{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1557,"total_is_capped":false,"direct_labels_cover":46,"predictions_cover":1557,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"90175592dfae","filters":{"topic":"Statistical Methods in Clinical Trials"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3681394256237464,"gpt":0.471576120107807,"spread":0.1034366944840607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002018413,0.0001383771,0.0006891791,0.0001904138,0.00004639043,0.00002780736,0.00009878015,0.0001086801,0.0004580326],"category_scores_gemma":[0.03161228,0.0001105422,0.0001024292,0.0002973614,0.0002611346,0.00007263636,0.00008472461,0.0001197705,0.00001882624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001975771,"about_ca_system_score_gemma":0.00003331175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004145021,"about_ca_topic_score_gemma":0.000002809059,"domain_scores_codex":[0.9980693,0.0001910105,0.001118887,0.0001334977,0.0003010637,0.0001861676],"domain_scores_gemma":[0.9744291,0.024639,0.0003937161,0.0003102655,0.000103705,0.0001241875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005949864,0.00008061097,0.003427716,0.0003239025,0.0006071583,2.681079e-7,0.0001038614,0.00001867224,0.00002730743,0.9708732,0.003554716,0.02092304],"study_design_scores_gemma":[0.0008860613,0.0002451232,0.03172955,0.00003832728,0.00205995,0.000002225704,0.0001778576,0.2415557,0.0002733005,0.7214663,0.001275975,0.0002896124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02043402,0.000005060273,0.9747825,0.00004313407,0.0001487401,0.0002132064,0.0003956085,0.0000402408,0.003937474],"genre_scores_gemma":[0.0913465,0.000008155534,0.9084182,0.00007589474,0.00005677631,0.00001258265,0.00001701913,0.00000982947,0.00005507294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.249407,"threshold_uncertainty_score":0.9765449,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Confidence interval; Robust confidence intervals; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8522175965034989,"gpt":0.719531494817121,"spread":0.132686101686378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02578625,0.0004276824,0.002059436,0.0003231454,0.0001488712,0.00003668727,0.001271597,0.0003656751,0.0005363745],"category_scores_gemma":[0.4956671,0.0003994788,0.0001902271,0.0005955325,0.0005248815,0.000230518,0.0003225261,0.0005009152,0.0001074076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001392008,"about_ca_system_score_gemma":0.000161388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003983152,"about_ca_topic_score_gemma":0.0001681544,"domain_scores_codex":[0.9851553,0.009714324,0.002501835,0.001513982,0.0003288114,0.0007856899],"domain_scores_gemma":[0.7412491,0.2554348,0.000782427,0.001824529,0.0004583908,0.0002507733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01265753,0.00156488,0.0005150178,0.0001460656,0.0006299007,0.00008256194,0.004810705,0.00001892928,0.05582126,0.6340705,0.2403562,0.04932648],"study_design_scores_gemma":[0.003633592,0.0008890323,0.0005114333,0.0001535086,0.0001218119,0.00002075884,0.000130717,0.001235957,0.003925509,0.9451931,0.04371529,0.0004692815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003822711,0.0001899677,0.9535991,0.000643205,0.03816098,0.001984017,0.0006853607,0.0001438032,0.0007708298],"genre_scores_gemma":[0.0006932145,0.0001418956,0.995872,0.001069634,0.001345415,0.0004375449,0.00003744047,0.00008315015,0.0003196574],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4698808,"threshold_uncertainty_score":0.9998457,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7929098891837675,"gpt":0.5963941095425003,"spread":0.1965157796412672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01005301,0.0001274527,0.0006767143,0.00004162043,0.000234554,0.00001742101,0.0001064451,0.0001357157,0.00001594931],"category_scores_gemma":[0.01944612,0.0001072508,0.0000188085,0.0002734374,0.0001237478,0.000123907,0.00007031023,0.001498142,7.512419e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002966118,"about_ca_system_score_gemma":0.0001920666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009129336,"about_ca_topic_score_gemma":0.0001183275,"domain_scores_codex":[0.9948822,0.003311231,0.001199439,0.0002105164,0.0001840135,0.0002126064],"domain_scores_gemma":[0.9792271,0.01998949,0.0002490451,0.0001785775,0.00007177663,0.0002839926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009165059,0.001075353,0.04875666,0.004643594,0.0001202929,0.000009048196,0.012408,0.000410388,0.0001434301,0.8972015,0.008274673,0.02604058],"study_design_scores_gemma":[0.00192104,0.002264617,0.01119576,0.0004515204,0.000035626,0.000004072344,0.007193748,0.1115585,0.000001491718,0.8648952,0.0003655464,0.000112889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5616601,0.00124881,0.4302222,0.004276982,0.0002240054,0.0005709663,0.00002327344,0.0001178626,0.001655909],"genre_scores_gemma":[0.6571102,0.002753652,0.3344667,0.005197659,0.0004226446,0.00001534603,0.00000586435,0.00001957995,0.000008304338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1111481,"threshold_uncertainty_score":0.9888135,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9873875398748938,"gpt":0.8105356203029017,"spread":0.1768519195719921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6132049,0.0003171879,0.003057324,0.0003498132,0.0001902024,0.0003357084,0.0007733087,0.001216768,0.002259343],"category_scores_gemma":[0.9914974,0.0001743535,0.000452038,0.000586948,0.003619401,0.0001995688,0.0008197997,0.00412223,0.0001003354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008199604,"about_ca_system_score_gemma":0.0008632043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005576465,"about_ca_topic_score_gemma":0.0009740432,"domain_scores_codex":[0.4428463,0.5486633,0.002810439,0.001200512,0.003222475,0.001257042],"domain_scores_gemma":[0.01351297,0.9832157,0.0004922445,0.001176087,0.0005657029,0.001037283],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002007049,0.0006758656,0.001062465,0.0002378381,0.0002595608,0.0002008088,0.0004191184,6.944042e-7,0.000443726,0.1533479,0.09015042,0.7511945],"study_design_scores_gemma":[0.002795205,0.0007395013,0.003342575,0.0003010958,0.00007178306,0.00002331985,0.001146674,0.002818521,0.0001748656,0.9853399,0.003051525,0.0001950714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08634765,0.0008052104,0.8229362,0.07917384,0.005781418,0.004025973,0.00002153574,0.0001135563,0.0007946452],"genre_scores_gemma":[0.01127589,0.001418719,0.9789947,0.002280421,0.005199804,0.0004293915,0.000001545456,0.00005411499,0.0003453895],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8319919,"threshold_uncertainty_score":0.9990922,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.793096103122032,"gpt":0.685672168665247,"spread":0.107423934456785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1863766,0.0002449922,0.004660171,0.0001509721,0.000129375,0.00003266475,0.0005490297,0.0006947443,0.0001314174],"category_scores_gemma":[0.5577547,0.0001352633,0.001647793,0.0002205645,0.0004618925,0.00008034299,0.00006938103,0.001154937,0.000003706827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004390714,"about_ca_system_score_gemma":0.00304216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007576065,"about_ca_topic_score_gemma":0.0001705457,"domain_scores_codex":[0.9790027,0.007064226,0.0122868,0.0003611312,0.0006702846,0.0006149138],"domain_scores_gemma":[0.4570891,0.5358066,0.005389487,0.0002891639,0.001113314,0.0003123452],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.06021269,0.003299183,0.0009177499,0.0004311755,0.001136401,0.0001218077,0.0001961527,0.00001269274,0.00005927038,0.3919279,0.01457974,0.5271052],"study_design_scores_gemma":[0.04725667,0.005812701,0.007793181,0.0007232937,0.001788215,0.000180652,0.0006692672,0.0001825417,0.000141363,0.9221726,0.01301986,0.0002596603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03328101,0.0003563839,0.9141458,0.0271165,0.01611434,0.005947098,0.001942816,0.00004996366,0.001046141],"genre_scores_gemma":[0.09209808,0.0001610007,0.9014199,0.0007232642,0.005337332,0.0001588558,0.000001493527,0.00005647431,0.00004360197],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5302447,"threshold_uncertainty_score":0.8377966,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9534115106481834,"gpt":0.8140813552163118,"spread":0.1393301554318717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08421661,0.0005588848,0.006891569,0.0004987524,0.000115955,0.00008884594,0.001389047,0.0009324162,0.0003984273],"category_scores_gemma":[0.4245676,0.0003195833,0.003179689,0.001127155,0.0003243099,0.0003035051,0.0001527578,0.002874904,0.000006707759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581812,"about_ca_system_score_gemma":0.005247324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001886587,"about_ca_topic_score_gemma":0.00004293351,"domain_scores_codex":[0.9671364,0.01850205,0.01159651,0.0004891626,0.001907922,0.0003679503],"domain_scores_gemma":[0.8820696,0.103936,0.01203378,0.0004029882,0.00129482,0.0002628515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002230427,0.0004868117,0.000004446238,0.00133765,0.0006199031,0.00001182987,0.00001604358,0.00005291518,0.000001414249,0.01407104,0.0109199,0.972255],"study_design_scores_gemma":[0.002758693,0.00009799228,0.00002232582,0.01195945,0.002169523,0.00003540701,0.000001137221,0.00005298216,0.000004628381,0.3511168,0.6315262,0.0002548477],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006025798,0.9402664,0.03505295,0.001158301,0.02048183,0.001791453,0.000636208,0.00001892191,0.0005878469],"genre_scores_gemma":[0.000001313785,0.6759012,0.3161355,0.0003871596,0.007267259,0.0000889193,0.000002357831,0.00003924003,0.0001770411],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9720001,"threshold_uncertainty_score":0.9999256,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.915936087266207,"gpt":0.7443180110581955,"spread":0.1716180762080115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020