.23340385,0.009338559],"study_design_scores_gemma":[0.0012466512,0.0006304217,0.000022770302,0.9562165,0.002717278,0.0000044001517,0.000031245738,0.0042258925,0.0020052947,0.03218955,0.0003162292,0.0003937554],"about_ca_topic_score_codex":0.000020342066,"about_ca_topic_score_gemma":0.000016381591,"teacher_disagreement_score":0.9042089,"about_ca_system_score_codex":0.0008451818,"about_ca_system_score_gemma":0.0010170992,"threshold_uncertainty_score":0.9996108},"labels":[],"label_agreement":null},{"id":"W7124828996","doi":"10.1007/s12630-025-03061-8","title":"In reply: Designing and reporting a noninferiority trial: points to ponder","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Anesthesia/Journal canadien d anesthésie","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Sinai Health System; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Key (lock); Set (abstract data type); Perspective (graphical); Point (geometry); Data collection","score_opus":0.2155244012491319,"score_gpt":0.4448520912783043,"score_spread":0.2293276900291724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124828996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9711993,0.00027535777,0.0033944538,0.022396237,0.001138533,0.0006703536,0.0000047869958,0.0000131495335,0.00090784533],"genre_scores_gemma":[0.6210793,0.000035322457,0.37458202,0.0022218574,0.0011160934,0.000016232621,3.7340882e-7,0.00010026132,0.0008485338],"study_design_codex":"case_report","study_design_gemma":"case_report","domain_scores_codex":[0.9925912,0.001072001,0.004463744,0.0003908882,0.00048754705,0.0009945956],"domain_scores_gemma":[0.98552465,0.0071511758,0.0032440543,0.00045395122,0.0008266136,0.0027995547],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.021329053,0.00036708015,0.0016404162,0.0015262241,0.00036028615,0.00035889808,0.000583857,0.00027540492,0.00015483065],"category_scores_gemma":[0.14130916,0.00033510296,0.00028443124,0.0009938143,0.00020458632,0.00033053913,0.000027749344,0.0013893114,0.000003860571],"study_design_candidate":"case_report","study_design_consensus":"case_report","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037976797,0.000096381016,0.00988459,0.00016101595,0.00019817844,0.943451,0.001998912,0.00002937265,0.00006036737,0.018136311,0.014931808,0.007254387],"study_design_scores_gemma":[0.00892569,0.0010553382,0.0037201555,0.0011288673,0.00018668931,0.62413543,0.00065558474,0.000015765194,0.00010775252,0.35579452,0.0038490784,0.00042514075],"about_ca_topic_score_codex":0.003789717,"about_ca_topic_score_gemma":0.007580075,"teacher_disagreement_score":0.37118757,"about_ca_system_score_codex":0.0009703752,"about_ca_system_score_gemma":0.0054564867,"threshold_uncertainty_score":0.9999101},"labels":[],"label_agreement":null},{"id":"W7132893096","doi":"","title":"Assessment of Generalizability Methods to Extend Phase III Clinical Trial Effect Estimates in the Non-Squamous Metastatic NSCLC Population","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Genentech; University of Toronto","keywords":"Generalizability theory; Clinical trial; Nonparametric statistics; Population; Bootstrapping (finance); Resampling; Inverse probability weighting; Parametric statistics; Weighting; Research design","score_opus":0.561847162656975,"score_gpt":0.7267986837832596,"score_spread":0.16495152112628464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132893096","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5459926,0.00006803728,0.43266466,0.0002287924,0.00650039,0.013930232,0.00014262492,0.00009144971,0.0003811832],"genre_scores_gemma":[0.17687991,0.000060190447,0.8194927,0.00011715253,0.00068007153,0.0018911848,0.000302786,0.00022752596,0.00034849945],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9314648,0.050267745,0.011824809,0.0025582619,0.0025675353,0.0013168469],"domain_scores_gemma":[0.6154513,0.37776673,0.0035831642,0.0023307204,0.00045932754,0.00040876