{"meta":{"query_hash":"65f19e95c375","filters":{"venue":"Pharmaceutical Statistics"},"cohort_total":55,"direct_labels_cover":2,"predictions_cover":55,"exported":55,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/65f19e95c375","api":"https://metacan.xera.ac/api/v1/cohort?venue=Pharmaceutical+Statistics"},"results":[{"id":"W1905891062","doi":"10.1002/pst.1704","title":"Bayesian inference in two‐arm trials using relative belief ratios","year":2015,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Inference; Statistical inference; Bayesian inference; Computer science; Artificial intelligence; Bayesian statistics; Fiducial inference; Measure (data warehouse); Machine learning; Frequentist inference; Econometrics; Statistics; Mathematics; Data mining","score_opus":0.8804641098560438,"score_gpt":0.7012657224618299,"score_spread":0.1791983873942139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1905891062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014833735,0.00008675235,0.9921043,0.0003331059,0.0010500144,0.0011783877,0.000749253,0.00011542266,0.0028994123],"genre_scores_gemma":[0.15299295,0.000036038775,0.8458791,0.00043174883,0.00042914436,0.000051265084,0.000009725577,0.000064258806,0.00010579159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98910785,0.005556908,0.002878029,0.0006577001,0.0009963049,0.00080318673],"domain_scores_gemma":[0.8246928,0.17298685,0.000607617,0.00044476494,0.00042462238,0.0008433689],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015221618,0.00044415312,0.0017217424,0.00017063064,0.00009914763,0.00010927119,0.00040747656,0.00020248267,0.0011077534],"category_scores_gemma":[0.5218032,0.00039077588,0.00013824058,0.0005987338,0.00044265206,0.00021278544,0.00023850493,0.0010669231,0.00011675962],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056610967,0.0008102831,0.0024858136,0.00012832927,0.00014031782,0.00018667767,0.00047605622,0.0003587576,0.0001894892,0.9649017,0.001461234,0.028295225],"study_design_scores_gemma":[0.004613851,0.00015552675,0.00006511564,0.00009937152,0.0003263364,0.0000064422347,0.000058906135,0.13091256,0.0007252907,0.8616699,0.00095355604,0.00041314436],"about_ca_topic_score_codex":0.00006889609,"about_ca_topic_score_gemma":0.000038870054,"teacher_disagreement_score":0.50658154,"about_ca_system_score_codex":0.00038558582,"about_ca_system_score_gemma":0.00042066752,"threshold_uncertainty_score":0.9998544},"labels":[],"label_agreement":null},{"id":"W1979781274","doi":"10.1002/pst.200","title":"Power and sample size considerations in clinical trials with competing risk endpoints","year":2006,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Sample size determination; Accrual; Event (particle physics); Weibull distribution; Clinical trial; Econometrics; Parametric statistics; Clinical endpoint; Sample (material); Statistics; Actuarial science; Computer science; Medicine; Economics; Mathematics; Internal medicine; Accounting","score_opus":0.6618107269419979,"score_gpt":0.6408193264275303,"score_spread":0.020991400514467684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979781274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05259555,0.000096377364,0.9373134,0.0007738231,0.0005972385,0.0015125053,0.00457074,0.00015950401,0.002380879],"genre_scores_gemma":[0.2516844,0.000079933845,0.7475139,0.0003804666,0.00023590632,0.0000343012,0.0000032724008,0.00004311347,0.00002470843],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863247,0.0083031515,0.0035664402,0.0006618543,0.00054189644,0.0006019303],"domain_scores_gemma":[0.362777,0.63577366,0.0006596732,0.00029240685,0.00017397513,0.00032330232],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022997811,0.00034623445,0.0016374026,0.00006813225,0.0001828272,0.00013462326,0.00013418266,0.00021596531,0.002481508],"category_scores_gemma":[0.7308038,0.00027147512,0.000118424185,0.00021083924,0.0007889185,0.000064949956,0.0001292901,0.0010918117,0.00002632577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083221885,0.0013840463,0.11557658,0.00017629842,0.00022859962,0.0002684898,0.00011071451,0.000024114159,0.000075539225,0.8552109,0.0068674274,0.019245086],"study_design_scores_gemma":[0.00467783,0.00020588368,0.029737258,0.00006745265,0.00034698527,0.000019360798,0.000042641415,0.0030727237,0.00015133256,0.96053374,0.0007938568,0.00035091836],"about_ca_topic_score_codex":0.000092018636,"about_ca_topic_score_gemma":0.0001153098,"teacher_disagreement_score":0.70780593,"about_ca_system_score_codex":0.000056245193,"about_ca_system_score_gemma":0.000112373666,"threshold_uncertainty_score":0.9999737},"labels":[],"label_agreement":null},{"id":"W1980598266","doi":"10.1002/pst.338","title":"Impact of baseline ECG collection on the planning, analysis and interpretation of ‘thorough’ QT trials","year":2008,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Cardiac electrophysiology and arrhythmias","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Health Canada","keywords":"Baseline (sea); Medicine; QT interval; Replicate; Time point; Statistics; Internal medicine; Mathematics","score_opus":0.08796446487793805,"score_gpt":0.43880973624290165,"score_spread":0.3508452713649636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980598266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8700707,0.00022140864,0.12886901,0.00014570053,0.000043062355,0.00024372428,0.00021212705,0.000009138561,0.00018516029],"genre_scores_gemma":[0.9976679,0.00037317237,0.0016521746,0.00012220003,0.000061023336,0.000006823435,0.00006261081,0.0000063589114,0.000047717986],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988397,0.00037834852,0.00038371704,0.00012407998,0.00015631315,0.00011789069],"domain_scores_gemma":[0.99706674,0.0024705676,0.0001652875,0.000103673694,0.00012389508,0.00006986539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000600513,0.000095702315,0.0005492996,0.0001140909,0.000062245956,0.0000021694113,0.00002361625,0.000048601774,0.00021798097],"category_scores_gemma":[0.0017386668,0.000058206857,0.0001921429,0.00037815532,0.0001929907,0.00001502084,0.000011632652,0.00018020463,0.0000020861673],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.081724465,0.0031021284,0.41542047,0.0008100571,0.03917854,0.0010741147,0.006735893,0.028439194,0.19036688,0.009677843,0.05557971,0.1678907],"study_design_scores_gemma":[0.0028621403,0.0026168672,0.35276645,0.000067295434,0.006305695,0.00017518511,0.00004042102,0.5999336,0.034025107,0.00088545855,0.00013808924,0.0001836642],"about_ca_topic_score_codex":0.000032367294,"about_ca_topic_score_gemma":0.0000010290877,"teacher_disagreement_score":0.5714944,"about_ca_system_score_codex":0.00003430027,"about_ca_system_score_gemma":0.0000637971,"threshold_uncertainty_score":0.23867387},"labels":[],"label_agreement":null},{"id":"W2019978533","doi":"10.1002/pst.244","title":"Assessment of the Gould‐Shih procedure for sample size re‐estimation","year":2006,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Standard deviation; Sample size determination; Statistics; Mathematics; Estimator; Standard error; Nominal level; Confidence interval","score_opus":0.5327868823583967,"score_gpt":0.6279960254321367,"score_spread":0.09520914307374007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019978533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021048314,0.000015051841,0.9894403,0.00085212855,0.0005780656,0.0016636336,0.004128759,0.00007066782,0.0011465662],"genre_scores_gemma":[0.18614449,0.000006491156,0.81298804,0.00028506477,0.00021858081,0.0001528095,0.000011004025,0.000041969568,0.00015156779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967411,0.00050751434,0.001276417,0.0003667678,0.0006734951,0.0004347018],"domain_scores_gemma":[0.8578741,0.1408698,0.00044243952,0.00038094085,0.0003096705,0.0001230626],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021249305,0.00024522436,0.00059336046,0.000025555402,0.00016490747,0.000042839307,0.00037751414,0.0001527416,0.00051321514],"category_scores_gemma":[0.17033862,0.00017476738,0.00016473542,0.00026011403,0.00035364466,0.00004308192,0.00012204,0.00036098112,0.000004111914],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008968214,0.00055026263,0.0023984932,0.0009819178,0.000063057305,0.0000015383426,0.00001923898,0.00013613656,0.00074030133,0.968522,0.020024404,0.0064729718],"study_design_scores_gemma":[0.00130002,0.00010154367,0.010135794,0.0000676439,0.00036868243,0.000001821217,0.000009164891,0.09176667,0.0021197624,0.89227957,0.0016586871,0.00019064028],"about_ca_topic_score_codex":0.000024674975,"about_ca_topic_score_gemma":0.000013188455,"teacher_disagreement_score":0.18403965,"about_ca_system_score_codex":0.00011276527,"about_ca_system_score_gemma":0.0001700215,"threshold_uncertainty_score":0.83664995},"labels":[],"label_agreement":null},{"id":"W2024015933","doi":"10.1002/pst.294","title":"Sequential design approaches for bioequivalence studies with crossover designs","year":2007,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Theratechnologies (Canada)","funders":"","keywords":"Sample size determination; Bioequivalence; Crossover; Variance (accounting); Crossover study; Statistics; Type I and type II errors; Statistical power; Clinical study design; A priori and a posteriori; Computer science; Mathematics; Econometrics; Clinical trial; Medicine; Machine learning; Placebo; Pharmacology; Pharmacokinetics","score_opus":0.9499294280480977,"score_gpt":0.6769455700599387,"score_spread":0.27298385798815894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024015933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005018375,0.00023853769,0.99548227,0.00019111783,0.0006009637,0.0018031155,0.0007165315,0.00017295188,0.0002926923],"genre_scores_gemma":[0.026120493,0.00009018419,0.9723901,0.00038403887,0.0005180414,0.00015318145,0.0000060646285,0.00009516204,0.00024274185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957122,0.0005995682,0.0011907405,0.0007026183,0.00073203206,0.0010628321],"domain_scores_gemma":[0.87751573,0.1209517,0.0002961455,0.00036706903,0.0004354459,0.00043390825],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007773739,0.00044040784,0.0008799425,0.00007936053,0.00028330684,0.00009160008,0.0003865692,0.00018391006,0.00016793206],"category_scores_gemma":[0.060723636,0.00033103136,0.00011392797,0.0002938384,0.0012387057,0.0000778929,0.00013350644,0.00043333616,0.000026839789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047788313,0.0006209284,0.00013829129,0.0010390279,0.00078845734,0.0001395825,0.00032404324,0.00009763594,0.00060947187,0.902356,0.008539382,0.080568306],"study_design_scores_gemma":[0.0033620347,0.0007173656,0.000050896087,0.0000796646,0.0009265163,0.000022952372,0.0001257416,0.008321926,0.0192227,0.9645975,0.0020009943,0.0005717041],"about_ca_topic_score_codex":0.0000017270233,"about_ca_topic_score_gemma":0.0000048496267,"teacher_disagreement_score":0.120352134,"about_ca_system_score_codex":0.00016858298,"about_ca_system_score_gemma":0.00012017925,"threshold_uncertainty_score":0.99991417},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2030706697","doi":"10.1002/pst.368","title":"The Rheumatoid Arthritis Drug Development Model: a case study in Bayesian clinical trial simulation","year":2009,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes","funders":"AstraZeneca","keywords":"Drug development; Clinical trial; Medicine; Rheumatoid arthritis; Bayesian probability; Outcome (game theory); Population; Intensive care medicine; Drug; Risk analysis (engineering); Medical physics; Computer science; Internal medicine; Pharmacology; Artificial intelligence; Mathematics","score_opus":0.6679110266087562,"score_gpt":0.6478830317170668,"score_spread":0.020027994891689382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030706697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12408167,0.00009341335,0.8708831,0.00036447617,0.000908428,0.0032089127,0.00008994668,0.00014474404,0.00022530717],"genre_scores_gemma":[0.5625781,0.00016527722,0.43669572,0.00023673712,0.00016926172,0.000081675455,0.0000021625335,0.000032865868,0.00003822729],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9902754,0.0032720088,0.0039317664,0.000742495,0.0009548604,0.00082350173],"domain_scores_gemma":[0.89799815,0.10033352,0.00041833165,0.00055466907,0.00020748546,0.0004878668],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013298714,0.00041505106,0.0010448612,0.00008379267,0.0004608106,0.00018736842,0.00043221394,0.00018729574,0.00011085986],"category_scores_gemma":[0.08118486,0.00031804314,0.00013892245,0.00035193822,0.00029217472,0.00009065886,0.00014956052,0.0011870265,0.000037318383],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.011894642,0.0058337376,0.000813237,0.000031980177,0.00014383483,0.0041026613,0.001161354,0.0016623886,9.4883615e-7,0.08434432,0.001950173,0.88806075],"study_design_scores_gemma":[0.034659326,0.0004839977,0.00016657733,0.000044922206,0.00006126784,0.00005927126,0.00025160707,0.42453104,0.0000103126395,0.538469,0.0008897886,0.0003729073],"about_ca_topic_score_codex":0.000014386698,"about_ca_topic_score_gemma":0.0002250095,"teacher_disagreement_score":0.8876878,"about_ca_system_score_codex":0.00016687972,"about_ca_system_score_gemma":0.0002828459,"threshold_uncertainty_score":0.99992716},"labels":[],"label_agreement":null},{"id":"W2042319973","doi":"10.1002/pst.443","title":"On assessing the presence of evaluation‐time bias in progression‐free survival in randomized trials","year":2010,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Randomized controlled trial; Computer science; Test (biology); Log-rank test; Randomized experiment; Progression-free survival; Statistics; Econometrics; Overall survival; Survival analysis; Medical physics; Medicine; Oncology; Mathematics; Internal