981,0.0002963858,0.0009653323,0.0001466595,0.0001132431,0.00005713073,0.0006240472,0.000228412,0.001776686],"category_scores_gemma":[0.2010913,0.0002316169,0.00024217,0.0006947675,0.00027161,0.0000603097,0.0002224239,0.0006152294,0.0001710537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008430584,"about_ca_system_score_gemma":0.00001257553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009550187,"about_ca_topic_score_gemma":0.000001708654,"domain_scores_codex":[0.9934767,0.003096048,0.001614716,0.0007637758,0.0004125689,0.000636223],"domain_scores_gemma":[0.9027226,0.09551849,0.0003194914,0.0007088883,0.0002298955,0.000500637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006887632,0.0008721092,0.001881923,0.00008779249,0.0001027283,0.0001020892,0.0006326517,0.00002360665,0.01061919,0.6164291,0.004276105,0.3642839],"study_design_scores_gemma":[0.0005004468,0.0002307715,0.01009108,0.0001076506,0.00007127367,0.00004729715,0.0001480489,0.0004133864,0.002427461,0.9839951,0.00162304,0.0003444463],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0253276,0.00004020152,0.9607531,0.0005206976,0.002222108,0.0006684487,0.00001751149,0.0002341467,0.01021612],"genre_scores_gemma":[0.1170871,0.000003497593,0.8805161,0.001873572,0.0003502162,0.00002039245,4.965482e-7,0.00003088066,0.00011783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.367566,"threshold_uncertainty_score":0.9991359,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9784678425915878,"gpt":0.7711311390194552,"spread":0.2073367035721326,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04327711,0.0001380547,0.001018919,0.00002761447,0.0003499571,0.00001092938,0.0003736808,0.00005820431,0.00004189062],"category_scores_gemma":[0.7134925,0.00009125499,0.00007244172,0.0002283495,0.0003848274,0.00005106624,0.0003231829,0.0001212817,0.000001261083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009585884,"about_ca_system_score_gemma":0.0004971356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005241434,"about_ca_topic_score_gemma":0.00007059676,"domain_scores_codex":[0.9905534,0.001913703,0.006516696,0.0003911468,0.0002593164,0.0003657754],"domain_scores_gemma":[0.7079672,0.2713978,0.01661799,0.001541302,0.002329863,0.0001458896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001102129,0.0002892035,0.00937507,0.001201248,0.001823314,0.000004134552,0.000611317,0.0000135652,0.002923105,0.07571726,0.8888193,0.01812037],"study_design_scores_gemma":[0.00175736,0.0004993865,0.003023941,0.0003317447,0.0002204702,0.000009238645,0.0006147874,0.03451212,0.001019833,0.9467784,0.01100725,0.000225518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1448984,0.0005456258,0.8196272,0.02336732,0.004799732,0.00536456,0.001110526,0.0001304562,0.0001561343],"genre_scores_gemma":[0.00468445,0.00006490527,0.9933572,0.0007654496,0.0008420834,0.00007438644,0.00002032547,0.00002288835,0.0001683132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.877812,"threshold_uncertainty_score":0.9851475,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6153986132544237,"gpt":0.5598863649413716,"spread":0.05551224831305213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00168368,0.0002225019,0.0007738843,0.0000773022,0.0003111787,0.00001975988,0.0003520948,0.0003032446,0.0004121476],"category_scores_gemma":[0.04908112,0.0002056152,0.0001766075,0.0001380735,0.0003375025,0.00009094081,0.000160179,0.0003018804,0.0001884153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009679824,"about_ca_system_score_gemma":0.0001696644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001118397,"about_ca_topic_score_gemma":0.00001021932,"domain_scores_codex":[0.9975452,0.0003503625,0.0008835791,0.0004391175,0.000213213,0.0005685455],"domain_scores_gemma":[0.964027,0.03488126,0.0003372057,0.0003639193,0.000247054,0.0001435987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002697405,0.01028944,0.0504006,0.0009474647,0.000410065,0.002487904,0.004801593,0.00001980196,0.04031233,0.5858542,0.04014538,0.2616338],"study_design_scores_gemma":[0.00235085,0.002649538,0.01932073,0.00005383993,0.0002798966,0.0001578177,0.00003973251,0.0002615238,0.0006277815,0.9731663,0.0006215314,0.000470395],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9941709,0.00002597236,0.002583368,0.0003169026,0.0009601116,0.001147446,0.0001289886,0.0002872304,0.0003790706],"genre_scores_gemma":[0.04233468,0.000004778757,0.9555046,0.0005242292,0.0005458869,0.0001994784,0.000006286499,0.00006710226,0.0008129928],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9529212,"threshold_uncertainty_score":0.9589289,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7630812926026873,"gpt":0.6042377862803687,"spread":0.1588435063223186,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.4148709,0.001014134,0.1164464,0.0005540444,0.00002298178,0.00004014766,0.0006475005,0.0007690542,0.000181969],"category_scores_gemma":[0.8856614,0.0005163375,0.01342855,0.0009286525,0.0002549633,0.00006583569,0.0001153961,0.0006699048,0.00001202401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001348053,"about_ca_system_score_gemma":0.0005417927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002087447,"about_ca_topic_score_gemma":0.000002271462,"domain_scores_codex":[0.8078439,0.1450358,0.04307658,0.0009414972,0.002518043,0.0005841406],"domain_scores_gemma":[0.3612947,0.6138863,0.02175382,0.002232933,0.0006648492,0.0001674243],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.003148338,0.0002758425,1.603791e-7,0.9458055,0.01775104,0.00004194452,0.00001606043,0.000001376871,2.758919e-7,0.001146868,0.0003123203,0.03150022],"study_design_scores_gemma":[0.06113948,0.0001513023,7.129068e-8,0.8277798,0.0986993,0.00003546726,0.000003209333,0.000005440244,0.00000314194,0.006275941,0.005483748,0.0004230999],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.806876e-7,0.8830435,0.03058672,0.00001822286,0.0003312342,0.08534601,0.0003696768,0.00003069966,0.0002737182],"genre_scores_gemma":[1.341182e-7,0.7385631,0.2571269,0.00003335453,0.0001815108,0.003917456,0.00001469449,0.000103618,0.00005918387],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4707904,"threshold_uncertainty_score":0.9997288,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5931554158815283,"gpt":0.536563227896454,"spread":0.05659218798507426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007860239,0.0002788653,0.00109805,0.00005484715,0.00003239422,0.00002295598,0.0003567959,0.0001338969,0.0005086406],"category_scores_gemma":[0.06700167,0.0002371898,0.0001017837,0.000151121,0.0002275069,0.0000454407,0.0001731736,0.0003710121,0.0004409748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008493871,"about_ca_system_score_gemma":0.00004673421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001267189,"about_ca_topic_score_gemma":0.000006633802,"domain_scores_codex":[0.9961703,0.001247652,0.00138021,0.0006274934,0.0002412021,0.000333165],"domain_scores_gemma":[0.9874932,0.01102174,0.0003907251,0.0007098116,0.0001122598,0.0002722451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003648782,0.0009984154,0.009594334,0.02887744,0.0001409591,0.00004502751,0.0009447082,3.58951e-7,0.00009470538,0.01584515,0.5667989,0.3762951],"study_design_scores_gemma":[0.006411582,0.000330357,0.00606827,0.02727095,0.0003828606,0.00003414593,0.0001851249,0.00007409725,0.00008829033,0.5011908,0.4565711,0.001392393],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.1472126,0.7319171,0.02115381,0.05363064,0.008418445,0.01664899,0.0002821383,0.0009968717,0.01973934],"genre_scores_gemma":[0.004875227,0.1155733,0.8753276,0.002778916,0.0003991329,0.0004556523,0.000001206971,0.0000714597,0.000517424],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8541738,"threshold_uncertainty_score":0.9672321,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9347214944396993,"gpt":0.7018322329760908,"spread":0.2328892614636086,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"category_scores_codex":[0.6358193,0.002005466,0.1899771,0.002001922,0.00007123475,0.0001864842,0.001771241,0.002152647,0.004417595],"category_scores_gemma":[0.9527566,0.00111719,0.02226497,0.00321657,0.0002949182,0.0001470139,0.0004938445,0.001062942,0.00008141722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001403617,"about_ca_system_score_gemma":0.00118311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001253679,"about_ca_topic_score_gemma":0.000002685907,"domain_scores_codex":[0.584206,0.2890239,0.1187325,0.002772732,0.003950239,0.001314629],"domain_scores_gemma":[0.1770166,0.7408543,0.07699674,0.003859854,0.0008545723,0.0004180003],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0008139888,0.0003252006,4.865825e-7,0.8757757,0.03887353,0.0000058414,0.00003428207,1.42463e-7,0.000001995766,0.005702276,0.003974842,0.07449174],"study_design_scores_gemma":[0.004550603,0.0003993597,1.433441e-7,0.6123487,0.3406359,0.000007977419,0.00001998248,0.00001452627,0.000009980212,0.01733835,0.02397026,0.0007041901],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.331288e-7,0.784909,0.00438886,0.00003249475,0.0008303617,0.2024719,0.00677595,0.00006978607,0.0005213936],"genre_scores_gemma":[1.29429e-7,0.8988734,0.06365179,0.00007429483,0.000889829,0.03560239,0.000155814,0.0002176878,0.0005345948],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4518304,"threshold_uncertainty_score":0.9992688,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.921579771556096,"gpt":0.6141508616884526,"spread":0.3074289098676435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01311294,0.0007734481,0.02878629,0.0002438574,0.00006647299,0.00003843409,0.0008081803,0.0005237996,0.009044421],"category_scores_gemma":[0.1198174,0.000533112,0.006298261,0.002450889,0.0001593024,0.00004014805,0.0003003374,0.000700099,0.0003625844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007941081,"about_ca_system_score_gemma":0.0001999546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005975476,"about_ca_topic_score_gemma":8.945834e-7,"domain_scores_codex":[0.9845842,0.007552568,0.005207378,0.0