944],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.12723412,0.0014601381,0.0075351587,0.0006303597,0.00027279198,0.00022254334,0.0016291263,0.0012118608,0.00064807467],"category_scores_gemma":[0.47289017,0.0010766909,0.0018455097,0.0024119979,0.0003887339,0.000119736804,0.00031362515,0.0024150524,0.000052465282],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.22891334,0.030247182,0.0030371628,0.01808598,0.00346754,0.00030077444,0.023871435,0.0021019427,0.0040423106,0.026681928,0.00210454,0.65714586],"study_design_scores_gemma":[0.2878623,0.03461951,0.064600326,0.0030964569,0.014681567,0.000010214582,0.007856835,0.11749685,0.0029452124,0.46367088,0.00005826789,0.0031015915],"about_ca_topic_score_codex":0.001516168,"about_ca_topic_score_gemma":0.00025957875,"teacher_disagreement_score":0.6540443,"about_ca_system_score_codex":0.00035927957,"about_ca_system_score_gemma":0.00060757116,"threshold_uncertainty_score":0.9998864},"labels":[],"label_agreement":null},{"id":"W7133061042","doi":"","title":"A Novel Multi-arm, Two-stage Randomized Basket Design","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario","funders":"Centre for Addiction and Mental Health","keywords":"Sample size determination; Type I and type II errors; Sequential analysis; Design of experiments; Statistical power; Sample (material); Interim; Statistical analysis","score_opus":0.6116594163695643,"score_gpt":0.624196116694852,"score_spread":0.012536700325287642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133061042","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004330934,0.001319314,0.9665644,0.0005999056,0.010938946,0.009783851,0.00040880323,0.0005182089,0.009433447],"genre_scores_gemma":[0.0009858594,0.00056282425,0.83615947,0.000236305,0.001036713,0.0012043223,0.00007854333,0.00058967544,0.15914626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9791798,0.0093058245,0.005504939,0.002603231,0.0018742634,0.0015319233],"domain_scores_gemma":[0.7362647,0.25874993,0.0020777227,0.0016270004,0.0006428974,0.0006377525],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0318753,0.0020490622,0.00799434,0.00055971293,0.00031558977,0.0006677292,0.0012963039,0.001994751,0.013262358],"category_scores_gemma":[0.42793077,0.0017729673,0.002537053,0.0010700999,0.0008218423,0.00011795871,0.0003269964,0.003408968,0.00335772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3555146,0.0073499796,0.0000013337216,0.021475542,0.009386772,0.00068659725,0.055561095,0.00074876763,0.018499278,0.50775427,0.008911083,0.01411068],"study_design_scores_gemma":[0.35850263,0.00043432158,0.0000026388761,0.005470551,0.009965557,0.000019121331,0.00729333,0.17359172,0.007588268,0.43329355,0.0011380935,0.0027002278],"about_ca_topic_score_codex":0.00033195756,"about_ca_topic_score_gemma":0.00006128948,"teacher_disagreement_score":0.39605546,"about_ca_system_score_codex":0.0003303601,"about_ca_system_score_gemma":0.0010467845,"threshold_uncertainty_score":0.9993009},"labels":[],"label_agreement":null},{"id":"W7135038482","doi":"10.5376/ijmms.2024.14.0012","title":"The Application and Challenges of Integrating Multiomics Data in Individualized Therapy","year":2024,"lang":"","type":"article","venue":"International Journal of Molecular Medical Science","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data collection; Precision medicine; MEDLINE; Personalized