medicine","score_opus":0.7951823931859413,"score_gpt":0.6931044078284545,"score_spread":0.1020779853574868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042319973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17779215,0.00026012867,0.7785403,0.0053504845,0.0069778403,0.01784914,0.0017224479,0.0001791767,0.011328334],"genre_scores_gemma":[0.29913732,0.0000406067,0.6999807,0.00014562906,0.00022656798,0.0003756092,0.000007167492,0.00004655996,0.000039832237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9601973,0.03132057,0.0046239374,0.00063134066,0.0025479055,0.0006789388],"domain_scores_gemma":[0.37889385,0.61894983,0.0009234143,0.00069591036,0.00036143692,0.00017556973],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13138388,0.0003142049,0.0025338796,0.00016629064,0.00007550101,0.00009401798,0.0006438875,0.00023427875,0.0023130036],"category_scores_gemma":[0.9009176,0.00018939546,0.00022792659,0.0005426999,0.0010259817,0.00008533974,0.00023398551,0.0014394823,0.00002843375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012166324,0.0013026465,0.0006157302,0.00021919556,0.00012264351,0.000037753787,0.00021418954,0.00007227167,0.0014537188,0.8917318,0.0019757925,0.09008792],"study_design_scores_gemma":[0.05567032,0.000048562182,0.0005783744,0.00016962721,0.00031124233,0.0000017829238,0.000016376835,0.11085637,0.001538857,0.83057266,0.000054186035,0.00018163478],"about_ca_topic_score_codex":0.000020660711,"about_ca_topic_score_gemma":0.000027629207,"teacher_disagreement_score":0.7695337,"about_ca_system_score_codex":0.000066122644,"about_ca_system_score_gemma":0.0002725744,"threshold_uncertainty_score":0.998599},"labels":[],"label_agreement":null},{"id":"W2049564589","doi":"10.1002/pst.289","title":"Comparing two independent incidence rates using conditional and unconditional exact tests","year":2007,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western Forest Products","funders":"","keywords":"Exact statistics; Mathematics; Statistics; Exact test; Wald test; Type I and type II errors; Score test; Poisson distribution; Likelihood-ratio test; Binomial distribution; p-value; Chi-square test; Negative binomial distribution; Binomial test; Nominal level; Statistic; Test statistic; Statistical hypothesis testing; Confidence interval","score_opus":0.7041238095391115,"score_gpt":0.6470359725829649,"score_spread":0.05708783695614661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049564589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12058225,0.000045505203,0.876714,0.000070888986,0.0004295484,0.00035842348,0.0010205854,0.000083693325,0.0006950882],"genre_scores_gemma":[0.49563912,0.00000807852,0.503669,0.00034520123,0.00026092303,0.0000060858347,0.000030673036,0.000025027311,0.000015888943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99637544,0.00041306778,0.0011595647,0.00050396926,0.0009048405,0.0006431212],"domain_scores_gemma":[0.93898284,0.059767816,0.00028658463,0.00019614398,0.00027867034,0.00048792822],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039730743,0.00031051273,0.0006097646,0.00010588361,0.00025534813,0.00010316459,0.00022115314,0.00012812152,0.0011634314],"category_scores_gemma":[0.031299066,0.0002991394,0.000059353977,0.00021204635,0.0006694726,0.00013716918,0.00023396485,0.0006834608,0.0000465216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002475749,0.00035300417,0.07414464,0.00018944492,0.00014146938,0.00029079808,0.000048153994,0.000060664188,0.001491235,0.9166765,0.0015749811,0.004781505],"study_design_scores_gemma":[0.0020539118,0.000061728024,0.045733564,0.00006911553,0.00021607352,0.0001280046,0.000024442994,0.025550656,0.0023302708,0.92314535,0.00031558014,0.00037129447],"about_ca_topic_score_codex":0.00002650529,"about_ca_topic_score_gemma":0.000027892629,"teacher_disagreement_score":0.37505686,"about_ca_system_score_codex":0.00018403276,"about_ca_system_score_gemma":0.000109228364,"threshold_uncertainty_score":0.99994606},"labels":[],"label_agreement":null},{"id":"W2064381090","doi":"10.1002/pst.111","title":"Carry‐over in cross‐over trials in bioequivalence: theoretical concerns and empirical evidence","year":2004,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pfizer (Canada)","funders":"","keywords":"Carry (investment); Bioequivalence; Estimator; Context (archaeology); Econometrics; Computer science; Test (biology); Order (exchange); Mathematics; Statistics; Economics; Medicine; Pharmacology","score_opus":0.8455461255403379,"score_gpt":0.7076831575087411,"score_spread":0.1378629680315968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064381090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42672777,0.00094682485,0.5627643,0.0030187927,0.0014217236,0.002486307,0.0017102435,0.00016771775,0.00075632334],"genre_scores_gemma":[0.6306677,0.00079295726,0.366963,0.0010624039,0.00036165435,0.00007459628,0.0000028443053,0.000055269073,0.000019559922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9898248,0.0038446705,0.003238529,0.0010005736,0.0010429933,0.0010484448],"domain_scores_gemma":[0.8341656,0.16442251,0.00032052232,0.00041174522,0.00012344927,0.0005562234],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016531724,0.0004893036,0.0019703815,0.0001801216,0.00008295218,0.00017889374,0.00046601694,0.00043261354,0.0026091062],"category_scores_gemma":[0.37030193,0.00040756527,0.00016455693,0.00057943666,0.0024278834,0.00019456203,0.0003571604,0.0013221377,0.00004917832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011848004,0.0005418724,0.04391392,0.00039073237,0.000049111095,0.00040528283,0.00032255726,0.00003067122,0.0002566106,0.94390523,0.00074283377,0.00825638],"study_design_scores_gemma":[0.006882178,0.00022031067,0.022565752,0.0004481715,0.00018732174,0.0000120126515,0.000027104512,0.0033033588,0.00076033466,0.9647604,0.00033264112,0.00050041603],"about_ca_topic_score_codex":0.00006921551,"about_ca_topic_score_gemma":0.000042776286,"teacher_disagreement_score":0.3537702,"about_ca_system_score_codex":0.00039279717,"about_ca_system_score_gemma":0.00027343785,"threshold_uncertainty_score":0.99983764},"labels":[],"label_agreement":null},{"id":"W2104082640","doi":"10.1002/pst.483","title":"Additional results for ‘Sequential design approaches for bioequivalence studies with crossover designs’","year":2011,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Theratechnologies (Canada)","funders":"","keywords":"Bioequivalence; Crossover; Sample size determination; Statistics; Crossover study; Type I and type II errors; Econometrics; Mathematics; Computer science; Medicine; Pharmacology; Artificial intelligence; Pharmacokinetics","score_opus":0.8859019112477156,"score_gpt":0.5762477195149607,"score_spread":0.3096541917327549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104082640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000041124415,0.00022889684,0.947814,0.00008327632,0.00030205172,0.0014982423,0.049121056,0.00005460373,0.0008567678],"genre_scores_gemma":[0.011617737,0.000018825462,0.9854012,0.0003040605,0.00018025986,0.0010994328,0.00034650706,0.000040383304,0.0009915975],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960055,0.00048028035,0.00087025214,0.00090151094,0.001092489,0.0006500178],"domain_scores_gemma":[0.9745771,0.023612859,0.0003139712,0.00035075255,0.0008409287,0.00030438832],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035724074,0.0003287175,0.00047184608,0.00012075977,0.00039450158,0.00019030871,0.00065211975,0.00009237118,0.0029652745],"category_scores_gemma":[0.013711357,0.00023119374,0.00011594361,0.00033847045,0.0010551861,0.0002676624,0.00012992612,0.00015446232,0.000087145476],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026129985,0.00076285127,0.0000266126,0.00010571208,0.00046588888,0.000040898565,0.0018691474,0.0007008105,0.0017470265,0.115948185,0.76507163,0.087131254],"study_design_scores_gemma":[0.0102002425,0.0043306295,0.00023010538,0.00009376231,0.0004897055,0.0000561542,0.0013001869,0.22872546,0.116059996,0.48999488,0.14705797,0.0014608923],"about_ca_topic_score_codex":0.0000021880103,"about_ca_topic_score_gemma":0.0000017839324,"teacher_disagreement_score":0.6180137,"about_ca_system_score_codex":0.00010590116,"about_ca_system_score_gemma":0.00017714516,"threshold_uncertainty_score":0.99794614},"labels":[],"label_agreement":null},{"id":"W2107812146","doi":"10.1002/pst.351","title":"Using short‐term evidence to predict six‐month outcomes in clinical trials of signs and symptoms in rheumatoid arthritis","year":2008,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital","funders":"","keywords":"Rheumatoid arthritis; Medicine; Clinical trial; Logistic regression; Bayesian probability; Randomized controlled trial; Internal medicine; Physical therapy; Statistics; Mathematics","score_opus":0.31636016439954256,"score_gpt":0.5100445254687855,"score_spread":0.19368436106924297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107812146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98287076,0.0077841985,0.00732638,0.00046929414,0.00014709726,0.0010570611,0.0002810465,0.000023940365,0.000040215145],"genre_scores_gemma":[0.9244395,0.06794541,0.007309501,0.00019016424,0.000035519166,0.00003099935,0.00001099736,0.000024402472,0.000013516865],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956991,0.0008248693,0.0019471906,0.00038453488,0.00061280443,0.0005315054],"domain_scores_gemma":[0.99417,0.0047363318,0.00011731098,0.00021994958,0.00012808308,0.0006283164],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003344113,0.00021672451,0.0013922187,0.00024923266,0.00005784485,0.000022474114,0.00012420585,0.00010836905,0.00018692257],"category_scores_gemma":[0.012155072,0.00018647639,0.00010446809,0.00026889704,0.0005500682,0.00013605587,0.00011604149,0.00049874734,0.000008415842],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010194057,0.00046220142,0.89145386,0.00008157585,0.00008381157,0.00052518444,0.00029668323,0.00001732828,0.0019189555,0.00043584537,0.00019877395,0.10350639],"study_design_scores_gemma":[0.011125151,0.0021145141,0.9632089,0.002933912,0.000021475715,0.00031142347,0.00009007849,0.016590262,0.0013839207,0.00053394027,0.0012694454,0.00041693682],"about_ca_topic_score_codex":0.0001447676,"about_ca_topic_score_gemma":0.00014989745,"teacher_disagreement_score":0.10308945,"about_ca_system_score_codex":0.00007034453,"about_ca_system_score_gemma":0.00022940552,"threshold_uncertainty_score":0.996166},"labels":[],"label_agreement":null},{"id":"W2111635289","doi":"10.1002/pst.433","title":"Optimal caliper widths for propensity‐score matching when estimating differences in means and differences in proportions in observational studies","year":2010,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3895,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Calipers; Statistics; Estimator; Mathematics; Logit; Matching (statistics); Observational study; Econometrics; Standard deviation; Confidence interval; Logistic regression; Medicine","score_opus":0.5850172035475715,"score_gpt":0.5093227869028153,"score_spread":0.07569441664475618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111635289","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7048489,0.000039273156,0.29310173,0.0004205741,0.00010536691,0.0009971044,0.00037524087,0.00007291753,0.000038930175],"genre_scores_gemma":[0.47615474,0.00002361761,0.52334493,0.000063169784,0.00003287132,0.00031639158,0.000026355883,0.000016773818,0.000021136719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798936,0.00010141182,0.00076289114,0.00039474992,0.0002937372,0.00045788183],"domain_scores_gemma":[0.99596053,0.003444055,0.00016898094,0.00013769526,0.00016493128,0.00012377546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067208987,0.00027215754,0.000583042,0.00015059032,0.000107504806,0.00006419125,0.00018363513,0.00010836694,0.00014272657],"category_scores_gemma":[0.0053334255,0.00022610907,0.000023546645,0.00017159648,0.00034571305,0.00026038743,0.00015340246,0.00071759283,0.0000010751643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011833147,0.00058959285,0.4410522,0.0011636569,0.00004771452,0.00006528252,0.005470528,0.00007393833,0.0017917563,0.54016095,0.00045085553,0.009015203],"study_design_scores_gemma":[0.0006265716,0.00007762445,0.05886068,0.0003398299,0.00003392851,0.000008525208,0.00042438603,0.0989402,0.00025393296,0.84006137,0.00003384267,0.0003391106],"about_ca_topic_score_codex":0.00006342919,"about_ca_topic_score_gemma":0.0018132363,"teacher_disagreement_score":0.38219154,"about_ca_system_score_codex":0.00009149244,"about_ca_system_score_gemma":0.000095098716,"threshold_uncertainty_score":0.92204607},"labels":[],"label_agreement":null},{"id":"W2116813387","doi":"10.1002/pst.1680","title":"Assessing the treatment effect in a randomized controlled trial with extensive non‐adherence: the EVOLVE trial","year":2015,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. John’s Health Sciences Centre","funders":"","keywords":"Randomized controlled trial; Medicine; Statistics; Medical physics; Mathematics; Internal medicine","score_opus":0.45167162741721173,"score_gpt":0.5365292550014282,"score_spread":0.0848576275842165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116813387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76307845,0.005346132,0.11963289,0.03595849,0.006298592,0.061644416,0.0005349623,0.00010124199,0.007404817],"genre_scores_gemma":[0.9815328,0.00029433222,0.003290991,0.0062137083,0.0013363499,0.006775715,0.000041480078,0.000054591314,0.0004600315],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9912612,0.0036956205,0.0037654503,0.00048306427,0.00025506687,0.00053958787],"domain_scores_gemma":[0.96678674,0.030616261,0.0017489452,0.00042222225,0.00015033231,0.00027550088],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037314907,0.00034363984,0.003131338,0.0001231868,0.0002379649,0.00034240988,0.0002923451,0.00011028571,0.0002016645],"category_scores_gemma":[0.01894831,0.00018207282,0.00025953414,0.00021432183,0.00039921267,0.0002206989,0.000032785603,0.0003711517,0.00040985068],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.9720802,0.00040065244,0.00037943645,0.000038500806,0.0004182664,0.000011092271,0.0019810142,0.00029378635,2.0218073e-7,0.019574478,0.004065335,0.00075707334],"study_design_scores_gemma":[0.8886463,0.0013924442,0.00008636787,0.00003074689,0.00018540277,0.0000026730488,0.00047115496,0.09636537,0.0000021275328,0.009167182,0.003437179,0.0002130246],"about_ca_topic_score_codex":0.00063163775,"about_ca_topic_score_gemma":0.00009426605,"teacher_disagreement_score":0.21845435,"about_ca_system_score_codex":0.00077831064,"about_ca_system_score_gemma":0.00048545544,"threshold_uncertainty_score":0.9912869},"labels":[],"label_agreement":null},{"id":"W2134800676","doi":"10.1002/pst.1721","title":"Optimal adaptive sequential designs for crossover bioequivalence studies","year":2015,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Bioequivalence; Sequential analysis; Crossover; Sample size