008672873,0.001233623,0.0005549341],"domain_scores_gemma":[0.9195079,0.07300408,0.004638235,0.002129713,0.0005128662,0.0002072343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.00000273727,0.0007801623,3.002277e-7,0.6064601,0.3683358,0.000003631094,0.00000183419,4.912505e-7,1.205612e-7,0.001762721,0.01154656,0.01110551],"study_design_scores_gemma":[0.00007078873,0.00004097237,1.357462e-8,0.1142184,0.8144678,9.704271e-7,1.624588e-7,0.0003456339,0.000001645288,0.02411405,0.04633402,0.0004054956],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.342415e-8,0.9871523,0.009049989,0.00002208,0.0001057456,0.002131335,0.0005274111,0.0002767881,0.0007342767],"genre_scores_gemma":[7.432721e-9,0.5390147,0.4602041,0.0000754189,0.0001984382,0.0001337978,0.00002517699,0.00007291194,0.0002754449],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4922417,"threshold_uncertainty_score":0.999712,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7812381245744865,"gpt":0.6905686159584271,"spread":0.09066950861605938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1264254,0.0001360561,0.001313419,0.0001618904,0.00002406333,0.00004996363,0.0006589736,0.0002081149,0.0001884332],"category_scores_gemma":[0.8324124,0.00006441595,0.0002288554,0.00005361416,0.0003292044,0.0003829055,0.0001149541,0.0004283934,0.000005728033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007363212,"about_ca_system_score_gemma":0.00003898541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001395285,"about_ca_topic_score_gemma":0.00003677962,"domain_scores_codex":[0.9717935,0.02392855,0.003376761,0.0003560595,0.0003059452,0.0002392417],"domain_scores_gemma":[0.5785593,0.4178737,0.002202132,0.0003954608,0.0007171807,0.0002521753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001595792,0.0002965989,0.02452192,0.000006401518,0.0003093884,0.0000231025,0.0001967426,0.00000740779,0.0007901813,0.1671965,0.09654795,0.7085081],"study_design_scores_gemma":[0.001513068,0.0004837886,0.01308558,0.0001235892,0.00004057787,0.00007328436,0.0001150098,0.0001218803,0.0001120362,0.9444407,0.03980529,0.00008522192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.07302389,0.0002420905,0.3876085,0.5336258,0.00524608,0.0002215888,0.00001529207,0.000009087292,0.00000763318],"genre_scores_gemma":[0.08474062,0.002062312,0.8895917,0.007744205,0.01570767,0.00001524647,6.345091e-7,0.00002263699,0.0001149923],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7772442,"threshold_uncertainty_score":0.8995289,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4241021929435487,"gpt":0.5779164790022724,"spread":0.1538142860587237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001924642,0.000172031,0.0008074914,0.0001359013,0.00002160374,0.000008488657,0.0001675667,0.0001309255,0.0003523325],"category_scores_gemma":[0.01609883,0.0001224345,0.00002708841,0.000154647,0.0008586697,0.00007046431,0.00007646738,0.0003080148,1.303527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004063725,"about_ca_system_score_gemma":0.00004377491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000464574,"about_ca_topic_score_gemma":0.000007696043,"domain_scores_codex":[0.9969909,0.0005794904,0.001403392,0.000257527,0.0005775525,0.0001911781],"domain_scores_gemma":[0.9824188,0.01641773,0.0006209838,0.0002440667,0.0001815258,0.0001169259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001705808,0.0004979622,0.01797379,0.001314293,0.00009745445,0.00002710582,0.0005407127,0.0001936103,0.03140313,0.9221156,0.003781611,0.02188419],"study_design_scores_gemma":[0.001005949,0.0002396711,0.001508164,0.0008931746,0.00006183166,0.000003085052,0.00009869772,0.259879,0.0002744701,0.7359542,8.227699e-7,0.00008094367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04975117,0.00008036116,0.9491192,0.00007728522,0.0002367592,0.0003428982,0.0001713458,0.000008486106,0.0002124999],"genre_scores_gemma":[0.4347288,0.00005514966,0.5650991,0.00003954291,0.00004062224,0.000007485965,0.000002692556,0.0000145768,0.00001207678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3849776,"threshold_uncertainty_score":0.992189,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6155333581101351,"gpt":0.5890310654222888,"spread":0.02650229268784632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01334272,0.0002394934,0.001638927,0.00009843972,0.00007040346,0.00006710234,0.000416508,0.0001589849,0.00001371766],"category_scores_gemma":[0.5130425,0.0001562204,0.0003075441,0.000288968,0.001028021,0.0001795201,0.0001033927,0.0006817201,0.000005194623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003990051,"about_ca_system_score_gemma":0.0001651047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004322752,"about_ca_topic_score_gemma":0.00002538649,"domain_scores_codex":[0.9938872,0.002230515,0.002469546,0.0003556101,0.0007157467,0.0003414025],"domain_scores_gemma":[0.7979907,0.1955118,0.004287973,0.0003594494,0.001292391,0.0005576125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.02865648,0.01532875,0.05000196,0.002017305,0.001569556,0.00008079249,0.001521613,0.00004901941,0.003143023,0.0227988,0.08770987,0.7871228],"study_design_scores_gemma":[0.02504079,0.04212536,0.009160887,0.002496816,0.001781502,0.0002991573,0.007232347,0.00484402,0.0009667644,0.8786159,0.02653627,0.0009001752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2934143,0.00009597672,0.6918514,0.01147638,0.0009112267,0.001825031,0.0003296429,0.00002200238,0.00007401558],"genre_scores_gemma":[0.3483125,0.0001229735,0.6502407,0.0004453929,0.0007526865,0.00005368407,0.000001463933,0.00003546419,0.00003513899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8558171,"threshold_uncertainty_score":0.6370483,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9770253359502199,"gpt":0.7704332796433205,"spread":0.2065920563068994,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1367559,0.0001455709,0.001044729,0.000274568,0.0001783844,0.00006654867,0.0006322794,0.0001461534,0.0003614637],"category_scores_gemma":[0.6178582,0.0001028979,0.0003167633,0.0004233398,0.0001879091,0.0001285301,0.0002254578,0.001123332,0.000008598132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001465524,"about_ca_system_score_gemma":0.0002999116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004155448,"about_ca_topic_score_gemma":0.000004584798,"domain_scores_codex":[0.9893446,0.003454744,0.005034415,0.0003200253,0.00124783,0.0005983819],"domain_scores_gemma":[0.9462683,0.04441097,0.004641337,0.0007018389,0.003626161,0.000351364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0323187,0.03845994,0.05152575,0.005406156,0.006018117,0.001543208,0.01824725,6.204118e-7,0.3710217,0.1986156,0.02317535,0.2536677],"study_design_scores_gemma":[0.002099564,0.003910783,0.007301653,0.00009776951,0.00005784724,0.00002309958,0.001190869,0.00002487381,0.0141751,0.9708483,0.0001353523,0.0001347488],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7387249,0.00007150882,0.2448397,0.001183138,0.0009674861,0.009730117,0.00004077059,0.0000566016,0.004385756],"genre_scores_gemma":[0.1462812,0.000006146064,0.8524747,0.00001084523,0.0006806771,0.0001198046,7.1425e-8,0.00003723912,0.0003893281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7722328,"threshold_uncertainty_score":0.8888915,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9412843850960871,"gpt":0.7413113448083124,"spread":0.1999730402877747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1190237,0.0006031622,0.02404243,0.0006043338,0.00005399742,0.0001192184,0.0004213574,0.000896298,0.0008979549],"category_scores_gemma":[0.7056667,0.0003932706,0.003091217,0.001207208,0.0001943197,0.00006560372,0.00009634906,0.0003794517,0.00002001745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000511391,"about_ca_system_score_gemma":0.0002544496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001088916,"about_ca_topic_score_gemma":0.000001067195,"domain_scores_codex":[0.9320394,0.05300352,0.01290718,0.0008492662,0.0008200333,0.0003806464],"domain_scores_gemma":[0.4682072,0.5221756,0.008446282,0.0008288783,0.0001862,0.0001558513],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002584778,0.0001273929,3.944357e-7,0.006546498,0.005184989,0.000004335746,0.00002378524,6.931853e-7,0.000002932345,0.008759883,0.002062255,0.9770284],"study_design_scores_gemma":[0.002239913,0.0002188271,0.00000353398,0.004523383,0.1019635,0.000003117961,0.00000367459,0.000008406782,0.00009641207,0.8073906,0.08306613,0.0004824557],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.946206e-7,0.6877106,0.3066769,0.00001175952,0.0003442795,0.004624931,0.0004038394,0.00004180153,0.0001855672],"genre_scores_gemma":[2.242092e-7,0.5926756,0.4064977,0.00001027449,0.0004423149,0.0001260568,0.0000149814,0.00003430994,0.0001985615],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9765459,"threshold_uncertainty_score":0.9998519,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3838805211543762,"gpt":0.5674083538348488,"spread":0.1835278326804726,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00412746,0.0001945669,0.001517728,0.0000911515,0.00004219319,0.00001731188,0.0003097609,0.0002468731,0.0004698087],"category_scores_gemma":[0.09060911,0.0001666467,0.0001760292,0.0001560628,0.001126205,0.0000573902,0.00006973734,0.0005707582,0.000007760424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001986632,"about_ca_system_score_gemma":0.00007503292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006584369,"about_ca_topic_score_gemma":0.000002344968,"domain_scores_codex":[0.995394,0.0008016667,0.00262454,0.0002798519,0.0006001014,0.0002998368],"domain_scores_gemma":[0.9570193,0.04111833,0.001022374,0.0002528609,0.000321433,0.0002657015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00106733,0.002550074,0.00003223445,0.0008726931,0.0001160038,0.0003531162,0.0001389029,0.000002944742,0.0003774954,0.9304078,0.0007061607,0.06337528],"study_design_scores_gemma":[0.00262484,0.003483661,0.007188027,0.001213235,0.0001725237,0.001472117,0.0000290219,0.00002485114,0.0002914882,0.9833226,0.00002904682