medicine","score_opus":0.46152939133335363,"score_gpt":0.5956865328050264,"score_spread":0.13415714147167274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135038482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13823758,0.060625307,0.72832775,0.06514545,0.0062613594,0.0006925457,0.00011128842,0.000016100248,0.0005826024],"genre_scores_gemma":[0.7119601,0.057733707,0.22968452,0.00019566283,0.00039752162,0.000005762377,8.346739e-7,0.00001864686,0.000003269099],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99206036,0.0008428895,0.002243342,0.0004563931,0.004128517,0.00026851933],"domain_scores_gemma":[0.9607593,0.036580842,0.000968972,0.0005524502,0.00084476423,0.00029366656],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03767305,0.00017510599,0.00049443997,0.0003172779,0.00007173196,0.0002682079,0.0041787676,0.00018128271,0.00003970042],"category_scores_gemma":[0.2071396,0.00010767012,0.000106335436,0.00058711035,0.0023410297,0.0003240877,0.00096987415,0.0009005094,0.0000018776883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104271276,0.00016839713,0.00007697878,0.0000611778,0.00013753932,0.00012916037,0.0006064392,0.0000024480914,0.004361774,0.19770208,0.000018857916,0.79663086],"study_design_scores_gemma":[0.0028565328,0.00041607366,0.00156681,0.004364468,0.00010288687,0.00038449792,0.0011889577,0.12162796,0.005986793,0.85348034,0.007741445,0.00028327017],"about_ca_topic_score_codex":0.000022875382,"about_ca_topic_score_gemma":0.000016850381,"teacher_disagreement_score":0.7963476,"about_ca_system_score_codex":0.00011704887,"about_ca_system_score_gemma":0.0012880267,"threshold_uncertainty_score":0.9909181},"labels":[],"label_agreement":null},{"id":"W7135517624","doi":"","title":"Adaptive Bayesian designs for dose-ranging trials.","year":2002,"lang":"en","type":"book-chapter","venue":"Research Portal (King's College London)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health","funders":"","keywords":"","score_opus":0.7750698381611185,"score_gpt":0.5807186148685368,"score_spread":0.1943512232925817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135517624","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005374866,0.0008650931,0.17330104,0.0006615516,0.0016409233,0.013022172,0.0056080674,0.00038684934,0.8045089],"genre_scores_gemma":[0.0011532415,0.00052773126,0.5282274,0.000120877085,0.0035063203,0.0010361911,0.00004758138,0.000624473,0.4647562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9841615,0.0033885122,0.004490248,0.0020311482,0.0036828672,0.0022457049],"domain_scores_gemma":[0.78400785,0.21082523,0.0014021489,0.0015072903,0.0014550633,0.0008024054],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.045783322,0.0011968211,0.004857789,0.0012746424,0.0008088326,0.0002526773,0.0014895307,0.0019639994,0.011364166],"category_scores_gemma":[0.21776292,0.0010854504,0.0020152328,0.0004652553,0.0010848567,0.00018463253,0.000584059,0.0033774802,0.00038136143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012782569,0.0001982306,0.000001863454,0.00064568274,0.0009310474,0.0009777299,0.0000756294,0.0000014653693,0.000024946417,0.8855435,0.095151626,0.015170026],"study_design_scores_gemma":[0.003697419,0.0012566012,0.0000019737329,0.0017113625,0.00054221076,0.000040177696,0.00008553079,0.0010211199,0.00014523658,0.9174594,0.07300139,0.0010375729],"about_ca_topic_score_codex":0.000025875797,"about_ca_topic_score_gemma":0.00005600542,"teacher_disagreement_score":0.35492635,"about_ca_system_score_codex":0.00044522103,"about_ca_system_score_gemma":0.0008677201,"threshold_uncertainty_score":0.99933165},"labels":[],"label_agreement":null},{"id":"W7135910475","doi":"","title":"Phase III trials","year":2005,"lang":"en","type":"book-chapter","venue":"Research Portal (King's College London)","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health","funders":"","keywords":"","score_opus":0.7064612760022773,"score_gpt":0.6257955215974309,"score_spread":0.08066575440484636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135910475","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007814077,0.0010719931,0.0032123397,0.0010017438,0.0016792739,0.006476198,0.0044739107,0.00038689256,0.98161954],"genre_scores_gemma":[0.0010091136,0.0014940653,0.17730422,0.00023740603,0.007504008,0.00040999547,0.000084451895,0.0005481914,0.8114085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98009384,0.0040850355,0.006281612,0.0020406025,0.005435256,0.002063677],