determination; Statistics; Mathematics; Crossover study; Adaptive design; Type I and type II errors; Nominal level; Computer science; Mathematical optimization; Confidence interval; Medicine; Machine learning; Clinical trial","score_opus":0.8262700275298006,"score_gpt":0.64127193821718,"score_spread":0.18499808931262063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134800676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003036842,0.0014179198,0.9911149,0.00025823552,0.0014579303,0.0006916271,0.000976675,0.00007369261,0.0009721798],"genre_scores_gemma":[0.15324175,0.000043730626,0.8444121,0.0006857688,0.00025512726,0.000098356315,0.000009271241,0.000034224446,0.0012196695],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952837,0.0006494634,0.00084663834,0.00076433166,0.0017553548,0.00070047134],"domain_scores_gemma":[0.9903796,0.0066965236,0.00022025063,0.0003751384,0.001470114,0.0008584304],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0046629147,0.00031501416,0.00054078235,0.00012447646,0.00023489862,0.0003199013,0.0007730286,0.00009518306,0.00048355557],"category_scores_gemma":[0.01868592,0.00024660392,0.0001255622,0.00046570908,0.00094272156,0.00040230164,0.0003885938,0.00023190753,0.00045623854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010446934,0.0010783764,0.0007848894,0.00009035785,0.00078086636,0.0003267597,0.0068744607,0.013821514,0.03570293,0.3807734,0.41784886,0.13147065],"study_design_scores_gemma":[0.0067622936,0.002414656,0.00013857184,0.0000324527,0.00036281408,0.000060835013,0.004822372,0.4878848,0.12064022,0.2744123,0.1011669,0.0013017947],"about_ca_topic_score_codex":0.000007343349,"about_ca_topic_score_gemma":0.0000013953122,"teacher_disagreement_score":0.47406328,"about_ca_system_score_codex":0.0002686265,"about_ca_system_score_gemma":0.0002874721,"threshold_uncertainty_score":0.9999986},"labels":[],"label_agreement":null},{"id":"W2745664880","doi":"10.1002/pst.1823","title":"Competing risk analysis in a large cardiovascular clinical trial: An <scp>APEX</scp> substudy","year":2017,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas Hospital; University of Calgary","funders":"Portola Pharmaceuticals","keywords":"Medicine; Proportional hazards model; Clinical endpoint; Internal medicine; Pulmonary embolism; Hazard ratio; Venous thromboembolism; Deep vein; Thrombosis; Clinical trial; Univariate analysis; Confidence interval; Cardiology; Multivariate analysis","score_opus":0.6114267450329344,"score_gpt":0.5681218487714129,"score_spread":0.04330489626152145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745664880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.851634,0.0020258632,0.13691851,0.0008900193,0.001478549,0.0014391206,0.0036978207,0.000079788966,0.0018362663],"genre_scores_gemma":[0.98354876,0.0010859978,0.012421147,0.0017982331,0.0007466744,0.00009794078,0.00014830219,0.000054799966,0.00009811905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9899453,0.0021286209,0.0057033184,0.0010689932,0.00026540796,0.0008883784],"domain_scores_gemma":[0.98943555,0.0054673594,0.0027667854,0.0015715448,0.00011875246,0.0006400085],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05801738,0.00030942378,0.0024087583,0.00037898886,0.00074735744,0.00039012692,0.0008069777,0.00023442417,0.00026776321],"category_scores_gemma":[0.039288722,0.00039210377,0.0005726679,0.0002957882,0.00022315145,0.00043262047,0.00021280505,0.000805975,0.0010474123],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014324073,0.00079851074,0.9678736,0.000098158875,0.0018446575,0.000022339533,0.0008300522,0.00059441186,7.6362625e-8,0.025335807,0.0012998068,0.0011593817],"study_design_scores_gemma":[0.022869987,0.00017974048,0.6507606,0.000017024016,0.0006953654,0.0000014056764,0.00071940746,0.23618254,9.957664e-7,0.0055203717,0.08277548,0.00027706067],"about_ca_topic_score_codex":0.0015384868,"about_ca_topic_score_gemma":0.0011400364,"teacher_disagreement_score":0.31711295,"about_ca_system_score_codex":0.0003086666,"about_ca_system_score_gemma":0.00012500907,"threshold_uncertainty_score":0.9998531},"labels":[],"label_agreement":null},{"id":"W2789675304","doi":"10.1002/pst.1853","title":"Bayesian statistical models to estimate <scp>EQ‐5D</scp> utility scores from <scp>EORTC QLQ</scp> data in myeloma","year":2018,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Statistics; Regression; Regression analysis; Linear regression; Bayesian probability; Variance (accounting); Mathematics; Medicine","score_opus":0.5672172281859323,"score_gpt":0.5016580102366126,"score_spread":0.06555921794931974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789675304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07481653,0.0007392331,0.8532458,0.002030628,0.0011335773,0.0013070599,0.06211789,0.00015614094,0.004453168],"genre_scores_gemma":[0.7171763,0.00016164538,0.26732588,0.010600061,0.0010676297,0.00015425493,0.0029838902,0.00015340747,0.00037690013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99002576,0.00081907125,0.0051006665,0.001968919,0.000441803,0.0016437627],"domain_scores_gemma":[0.9823632,0.0130315805,0.0010691808,0.0018215947,0.00021528268,0.0014991355],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011039928,0.00060483615,0.001720186,0.00040332007,0.00036495127,0.00035112072,0.0014920372,0.00032078297,0.00088449224],"category_scores_gemma":[0.027237495,0.0007728397,0.00007754461,0.0005233143,0.0005778597,0.0008460656,0.0008145072,0.0007483317,0.0053673335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055259086,0.00084974297,0.11100531,0.000659813,0.00030125424,0.0000888261,0.0047564735,0.00090837816,0.00001781519,0.4698921,0.4042447,0.00722032],"study_design_scores_gemma":[0.0011341389,0.0001282148,0.06477757,0.000079844016,0.000045580877,0.0000055748064,0.00026041127,0.6639238,0.00003445329,0.16748935,0.10191388,0.00020721366],"about_ca_topic_score_codex":0.002487799,"about_ca_topic_score_gemma":0.0016548649,"teacher_disagreement_score":0.66301537,"about_ca_system_score_codex":0.0006157868,"about_ca_system_score_gemma":0.00039017966,"threshold_uncertainty_score":0.99947226},"labels":[],"label_agreement":null},{"id":"W2897367577","doi":"10.1002/pst.1906","title":"Applications of Bayesian statistical methodology to clinical trial design: A case study of a phase 2 trial with an interim futility assessment in patients with knee osteoarthritis","year":2018,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Xenon Pharmaceuticals (Canada)","funders":"Eli Lilly and Company","keywords":"Interim; Interim analysis; Medicine; Placebo; Clinical trial; WOMAC; Osteoarthritis; Sample size determination; Celecoxib; Randomized controlled trial; Bayesian probability; Clinical study design; Physical therapy; Medical physics; Computer science; Surgery; Internal medicine; Alternative medicine; Statistics; Artificial intelligence","score_opus":0.7394911056247505,"score_gpt":0.6836660418249617,"score_spread":0.0558250637997888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897367577","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35637304,0.000001373465,0.63335556,0.000015286221,0.00031294706,0.008425682,0.0014528402,0.000033288416,0.000029962537],"genre_scores_gemma":[0.45817116,7.205667e-7,0.5408816,0.000048910617,0.00021775062,0.0006188423,0.000013770868,0.00004516936,0.000002073183],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9815742,0.011307181,0.0041288794,0.0011555211,0.0011275773,0.00070664653],"domain_scores_gemma":[0.9232951,0.07293544,0.0008981401,0.0010169494,0.0010154449,0.0008389584],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00996171,0.00050641305,0.0023477846,0.0002437182,0.000121205594,0.00004252936,0.0004716846,0.00025841274,0.00064519455],"category_scores_gemma":[0.031128282,0.000398866,0.00008660834,0.0007855755,0.0014712992,0.00010016027,0.0002423826,0.0009429301,0.00000531176],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.6675031,0.043721933,0.0030861008,0.00015252351,0.00032700782,0.00036603343,0.00059301686,0.000002832663,0.0000045134498,0.014455259,0.00006969189,0.269718],"study_design_scores_gemma":[0.604518,0.31144148,0.0010646691,0.000077714954,0.0012819454,0.0000333108,0.0009280349,0.0025859924,0.00006802182,0.0773544,0.00007786984,0.0005685773],"about_ca_topic_score_codex":0.00013503637,"about_ca_topic_score_gemma":0.00039885557,"teacher_disagreement_score":0.26914942,"about_ca_system_score_codex":0.000120999845,"about_ca_system_score_gemma":0.00045339737,"threshold_uncertainty_score":0.99984634},"labels":[],"label_agreement":null},{"id":"W2991547990","doi":"10.1002/pst.1984","title":"Comparisons of outlier tests for potency bioassays","year":2019,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Potency; Outlier; Bioassay; Statistics; Mathematics; Computer science; Chemistry; Biology","score_opus":0.2950893604694196,"score_gpt":0.5342374065051462,"score_spread":0.2391480460357266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991547990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034602878,0.00016714237,0.9900839,0.00023662946,0.0009142841,0.0005211452,0.001821252,0.000040679915,0.0027547027],"genre_scores_gemma":[0.6873971,0.000012116075,0.31147453,0.00011116802,0.00007961639,0.000018177037,0.000015098276,0.000022345625,0.000869792],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99661934,0.00009952806,0.0009832056,0.0005295727,0.0012615931,0.0005067284],"domain_scores_gemma":[0.98731893,0.01086072,0.0002789258,0.00039530848,0.000836447,0.00030967293],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010814682,0.00020258536,0.0005288773,0.0001238738,0.0001014059,0.00007373132,0.00064521254,0.000075143435,0.00093067257],"category_scores_gemma":[0.009890947,0.00016317167,0.000081338556,0.00045175632,0.00025489612,0.00016827245,0.0001592278,0.0002503989,0.00056452793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039424014,0.0005148463,0.060997102,0.00026375652,0.00007368188,0.000015810603,0.00018531969,0.0015862447,0.004038841,0.6177305,0.031812105,0.28238755],"study_design_scores_gemma":[0.0023558147,0.00039871183,0.010554663,0.000041814168,0.00011642578,0.000007886086,0.0002676157,0.29139063,0.0057939375,0.49643096,0.19203849,0.0006030342],"about_ca_topic_score_codex":0.0000053171098,"about_ca_topic_score_gemma":0.0000032287844,"teacher_disagreement_score":0.68393683,"about_ca_system_score_codex":0.000049706192,"about_ca_system_score_gemma":0.00008089744,"threshold_uncertainty_score":0.9999826},"labels":[],"label_agreement":null},{"id":"W3006624376","doi":"10.1002/pst.2005","title":"START: single‐to‐double arm transition design for phase II clinical trials","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Randomization; Frequentist inference; Computer science; Restricted randomization; Null hypothesis; Clinical study design; Clinical trial; Randomized controlled trial; Statistics; Research design; Gold standard (test); Medical physics; Medicine; Mathematics; Surgery; Bayesian probability; Internal medicine; Bayesian inference","score_opus":0.9480752190546133,"score_gpt":0.7157514049968547,"score_spread":0.2323238140577586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006624376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006861018,0.00003976919,0.9785313,0.008933083,0.001326423,0.0052348347,0.0046710027,0.00031645293,0.0002610309],"genre_scores_gemma":[0.018480292,0.000050914467,0.9701976,0.008428275,0.0022385926,0.00035480232,0.000046286197,0.00013857699,0.00006465007],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98763174,0.004905534,0.004552674,0.0010892561,0.00085347175,0.0009673483],"domain_scores_gemma":[0.8068024,0.18984646,0.00058543996,0.00039675413,0.0004611614,0.0019078255],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022166694,0.00053534016,0.002443877,0.000073716285,0.0003072273,0.00012866288,0.0005190884,0.00036500368,0.00196165],"category_scores_gemma":[0.31978798,0.00047962638,0.0005242293,0.0004232185,0.00033745304,0.00010088261,0.00015520267,0.00081562385,0.00018563497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030961014,0.009319725,0.0000041287626,0.00089705206,0.00076125475,0.00009895299,0.0010151421,0.0001553969,0.005775302,0.3656887,0.20588115,0.3794422],"study_design_scores_gemma":[0.03184917,0.012177281,0.0000017642188,0.00007601994,0.0019993351,0.0000043515142,0.000054765133,0.08089796,0.019392082,0.79698354,0.055740785,0.00082293275],"about_ca_topic_score_codex":0.0000014938358,"about_ca_topic_score_gemma":5.685975e-7,"teacher_disagreement_score":0.43129486,"about_ca_system_score_codex":0.00009776677,"about_ca_system_score_gemma":0.00017838762,"threshold_uncertainty_score":0.9997655},"labels":[],"label_agreement":null},{"id":"W3013414970","doi":"10.1002/pst.2012","title":"A critical review of graphics for subgroup analyses in clinical trials","year":2020,"lang":"en","type":"review","venue":"Pharmaceutical Statistics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Horizon 2020 Framework Programme; Medical Research Council Canada; European Commission; Marie Curie; National Institute for Health and Care Research","keywords":"Subgroup analysis; Computer science; Population; Plot (graphics); Identification (biology); Clinical trial; Visualization; Econometrics; Statistics; Data mining; Medicine; Mathematics; Pathology","score_opus":0.7492670943859359,"score_gpt":0.6880764956332216,"score_spread":0.061190598752714265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013414970","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3158727e-10,0.5135837,0.4835107,0.00023352512,0.00022770396,0.0005912197,0.001804848,0.000023764405,0.000024536506],"genre_scores_gemma":[2.9956394e-7,0.9256588,0.07136103,0.0021388817,0.00017783798,0.00007160734,0.000552147,0.00003103326,0.000008332101],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99021083,0.003136919,0.0049136826,0.0007481274,0.00057659746,0.00041383598],"domain_scores_gemma":[0.97537965,0.022202892,0.0009630944,0.0005654152,0.00040815468,0.0004808181],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0071037165,0.00042823498,0.0051021725,0.0002268911,0.000042018255,0.00011400147,0.0013859103,0.00024736582,0.00009396841],"category_scores_gemma":[0.058151968,0.00033960954,0.00108374,0.0015143204,0.00025886277,0.00015021705,0.00036978262,0.00068647583,0.000032354976],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035770377,0.00015622907,7.96024e-7,0.103437595,0.00011212765,0.000025480733,0.000003279105,6.3772056e-8,2.852286e-8,0.30667555,0.011489925,0.5780954],"study_design_scores_gemma":[0.00033911146,0.000092380586,4.7006824e-7,0.024679396,0.0022161875,0.000007002977,7.603175e-7,0.034158994,5.71772e-7,0.0030858647,0.9351,0.0003192241],"about_ca_topic_score_codex":0.000002438209,"about_ca_topic_score_gemma":0.0000012769984,"teacher_disagreement_score":0.9236101,"about_ca_system_score_codex":0.00004635685,"about_ca_system_score_gemma":0.0006357933,"threshold_uncertainty_score":0.9999056},"labels":[],"label_agreement":null},{"id":"W3027176385","doi":"10.1002/pst.2029","title":"Investigating