,0.0001486122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06149862,0.0001712837,0.9338751,0.0006439546,0.0002774198,0.0002473978,0.0002872996,0.00001198294,0.002986924],"genre_scores_gemma":[0.3750048,0.00009841636,0.6246401,0.0001423871,0.00008170565,0.000003197998,4.410184e-7,0.00001668823,0.0000122633],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3135062,"threshold_uncertainty_score":0.9170511,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9271468758360674,"gpt":0.6894751672155476,"spread":0.2376717086205198,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1078224,0.001009464,0.01142797,0.001142898,0.00009904133,0.0002077215,0.0007852017,0.001625768,0.0001378823],"category_scores_gemma":[0.6193176,0.0006580187,0.003056751,0.001518743,0.0002591085,0.00007034794,0.000197155,0.001282114,0.000005354772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004701805,"about_ca_system_score_gemma":0.001416407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009012686,"about_ca_topic_score_gemma":0.00007820493,"domain_scores_codex":[0.9790275,0.005951077,0.009720458,0.002351188,0.001993512,0.0009563278],"domain_scores_gemma":[0.7893006,0.2036614,0.003024126,0.001803189,0.001502666,0.0007079853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01860356,0.01363315,0.01263885,0.007618111,0.02893804,0.0002908788,0.0003108457,0.01022247,0.00001993108,0.03759201,0.1851487,0.6849834],"study_design_scores_gemma":[0.004914593,0.001268602,0.0008926746,0.0009278898,0.03205551,0.00001935204,0.000105978,0.1738262,0.00005212394,0.7842565,0.0001729879,0.001507592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003817903,0.00009576824,0.9723491,0.000264856,0.0003951419,0.004111359,0.0003964402,0.0001665924,0.02183894],"genre_scores_gemma":[0.001380383,0.0001758348,0.9895896,0.0001591804,0.001135046,0.0004453886,0.00009391086,0.0001553321,0.006865382],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7466644,"threshold_uncertainty_score":0.9996703,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4903035578928938,"gpt":0.6284214039490661,"spread":0.1381178460561723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02677309,0.0004522564,0.001305008,0.00009353076,0.0001161482,0.0002005614,0.0008736,0.0002704611,0.0003862732],"category_scores_gemma":[0.1349491,0.000258065,0.0001769397,0.0003736835,0.0004533623,0.0001029205,0.0002317018,0.001118268,0.00001260881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008788912,"about_ca_system_score_gemma":0.000009799477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004307423,"about_ca_topic_score_gemma":0.00006777177,"domain_scores_codex":[0.9742556,0.02219982,0.00120455,0.001125451,0.0006137919,0.0006007593],"domain_scores_gemma":[0.8201193,0.1783938,0.0002463637,0.0008293131,0.00009161534,0.0003195554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003248772,0.001482778,0.001753689,0.00007883898,0.0001493705,0.00141331,0.004737314,0.00004563609,0.00253815,0.08425903,0.0001765652,0.9001166],"study_design_scores_gemma":[0.004365852,0.003428238,0.011923,0.0001324631,0.0001408336,0.0007971115,0.0004047396,0.002135997,0.001445774,0.9746147,0.00007682775,0.0005344829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4430777,0.00002370074,0.5545641,0.000553954,0.0002914468,0.00101049,0.00003270695,0.000056651,0.0003892524],"genre_scores_gemma":[0.448929,0.00000814065,0.5493469,0.001304301,0.0001785936,0.00020375,2.688928e-7,0.0000181095,0.00001093341],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8995821,"threshold_uncertainty_score":0.9999872,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2928198787070505,"gpt":0.5376139426936772,"spread":0.2447940639866267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01261046,0.0002245429,0.0005493872,0.00002943794,0.0004801256,0.00002895724,0.00008158699,0.0001252467,0.00003953691],"category_scores_gemma":[0.04249807,0.0001497427,0.00006051299,0.00008715504,0.0006799214,0.0001255861,0.0001343274,0.000403232,0.000003949852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001593767,"about_ca_system_score_gemma":0.00002738007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001227311,"about_ca_topic_score_gemma":0.00001565683,"domain_scores_codex":[0.9944857,0.003591082,0.0008653254,0.0003635009,0.0001109279,0.0005834334],"domain_scores_gemma":[0.9076727,0.09144142,0.0003028634,0.000183699,0.00005163355,0.0003476721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001274108,0.0005363564,0.2045853,0.0003359471,0.0004271949,0.000002813152,0.0008978103,2.496978e-7,0.0001047094,0.3255642,0.03266035,0.433611],"study_design_scores_gemma":[0.002827203,0.0001977486,0.1463285,0.00004951273,0.0005549119,0.00006258768,0.0003604371,0.000580503,0.0005339336,0.6755195,0.1724809,0.0005043623],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9165038,0.01690138,0.01276249,0.04123329,0.003597147,0.002787192,0.0002050097,0.0005038694,0.005505766],"genre_scores_gemma":[0.8533343,0.007020317,0.1375634,0.0008299677,0.0007164751,0.0001535129,0.00000537003,0.00002739783,0.0003492702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4331066,"threshold_uncertainty_score":0.9655674,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4928062528372004,"gpt":0.5403994502683522,"spread":0.04759319743115181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005188369,0.0001054789,0.0009108288,0.00004001239,0.00005723756,0.000002131514,0.0001809362,0.00004982181,0.00009403559],"category_scores_gemma":[0.3511679,0.00005376829,0.0001297734,0.0001598955,0.001379387,0.00007058246,0.00004476885,0.0004013587,8.580914e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003091116,"about_ca_system_score_gemma":0.00004067772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007468774,"about_ca_topic_score_gemma":0.000001336438,"domain_scores_codex":[0.9936152,0.004602209,0.001362491,0.0001179775,0.0001520334,0.0001500514],"domain_scores_gemma":[0.7469386,0.2499311,0.002725538,0.0001926112,0.0001600648,0.00005210698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002122093,0.0007389027,0.01024355,0.00005473848,0.0009477338,0.000009671157,0.000879301,0.001387124,0.003997108,0.2457699,0.5402874,0.1935625],"study_design_scores_gemma":[0.000666199,0.002099878,0.002656282,0.0001716031,0.0001715026,0.0001754119,0.0002466612,0.002994117,0.003166191,0.9864867,0.001057284,0.0001081564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6679761,0.00005987461,0.326674,0.004312947,0.0003640708,0.0002058559,0.0001740236,0.000003967116,0.0002291542],"genre_scores_gemma":[0.6516407,0.0002144467,0.3467028,0.001336525,0.00005469946,0.000003645469,7.174567e-7,0.00001129681,0.00003515945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7407168,"threshold_uncertainty_score":0.6542975,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1892562064606019,"gpt":0.455272008541823,"spread":0.2660158020812211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004302433,0.0001439982,0.0006834382,0.0001298494,0.00007577704,0.00006635112,0.0001513571,0.00007718996,0.00001720144],"category_scores_gemma":[0.205847,0.0001062079,0.00005814108,0.0004478677,0.0001785809,0.0003914639,0.00008014996,0.0003751325,0.000001983998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002228353,"about_ca_system_score_gemma":0.00007182034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004142966,"about_ca_topic_score_gemma":0.00001019394,"domain_scores_codex":[0.9966992,0.0007270435,0.001644246,0.0001170881,0.0005838437,0.0002285612],"domain_scores_gemma":[0.9574437,0.03872461,0.003189862,0.0001302404,0.0004131947,0.00009835237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003360173,0.000294369,0.09824207,0.000233497,0.000157657,0.000003330413,0.001241932,0.001384282,0.0004036869,0.03145749,0.001600118,0.8646455],"study_design_scores_gemma":[0.001885183,0.0006889952,0.2256096,0.0004305108,0.0003983262,0.00004387724,0.00066453,0.1838212,0.0001620486,0.5858217,0.0001864085,0.000287548],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7400749,0.00004679234,0.2573332,0.001742432,0.0001255926,0.0002822471,0.0001300887,0.00001534439,0.0002494024],"genre_scores_gemma":[0.4359147,0.00003129776,0.563827,0.0001108236,0.00009627156,0.000002681277,6.860593e-7,0.000008343659,0.000008114723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.864358,"threshold_uncertainty_score":0.8008425,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9616323734160546,"gpt":0.7454275232970856,"spread":0.2162048501189689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7328447,0.001110395,0.05532908,0.0003145689,0.00006958227,0.00004891877,0.0008503644,0.001753667,0.001868728],"category_scores_gemma":[0.9791836,0.0006266278,0.007253383,0.0005623136,0.0002658203,0.00008141533,0.0003059618,0.0008394555,0.0001038787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003864002,"about_ca_system_score_gemma":0.0002638244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004615142,"about_ca_topic_score_gemma":0.000002594342,"domain_scores_codex":[0.5420108,0.4241562,0.03016429,0.001636135,0.0009474471,0.001085137],"domain_scores_gemma":[0.05659938,0.9297346,0.01166347,0.001411091,0.0003301627,0.0002613253],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01353574,0.0001833028,2.389432e-8,0.09865976,0.0004907298,0.000001989592,0.000005829932,1.121651e-8,7.64204e-7,0.01250554,0.01817019,0.8564461],"study_design_scores_gemma":[0.03293963,0.0000582897,6.240328e-9,0.05858262,0.01570784,0.000008914509,5.103282e-7,0.000009266213,0.00001166596,0.2872086,0.6049905,0.0004822063],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.104856e-9,0.5848168,0.3781655,0.0003698354,0.0009048695,0.03500606,0.0004370541,0.000137717,0.0001621282],"genre_scores_gemma":[5.140917e-9,0.5024278,0.4798317,0.000399479,0.001721824,0.01519046,0.00007633487,0.00008542603,0.0002669267],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8559639,"threshold_uncertainty_score":0.9996185,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9492111274371475,"gpt":0.7575105690970199,"spread":0.1917005583401