"domain_scores_gemma":[0.8288525,0.16461574,0.00180109,0.0022455577,0.0013939979,0.0010911674],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.062419344,0.0012091794,0.0058886907,0.0012087653,0.0005838494,0.0002626626,0.0018161314,0.002181042,0.043698594],"category_scores_gemma":[0.24980433,0.0010621472,0.0017529116,0.00045358323,0.001459453,0.00019928701,0.0010358008,0.0050144144,0.0017518803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014371306,0.0006876847,6.5316505e-7,0.00034300247,0.00074113323,0.0019673775,0.000035346802,2.2593736e-7,0.00005533742,0.7804926,0.17759156,0.036647957],"study_design_scores_gemma":[0.008836628,0.00085631997,4.2261203e-7,0.0008644471,0.00033527348,0.00004990334,0.000029921506,0.00004058937,0.00021587401,0.64394534,0.34411272,0.00071255607],"about_ca_topic_score_codex":0.000034324978,"about_ca_topic_score_gemma":0.00010892513,"teacher_disagreement_score":0.187385,"about_ca_system_score_codex":0.00039258922,"about_ca_system_score_gemma":0.0014917994,"threshold_uncertainty_score":0.9991829},"labels":[],"label_agreement":null},{"id":"W71576337","doi":"10.1023/a:1011015924429","title":"Evaluation of the Bioequivalence of Highly-Variable Drugs and Drug Products","year":2001,"lang":"en","type":"article","venue":"Pharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Mathematics; Statistics; Variable (mathematics); Power (physics); Geometric mean; Statistical analysis; Applied mathematics; Econometrics; Pharmacokinetics; Pharmacology; Thermodynamics; Mathematical analysis; Medicine","score_opus":0.8858350907793737,"score_gpt":0.7094881880146106,"score_spread":0.17634690276476317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W71576337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9530062,0.0013551997,0.0034729743,0.010163686,0.0006606871,0.003635217,0.000060937164,0.000046178782,0.027598912],"genre_scores_gemma":[0.90747094,0.00025946356,0.091612324,0.000037878784,0.00014366698,0.0000557465,2.0885467e-7,0.000018780322,0.00040101848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98774403,0.006955424,0.0007795785,0.00039435696,0.003664367,0.0004622299],"domain_scores_gemma":[0.9346851,0.061363604,0.00017188623,0.0007207122,0.0028709162,0.00018774561],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06390376,0.00010882013,0.00036333117,0.00009115806,0.00010046891,0.000018069939,0.0004850422,0.0000804012,0.0005705417],"category_scores_gemma":[0.32567617,0.00007129857,0.00005205514,0.0010878776,0.001242766,0.00006275701,0.0004704799,0.0005993492,0.000010050178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063431874,0.0012871862,0.0024735352,0.0016968267,0.0001989967,0.000002888633,0.000736786,0.000009862495,0.10539718,0.7117745,0.005405997,0.17038187],"study_design_scores_gemma":[0.0010120057,0.000051693605,0.00047474043,0.0001489096,0.00020147792,0.0000023574678,0.00007928963,0.0042726495,0.14903276,0.84323883,0.0014098472,0.00007545786],"about_ca_topic_score_codex":0.00003339745,"about_ca_topic_score_gemma":9.42866e-7,"teacher_disagreement_score":0.2617724,"about_ca_system_score_codex":0.000072592054,"about_ca_system_score_gemma":0.0003709609,"threshold_uncertainty_score":0.9639081},"labels":[],"label_agreement":null},{"id":"W7162106698","doi":"10.82308/18322","title":"Novel Bayesian approaches for the planning and monitoring phases of clinical studies","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sample size determination; Frequentist inference; Bayesian probability; Randomized controlled trial; Accrual; Variance (accounting); Sample (material); Clinical trial; Research