the appropriateness of different concordance measures in a time‐to‐event setting","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Censoring (clinical trials); Concordance; Statistic; Statistics; Comparability; Parametric statistics; Event (particle physics); Mathematics; Econometrics; Computer science; Medicine; Internal medicine","score_opus":0.08646133817187293,"score_gpt":0.3480782208862438,"score_spread":0.2616168827143709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027176385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04491257,0.00006723049,0.94778866,0.0064898725,0.000090479596,0.0004123222,0.000024689014,0.00005855154,0.00015562469],"genre_scores_gemma":[0.9504816,0.000009044712,0.046228394,0.0031604853,0.00005865377,0.00003343026,0.0000020559257,0.0000128322445,0.000013494338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978687,0.000281722,0.00053703506,0.0003489674,0.0005660398,0.00039754336],"domain_scores_gemma":[0.9983719,0.00084634696,0.00012349905,0.00023859079,0.00013173286,0.0002879201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006136419,0.00016134317,0.00024559727,0.000034776152,0.000096640724,0.00010221441,0.001088143,0.000031760464,0.000043272248],"category_scores_gemma":[0.0015981948,0.00012068419,0.000032738863,0.00055935263,0.00014066107,0.00011116886,0.00048303968,0.00030124665,0.00013962253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090104906,0.0004776324,0.020204015,0.0005105974,0.00008887471,0.00011370108,0.018359175,0.024857571,0.11024034,0.3406437,0.0032119753,0.48120233],"study_design_scores_gemma":[0.00017777186,0.00008765964,0.0017866857,0.000058151483,0.000012019714,0.000002174344,0.00009568452,0.8794835,0.104704276,0.011839337,0.0015546646,0.00019805014],"about_ca_topic_score_codex":0.00003591736,"about_ca_topic_score_gemma":0.000010080243,"teacher_disagreement_score":0.905569,"about_ca_system_score_codex":0.000057503108,"about_ca_system_score_gemma":0.000073555224,"threshold_uncertainty_score":0.49213585},"labels":[],"label_agreement":null},{"id":"W3081849395","doi":"10.1002/pst.2067","title":"A stochastically curtailed two‐arm randomised phase<scp>II</scp>trial design for binary outcomes","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Cancer Research UK","keywords":"Interim; Interim analysis; Research design; Early stopping; Sample size determination; Outcome (game theory); Clinical study design; Null hypothesis; Randomized controlled trial; Computer science; Statistics; Medicine; Mathematics; Clinical trial; Surgery; Machine learning; Internal medicine","score_opus":0.6908497330030037,"score_gpt":0.6098577142060511,"score_spread":0.08099201879695261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081849395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002343198,0.000061977524,0.98122233,0.0018888928,0.0016414254,0.008352775,0.0035857907,0.00047793562,0.00042565112],"genre_scores_gemma":[0.017705698,0.000037874834,0.97525585,0.0037602058,0.0015712494,0.0011902684,0.000050376184,0.0002170554,0.00021143278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912089,0.0020359396,0.0028368714,0.0012195533,0.0012454785,0.0014532172],"domain_scores_gemma":[0.74346805,0.2536289,0.00052946876,0.00045844144,0.00045186887,0.0014632603],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00477959,0.00085570256,0.0024429162,0.00010352921,0.00045960344,0.00016624748,0.0008865992,0.0003524349,0.0007576511],"category_scores_gemma":[0.44364116,0.0007284728,0.0005564381,0.00045518664,0.0006340509,0.000119981116,0.00041129428,0.0010721075,0.00017147698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.19980405,0.0073388848,0.000025923537,0.0010784776,0.0016831423,0.00026206675,0.0006714025,0.00022907623,0.002547823,0.643594,0.11669336,0.026071796],"study_design_scores_gemma":[0.31675056,0.0049087764,0.0000030792328,0.000037540496,0.0015550334,0.0000035513451,0.000034936205,0.1364043,0.0018453739,0.5323464,0.0057485187,0.00036187647],"about_ca_topic_score_codex":0.0000018728248,"about_ca_topic_score_gemma":4.5067432e-7,"teacher_disagreement_score":0.43886158,"about_ca_system_score_codex":0.00011983753,"about_ca_system_score_gemma":0.00031714988,"threshold_uncertainty_score":0.9995166},"labels":[],"label_agreement":null},{"id":"W3087544668","doi":"10.1002/pst.2068","title":"Assessing the quality of studies in meta‐research: Review/guidelines on the most important quality assessment tools","year":2020,"lang":"en","type":"review","venue":"Pharmaceutical Statistics","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":225,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Jadad scale; Systematic review; Observational study; Meta-analysis; Quality (philosophy); Scale (ratio); Publication bias; Consolidated Standards of Reporting Trials; Randomized controlled trial; Computer science; MEDLINE; Management science; Medicine; Engineering; Cochrane Library; Pathology","score_opus":0.996400707501376,"score_gpt":0.8337696602368216,"score_spread":0.16263104726455435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087544668","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000013490574,0.9796069,0.00619727,0.007194105,0.0003924206,0.0042539136,0.0011988273,0.000005420069,0.0011497798],"genre_scores_gemma":[0.00002625975,0.9884336,0.007619636,0.0027568296,0.00017355868,0.0006353392,0.000049051934,0.000033813063,0.0002719298],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6569226,0.25015128,0.062189166,0.002758909,0.026863687,0.0011143986],"domain_scores_gemma":[0.5374619,0.41899183,0.02525914,0.007834525,0.0099229505,0.0005296677],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5529103,0.00093889306,0.021192381,0.00023980864,0.00038748485,0.0012499504,0.0045885313,0.00015396642,0.0036895827],"category_scores_gemma":[0.5636719,0.00028410187,0.004065914,0.0044912505,0.00086259964,0.00018797725,0.0010243502,0.0023002727,0.00044061808],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030594726,0.00013389425,0.000043622695,0.04116113,0.0044990596,0.000027945722,0.00008406862,0.0000041734893,3.4911355e-7,0.08413507,0.12531503,0.7445926],"study_design_scores_gemma":[0.000071955714,0.00002663454,0.000046470475,0.008181733,0.007882097,0.0000033620447,0.00054391735,0.000918482,3.6976604e-7,0.008913156,0.97311825,0.00029355992],"about_ca_topic_score_codex":0.000040935283,"about_ca_topic_score_gemma":0.000031476087,"teacher_disagreement_score":0.84780324,"about_ca_system_score_codex":0.00025649427,"about_ca_system_score_gemma":0.00093741965,"threshold_uncertainty_score":0.99996114},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"agree"},{"id":"W3092379046","doi":"10.1002/pst.2073","title":"Utilizing Bayesian predictive power in clinical trial design","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of British Columbia","funders":"","keywords":"Bayesian probability; Interim; Interim analysis; Computer science; Adaptive design; Machine learning; Computation; Clinical trial; Predictive power; Clinical study design; Artificial intelligence; Data mining; Algorithm; Medicine","score_opus":0.8404547068645039,"score_gpt":0.6558272472679741,"score_spread":0.1846274595965297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092379046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097506685,0.00004536113,0.9909415,0.0014268296,0.0013527847,0.0020554313,0.00053354783,0.000218129,0.0024513344],"genre_scores_gemma":[0.1562919,0.000082009836,0.8399673,0.002660813,0.0008012603,0.00008532997,0.0000044623243,0.00008477647,0.00002213073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98966694,0.004574076,0.0030749994,0.0009644861,0.00085965585,0.0008598648],"domain_scores_gemma":[0.8824727,0.11550359,0.0003823479,0.00037955327,0.00016700396,0.0010948195],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0071483687,0.0004263998,0.001362138,0.000069876565,0.0000905986,0.00007944616,0.00056141906,0.00037324696,0.0022002957],"category_scores_gemma":[0.26593456,0.00039258576,0.00021986561,0.00051075686,0.00054465095,0.00009896429,0.00026683384,0.0016876936,0.0001870642],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16383407,0.003391318,0.0019951498,0.0004114036,0.0004887429,0.0010731966,0.0007426134,0.000068466354,0.000081182814,0.67907476,0.0532038,0.09563528],"study_design_scores_gemma":[0.051225845,0.0030139578,0.00047096342,0.00006644979,0.00033119056,0.000004289274,0.000088428234,0.09578563,0.00023484784,0.8446875,0.0035114097,0.0005794695],"about_ca_topic_score_codex":0.0000028641448,"about_ca_topic_score_gemma":0.0000011298224,"teacher_disagreement_score":0.2587862,"about_ca_system_score_codex":0.00010132294,"about_ca_system_score_gemma":0.00020987452,"threshold_uncertainty_score":0.9998526},"labels":[],"label_agreement":null},{"id":"W3092430397","doi":"10.1002/pst.2072","title":"The current state of Bayesian methods in nonclinical pharmaceutical statistics: Survey results and recommendations from the <scp>DIA</scp>/<scp>ASA‐BIOP</scp> Nonclinical Bayesian Working Group","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Bayesian probability; Bayesian statistics; Bayesian inference; Medicine; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.5640579803130207,"score_gpt":0.595575910905105,"score_spread":0.0315179305920843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092430397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017597879,0.0013871453,0.9641647,0.0035663527,0.0024203255,0.002112919,0.024013922,0.0001647656,0.0004101127],"genre_scores_gemma":[0.03589484,0.0068155257,0.9530812,0.002235282,0.0010936827,0.00015807258,0.0004399735,0.00022611771,0.000055287714],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9655889,0.020981234,0.0075061233,0.0020792591,0.0017795783,0.00206486],"domain_scores_gemma":[0.49988705,0.49620467,0.0012593488,0.0008607248,0.00042959128,0.0013586086],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.027836036,0.0010792075,0.0024898052,0.00011905553,0.00066911115,0.00045602204,0.0018634371,0.00042243738,0.00008897272],"category_scores_gemma":[0.5384909,0.0007857337,0.0003447849,0.0013098901,0.0028696498,0.00016074587,0.0014067697,0.0051336354,0.000061230574],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007859891,0.0013955886,0.010732273,0.00034233462,0.0006940117,0.00010314823,0.0015243507,0.000022795144,0.00016268154,0.04639479,0.056153886,0.8816882],"study_design_scores_gemma":[0.008845013,0.0007033272,0.030314146,0.0004141786,0.001302228,0.000008551772,0.00032124872,0.14712235,0.0006653884,0.6829378,0.12690319,0.00046259898],"about_ca_topic_score_codex":0.00009363052,"about_ca_topic_score_gemma":0.0003621197,"teacher_disagreement_score":0.8812255,"about_ca_system_score_codex":0.00017791486,"about_ca_system_score_gemma":0.00041032516,"threshold_uncertainty_score":0.99984396},"labels":[],"label_agreement":null},{"id":"W3110632768","doi":"10.1002/pst.2082","title":"Joint analysis of longitudinal measurements and survival times with a cure fraction based on partly linear mixed and semiparametric cure models","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Random effects model; Mixed model; Semiparametric model; Inference; Clinical trial; Trajectory; Semiparametric regression; Survival analysis; Hazard ratio; Fraction (chemistry); Longitudinal study; Mathematics; Statistics; Medicine; Econometrics; Computer science; Regression analysis; Confidence interval; Internal medicine; Parametric statistics; Artificial intelligence; Meta-analysis","score_opus":0.42214573473327416,"score_gpt":0.4370171898770877,"score_spread":0.01487145514381355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110632768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02260536,0.000074506876,0.9756697,0.0003619236,0.00003361625,0.00023360494,0.00070611184,0.00003156426,0.00028360277],"genre_scores_gemma":[0.64284,0.000055388136,0.35685173,0.00017474676,0.000027711949,0.0000086668515,0.000020796535,0.000017500342,0.000003469739],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979406,0.00027957195,0.0004435459,0.00039986963,0.0006743211,0.00026211698],"domain_scores_gemma":[0.99636525,0.0026547115,0.00018648666,0.00015142407,0.00026346993,0.0003786453],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051526306,0.00024209781,0.00067013636,0.000151717,0.000076651886,0.000039131206,0.00007489895,0.000077168734,0.00019493644],"category_scores_gemma":[0.0020343242,0.00018867491,0.000048000074,0.00078856875,0.00018303882,0.000058510126,0.00004455625,0.0003290508,0.000002059291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0064819823,0.0038211416,0.1897069,0.0056283125,0.009366835,0.00023404227,0.0012951603,0.045263972,0.0023206794,0.6281647,0.0073230662,0.10039321],"study_design_scores_gemma":[0.0009206456,0.00043644436,0.0043476643,0.000044815595,0.0025166846,9.844018e-7,0.000037412705,0.9696825,0.0010089456,0.020713156,0.00006575611,0.00022498608],"about_ca_topic_score_codex":0.000016100428,"about_ca_topic_score_gemma":0.000005216112,"teacher_disagreement_score":0.9244185,"about_ca_system_score_codex":0.00002869468,"about_ca_system_score_gemma":0.000043559412,"threshold_uncertainty_score":0.7693939},"labels":[],"label_agreement":null},{"id":"W3120519245","doi":"10.1002/pst.2092","title":"A weighted log‐rank test and associated effect estimator for cancer trials with delayed treatment effect","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"National Institutes of Health","keywords":"Mathematics; Estimator; Statistics; Log-rank test; Test statistic; Statistic; Robustness (evolution); Hazard ratio; Proportional hazards model; Sample size determination; Statistical hypothesis testing; Confidence