277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow","research_integrity"],"category_scores_codex":[0.4770573,0.001484444,0.04578477,0.0003499268,0.000133862,0.00006247226,0.002024584,0.006649137,0.000505089],"category_scores_gemma":[0.9890292,0.00105018,0.0078935,0.0005338856,0.003820203,0.00007444168,0.001196481,0.006176051,0.0003012495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001927782,"about_ca_system_score_gemma":0.001459939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005281159,"about_ca_topic_score_gemma":0.00001346677,"domain_scores_codex":[0.6138697,0.3197258,0.05692628,0.005639709,0.0008442439,0.002994193],"domain_scores_gemma":[0.04100369,0.9437801,0.01053829,0.002236869,0.0003670701,0.002073965],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001214972,0.000603102,0.0001452909,0.005978483,0.0009561002,0.0000830725,0.000007003253,8.94454e-8,5.141426e-7,0.1445116,0.01050668,0.8359931],"study_design_scores_gemma":[0.003649474,0.001258571,0.00007637265,0.005510892,0.002142259,0.00002390001,0.000001569209,0.0002571483,5.725089e-8,0.4585261,0.528021,0.000532623],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001166865,0.8740439,0.1088527,0.003061252,0.003574245,0.009145617,0.0007514943,0.0001478234,0.0004113319],"genre_scores_gemma":[0.000001949383,0.6156446,0.3773182,0.001353285,0.004015779,0.001198757,0.00001769598,0.000188809,0.0002608753],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8354605,"threshold_uncertainty_score":0.9997905,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8271081619909781,"gpt":0.6490336892071032,"spread":0.1780744727838749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04863141,0.0005508542,0.004579778,0.0001448536,0.0003198493,0.0000127909,0.001751279,0.0003398882,0.00007170795],"category_scores_gemma":[0.06647392,0.0002669294,0.0005586774,0.0006651687,0.000904021,0.00007716483,0.001133698,0.001449366,0.000005415372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004848551,"about_ca_system_score_gemma":0.0004466284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000218668,"about_ca_topic_score_gemma":0.00000770715,"domain_scores_codex":[0.9758838,0.01934376,0.002908647,0.000943656,0.0003081794,0.0006119888],"domain_scores_gemma":[0.7746774,0.2205348,0.002889476,0.001711322,0.00008273217,0.0001043227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005201594,0.0002738477,0.0001882997,0.04624811,0.002016941,0.000005781251,0.0003706695,0.00002329741,9.300897e-7,0.06754044,0.009485191,0.8686449],"study_design_scores_gemma":[0.01933751,0.0001339495,0.00004306429,0.01691853,0.02669737,0.000086416,0.0002368718,0.006738171,0.00001168588,0.3367649,0.5912829,0.001748628],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001063993,0.9730147,0.01342046,0.00052039,0.004624754,0.006329291,0.0009747786,0.00008096349,0.0009282706],"genre_scores_gemma":[0.00005374515,0.9558753,0.0413218,0.000274864,0.001994373,0.00009647069,0.00002929938,0.00008595422,0.0002681572],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8668963,"threshold_uncertainty_score":0.9999783,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5529050393700715,"gpt":0.614777663946381,"spread":0.06187262457630949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0549498,0.000258591,0.002603902,0.0001103709,0.00008621045,0.00007493851,0.0004678405,0.0003440981,0.0003686151],"category_scores_gemma":[0.8557512,0.0001476019,0.0009210929,0.00005220251,0.0003905545,0.0001426987,0.0001101255,0.0004525768,0.000005230354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001591036,"about_ca_system_score_gemma":0.0001166683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005023312,"about_ca_topic_score_gemma":0.000004535922,"domain_scores_codex":[0.985866,0.008813848,0.004175599,0.0003463528,0.0004716606,0.0003265013],"domain_scores_gemma":[0.343079,0.6529865,0.002888144,0.0002463969,0.0006739243,0.000126037],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.5272037,0.0004352576,0.02699467,0.0001231827,0.004195112,0.00001708354,0.0005179259,0.00680628,0.001388097,0.4204813,0.006031785,0.005805526],"study_design_scores_gemma":[0.1477391,0.0002770511,0.001840984,0.0001416375,0.0003202893,0.0000617969,0.00001845603,0.04570004,0.00004902063,0.8019127,0.001751709,0.0001871873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3437035,0.00009355142,0.6413427,0.002703428,0.0100155,0.001881964,0.0002158472,0.00001225635,0.00003121807],"genre_scores_gemma":[0.2600718,0.0000395993,0.7330459,0.001956423,0.00472414,0.00004637971,0.00000390544,0.00003747293,0.00007432119],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8008013,"threshold_uncertainty_score":0.9731281,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5624346742081207,"gpt":0.6001798666323802,"spread":0.03774519242425955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004747816,0.0002088345,0.001023645,0.00018084,0.00004978231,0.0000108188,0.000296851,0.0001643093,0.0005797995],"category_scores_gemma":[0.2249355,0.00012904,0.00003423355,0.0007293968,0.0005066833,0.00003807149,0.00008817995,0.0004530701,0.00000585902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001744657,"about_ca_system_score_gemma":0.000198628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006772228,"about_ca_topic_score_gemma":0.0001384239,"domain_scores_codex":[0.9963841,0.0009272852,0.001595113,0.0003081833,0.0004924686,0.0002928249],"domain_scores_gemma":[0.970709,0.02773507,0.0007021452,0.000486944,0.000295038,0.00007186142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006070863,0.0002602652,0.004528323,0.0006208214,0.00009215776,0.00007515206,0.003629701,0.0004233468,0.008536065,0.975642,0.00334475,0.002240334],"study_design_scores_gemma":[0.003756336,0.0002083429,0.003439062,0.001253103,0.0001588075,0.000002525094,0.0003699273,0.001777568,0.0005391135,0.9882916,0.00007056141,0.0001330174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02909794,0.0001363408,0.9628906,0.001250949,0.002045406,0.001187174,0.0001965385,0.00003915855,0.00315594],"genre_scores_gemma":[0.3235398,0.00004757665,0.6757451,0.0002629384,0.0001239902,0.00001580211,0.00000951733,0.0000262091,0.0002291229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2944418,"threshold_uncertainty_score":0.7815932,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4627300461880791,"gpt":0.5825008320195479,"spread":0.1197707858314688,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02762078,0.00007196935,0.0006179454,0.0002334303,0.00002117781,0.00002156509,0.0003579354,0.00007709048,0.00001965578],"category_scores_gemma":[0.07499105,0.00005315685,0.00005360906,0.0005164586,0.0001528311,0.0002806297,0.00008184087,0.00009058055,9.616272e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003420625,"about_ca_system_score_gemma":0.0001284876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001703853,"about_ca_topic_score_gemma":0.000002987573,"domain_scores_codex":[0.996649,0.0002387317,0.002311588,0.0001475974,0.0004863222,0.0001667763],"domain_scores_gemma":[0.9936362,0.004726628,0.0008603741,0.0001046075,0.0004244015,0.0002477964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008152379,0.002019177,0.004473413,0.0002783972,0.000049202,0.000001136135,0.001167985,0.0001075134,0.003137458,0.006182501,0.0002424533,0.9815255],"study_design_scores_gemma":[0.04110496,0.04201471,0.5676564,0.00193063,0.0007243953,0.00001408353,0.003286547,0.1212253,0.02191118,0.1964723,0.002561478,0.001097995],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5754164,0.000003833281,0.4234822,0.00005787315,0.0002749714,0.0007433064,0.000008224459,0.000004631663,0.000008579808],"genre_scores_gemma":[0.3474984,0.000009800978,0.652397,0.00001488966,0.00005727222,0.00001574609,7.15025e-7,0.000005472461,7.444334e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9804275,"threshold_uncertainty_score":0.9572867,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4469013499055617,"gpt":0.5635049915159488,"spread":0.1166036416103871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1663085,0.0002378437,0.005939792,0.000176304,0.00004319032,0.00002023777,0.0001865249,0.0001362806,0.0009731987],"category_scores_gemma":[0.6872705,0.0001606954,0.0009832832,0.0002804372,0.0002629868,0.00004142207,0.00007482371,0.0001846762,0.000001676016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002159463,"about_ca_system_score_gemma":0.0001266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001539499,"about_ca_topic_score_gemma":0.00000197087,"domain_scores_codex":[0.9723406,0.01112377,0.01503004,0.0004699758,0.0007687268,0.0002668923],"domain_scores_gemma":[0.7908946,0.1643804,0.04320049,0.0005565056,0.000851522,0.0001165057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02712101,0.0004545119,0.8876359,0.001962558,0.01576965,0.000008532779,0.001055802,0.0001426707,0.04289712,0.00046169,0.005372381,0.01711813],"study_design_scores_gemma":[0.2687288,0.001145574,0.4423322,0.001504433,0.04181717,0.00001126469,0.0006337537,0.01554816,0.09109859,0.1356896,0.00006498877,0.00142549],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8103694,0.0002386376,0.1845033,0.00005685972,0.0004933461,0.00312679,0.0005046466,0.00002384977,0.0006831415],"genre_scores_gemma":[0.8246808,0.0002006947,0.1742592,0.00002292837,0.000314357,0.00007849102,0.00001247642,0.00003724221,0.0003938378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5209619,"threshold_uncertainty_score":0.99994,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8925548796379184,"gpt":0.6694180607045064,"spread":0.223136818933412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01089868,0.000965921,0.006032603,0.0001185395,0.0002320552,0.0001534336,0.003934621,0.0012343,0.0002353199],"category_scores_gemma":[0.3396956,0.0007828465,0.001115228,0.000438987,0.0004018169,0.0001574948,0.002236621,0.001295059,0.00005778515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552165,"about_ca_system_score_gemma":0.0006856197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001084417,"about_ca_topic_score_gemma":0.000