design","score_opus":0.9481069479961498,"score_gpt":0.7179419872274648,"score_spread":0.23016496076868498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162106698","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030466096,0.0059243557,0.9374728,0.00034888805,0.016895076,0.0049736477,0.0004210958,0.0004066163,0.0030913868],"genre_scores_gemma":[0.006409498,0.00054989016,0.98649836,0.000009775191,0.0014255459,0.00030786765,0.000010828631,0.000086089414,0.00470217],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970637,0.00019539117,0.001832731,0.0004108934,0.00029401825,0.00020329586],"domain_scores_gemma":[0.71954817,0.27935708,0.00064226944,0.00025802167,0.0001473773,0.000047080543],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0061331056,0.00024819205,0.0014010414,0.000058236135,0.00012100224,0.000026187832,0.0002373834,0.00034468595,0.00000796377],"category_scores_gemma":[0.2631244,0.00014853061,0.00027446274,0.00011294715,0.00018060146,0.000023177767,0.00006275476,0.00035413099,6.094921e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002384192,0.0009742482,0.0041532107,0.013641628,0.008601366,0.000007691487,0.006997982,0.000026149062,0.00015199342,0.22292167,0.008990667,0.7311492],"study_design_scores_gemma":[0.0017287428,0.0003245058,0.0041042552,0.0017710505,0.0017062973,9.635505e-7,0.03269341,0.0013211037,0.0014833926,0.9543791,0.0001168257,0.00037036152],"about_ca_topic_score_codex":0.000006681432,"about_ca_topic_score_gemma":0.000008518093,"teacher_disagreement_score":0.7314574,"about_ca_system_score_codex":0.000008685311,"about_ca_system_score_gemma":0.00005251873,"threshold_uncertainty_score":0.74308264},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W76453628","doi":"10.1007/978-3-642-55345-5_12","title":"Statistical Considerations in the Use of Composite Endpoints in Time to Event Analyses","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Event (particle physics); Composite number; Statistics; Computer science; Econometrics; Mathematics; Algorithm; Physics","score_opus":0.793302905860769,"score_gpt":0.5995200307315685,"score_spread":0.19378287512920056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W76453628","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018897916,0.000015085713,0.8270064,0.0014036589,0.0001669725,0.002473483,0.001433418,0.00004739503,0.16726461],"genre_scores_gemma":[0.0013297715,0.000005541089,0.9540446,0.0012167043,0.00006983547,0.000029525381,0.000013869103,0.000043848217,0.043246333],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956304,0.0010916273,0.0020411152,0.00039191946,0.0006268958,0.00021808072],"domain_scores_gemma":[0.8223488,0.17661326,0.00027784074,0.0005724636,0.000101764235,0.00008589523],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003026629,0.00028709052,0.0013274542,0.00024959343,0.000024301344,0.000056499015,0.00026261527,0.00028252183,0.009303371],"category_scores_gemma":[0.07269263,0.00019524003,0.00014852732,0.000063349114,0.0002022422,0.000021558817,0.0001410212,0.00048986095,0.0004259206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045818055,0.000120109515,0.00002517487,0.00006526422,0.00006620405,0.000042793763,0.00006581729,0.00003752668,0.000047338486,0.9796608,0.018722136,0.0011010229],"study_design_scores_gemma":[0.00039935453,0.00012749012,0.00033920404,0.00034229993,0.00015824076,0.0000051425964,0.0000029058158,0.000347658,0.00005952315,0.99460095,0.0033976482,0.00021957571],"about_ca_topic_score_codex":0.000043947464,"about_ca_topic_score_gemma":0.00015367045,"teacher_disagreement_score":0.17552163,"about_ca_system_score_codex":0.00005607043,"about_ca_system_score_gemma":0.00006278031,"threshold_uncertainty_score":0.99160224},"labels":[],"label_agreement":null},{"id":"W80130378","doi":"10.22237/jmasm/1177992720","title":"The Effects of Heteroscedasticity on Tests of Equivalence","year":2007,"lang":"en","type":"article","venue":"Journal of Modern Applied Statistical Methods","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; York University","funders":"","keywords":"Heteroscedasticity; Mathematics; Equivalence (formal languages); Statistics; Econometrics; Monte Carlo method; Sample size determination; Statistical hypothesis testing; Discrete