interval","score_opus":0.4828785734049401,"score_gpt":0.6096617833509836,"score_spread":0.12678320994604353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120519245","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027431263,0.00084407686,0.9466155,0.0008814103,0.00086232234,0.004798785,0.018061131,0.0002949048,0.00021061972],"genre_scores_gemma":[0.034128964,0.00053662993,0.96241254,0.00033841375,0.0004105674,0.001578439,0.00013142364,0.00016124672,0.0003017587],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99273765,0.0036771665,0.001437812,0.0008097189,0.00055108656,0.0007865889],"domain_scores_gemma":[0.6649986,0.33358014,0.0003702053,0.00027004667,0.0003189544,0.00046210407],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0056267804,0.00063791615,0.0026629744,0.000056739213,0.0002550378,0.00014460339,0.00015648371,0.0002862361,0.00063791353],"category_scores_gemma":[0.25941348,0.00040749917,0.00023098852,0.00032483652,0.00034130344,0.000049850045,0.00007960894,0.00037503333,0.000014754532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020005014,0.005312126,0.01978167,0.0044235317,0.01134616,0.0016100471,0.0002415171,0.000019234134,0.0093098655,0.13965596,0.020109825,0.768185],"study_design_scores_gemma":[0.068077974,0.016606841,0.0015490929,0.0008375208,0.024570951,0.000100976176,0.000017556496,0.087560475,0.1358432,0.6535324,0.009216587,0.0020864329],"about_ca_topic_score_codex":0.00002180215,"about_ca_topic_score_gemma":0.000049779897,"teacher_disagreement_score":0.7660986,"about_ca_system_score_codex":0.00031120772,"about_ca_system_score_gemma":0.00024990345,"threshold_uncertainty_score":0.9998377},"labels":[],"label_agreement":null},{"id":"W3137022898","doi":"10.1002/pst.2119","title":"Treatment allocation strategies for umbrella trials in the presence of multiple biomarkers: A comparison of methods","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Fakultet Medicinskih Nauka, Univerziteta U Kragujevcu; Newcastle University; Medical Research Council Canada; Cancer Research UK","keywords":"Biomarker; Context (archaeology); Bayesian probability; Set (abstract data type); Medicine; Matching (statistics); Computer science; Hierarchy; Artificial intelligence; Pathology","score_opus":0.8703654930178174,"score_gpt":0.7163172398238357,"score_spread":0.15404825319398174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137022898","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022062468,0.00045181357,0.99358344,0.00035356914,0.00031226152,0.0014139536,0.0014036294,0.000015074358,0.0002599929],"genre_scores_gemma":[0.17610484,0.00017962672,0.82339746,0.000037090344,0.00006447841,0.00016734528,0.000018836407,0.000018433164,0.000011868885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98759013,0.008542736,0.0027971652,0.0003565204,0.00038988568,0.00032357508],"domain_scores_gemma":[0.6510043,0.34766757,0.0006078456,0.0003259863,0.00032161883,0.00007262942],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0118394075,0.00021820211,0.0015879616,0.000058148013,0.00004687268,0.000039870272,0.00029461453,0.00013452879,0.0001282308],"category_scores_gemma":[0.28698254,0.0001481312,0.00022975348,0.0003531744,0.00034851732,0.0000436882,0.000057441084,0.00017764636,0.000001296908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011480475,0.002825758,0.0009004755,0.0013871227,0.0004920107,0.000008999194,0.001452315,0.000088084504,0.015607862,0.7596883,0.0016802875,0.21472074],"study_design_scores_gemma":[0.0035294658,0.00043673863,0.0002590501,0.00009306623,0.00073825865,0.0000031006593,0.0016265017,0.08186059,0.08109551,0.82848334,0.0017082271,0.00016613177],"about_ca_topic_score_codex":0.000035098536,"about_ca_topic_score_gemma":0.000030855423,"teacher_disagreement_score":0.33912483,"about_ca_system_score_codex":0.00005586753,"about_ca_system_score_gemma":0.0002565307,"threshold_uncertainty_score":0.7190235},"labels":[],"label_agreement":null},{"id":"W3160632722","doi":"10.1002/pst.2132","title":"Selection bias, investment decisions and treatment effect distributions","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Caprion (Canada)","funders":"","keywords":"Selection (genetic algorithm); Selection bias; Bayesian probability; Phase (matter); Investment (military); Econometrics; Distribution (mathematics); Computer science; Actuarial science; Economics; Risk analysis (engineering); Statistics; Business; Machine learning; Mathematics; Artificial intelligence; Political science","score_opus":0.5404197726327826,"score_gpt":0.5112801002807985,"score_spread":0.029139672351984114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160632722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2569971,0.009057231,0.6706946,0.037042014,0.0017577384,0.0020202366,0.015919883,0.00023995663,0.006271232],"genre_scores_gemma":[0.8732437,0.0049832836,0.09754973,0.019336313,0.00078167283,0.0005247695,0.0015771906,0.00009153116,0.0019118055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997064,0.0004344603,0.001578716,0.00047106217,0.00008556677,0.0003661885],"domain_scores_gemma":[0.99508643,0.0038637323,0.00036632273,0.00020583067,0.000074302385,0.0004033761],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026409018,0.00019412911,0.00060486794,0.00008690225,0.00031403935,0.00011112383,0.00006558957,0.000083955165,0.00078019674],"category_scores_gemma":[0.006780798,0.0002103939,0.00006426611,0.00020826633,0.000090257534,0.00012593296,0.000048465066,0.00014390172,0.0008566207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026442525,0.0003712028,0.06259993,0.000107679974,0.0002123042,0.000015727324,0.000255506,0.000052193624,0.000032204483,0.8955689,0.03284092,0.007916984],"study_design_scores_gemma":[0.0031081894,0.00045157355,0.050091274,0.000062274594,0.0001295073,0.00007190704,0.00010250945,0.060322154,0.000765498,0.077275604,0.8070099,0.0006096222],"about_ca_topic_score_codex":0.00013569096,"about_ca_topic_score_gemma":0.00010157207,"teacher_disagreement_score":0.81829333,"about_ca_system_score_codex":0.00077550334,"about_ca_system_score_gemma":0.00013821591,"threshold_uncertainty_score":0.9999213},"labels":[],"label_agreement":null},{"id":"W3161958318","doi":"10.1002/pst.2129","title":"The detailed clinical objectives approach to designing clinical trials and choosing estimands","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Boehringer Ingelheim (Canada)","funders":"","keywords":"Clinical trial; Medical physics; Computer science; Medicine; Econometrics; Mathematics; Internal medicine","score_opus":0.8294575017396123,"score_gpt":0.6433639861404327,"score_spread":0.18609351559917964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161958318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01280952,0.0053604627,0.96158844,0.013216369,0.0018172556,0.0010155044,0.0005084434,0.00006208356,0.003621939],"genre_scores_gemma":[0.34499672,0.004430264,0.61283475,0.033637665,0.0026381228,0.00025123876,0.00009655146,0.000114810595,0.0009998608],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98561877,0.0049938443,0.007780553,0.00086962205,0.00015057863,0.0005866406],"domain_scores_gemma":[0.95568204,0.041514494,0.0014362558,0.0004291403,0.00017016112,0.00076793594],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09645499,0.000230788,0.0017170855,0.00007548184,0.00056320906,0.0003661037,0.0002501183,0.00018613717,0.00013420386],"category_scores_gemma":[0.13265193,0.00022021643,0.00018719619,0.00021280002,0.00031200852,0.00015893082,0.00017247845,0.0006264959,0.0005071389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035771643,0.0008085269,0.26551706,0.00038525736,0.000825997,0.000018151191,0.001081357,0.0001891756,0.0000090753865,0.5874598,0.07500792,0.06833997],"study_design_scores_gemma":[0.0064573376,0.00039489556,0.187417,0.00013478207,0.0002932724,0.000052915042,0.0015973757,0.34906578,0.000054156077,0.09746888,0.35576648,0.0012971377],"about_ca_topic_score_codex":0.000019383411,"about_ca_topic_score_gemma":0.00001443764,"teacher_disagreement_score":0.4899909,"about_ca_system_score_codex":0.0001565678,"about_ca_system_score_gemma":0.00027945597,"threshold_uncertainty_score":0.9303897},"labels":[],"label_agreement":null},{"id":"W4200071936","doi":"10.1002/pst.2186","title":"Empirical likelihood confidence interval for sensitivity to the early disease stage","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; Simons Foundation; U.S. Department of Defense","keywords":"Confidence interval; Disease; Inference; Stage (stratigraphy); Sensitivity (control systems); Statistics; Medicine; Computer science; Artificial intelligence; Internal medicine; Mathematics","score_opus":0.09480981289805816,"score_gpt":0.4347240200643359,"score_spread":0.33991420716627774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200071936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054229544,0.00011966887,0.9553177,0.037199657,0.0006734719,0.0004381419,0.0006411132,0.000121849065,0.00006544579],"genre_scores_gemma":[0.8114731,0.000012192159,0.17209664,0.015656676,0.0002676231,0.0000683527,0.000025844065,0.0000225994,0.00037700086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741477,0.00062747014,0.00030984683,0.0005694524,0.0004839371,0.0005945477],"domain_scores_gemma":[0.9953823,0.0027360278,0.000058947368,0.0005891175,0.00042833202,0.0008052622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008164458,0.00018042082,0.00020597815,0.000029523597,0.0002743573,0.0002913732,0.00052056805,0.000040766452,0.00007800209],"category_scores_gemma":[0.0032584511,0.00014603404,0.00007259647,0.00030930867,0.00007635954,0.000116332696,0.0005782428,0.0004747273,0.00014263934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037055035,0.00054821407,0.06330568,0.0008147028,0.000116853094,0.0022089581,0.0036491202,0.0019577476,0.0004418124,0.62657046,0.042009834,0.25800607],"study_design_scores_gemma":[0.00043626534,0.00013462409,0.061804786,0.000037394053,0.000039720067,0.000023230648,0.000025815632,0.7636022,0.0005658274,0.008327715,0.16468157,0.00032087092],"about_ca_topic_score_codex":0.000053796743,"about_ca_topic_score_gemma":0.00006316425,"teacher_disagreement_score":0.8060501,"about_ca_system_score_codex":0.00007764423,"about_ca_system_score_gemma":0.000355758,"threshold_uncertainty_score":0.5955095},"labels":[],"label_agreement":null},{"id":"W4200543014","doi":"10.1002/pst.2181","title":"A dose‐finding design for dual‐agent trials with patient‐specific doses for one agent with application to an opiate detoxification trial","year":2021,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Clinical trial; Medicine; Maximum tolerated dose; Dosing; Detoxification (alternative medicine); Clinical study design; Medical physics; Pharmacology; Computer science; Internal medicine; Alternative medicine; Pathology","score_opus":0.8261641552162479,"score_gpt":0.618695554779733,"score_spread":0.20746860043651483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200543014","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00377152,0.00005341326,0.9795985,0.0006277207,0.000576871,0.012216694,0.0029697744,0.00014695391,0.00003855111],"genre_scores_gemma":[0.020644844,0.00008003296,0.9718991,0.00049098773,0.00079675793,0.005657903,0.00021235585,0.00015061944,0.00006739939],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9927463,0.0021746082,0.0022097495,0.0011651717,0.0009030569,0.00080114236],"domain_scores_gemma":[0.91762364,0.07918989,0.00075858296,0.00069838064,0.0010076341,0.0007218735],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006444635,0.0004896733,0.0015054948,0.00011153178,0.0003500099,0.00025727536,0.00028461553,0.00020325946,0.00020392606],"category_scores_gemma":[0.051348194,0.0003937728,0.00016444367,0.0004863907,0.00017197123,0.000117363445,0.00007842117,0.00030098335,0.000024770641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16453162,0.0045289984,0.000018309924,0.0008951019,0.00083074055,0.00004119465,0.00065091206,0.00070006726,0.009681208,0.4478247,0.0047252923,0.36557186],"study_design_scores_gemma":[0.084885694,0.010668269,0.00007005586,0.00028773595,0.003017275,0.000020577223,0.00031490196,0.019322403,0.08636992,0.75805295,0.03549572,0.0014944867],"about_ca_topic_score_codex":0.0000025478632,"about_ca_topic_score_gemma":0.000009263332,"teacher_disagreement_score":0.3640774,"about_ca_system_score_codex":0.00026548037,"about_ca_system_score_gemma":0.00028571335,"threshold_uncertainty_score":0.9998514},"labels":[],"label_agreement":null},{"id":"W4280542190","doi":"10.1002/pst.2234","title":"Standard and reference‐based conditional mean imputation","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Missing data; Jackknife resampling; Frequentist inference; Imputation (statistics); Pooling; Computer science; Statistics; Inference; Bayesian probability; Econometrics; Bayesian inference; Mathematics; Estimator; Artificial intelligence","score_opus":0.6731853966455711,"score_gpt":0.6174407262752281,"score_spread":0.05574467037034303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280542190","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025812113,0.000037762136,0.9832269,0.00079589273,0.00037159424,0.00046198856,0.011187673,0.00012762703,0.0012093771],"genre_scores_gemma":[0.22387663,0.0000134119055,0.77456295,0.0011140183,0.00010134939,0.00010810935,0.0001196899,0.000035461086,0.00006839646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99635136,0.0011813228,0.00073198037,0.00041690958,0.00094268174,0.00037573566],"domain_scores_gemma":[0.9646532,0.03448611,0.00019051488,0.00018926727,0.00016483126,0.0003161095],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002377775,0.00020537393,0.00043934802,0.000072675706,0.0004041483,0.000055890552,0.00018628828,0.000061879626,0.007100018],"category_scores_gemma":[0.014729859,0.00020411133,0.00004577581,0.00019126381,0.0003269003,0.000042394528,0.00020608676,0.0006723935,0.000020455496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046352847,0.00019516518,0.00023072171,0.00012008679,0.000056175082,0.00005639077,0.000055712066,0.00007420139,0.00009741197,0.95832396,0.013394936,0.026931744],"study_design_scores_gemma":[0.0020169981,0.00032879738,0.00030306188,0.000006778095,0.0001713026,0.000014182257,0.000047501253,0.025863592,0.00028537342,0.9508915,0.019820236,0.0002506862],"about_ca_topic_score_codex":0.000004413636,"about_ca_topic_score_gemma":0.0000020183782,"teacher_disagreement_score":0.22129542,"about_ca_system_score_codex":0.00016274591,"about_ca_system_score_gemma":0.00013312462,"threshold_uncertainty_score":0.9938076},"labels":[],"label_agreement":null},{"id":"W4280562270","doi":"10.1002/pst.2231","title":"Two‐stage