002517367,"domain_scores_codex":[0.9886574,0.002408723,0.005553665,0.002042739,0.0004869773,0.0008504821],"domain_scores_gemma":[0.725537,0.2670068,0.002618715,0.004418594,0.0001518575,0.0002670069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001236306,0.00248991,0.000003733311,0.03609641,0.001086999,0.00001872499,0.00001434284,3.088966e-8,0.00001094944,0.0164206,0.1624681,0.7812666],"study_design_scores_gemma":[0.0008581697,0.0001939845,0.000002413004,0.006054173,0.002730761,0.00001475973,0.000003930966,0.0001196286,0.000002794043,0.1054638,0.8837377,0.0008178717],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.000008934147,0.942593,0.007419548,0.0002036364,0.005596362,0.009519531,0.02298422,0.0008972785,0.01077754],"genre_scores_gemma":[0.000002395866,0.3549038,0.6415662,0.00007655108,0.002233808,0.0002359829,0.0004782388,0.0002226987,0.0002803105],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.7804487,"threshold_uncertainty_score":0.9994622,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.590758071255841,"gpt":0.4869642464323993,"spread":0.1037938248234417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003752818,0.0002173845,0.000574424,0.00002160857,0.001104086,0.0007120917,0.0005123286,0.0001172107,0.000009343811],"category_scores_gemma":[0.3595066,0.0001395965,0.00006272197,0.00003441548,0.001256527,0.0001236158,0.0004219114,0.0002602516,0.000001503273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001298256,"about_ca_system_score_gemma":0.00001534416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006416924,"about_ca_topic_score_gemma":0.00006609749,"domain_scores_codex":[0.9979202,0.0003214978,0.00057331,0.000374224,0.0003004649,0.0005103622],"domain_scores_gemma":[0.7629502,0.2356948,0.0003420665,0.000708318,0.00006397441,0.0002406406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002377606,0.00006310478,0.583567,0.00009433328,0.00006916635,0.000004743431,0.00008776748,6.688206e-9,0.00000459038,0.03243649,0.001224266,0.3824248],"study_design_scores_gemma":[0.00049651,0.00002807689,0.4517093,0.0000144494,0.00007297385,0.000001234689,0.00002992536,0.00001479112,0.00006422575,0.5466545,0.0007971175,0.000116866],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9218816,0.001441153,0.02294334,0.0278797,0.002352429,0.006482413,0.00254215,0.0006510913,0.01382616],"genre_scores_gemma":[0.9269372,0.0003452375,0.07087681,0.0001568209,0.0005846086,0.0006098354,8.045552e-7,0.00003186656,0.0004568237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.514218,"threshold_uncertainty_score":0.8491846,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Clinical trial; Medicine; Population; Randomization; Medical physics; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.8591717291981216,"gpt":0.6998938575083188,"spread":0.1592778716898028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.06213558,0.0005631667,0.008790208,0.0002046023,0.00003636702,0.00003541933,0.002611594,0.003172626,0.006880996],"category_scores_gemma":[0.83948,0.0002606606,0.001943071,0.000870452,0.0005092737,0.0000228952,0.0003352011,0.003628925,0.00005021092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006450816,"about_ca_system_score_gemma":0.001270957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009823618,"about_ca_topic_score_gemma":0.00002620462,"domain_scores_codex":[0.9610249,0.02796863,0.006396849,0.0006772974,0.003413827,0.0005184308],"domain_scores_gemma":[0.577539,0.4185084,0.001726013,0.001432598,0.000229533,0.0005645446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000131068,0.0001217642,0.000001004157,0.03397736,0.00009387497,0.0004770678,0.0007880506,2.233593e-10,8.124283e-10,0.0783012,0.005476014,0.8807505],"study_design_scores_gemma":[0.0005012216,0.00009626008,6.467026e-7,0.05133805,0.000910505,0.00008392886,0.00007948442,4.164365e-7,1.157547e-7,0.1793454,0.7674155,0.0002285264],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.752078e-7,0.9904303,0.001591434,0.0002869296,0.00158041,0.001570931,0.0003169888,0.00003867469,0.004183857],"genre_scores_gemma":[0.000001573269,0.9597266,0.03788779,0.0003447038,0.001584097,0.0003019343,0.00004070588,0.00006756624,0.00004506372],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.880522,"threshold_uncertainty_score":0.9999846,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Cytotoxic T cell; Solid tumor; Medicine; Biology; Cancer; Internal medicine; Genetics; In vitro","retraction":null,"screen_n_in":null,"score":{"opus":0.8358492860840319,"gpt":0.7003415538770064,"spread":0.1355077322070255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02117866,0.0003908197,0.002876415,0.0002115803,0.0001733904,0.00003826933,0.0006878784,0.000226835,0.00003224947],"category_scores_gemma":[0.4649375,0.0002262301,0.000956448,0.0003229541,0.0005507353,0.0002950684,0.0001429979,0.0007032292,0.000001161496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007966715,"about_ca_system_score_gemma":0.003825047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001359483,"about_ca_topic_score_gemma":9.050179e-7,"domain_scores_codex":[0.9925731,0.00256522,0.003111518,0.0002742555,0.001248023,0.0002278202],"domain_scores_gemma":[0.875796,0.1148199,0.00671452,0.0002164189,0.002336221,0.0001169915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1201017,0.005201881,9.447174e-8,0.07576878,0.02226567,0.00009983558,0.0007472528,0.0006093304,0.000049653,0.2628295,0.04089608,0.4714303],"study_design_scores_gemma":[0.02926091,0.001277724,6.242511e-8,0.0193812,0.006233605,0.0002184839,0.00003651285,0.000007598001,0.00009821009,0.7267547,0.2164625,0.0002684148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001211751,0.8733596,0.112704,0.000296782,0.008821598,0.003766463,0.0009540592,0.000007948833,0.00007738498],"genre_scores_gemma":[0.00001115277,0.6577637,0.3390718,0.0002223171,0.002593711,0.0002240597,0.000001125805,0.00004037408,0.00007176516],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4711618,"threshold_uncertainty_score":0.9225397,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8869929090371754,"gpt":0.7068485700059751,"spread":0.1801443390312003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2927062,0.0006528515,0.01097556,0.0004818782,0.00006274988,0.00002400492,0.0005551698,0.0009404628,0.0007850831],"category_scores_gemma":[0.93373,0.000482771,0.003155793,0.0007894145,0.000205444,0.00005324891,0.000129979,0.001044524,0.00005282431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002711898,"about_ca_system_score_gemma":0.0003884599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003800492,"about_ca_topic_score_gemma":0.00002391418,"domain_scores_codex":[0.6921057,0.2869046,0.01853535,0.001192584,0.0005334258,0.0007284048],"domain_scores_gemma":[0.3027395,0.6918125,0.00422263,0.0009259381,0.00008469092,0.0002147656],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003152453,0.0008657665,0.0001567492,0.003497076,0.0007694933,0.00002330275,0.00003085318,9.686043e-8,9.31408e-8,0.0006295983,0.006313343,0.9876821],"study_design_scores_gemma":[0.003660308,0.0005526339,0.00002493004,0.04232877,0.003246206,0.00001078341,0.00006089096,0.0005172467,0.000002382243,0.2129271,0.7356059,0.00106288],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00000126506,0.7424142,0.2521073,0.00009361305,0.0006954628,0.003062208,0.001158392,0.00007509762,0.0003924373],"genre_scores_gemma":[0.0000015113,0.6278976,0.3713476,0.00003317325,0.0002907914,0.0002002504,0.00006914551,0.00007116112,0.0000888116],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9866192,"threshold_uncertainty_score":0.9997624,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7857781232112138,"gpt":0.682581246318719,"spread":0.1031968768924948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01370645,0.0003447391,0.008195514,0.00005609909,0.00004674376,0.00001581304,0.000414482,0.0004766287,0.0001362207],"category_scores_gemma":[0.01648445,0.0001289846,0.0003180098,0.0001231144,0.000449363,0.00001148465,0.0001863131,0.000460711,0.000003206503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008960785,"about_ca_system_score_gemma":0.0001347208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006389874,"about_ca_topic_score_gemma":0.0001058075,"domain_scores_codex":[0.9843611,0.01291778,0.00192821,0.0003386523,0.0001514781,0.000302766],"domain_scores_gemma":[0.7988917,0.1990688,0.001384428,0.0005835702,0.00002564613,0.00004588539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000077623,0.00006846736,0.0001402379,0.003789659,0.0004403824,0.00000409822,0.0001319219,2.341387e-8,5.394221e-8,0.0196777,0.002546949,0.9731229],"study_design_scores_gemma":[0.001606161,0.0001803585,0.0002038558,0.0007527879,0.001685013,0.000008635299,0.00001792555,0.000001505209,3.354453e-7,0.1832808,0.8121597,0.0001029704],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000383093,0.9868216,0.00008766646,0.008113361,0.0008665255,0.002249944,0.0004262163,0.00001662537,0.001379784],"genre_scores_gemma":[0.000001773986,0.9759104,0.01756318,0.0001632588,0.00558314,0.0005243314,0.000002124194,0.0000319477,0.0002198208],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9730199,"threshold_uncertainty_score":0.9918001,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8284200588886782,"gpt":0.7350414308632734,"spread":0.09337862802540475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00936028,0.0004405157,0.001807687,0.0007069516,0.0002447876,0.001262763,0.004038271,0.0003534258,0.02011561],"category_scores_gemma":[0.2635971,0.0003704221,0.0004365259,0.00167696,0.0002246624,0.001044758,0.00088854,0.0009876463,0.00003856011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005554664,"about_ca_system_score_gemma":0.0004137069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002367563,"about_ca_topic_score_gemma":0.00004615671,"domain_scores_codex":[0.9948481,0.0005636293,0.00227713,0.0006929154,0.0009770689,0.0006411693],"domain_scores_gemma":[0.8811889,0.1150616,0.001732345,0.000875991,0.0005461695,0.0005949902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