mathematics","score_opus":0.350219326683328,"score_gpt":0.5933100596443849,"score_spread":0.24309073296105688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W80130378","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066880174,0.0001041112,0.9899601,0.000050014925,0.00083518686,0.0004209374,0.000044768214,0.000013330993,0.0018835673],"genre_scores_gemma":[0.267508,0.00003624971,0.73216975,0.000048720794,0.0001878605,0.0000047113504,1.11573804e-7,0.00003148621,0.0000131034785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927571,0.0019781238,0.0031978271,0.00029046994,0.0012501277,0.00052639336],"domain_scores_gemma":[0.62166184,0.37569973,0.0016282606,0.0004153101,0.00035030284,0.00024452884],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022095978,0.0002901857,0.0014801711,0.00012942338,0.00009224191,0.000021059906,0.00068480807,0.00022083751,0.000036099034],"category_scores_gemma":[0.305412,0.00018077524,0.00025831372,0.00025341983,0.00084759307,0.000032617216,0.00013945528,0.00086274353,0.0000021385874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013121351,0.00032624914,0.000025506855,0.0004996021,0.0001319065,0.00002284377,0.000081555234,0.000009112192,0.07100046,0.49329832,0.00013520659,0.43315712],"study_design_scores_gemma":[0.0011718825,0.0013506432,0.002603792,0.00028001913,0.000258496,0.00001328255,0.000021081583,0.00045881007,0.100530125,0.89312214,0.000042507305,0.00014719384],"about_ca_topic_score_codex":0.0000012445696,"about_ca_topic_score_gemma":8.411896e-7,"teacher_disagreement_score":0.43300992,"about_ca_system_score_codex":0.000074632466,"about_ca_system_score_gemma":0.00009896582,"threshold_uncertainty_score":0.765807},"labels":[],"label_agreement":null},{"id":"W87870904","doi":"10.1023/a:1022695819135","title":"Limits for the Scaled Average Bioequivalence of Highly Variable Drugs and Drug Products","year":2003,"lang":"en","type":"article","venue":"Pharmaceutical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Mathematics; Statistics; Limit (mathematics); Confidence interval; Geometric mean; Logarithm; Linearization; Limiting; Variable (mathematics); Applied mathematics; Pharmacokinetics; Mathematical analysis; Pharmacology; Medicine; Nonlinear system; Physics","score_opus":0.7892181539649511,"score_gpt":0.6590397458225726,"score_spread":0.13017840814237847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W87870904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14954756,0.009944409,0.6879244,0.054383878,0.004325029,0.028010884,0.0007927986,0.0004957437,0.06457534],"genre_scores_gemma":[0.4463935,0.000600608,0.5500821,0.00018994001,0.0002609205,0.0003007836,5.4140565e-7,0.000051202336,0.0021204257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937962,0.0028935056,0.00076366623,0.00057411334,0.0011404264,0.000832066],"domain_scores_gemma":[0.74478406,0.2532469,0.00010439484,0.0006367737,0.00090788945,0.0003199925],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031189092,0.00017819444,0.0004973543,0.00009507072,0.0002849686,0.00006752567,0.0005232516,0.000111401,0.00031674167],"category_scores_gemma":[0.35690197,0.00011639514,0.00007884454,0.0007439842,0.0012077151,0.00007213738,0.00020207277,0.0008114949,0.000021027618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045787057,0.0003926871,0.000082980485,0.0011608585,0.0000981642,0.0000032228925,0.00020252222,0.0000018603187,0.013680607,0.9633978,0.0065469183,0.0139745185],"study_design_scores_gemma":[0.0014873907,0.00012258218,0.000028153921,0.00008791675,0.0000979174,0.000003269255,0.00007393299,0.0015571709,0.15407752,0.81867397,0.02364816,0.00014199557],"about_ca_topic_score_codex":0.000008853888,"about_ca_topic_score_gemma":3.94662e-7,"teacher_disagreement_score":0.3257129,"about_ca_system_score_codex":0.00004522263,"about_ca_system_score_gemma":0.00022109806,"threshold_uncertainty_score":0.9975947},"labels":[],"label_agreement":null}]}