subgroup‐specific time‐to‐event (2S‐Sub‐TITE): An adaptive two‐stage time‐to‐toxicity design for subgroup‐specific dose finding in phase I oncology trials","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Subgroup analysis; Mathematics; Statistics; Sample size determination; Cluster analysis; Event (particle physics); Confidence interval","score_opus":0.7099022599683399,"score_gpt":0.6160788559671313,"score_spread":0.09382340400120859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280562270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010889496,0.0001231648,0.95303416,0.00063598884,0.0013918517,0.010253717,0.02258696,0.00032996648,0.000754697],"genre_scores_gemma":[0.019781778,0.000068199064,0.9722874,0.0016084488,0.0011821276,0.0027513343,0.00027058815,0.00038260565,0.0016675068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9715206,0.016084798,0.005470898,0.0024369778,0.0019590931,0.0025276546],"domain_scores_gemma":[0.8396204,0.1558236,0.0011809963,0.0011169421,0.0004082999,0.0018497613],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.037685916,0.0012213909,0.004061324,0.000751467,0.000832633,0.00027326652,0.0016345922,0.0003617206,0.028377214],"category_scores_gemma":[0.059848987,0.001267728,0.0005334694,0.0016751729,0.0004964345,0.00024560324,0.0010332417,0.0021549026,0.0016689894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05659872,0.018376958,0.000027584365,0.00046797935,0.0008105575,0.0016967733,0.0017392421,0.009113785,0.082508855,0.42236727,0.089315936,0.31697634],"study_design_scores_gemma":[0.04565733,0.013345435,0.000038149217,0.00015723148,0.00093921256,0.000041333988,0.00043736957,0.232789,0.02155168,0.47677666,0.20510033,0.0031662732],"about_ca_topic_score_codex":0.000024953035,"about_ca_topic_score_gemma":0.000014071256,"teacher_disagreement_score":0.31381005,"about_ca_system_score_codex":0.0025143481,"about_ca_system_score_gemma":0.00050662213,"threshold_uncertainty_score":0.9991083},"labels":[],"label_agreement":null},{"id":"W4285732331","doi":"10.1002/pst.2257","title":"Left truncation in linked data: A practical guide to understanding left truncation and applying it using <scp>SAS</scp> and R","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"Genentech","keywords":"Truncation (statistics); Mathematics; Computer science; Left behind; Statistics; Medicine","score_opus":0.13040517423521852,"score_gpt":0.4019486621779917,"score_spread":0.27154348794277317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285732331","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075698666,0.0003887991,0.92120475,0.0009846608,0.00021348671,0.000672798,0.00040135038,0.00001285976,0.0004226309],"genre_scores_gemma":[0.91664666,0.00044864687,0.07941524,0.0022321984,0.00017595122,0.000023052697,0.0009026576,0.000034044228,0.00012157032],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985878,0.00010675653,0.00039204484,0.0003783572,0.00020862307,0.00032642944],"domain_scores_gemma":[0.99920523,0.00022266201,0.000101070706,0.00024581354,0.000030888135,0.0001943314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077428465,0.0001579517,0.00016488104,0.00006772125,0.00027941496,0.000092111746,0.00011111521,0.00008101584,0.000019831581],"category_scores_gemma":[0.00039223328,0.00017684544,0.000013148657,0.00009118399,0.000084472995,0.0000201118,0.00064031733,0.00028770798,0.0000018713172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014759016,0.001727411,0.044565592,0.0020080886,0.0011725711,0.00035551444,0.013679723,0.029183943,0.36665317,0.15878423,0.26507556,0.11531829],"study_design_scores_gemma":[0.0014782791,0.00018486772,0.00090330857,0.000022113922,0.00012907578,0.00030291313,0.0021436035,0.6886213,0.0005769439,0.0036043974,0.30178285,0.0002503616],"about_ca_topic_score_codex":0.000024629635,"about_ca_topic_score_gemma":0.000063487365,"teacher_disagreement_score":0.8417895,"about_ca_system_score_codex":0.00012236468,"about_ca_system_score_gemma":0.000117991316,"threshold_uncertainty_score":0.7211548},"labels":[],"label_agreement":null},{"id":"W4289544708","doi":"10.1002/pst.2258","title":"Key considerations for choosing a statistical method to deal with incomplete treatment adherence in pragmatic trials","year":2022,"lang":"en","type":"review","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Inverse probability weighting; Covariate; Computer science; Weighting; Statistical inference; Inference; Key (lock); Clinical trial; Medicine; Machine learning; Econometrics; Artificial intelligence; Statistics; Mathematics; Estimator","score_opus":0.7492029465102941,"score_gpt":0.639858577016374,"score_spread":0.10934436949392001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289544708","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5025162e-7,0.100547954,0.8790714,0.000055100554,0.00006271984,0.008033418,0.011844799,0.0001953313,0.00018911004],"genre_scores_gemma":[0.0000015864046,0.27988094,0.7123267,0.00011765128,0.00007238447,0.0070005734,0.0004252872,0.00013283009,0.00004201877],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99190396,0.0031728814,0.0025474066,0.0009042112,0.00059960096,0.00087191636],"domain_scores_gemma":[0.9032574,0.0949738,0.00075188343,0.0004235008,0.0001447328,0.0004486629],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034881234,0.0009011525,0.004367819,0.00036317954,0.0002661463,0.00015597865,0.00030524546,0.00019763484,0.0019272771],"category_scores_gemma":[0.010134075,0.0006864075,0.0002296556,0.0004785649,0.00013511232,0.00009048303,0.00018167823,0.0007905546,0.000023493272],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007351906,0.00029262673,5.029554e-7,0.0055017336,0.00022044846,0.0001049252,0.00018216102,0.0000126017585,0.0000012276598,0.34122604,0.0013210685,0.65106314],"study_design_scores_gemma":[0.000895896,0.00092299277,1.74953e-7,0.0016558367,0.0021790487,0.0000913726,0.000026423208,0.0011305016,0.000010407456,0.32104403,0.67141986,0.0006234589],"about_ca_topic_score_codex":0.00004618972,"about_ca_topic_score_gemma":0.00014250241,"teacher_disagreement_score":0.6700988,"about_ca_system_score_codex":0.0015304136,"about_ca_system_score_gemma":0.0010767253,"threshold_uncertainty_score":0.9995587},"labels":[],"label_agreement":null},{"id":"W4293724130","doi":"10.1002/pst.2263","title":"A comparison of statistical methods for animal oncology studies","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Statistics; Missing data; Data set; Statistical power; Medicine; Volume (thermodynamics); Oncology; Medical physics; Computer science; Mathematics","score_opus":0.4606261912846036,"score_gpt":0.6514265736967599,"score_spread":0.19080038241215636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293724130","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033217447,0.0006273504,0.99104565,0.00056393014,0.00037618697,0.0009199024,0.0021911664,0.00008705394,0.00086698617],"genre_scores_gemma":[0.17982896,0.000015617106,0.81926984,0.0002586116,0.00005329371,0.0004044701,0.00005260915,0.00003872409,0.000077885445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964015,0.0011797261,0.0011329155,0.0003866581,0.00034830783,0.0005508811],"domain_scores_gemma":[0.96884376,0.03005765,0.00034835795,0.00024396565,0.00025005467,0.00025622555],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024503372,0.0002533007,0.0011788888,0.00008753611,0.00028286438,0.00000818955,0.00036418816,0.00007137471,0.001912986],"category_scores_gemma":[0.012667845,0.00022851297,0.00009882104,0.0001992455,0.00061150047,0.000025011983,0.00048114752,0.00053713046,0.000008460016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005723192,0.0012848653,0.00023529178,0.0008585325,0.00030704733,0.000014698225,0.0009479269,0.0000043934856,0.0023839062,0.94061065,0.02971805,0.023062348],"study_design_scores_gemma":[0.0014465951,0.0021758585,0.00004550087,0.000009791938,0.0005805675,0.00003808137,0.0011792075,0.05208888,0.0056693903,0.88032806,0.05613451,0.00030354035],"about_ca_topic_score_codex":0.0000014693032,"about_ca_topic_score_gemma":0.0000011752203,"teacher_disagreement_score":0.17650722,"about_ca_system_score_codex":0.00024343084,"about_ca_system_score_gemma":0.00015154525,"threshold_uncertainty_score":0.9989994},"labels":[],"label_agreement":null},{"id":"W4297811834","doi":"10.1002/pst.2336","title":"Evaluating hybrid controls methodology in early‐phase oncology trials: A simulation study based on the <scp>MORPHEUS‐UC</scp> trial","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Roche (Canada)","funders":"F. Hoffmann-La Roche","keywords":"Frequentist inference; Bayesian probability; Sample size determination; Prior probability; Statistics; Clinical trial; Computer science; Econometrics; Medicine; Oncology; Bayesian inference; Mathematics; Internal medicine","score_opus":0.9531832501912486,"score_gpt":0.7584745799826099,"score_spread":0.1947086702086387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297811834","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22425951,0.000015087485,0.7627189,0.0006380573,0.0022228386,0.008394783,0.0011691374,0.00028889487,0.000292755],"genre_scores_gemma":[0.44046867,0.000015811669,0.555485,0.0013716947,0.0010322556,0.0013770355,0.000029589657,0.00012653635,0.00009341635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.92940533,0.061639618,0.0046659242,0.0011667038,0.0017896268,0.0013328242],"domain_scores_gemma":[0.42053577,0.57748175,0.00083326414,0.000575019,0.0002721116,0.00030206927],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10514563,0.00059492793,0.002818358,0.0003708984,0.0003013822,0.00013757091,0.0006977348,0.0003222419,0.0007320004],"category_scores_gemma":[0.8400598,0.0004281533,0.0003307745,0.0010917835,0.00044645526,0.00006453421,0.0002427964,0.0017458445,0.0003367996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10846021,0.030546246,0.000974042,0.00052066887,0.0019351591,0.0024075496,0.0032492338,0.055436853,0.0020595994,0.21644688,0.01850704,0.5594565],"study_design_scores_gemma":[0.08352025,0.0050169127,0.00015470201,0.00003311015,0.00071289064,0.0000013875717,0.00020490878,0.56161875,0.00017097648,0.3475836,0.0008484786,0.000134048],"about_ca_topic_score_codex":0.00002670312,"about_ca_topic_score_gemma":0.000010102523,"teacher_disagreement_score":0.7349142,"about_ca_system_score_codex":0.0003248276,"about_ca_system_score_gemma":0.00037338008,"threshold_uncertainty_score":0.999817},"labels":[],"label_agreement":null},{"id":"W4311687382","doi":"10.1002/pst.2280","title":"Parametric and nonparametric methods for confidence intervals and sample size planning for win probability in parallel‐group randomized trials with Likert item and Likert scale data","year":2022,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Likert scale; Nonparametric statistics; Statistics; Confidence interval; Sample size determination; Context (archaeology); Parametric statistics; Computer science; Mathematics","score_opus":0.863855780924001,"score_gpt":0.6504602847221514,"score_spread":0.2133954962018495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311687382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018436369,0.006755784,0.96475077,0.0004909609,0.00013475803,0.007262008,0.0021426445,0.000007937199,0.000018766394],"genre_scores_gemma":[0.10902842,0.00026941657,0.88879627,0.0003980416,0.0000313495,0.001297508,0.00006489455,0.000020658807,0.00009341646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9584158,0.029028747,0.008138851,0.0019577986,0.0019069229,0.00055185467],"domain_scores_gemma":[0.24998406,0.74361235,0.003415593,0.0018892911,0.0005985558,0.0005001583],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28813282,0.00039625083,0.006430179,0.0004309264,0.00031191646,0.0008453489,0.0010153165,0.00007097115,0.00062211324],"category_scores_gemma":[0.5918576,0.00021788849,0.00031390862,0.0016550361,0.00040035677,0.00023601016,0.00070887955,0.0003193214,0.0000017992652],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06344173,0.0008890522,0.06647411,0.0027276594,0.0020472496,0.000018290451,0.0024237903,0.00089565007,0.00010833169,0.020356825,0.017225781,0.82339156],"study_design_scores_gemma":[0.031401552,0.00029621695,0.0017391411,0.00004229405,0.0014906547,0.000026420279,0.0003595544,0.7898223,0.000010593328,0.14455529,0.02990826,0.00034776249],"about_ca_topic_score_codex":0.000056248402,"about_ca_topic_score_gemma":0.000020844289,"teacher_disagreement_score":0.82304376,"about_ca_system_score_codex":0.000049765298,"about_ca_system_score_gemma":0.00007737108,"threshold_uncertainty_score":0.8885235},"labels":[],"label_agreement":null},{"id":"W4315619070","doi":"10.1002/pst.2285","title":"Natural cubic splines for the analysis of Alzheimer's clinical trials","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; National Center for Advancing Translational Sciences; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Categorical variable; Repeated measures design; Clinical trial; Type I and type II errors; Statistics; Mixed model; Mathematics; Covariate; Computer science; Medicine; Econometrics","score_opus":0.7673059866440124,"score_gpt":0.6597566135267552,"score_spread":0.10754937311725721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315619070","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002663204,0.00048399888,0.99067,0.0007392496,0.001089941,0.00079756795,0.0033663139,0.00009645125,0.00009322417],"genre_scores_gemma":[0.25613257,0.00079184154,0.741388,0.00049399113,0.0005787912,0.00016915516,0.00016391854,0.0000561262,0.00022562138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598473,0.0010307321,0.0018243594,0.0003184614,0.00042481386,0.00041687826],"domain_scores_gemma":[0.8797943,0.118997954,0.00039435163,0.00031971995,0.0003278174,0.0001658636],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010819284,0.00020368608,0.0012447147,0.00015133987,0.00013697788,0.000038445487,0.0003261454,0.00009752358,0.0005001162],"category_scores_gemma":[0.0751076,0.00012277221,0.00050137663,0.0011373525,0.00038272786,0.000025082865,0.000111723115,0.0003328147,0.000028514303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019435842,0.00014600337,0.000571083,0.000112026944,0.0054485505,0.0000058946384,0.00006336491,0.000042542957,0.00019942941,0.69934434,0.028931292,0.2649411],"study_design_scores_gemma":[0.00076612365,0.00007174139,0.006799551,0.000012908373,0.015909072,6.700812e-7,0.000047457273,0.66541255,0.00060232903,0.3037853,0.0064026425,0.000189678],"about_ca_topic_score_codex":0.0000100906655,"about_ca_topic_score_gemma":0.000007784642,"teacher_disagreement_score":0.66537,"about_ca_system_score_codex":0.0000116250485,"about_ca_system_score_gemma":0.000058543814,"threshold_uncertainty_score":0.93268317},"labels":[],"label_agreement":null},{"id":"W4319657136","doi":"10.1002/pst.2292","title":"Bayesian