001080712,0.002185487,0.07342542,0.0007280229,0.0008193679,0.00005730275,0.0001438553,0.00001751281,0.1333836,0.08851691,0.3279957,0.3716461],"study_design_scores_gemma":[0.001470582,0.00005339377,0.02968638,0.0002410787,0.0002633377,0.00001172495,0.0000117482,0.0001386146,0.01874773,0.9406485,0.008251711,0.0004751908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06081313,0.00271145,0.9108847,0.0007896897,0.007600911,0.003451166,0.0007196829,0.0001802492,0.012849],"genre_scores_gemma":[0.1023471,0.0008606961,0.8932035,0.0002986288,0.00171893,0.0001322228,0.000003182309,0.0001262603,0.001309477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8521316,"threshold_uncertainty_score":0.9998748,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2100571163939553,"gpt":0.537255500117731,"spread":0.3271983837237757,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009642188,0.0001654348,0.0006273185,0.0001040859,0.00006652711,0.00001728893,0.0001510012,0.0003427796,0.0005021446],"category_scores_gemma":[0.07395963,0.0001568813,0.0000473947,0.0001793517,0.0002724307,0.00005361922,0.0001166676,0.0005652343,0.00006834891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000176377,"about_ca_system_score_gemma":0.00006600303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003785643,"about_ca_topic_score_gemma":0.0001250461,"domain_scores_codex":[0.9935718,0.004606232,0.000777728,0.0005023089,0.0001282498,0.0004137064],"domain_scores_gemma":[0.9322332,0.06713937,0.0001903628,0.0002833738,0.00005810495,0.00009562015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003795144,0.0001741202,0.2337259,0.0002100623,0.00004964561,0.00001498606,0.0003046921,0.0000268375,0.003321353,0.7279707,0.0006818308,0.03314038],"study_design_scores_gemma":[0.0005472021,0.0002356306,0.1907427,0.00004446047,0.00002985518,0.000006079828,0.00009390026,0.004986249,0.0001787383,0.8028807,0.000102998,0.0001514585],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1563446,0.00002971905,0.8382403,0.0004927855,0.001161411,0.0005146993,0.00002713724,0.0000628725,0.003126455],"genre_scores_gemma":[0.3060703,0.00001158527,0.6933671,0.0001127187,0.00006438178,0.00003247334,7.592157e-7,0.00001631046,0.0003243427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1497256,"threshold_uncertainty_score":0.9338408,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9463831388066777,"gpt":0.7778418496968618,"spread":0.1685412891098159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5551415,0.0009410062,0.0260746,0.001227283,0.0002129987,0.000166126,0.002211444,0.001768083,0.001011599],"category_scores_gemma":[0.9736168,0.0005055639,0.002429883,0.004074937,0.004184239,0.00008597986,0.00109363,0.004243182,0.000006155733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002059849,"about_ca_system_score_gemma":0.001498848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004566109,"about_ca_topic_score_gemma":0.00001128985,"domain_scores_codex":[0.510965,0.4708693,0.009951133,0.002088987,0.004582991,0.00154251],"domain_scores_gemma":[0.04442916,0.9503744,0.0015042,0.001542133,0.0007138472,0.001436248],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00658107,0.0001948246,2.579657e-8,0.01889027,0.003266099,0.00003722822,0.00005871476,0.000002707367,8.033118e-8,0.3820854,0.0006756268,0.5882079],"study_design_scores_gemma":[0.0196732,0.0003341664,3.260747e-7,0.00525555,0.02015654,0.000003361065,0.00002529548,0.2544487,0.00000111479,0.680052,0.01971435,0.0003352986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.147023e-8,0.4587681,0.5290315,0.000218344,0.0003186032,0.01104832,0.000546974,0.00002315518,0.00004499701],"genre_scores_gemma":[9.028888e-8,0.4911679,0.5047529,0.00006965491,0.0002022741,0.003678867,0.00002127306,0.0000884597,0.00001852195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5878726,"threshold_uncertainty_score":0.9999016,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5062045424251019,"gpt":0.6209226704404257,"spread":0.1147181280153238,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05315469,0.0001324694,0.002234052,0.00004143551,0.00003887423,0.000007085114,0.0006133611,0.0008016671,0.0002963057],"category_scores_gemma":[0.6388645,0.00006850441,0.0007018838,0.000443751,0.001042392,0.00003077283,0.0002822258,0.001171999,0.000006891917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001851862,"about_ca_system_score_gemma":0.001152006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003231146,"about_ca_topic_score_gemma":0.0001136451,"domain_scores_codex":[0.9402244,0.05465157,0.003985956,0.000373084,0.0005025108,0.0002624496],"domain_scores_gemma":[0.498038,0.4993135,0.001477172,0.000783174,0.0003433854,0.00004478564],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.4461532,0.003525533,0.0002978434,0.00006444454,0.0001370974,0.00003062447,0.0005928125,0.000006048721,0.00021824,0.3619189,0.005017311,0.1820379],"study_design_scores_gemma":[0.3391635,0.0009580592,0.00108363,0.00005998772,0.0001985243,0.00001194893,0.0002116693,0.0002299295,0.0002146071,0.6550515,0.002765422,0.000051153],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8396345,0.0003715813,0.08502742,0.02617938,0.01192777,0.006295986,0.00006759122,0.00003227143,0.03046345],"genre_scores_gemma":[0.5210251,0.0002016636,0.4763527,0.0009637403,0.001099841,0.0002123767,0.000001346033,0.00002051707,0.000122685],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5857098,"threshold_uncertainty_score":0.9749765,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9461285919310349,"gpt":0.6823623987532028,"spread":0.2637661931778321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08384932,0.0004264817,0.001627881,0.000142988,0.0007671227,0.0001668413,0.00155595,0.0007401212,0.0002238955],"category_scores_gemma":[0.5679737,0.0002660551,0.0005950127,0.001374535,0.003654025,0.0001447162,0.0008276859,0.004492684,0.00001325379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002059391,"about_ca_system_score_gemma":0.004298253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003348926,"about_ca_topic_score_gemma":0.0005377157,"domain_scores_codex":[0.9669268,0.01992807,0.007330248,0.001600498,0.003449702,0.0007646853],"domain_scores_gemma":[0.630789,0.3625194,0.002093771,0.001751494,0.001964443,0.0008818351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.6702516,0.01022212,0.009353511,0.0000905517,0.001010783,0.00002800926,0.0005926752,0.001543125,0.0001660646,0.04474416,0.08223962,0.1797578],"study_design_scores_gemma":[0.2471476,0.0100765,0.01582357,0.0006540812,0.0005130778,0.000005348564,0.00006326619,0.01556321,0.0004889071,0.7013312,0.00746499,0.0008682408],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8349006,0.0000889661,0.1237226,0.01496915,0.01099216,0.01422509,0.0007703896,0.0001006067,0.0002304462],"genre_scores_gemma":[0.4602635,0.0001211596,0.526312,0.001387596,0.008810285,0.002731724,0.00002840633,0.0001210032,0.0002243845],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6565871,"threshold_uncertainty_score":0.9999791,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Class (philosophy); Binary number; Mathematical economics; Mathematics; Computer science; Econometrics; Actuarial science; Artificial intelligence; Economics; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.4361016309661956,"gpt":0.4725475954723197,"spread":0.03644596450612408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001307559,0.0001189128,0.0003550939,0.0001703111,0.00009220971,0.00006560223,0.000173605,0.00009014785,0.0002081689],"category_scores_gemma":[0.01506369,0.00009438465,0.00004408039,0.0001843871,0.0001969215,0.00006853988,0.000003621934,0.0002760263,0.00001252494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001808137,"about_ca_system_score_gemma":0.0008515169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006685427,"about_ca_topic_score_gemma":0.00651241,"domain_scores_codex":[0.9982729,0.0002388997,0.0008352472,0.0001154546,0.000290014,0.0002474649],"domain_scores_gemma":[0.9916123,0.006637946,0.0006269071,0.0001862509,0.0005824769,0.0003541829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004466499,0.00003029036,0.003562667,0.00004132598,0.00003293604,0.0002220939,0.00003589481,0.00002434558,0.00006668834,0.9555516,0.03273604,0.007651477],"study_design_scores_gemma":[0.0005568257,0.0002869723,0.01977132,0.00009089297,0.0001253142,0.0001123981,0.00005686169,0.0002202811,0.00007876779,0.9750461,0.003520486,0.0001337803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00776162,0.0000386851,0.9879899,0.0003666513,0.000442362,0.0001347615,0.0003424951,0.000008947018,0.002914561],"genre_scores_gemma":[0.2017991,0.000005753207,0.7975348,0.0000494149,0.000361744,0.000001739293,0.000003580226,0.00002311484,0.0002208076],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1940375,"threshold_uncertainty_score":0.9932328,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9032678520110035,"gpt":0.6778586125422745,"spread":0.2254092394687289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009173804,0.0002065884,0.001063946,0.00004914518,0.00009879432,0.00001225924,0.0002947208,0.0001902977,0.000525408],"category_scores_gemma":[0.1358759,0.0001763823,0.0001824709,0.0001323703,0.0001770699,0.00004037108,0.0001419704,0.0002319869,0.000008965491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008310012,"about_ca_system_score_gemma":0.00008694465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008754418,"about_ca_topic_score_gemma":0.00005500115,"domain_scores_codex":[0.9953949,0.0008768084,0.002514813,0.0006516391,0.0001235132,0.0004383652],"domain_scores_gemma":[0.98602,0.01084123,0.002017333,0.0007460323,0.0002542887,0.0001210796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004063759,0.005888928,0.2850852,0.0009034093,0.0008320253,0.0004709793,0.01106423,5.479925e-7,0.04155178,0.3768388,0.005841225,0.2674591],"study_design_scores_gemma":[0.001867264,0.0007878745,0.0491371,0.0000179115,0.0002120369,0.00001247316,0.0004667595,0.00002067784,0.005506491,0.9414008,0.0002802533