single‐to‐double arm transition design using both short‐term and long‐term endpoints","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Clinical endpoint; Frequentist inference; Sample size determination; Bayesian probability; Computer science; Statistics; Randomized controlled trial; Bayesian inference; Medicine; Mathematics; Internal medicine","score_opus":0.7559694574546456,"score_gpt":0.6006447139559284,"score_spread":0.15532474349871717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319657136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017564705,0.000027510634,0.9788319,0.0002973548,0.00066438894,0.0012689073,0.0007541717,0.00034818953,0.00024289849],"genre_scores_gemma":[0.18093574,0.00007909397,0.8178675,0.00050686195,0.00035553353,0.000050891515,0.000021268948,0.00011952224,0.00006354108],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99540246,0.0008772906,0.0012115489,0.00077684666,0.0007620723,0.00096975703],"domain_scores_gemma":[0.9748948,0.023481311,0.00013012024,0.00040114156,0.00013992088,0.00095270335],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002895735,0.0004520865,0.0008463656,0.00019757172,0.00024455186,0.00018763891,0.00028878276,0.00022921959,0.0007105401],"category_scores_gemma":[0.009231768,0.00044252173,0.00010088567,0.00059330446,0.00034861223,0.00011525302,0.00017771132,0.00053362176,0.00010657077],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0075706067,0.0050592166,0.0038413787,0.0051770573,0.001381293,0.0040457807,0.004151059,0.0009931362,0.082844146,0.2672783,0.013837809,0.6038202],"study_design_scores_gemma":[0.004815439,0.0009201237,0.0032354568,0.00045292597,0.00140921,0.00011117668,0.00006446616,0.12437548,0.023483839,0.8394352,0.00023941239,0.001457244],"about_ca_topic_score_codex":0.000003847049,"about_ca_topic_score_gemma":0.000003262448,"teacher_disagreement_score":0.60236293,"about_ca_system_score_codex":0.0001629612,"about_ca_system_score_gemma":0.00006988644,"threshold_uncertainty_score":0.99980265},"labels":[],"label_agreement":null},{"id":"W4378803918","doi":"10.1002/pst.2317","title":"Variance estimation of the risk difference when using propensity‐score matching and weighting with time‐to‐event outcomes","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Ministry of Long-Term Care; Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences; Ministry of Health, Ontario","keywords":"Propensity score matching; Weighting; Statistics; Matching (statistics); Variance (accounting); Event (particle physics); Estimation; Mathematics; Event data; Econometrics; Inverse probability weighting; Medicine; Covariate; Economics","score_opus":0.20647756529539354,"score_gpt":0.4342598912393333,"score_spread":0.22778232594393974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378803918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39376673,0.0000047890903,0.60544753,0.00010825791,0.000021586013,0.0003952169,0.00010509591,0.00011214373,0.00003863772],"genre_scores_gemma":[0.5689193,0.000010381729,0.4308075,0.00007427399,0.000010845843,0.000016736638,0.000003729001,0.000027476659,0.0001297804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99862915,0.00013966489,0.00034965563,0.0002336919,0.00036583582,0.0002820148],"domain_scores_gemma":[0.9979639,0.0013422746,0.0002370396,0.0002430518,0.00010821153,0.00010549999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000424215,0.00018952253,0.00031415097,0.00004988058,0.00018185144,0.00003908291,0.00018520496,0.000042421485,0.000047543228],"category_scores_gemma":[0.0011886684,0.00011899287,0.000023159251,0.00023669343,0.00013965828,0.00008695851,0.00026311819,0.0002788819,0.00001472806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004005523,0.00059639727,0.18265204,0.00275152,0.0005618711,0.000112611844,0.007443841,0.020821303,0.03736865,0.5265078,0.0012017895,0.21958163],"study_design_scores_gemma":[0.00031325838,0.00006799711,0.030880442,0.00035299093,0.00022240684,0.000013209314,0.000026242626,0.26984593,0.007336361,0.69062394,0.000042375465,0.00027485614],"about_ca_topic_score_codex":0.000029657334,"about_ca_topic_score_gemma":0.0000064824003,"teacher_disagreement_score":0.24902461,"about_ca_system_score_codex":0.0000597638,"about_ca_system_score_gemma":0.000038824346,"threshold_uncertainty_score":0.48523885},"labels":[],"label_agreement":null},{"id":"W4380728286","doi":"10.1002/pst.2318","title":"Alone, together: On the benefits of Bayesian borrowing in a meta‐analytic setting","year":2023,"lang":"en","type":"review","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Veterinarians of British Columbia; NeuroDevNet","funders":"","keywords":"Bayes' theorem; Bayesian probability; Randomized controlled trial; Inference; Sample size determination; Bayesian inference; Econometrics; Fraction (chemistry); Bayesian hierarchical modeling; Randomized response; Meta-analysis; Bayes factor; Statistics; Computer science; Mathematics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.8273449729662699,"score_gpt":0.6381815326863675,"score_spread":0.1891634402799024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380728286","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012514819,0.893301,0.09223382,0.00047611995,0.00091505883,0.0036780797,0.007871975,0.00020038588,0.0013222703],"genre_scores_gemma":[0.00000683319,0.72847843,0.2703133,0.000249664,0.000261946,0.0003229724,0.000020968302,0.00022939444,0.00011649335],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878164,0.0050267903,0.004016462,0.0009343748,0.001233049,0.00097290735],"domain_scores_gemma":[0.72298086,0.27490532,0.0009625757,0.0007749011,0.00012328984,0.00025302323],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011753892,0.00092188007,0.006034459,0.00032161962,0.00012102135,0.00007383463,0.0011030494,0.00052773725,0.0009799164],"category_scores_gemma":[0.16679256,0.0005680187,0.0010978057,0.001349339,0.00040087852,0.00003513862,0.00040033928,0.002301235,0.00020446033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029840274,0.00023302535,0.0000017860012,0.02040976,0.0034457105,0.00008473839,0.000048127473,0.000011232887,1.1859821e-7,0.48420757,0.0019665454,0.48956153],"study_design_scores_gemma":[0.0006519111,0.00013379221,0.0000022240306,0.012193061,0.035306584,0.000012089826,0.000025825528,0.0023539762,0.000014734296,0.8498337,0.098603904,0.00086816587],"about_ca_topic_score_codex":0.000020443742,"about_ca_topic_score_gemma":0.000017117802,"teacher_disagreement_score":0.4886934,"about_ca_system_score_codex":0.00018947628,"about_ca_system_score_gemma":0.00025890407,"threshold_uncertainty_score":0.9999333},"labels":[],"label_agreement":null},{"id":"W4386810972","doi":"10.1002/pst.2338","title":"A marginalized two‐part joint model for a longitudinal biomarker and a terminal event with application to advanced head and neck cancers","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut National Du Cancer","keywords":"Biomarker; Covariate; Medicine; Oncology; Head and neck cancer; Clinical trial; Event (particle physics); Statistics; Internal medicine; Cancer; Mathematics; Biology","score_opus":0.5750052390768035,"score_gpt":0.5987650466759101,"score_spread":0.023759807599106675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386810972","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028698446,0.000038265924,0.9661779,0.0010609587,0.00011430815,0.0020465816,0.0016841715,0.00012446956,0.00005490657],"genre_scores_gemma":[0.06579154,0.00010065402,0.93218714,0.00042315485,0.00009613832,0.0010857255,0.000021087259,0.000064754335,0.00022981274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740523,0.00017196791,0.00073357014,0.00069470133,0.00040433666,0.0005901936],"domain_scores_gemma":[0.9892689,0.009518442,0.00016893372,0.00026896474,0.00018658182,0.0005881876],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001448051,0.0003057349,0.00065826223,0.000095833,0.00015882165,0.000062545885,0.00012011724,0.00007534843,0.00004577811],"category_scores_gemma":[0.007882001,0.00025566068,0.000047571157,0.00031628212,0.00027333447,0.000053734457,0.00014710485,0.00020600809,0.000013598827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012595537,0.00054114044,0.0016336717,0.003107641,0.0005450329,0.00015453956,0.0006215404,0.0019814149,0.002902566,0.4020708,0.018079426,0.5557667],"study_design_scores_gemma":[0.0042961156,0.00026708498,0.0010038291,0.00013391394,0.00030037935,0.00002120658,0.000017659502,0.63802385,0.0001526121,0.35298133,0.0024909931,0.00031104204],"about_ca_topic_score_codex":0.000015399377,"about_ca_topic_score_gemma":0.00005344619,"teacher_disagreement_score":0.6360424,"about_ca_system_score_codex":0.000128025,"about_ca_system_score_gemma":0.00010451814,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W4390236152","doi":"10.1002/pst.2357","title":"Evaluation of a flexible piecewise linear mixed‐effects model in the analysis of randomized cross‐over trials","year":2023,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Government of Canada","keywords":"Univariate; Mixed model; Random effects model; Generalized linear mixed model; Piecewise; Linear model; Statistics; Computer science; Sample size determination; Residual; Piecewise linear function; Econometrics; Meta-analysis; Mathematics; Medicine; Algorithm; Multivariate statistics; Internal medicine","score_opus":0.8296799381412743,"score_gpt":0.7032816473815637,"score_spread":0.12639829075971054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390236152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06910845,0.00016224835,0.9245887,0.000105194544,0.00047284257,0.0030507187,0.001959478,0.000059774076,0.0004926128],"genre_scores_gemma":[0.49075413,0.00018071194,0.50822026,0.00011702666,0.000104036895,0.00048055314,0.000041985855,0.000039326467,0.0000619612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96993154,0.021211246,0.004484775,0.00051848846,0.0033015402,0.0005523951],"domain_scores_gemma":[0.6906849,0.30705062,0.0008885551,0.0004858894,0.0007715098,0.0001185088],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12584095,0.0002765193,0.0033474043,0.00047673608,0.000052915715,0.000032896496,0.00045913222,0.00019006077,0.00065582583],"category_scores_gemma":[0.55810446,0.00018180275,0.00070809165,0.0026111628,0.00064684835,0.00005416464,0.00012483395,0.0003991924,0.000017261122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.021737363,0.0015442921,0.00047885554,0.0009988544,0.0073683406,0.0000241526,0.0014841121,0.048607476,0.00057222694,0.8505479,0.0030880342,0.06354836],"study_design_scores_gemma":[0.031168723,0.00002550489,0.00066881126,0.000029393104,0.0131392935,1.4860264e-7,0.000017051212,0.50647855,0.0008874774,0.44748405,0.000005172753,0.00009583998],"about_ca_topic_score_codex":0.000025762372,"about_ca_topic_score_gemma":0.000006401874,"teacher_disagreement_score":0.45787108,"about_ca_system_score_codex":0.0000755614,"about_ca_system_score_gemma":0.00016532018,"threshold_uncertainty_score":0.9001307},"labels":[],"label_agreement":null},{"id":"W4391650553","doi":"10.1002/pst.2365","title":"Assessing the performance of group‐based trajectory modeling method to discover different patterns of medication adherence","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact; University of Victoria; Public Health Ontario; University of Toronto; Cascades (Canada); Université Laval; NeuroDevNet","funders":"","keywords":"Covariate; Nonparametric statistics; Variance (accounting); Trajectory; Statistics; Computer science; Medicine; Repeated measures design; Quality (philosophy); Medication adherence; Random effects model; Mathematics; Econometrics; Internal medicine; Meta-analysis","score_opus":0.620705524597161,"score_gpt":0.6302486008024275,"score_spread":0.00954307620526651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391650553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09073558,0.00007821642,0.90714574,0.00022154427,0.00061604736,0.00047102716,0.0006203146,0.000051120125,0.00006044019],"genre_scores_gemma":[0.5211497,0.00002925788,0.47856155,0.00010046329,0.000085666245,0.00003495572,0.0000054772067,0.00002536257,0.000007547335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959903,0.0010983549,0.0013205202,0.00039343355,0.0008612642,0.0003361429],"domain_scores_gemma":[0.9496598,0.049446624,0.00019315987,0.00035789376,0.00014602169,0.00019646934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035379138,0.00024110766,0.0006116077,0.00008430226,0.00006663129,0.00006954826,0.00040200487,0.0000991919,0.0004176266],"category_scores_gemma":[0.010244667,0.00015484708,0.00011890466,0.00025125104,0.0001583527,0.00009877673,0.00011912767,0.00051085785,0.0000075233515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003607734,0.0011133214,0.00396829,0.010372874,0.00045969547,0.000021530099,0.0008265578,0.004615426,0.017271256,0.45965737,0.000650346,0.5006826],"study_design_scores_gemma":[0.00039308227,0.0001960902,0.0011992818,0.0006716483,0.0004257342,0.000001572131,0.000052594663,0.88655704,0.012196591,0.09804442,0.000077636985,0.00018430158],"about_ca_topic_score_codex":0.00001941526,"about_ca_topic_score_gemma":0.0000029084147,"teacher_disagreement_score":0.8819416,"about_ca_system_score_codex":0.000074638585,"about_ca_system_score_gemma":0.00010380544,"threshold_uncertainty_score":0.9980925},"labels":[],"label_agreement":null},{"id":"W4400056122","doi":"10.1002/pst.2414","title":"<scp>T3</scp> + 3: 3 + 3 Design With Delayed Outcomes","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Isotonic regression; Maximum tolerated dose; Toxicity; Clinical trial; Outcome (game theory); Research design; Duration (music); Clinical study design; Computer science; Logistic regression; Medicine; Reliability engineering; Statistics; Mathematics; Internal medicine; Engineering; Machine