,0.0002903772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6948947,0.00009809386,0.2915048,0.000326086,0.003430731,0.003547267,0.0002441346,0.0003340895,0.005620065],"genre_scores_gemma":[0.2662402,0.000007955752,0.73168,0.0002996179,0.0005159689,0.0008131709,9.608879e-7,0.00005023952,0.0003918578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.564562,"threshold_uncertainty_score":0.871403,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9293997658481492,"gpt":0.77552257358576,"spread":0.1538771922623892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07067659,0.0002352842,0.0006888845,0.00006532417,0.0008528597,0.0003443585,0.0016745,0.0008205347,0.001844685],"category_scores_gemma":[0.4899555,0.0001402205,0.0003028617,0.0007362232,0.003832454,0.00008427187,0.0005422208,0.007012762,0.0003190964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007064987,"about_ca_system_score_gemma":0.0007371856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004633197,"about_ca_topic_score_gemma":0.00009732362,"domain_scores_codex":[0.9882316,0.006388064,0.001756662,0.0008620814,0.001659352,0.001102259],"domain_scores_gemma":[0.5650147,0.4311458,0.0002741835,0.001392041,0.00165139,0.0005219341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005899582,0.0008165739,0.002636164,0.0000736559,0.000412004,0.00009208643,0.0001119134,0.00001014447,0.003489396,0.5459272,0.2286101,0.2119212],"study_design_scores_gemma":[0.00118935,0.0004757538,0.00224028,0.00004604017,0.00003173449,0.00000171069,0.00003168148,0.0005393244,0.003449813,0.9742391,0.01755017,0.0002050967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3802807,0.002671826,0.4625733,0.04129512,0.05122392,0.01936238,0.001114584,0.001815346,0.03966286],"genre_scores_gemma":[0.2539243,0.0007910292,0.7293174,0.0005998096,0.006400472,0.0009641284,0.00000165708,0.0001751844,0.007826094],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4283118,"threshold_uncertainty_score":0.9990678,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5587308049738138,"gpt":0.6187845387614808,"spread":0.06005373378766699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01865485,0.0001318152,0.0006477474,0.00006821886,0.0000634176,0.0000145403,0.0002213538,0.0001340299,0.00008487343],"category_scores_gemma":[0.3376411,0.00008076955,0.00003089282,0.0001519213,0.0009333927,0.0000684545,0.0000707949,0.0003898998,0.000007382561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817367,"about_ca_system_score_gemma":0.00008635099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001161245,"about_ca_topic_score_gemma":0.000007046101,"domain_scores_codex":[0.9950607,0.001457587,0.002590185,0.0001585994,0.0005026592,0.0002302093],"domain_scores_gemma":[0.8475086,0.1514656,0.0005115395,0.000281843,0.0001366871,0.00009570134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00653325,0.00008258587,0.00006960158,0.00005099456,0.00003150037,0.00000245476,0.0002478989,0.00002910914,0.000002312445,0.7330124,0.01336177,0.2465761],"study_design_scores_gemma":[0.02598109,0.001740946,0.0006570011,0.0001019282,0.00009625724,0.000002700716,0.0001621973,0.01439383,0.00002182247,0.9533074,0.003434558,0.000100239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002942194,0.00007956684,0.9934734,0.00114406,0.000808301,0.000795131,0.00006130837,0.00001650723,0.0006795272],"genre_scores_gemma":[0.007743992,0.0005403189,0.9908193,0.0002112728,0.0005988994,0.00002521435,0.000002594898,0.0000111811,0.00004721653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3189862,"threshold_uncertainty_score":0.6679382,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9552590505586375,"gpt":0.7305588347048191,"spread":0.2247002158538184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08004504,0.0002329358,0.001677058,0.00005561908,0.0002476379,0.00005949972,0.0002038016,0.0004406294,0.0004242769],"category_scores_gemma":[0.8862401,0.0001859832,0.0007820483,0.00009719199,0.0005068943,0.00005620324,0.00005641663,0.0002283106,0.00009949572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003057152,"about_ca_system_score_gemma":0.0004435697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002557469,"about_ca_topic_score_gemma":0.00001559802,"domain_scores_codex":[0.9878659,0.00658071,0.004276298,0.000605088,0.0002504571,0.0004215148],"domain_scores_gemma":[0.2271218,0.7696115,0.001361148,0.0006980884,0.0009799917,0.0002274725],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002217467,0.0003803088,0.00002059883,0.00003592868,0.0003783372,0.000001720828,0.0001486943,9.956279e-7,0.00003507764,0.4802012,0.494188,0.02239172],"study_design_scores_gemma":[0.00427155,0.002459488,0.00003525224,0.00006953437,0.000614351,0.000002973884,0.00007779279,0.004824508,0.0007724234,0.9715386,0.01508016,0.0002533866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008287303,0.0000160358,0.9824475,0.004084447,0.002833297,0.008480642,0.0004648845,0.0001264803,0.001463861],"genre_scores_gemma":[0.002749128,0.000006734153,0.9857111,0.001900179,0.007224127,0.001678661,0.000002159702,0.00006744993,0.0006604855],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8061951,"threshold_uncertainty_score":0.9472872,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9772817153848696,"gpt":0.7307094998449754,"spread":0.2465722155398943,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2205771,0.0006035994,0.006994665,0.0001335079,0.0003987238,0.00008899564,0.0008476813,0.001620519,0.00037915],"category_scores_gemma":[0.9264608,0.0004691704,0.004040637,0.0004116771,0.001453419,0.0001349282,0.0002975665,0.00146484,0.0002090442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009086327,"about_ca_system_score_gemma":0.0006424894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007391456,"about_ca_topic_score_gemma":0.000002300503,"domain_scores_codex":[0.9445345,0.03285517,0.01839224,0.00213342,0.0009653827,0.00111924],"domain_scores_gemma":[0.2431925,0.7495364,0.003834724,0.001972497,0.0004677245,0.0009961684],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1381226,0.006530461,0.00106249,0.0002443983,0.001584456,0.00009074555,0.00008179196,0.000005859795,0.00002415015,0.1682257,0.2454717,0.4385557],"study_design_scores_gemma":[0.1571015,0.004514127,0.0004044351,0.0001938742,0.001026669,0.00002608096,0.00005367846,0.001040609,0.0002484113,0.8169404,0.01762435,0.0008258701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2894155,0.0003494565,0.6130906,0.004505509,0.04986492,0.02535537,0.0007671203,0.001349132,0.01530234],"genre_scores_gemma":[0.03545307,0.0005034011,0.9384357,0.0008664038,0.02220589,0.0005596886,0.00001559493,0.0001767746,0.001783456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7166812,"threshold_uncertainty_score":0.999776,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7954584011993118,"gpt":0.678490372859101,"spread":0.1169680283402108,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_broad","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4546899,0.000322032,0.03045741,0.0001415553,0.00008110636,0.000009002053,0.0007188786,0.0005646948,0.0005220788],"category_scores_gemma":[0.9929243,0.0001416781,0.004483221,0.0001531367,0.003540024,0.0001086439,0.00009431402,0.001551611,0.000008721194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000195736,"about_ca_system_score_gemma":0.000771356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001325339,"about_ca_topic_score_gemma":0.000001796585,"domain_scores_codex":[0.6180377,0.3182268,0.06154222,0.0005703026,0.001035476,0.0005875734],"domain_scores_gemma":[0.02189254,0.9482471,0.02805848,0.000473542,0.001003841,0.0003245157],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.488846,0.0007871134,0.005275751,0.0001290771,0.003863066,0.00007070564,0.0002707286,0.0000638211,0.00003338903,0.472519,0.01159967,0.01654167],"study_design_scores_gemma":[0.1345706,0.000933777,0.001163502,0.0002315867,0.0008302222,0.00004069316,0.00004291292,0.007713382,0.00003188799,0.8542461,0.00007887548,0.0001165116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01287012,0.0006946984,0.9766692,0.004090431,0.002888175,0.001342931,0.00003413524,0.0000150948,0.001395228],"genre_scores_gemma":[0.6006829,0.001215197,0.3962267,0.0009526445,0.0008305837,0.00003052739,6.993794e-7,0.00001421621,0.00004653822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6300203,"threshold_uncertainty_score":0.9991718,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6090490742207253,"gpt":0.5329850486829449,"spread":0.07606402553778036,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004384618,0.0002050755,0.0008513732,0.00006930033,0.00005986699,0.000004519154,0.0003525388,0.00007944301,0.00004454592],"category_scores_gemma":[0.1536168,0.00007045064,0.00008970518,0.000128932,0.0007947853,0.0000163228,0.00005394586,0.0002071665,4.573518e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005111064,"about_ca_system_score_gemma":0.0000644866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007620549,"about_ca_topic_score_gemma":0.000006848236,"domain_scores_codex":[0.997444,0.0004068706,0.001170678,0.0002246957,0.000470792,0.0002830104],"domain_scores_gemma":[0.8604295,0.1384452,0.0005214434,0.0004059188,0.0001489664,0.00004888378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009997964,0.0004583304,0.03552201,0.0009509864,0.0002925588,0.000001594305,0.001593688,0.0004479432,0.00121152,0.92904,0.001633613,0.02784801],"study_design_scores_gemma":[0.002184932,0.002055496,0.009312034,0.001963553,0.0002067433,8.396643e-7,0.0002092338,0.1986456,0.0009474216,0.784352,0.000001335051,0.0001208108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3953355,0.00002455877,0.6026335,0.000290307,0.0001550652,0.001030751,0.0004163462,0.000009793811,0.0001042106],"genre_scores_gemma":[0.8511531,0.00007501791,0.1484722,0.00001389679,0.0001036638,0.0001197956,0.000002022924,0.00002547011,0.00003482617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4558177,"threshold_uncertainty_score":0.8535126,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}