learning","score_opus":0.6329948285871682,"score_gpt":0.5963440292239538,"score_spread":0.03665079936321436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400056122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005819221,0.0003239795,0.9912299,0.00044423083,0.0011941742,0.0008942167,0.0013330077,0.00069411116,0.003304461],"genre_scores_gemma":[0.011740908,0.00013681158,0.9847422,0.0008366454,0.00034965982,0.00012093694,0.0000113486685,0.00016729908,0.0018941456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99495566,0.0011207195,0.0011692422,0.0007869269,0.0010278639,0.0009395751],"domain_scores_gemma":[0.8190125,0.17965852,0.000119877244,0.00042972484,0.00019142732,0.0005879534],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030521774,0.000531802,0.00095029036,0.00012417827,0.00015193592,0.00029145562,0.00045267478,0.00022612482,0.00088146864],"category_scores_gemma":[0.0696193,0.00037526627,0.00014734088,0.00052145583,0.00050460413,0.00011864917,0.00015430494,0.0010157278,0.0007172267],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010781425,0.000328533,0.0003167915,0.00051926816,0.0007400389,0.0008436135,0.0001574162,0.000027604197,0.000097059245,0.86467177,0.09624841,0.035941698],"study_design_scores_gemma":[0.0011999349,0.00039929498,0.0002247314,0.000119028926,0.0010187355,0.000047854006,0.00003572815,0.031971563,0.0012178357,0.9179447,0.04557063,0.0002499138],"about_ca_topic_score_codex":0.0000062231034,"about_ca_topic_score_gemma":0.0000026657403,"teacher_disagreement_score":0.1785378,"about_ca_system_score_codex":0.00012987043,"about_ca_system_score_gemma":0.00019882272,"threshold_uncertainty_score":0.99986994},"labels":[],"label_agreement":null},{"id":"W4402323319","doi":"10.1002/pst.2436","title":"Propensity Score Analysis With Baseline and Follow‐Up Measurements of the Outcome Variable","year":2024,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Baseline (sea); Statistics; Weighting; Estimator; Observational study; Variable (mathematics); Matching (statistics); Regression analysis; Mathematics; Medicine","score_opus":0.4838276404501285,"score_gpt":0.4782297378790365,"score_spread":0.005597902571091995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402323319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018065337,0.0001271427,0.98023665,0.00012899836,0.00009485927,0.00043073963,0.0002990825,0.00013841865,0.0004787592],"genre_scores_gemma":[0.7782694,0.000018282484,0.22116576,0.00012649152,0.000019322228,0.00002012221,0.000009976268,0.000025050163,0.00034555295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985611,0.00012812363,0.00037379822,0.00024893216,0.00046635093,0.0002216885],"domain_scores_gemma":[0.998556,0.0007638929,0.00008327199,0.00027395945,0.00022020777,0.000102678685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078695844,0.00017031313,0.00035796402,0.00006721527,0.00006970308,0.00004445928,0.00015765509,0.000045436333,0.0001834842],"category_scores_gemma":[0.00096325955,0.000099059565,0.000047747093,0.0006556474,0.00019660637,0.00008251629,0.00012538963,0.00027450948,0.0000025599602],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029682365,0.0003582284,0.4034584,0.0024671997,0.0028239603,0.000054256423,0.00032340837,0.0001283463,0.0060947216,0.5673823,0.0037648866,0.012847508],"study_design_scores_gemma":[0.002461731,0.00043036707,0.016132742,0.00081636914,0.020016551,0.000052360032,0.000047634894,0.12914056,0.08975075,0.733953,0.005820202,0.0013777073],"about_ca_topic_score_codex":0.000024428466,"about_ca_topic_score_gemma":0.000040479605,"teacher_disagreement_score":0.7602041,"about_ca_system_score_codex":0.000057354177,"about_ca_system_score_gemma":0.00006110372,"threshold_uncertainty_score":0.4039532},"labels":[],"label_agreement":null},{"id":"W4409232946","doi":"10.1002/pst.70014","title":"Chauhan Weighted Trajectory Analysis of Combined Efficacy and Safety Outcomes for Risk–Benefit Analysis","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"","keywords":"Sample size determination; Medicine; Clinical trial; Confidence interval; Statistics; Clinical endpoint; Computer science; Mathematics; Internal medicine","score_opus":0.23610505534910645,"score_gpt":0.4808698903269627,"score_spread":0.24476483497785625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409232946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16673528,0.0014458635,0.8003817,0.0055678436,0.0003683154,0.0011860875,0.023506695,0.000053826257,0.00075437233],"genre_scores_gemma":[0.96298814,0.000672457,0.031204022,0.0036231568,0.00004549268,0.00009945778,0.0007187745,0.000026734082,0.0006217753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9952908,0.00022174593,0.0034430842,0.00056260487,0.00010123788,0.0003804962],"domain_scores_gemma":[0.9905186,0.007419073,0.0013045314,0.00039466438,0.0001402929,0.00022282287],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0057197884,0.00022607832,0.002008489,0.0012362169,0.0002127169,0.000045645927,0.00021568626,0.00012311061,0.0004939869],"category_scores_gemma":[0.003332016,0.00026323274,0.00031336595,0.001462181,0.00015170632,0.00008912813,0.000054314445,0.00017364346,0.000027551125],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001909986,0.00027965626,0.5452353,0.00035975428,0.013296317,3.6604234e-7,0.00035631796,0.0011969082,0.0000020898685,0.43634647,0.001401791,0.0013340673],"study_design_scores_gemma":[0.0022740501,0.000051651397,0.5956953,0.000010019207,0.004531172,5.1589055e-8,0.00006391159,0.3753314,0.000006783363,0.013848222,0.007961723,0.00022567312],"about_ca_topic_score_codex":0.00042617932,"about_ca_topic_score_gemma":0.00032383623,"teacher_disagreement_score":0.79625285,"about_ca_system_score_codex":0.00022444667,"about_ca_system_score_gemma":0.00006132455,"threshold_uncertainty_score":0.999982},"labels":[],"label_agreement":null},{"id":"W4413024598","doi":"10.1002/pst.70029","title":"Target Aggregate Data Adjustment Method for Transportability Analysis Utilizing Summary‐Level Data From the Target Population","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of British Columbia; York University; Centre for Advancing Health Outcomes; Impact; Simon Fraser University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Censoring (clinical trials); Interpretability; Computer science; Weighting; Causal inference; Population; Statistics; Aggregate data; Statistical inference; Inference; Inverse probability weighting; Econometrics; Data mining; Estimator; Artificial intelligence; Mathematics; Medicine","score_opus":0.513051299481403,"score_gpt":0.5578152948638562,"score_spread":0.044763995382453126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413024598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016097771,0.00051147415,0.90627193,0.0006918149,0.00018910013,0.001079428,0.09076774,0.00020721914,0.00012032456],"genre_scores_gemma":[0.02206435,0.0002126538,0.94603753,0.0006672596,0.000099124154,0.000088252265,0.03071651,0.00003446834,0.000079852194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967419,0.00039375178,0.00093774544,0.0009909213,0.0004408203,0.00049486774],"domain_scores_gemma":[0.98808014,0.008619275,0.00026657083,0.0026903932,0.00019748896,0.00014614615],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022952245,0.00034186267,0.00066929555,0.00008520847,0.00024533583,0.00007005839,0.0018508882,0.00012644735,0.00041915776],"category_scores_gemma":[0.0039249784,0.00026660706,0.00009512868,0.00061916607,0.00013480717,0.00035343075,0.000675447,0.00041790944,0.0000032228704],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073832145,0.0011866787,0.045884773,0.00088728283,0.0052211727,0.000018491413,0.00031136983,0.00046950436,0.00052265363,0.69278115,0.11516026,0.13681832],"study_design_scores_gemma":[0.00035051725,0.000012489073,0.0043354505,0.000032606917,0.0028015333,2.0501734e-7,0.000043459528,0.43915883,0.0007807065,0.53401065,0.018262453,0.00021109016],"about_ca_topic_score_codex":0.00050677615,"about_ca_topic_score_gemma":0.0005856783,"teacher_disagreement_score":0.43868932,"about_ca_system_score_codex":0.00014237904,"about_ca_system_score_gemma":0.000100721394,"threshold_uncertainty_score":0.9999786},"labels":[],"label_agreement":null},{"id":"W4413114376","doi":"10.1002/pst.70037","title":"Drift Parameter Based Sample Size Determination in Multi‐Stage Bayesian Randomized Clinical Trials","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Bayesian probability; Statistics; Stage (stratigraphy); Randomized controlled trial; Clinical trial; Mathematics; Computer science; Econometrics; Medicine; Internal medicine; Biology","score_opus":0.7611773147160606,"score_gpt":0.6919872169274078,"score_spread":0.06919009778865282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413114376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042133758,0.000051400668,0.99082136,0.00097233517,0.001837047,0.0032715776,0.0018507246,0.00016673206,0.0006074835],"genre_scores_gemma":[0.034520432,0.00012475459,0.96186864,0.0024254564,0.00017467972,0.00039301522,0.000021555717,0.00006589359,0.0004055774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9573543,0.03273736,0.0071592084,0.0010494327,0.0007841587,0.00091555977],"domain_scores_gemma":[0.2717196,0.7261973,0.00081788143,0.0005873442,0.00026404494,0.00041381983],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07151701,0.0005498469,0.0040852726,0.0002453671,0.00012476444,0.00015351154,0.00054959994,0.0005586592,0.0024764547],"category_scores_gemma":[0.9340418,0.000455615,0.0007132413,0.0006175946,0.0009931755,0.00008604765,0.00018335036,0.0013603341,0.00003848404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.050273437,0.0036068864,0.0051969066,0.0012262976,0.00053318345,0.00018842866,0.00008429118,0.000037336296,0.00011472943,0.52447957,0.0037386373,0.4105203],"study_design_scores_gemma":[0.09237625,0.00005159776,0.00033405522,0.00011421032,0.0006203427,4.3568224e-7,0.000010109527,0.36803508,0.0004951521,0.5364073,0.0012465047,0.000308949],"about_ca_topic_score_codex":0.000043868255,"about_ca_topic_score_gemma":0.000035226214,"teacher_disagreement_score":0.86252475,"about_ca_system_score_codex":0.00016877858,"about_ca_system_score_gemma":0.0003129328,"threshold_uncertainty_score":0.99978954},"labels":[],"label_agreement":null},{"id":"W4414140358","doi":"10.1002/pst.70022","title":"Finding the Optimal Number of Splits and Repetitions in Double Cross‐Fitting Targeted Maximum Likelihood Estimators","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Estimator; Range (aeronautics); Sample size determination; Selection (genetic algorithm); Maximum likelihood; Sample (material); Design of experiments","score_opus":0.03203732618303272,"score_gpt":0.3995152458703245,"score_spread":0.36747791968729177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414140358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013132475,0.00017964459,0.98325986,0.0006163221,0.00021752997,0.00017892465,0.000040496056,0.0000333309,0.0023414004],"genre_scores_gemma":[0.26116467,0.000039255392,0.73842585,0.0002541282,0.000015464293,0.0000105903955,0.0000025879708,0.000006017354,0.000081455764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872583,0.00011509825,0.0003653578,0.00029429712,0.00016783754,0.00033160605],"domain_scores_gemma":[0.9988456,0.0006691689,0.000071593866,0.00023570785,0.00008195681,0.00009599526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007271021,0.00012764637,0.00018894987,0.000058900805,0.00014498904,0.00013317355,0.0003402099,0.00005812763,0.000034172186],"category_scores_gemma":[0.00019299205,0.00010176058,0.000028792972,0.00043057647,0.00016593462,0.00013647298,0.00028737288,0.00030673222,0.000005163801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023930512,0.00005945152,0.009803436,0.00008800824,0.000021271206,0.000020229183,0.00029244088,0.000080234124,0.0002231066,0.9321417,0.00025309782,0.056993097],"study_design_scores_gemma":[0.0016065035,0.00002151482,0.011991146,0.0001166481,0.00004966691,0.000028440174,0.000014863736,0.59460175,0.004889579,0.38423657,0.0021977045,0.0002456334],"about_ca_topic_score_codex":0.000028466331,"about_ca_topic_score_gemma":0.000003323551,"teacher_disagreement_score":0.5945215,"about_ca_system_score_codex":0.000030468545,"about_ca_system_score_gemma":0.000082148,"threshold_uncertainty_score":0.41496763},"labels":[],"label_agreement":null},{"id":"W4414534411","doi":"10.1002/pst.70031","title":"Adjustment for Inconsistency in Adaptive Phase 2/3 Designs With Dose Optimization","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Canada Research Chairs; Michael Smith Health Research BC","keywords":"Phase (matter); Selection (genetic algorithm); Maximum tolerated dose; Computerized adaptive testing; Adaptive design; Cutoff","score_opus":0.34858204789850666,"score_gpt":0.5624556527276947,"score_spread":0.21387360482918805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414534411","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004937103,0.00034942967,0.99413574,0.0002729522,0.00029122006,0.0012180603,0.00030678345,0.0000323118,0.0028998153],"genre_scores_gemma":[0.11098755,0.00003226885,0.8874934,0.0007476104,0.000027964074,0.00022533459,0.000021307054,0.000016754591,0.00044783295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971134,0.0005033089,0.00073296524,0.00057270826,0.0006763983,0.00040118332],"domain_scores_gemma":[0.99387985,0.0051286686,0.00013748652,0.00028045886,0.0003826734,0.0001908455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018183453,0.00022089217,0.00038057493,0.00029928074,0.00011772394,0.0001210094,0.0003796767,0.00007204958,0.00041763383],"category_scores_gemma":[0.002350913,0.00016821623,0.000049372746,0.0009852106,0.00024689114,0.0001975319,0.00009928531,0.00018367762,0.000023935412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0097835725,0.0031144922,0.0009588351,0.000060064467,0.00016005497,0.000092093054,0.0007863194,0.10778921,0.0039673066,0.35239002,0.009740302,0.51115775],"study_design_scores_gemma":[0.0066197477,0.00078485307,0.00031606056,0.000037529022,0.00008671457,0.000003515235,0.00034799182,0.94136345,0.0056823273,0.041235905,0.0032635473,0.00025834516],"about_ca_topic_score_codex":0.000013734493,"about_ca_topic_score_gemma":0.000009904795,"teacher_disagreement_score":0.83357424,"about_ca_system_score_codex":0.00022801198,"about_ca_system_score_gemma":0.00023803746,"threshold_uncertainty_score":0.6859659},"labels":[],"label_agreement":null},{"id":"W4415152696","doi":"10.1002/pst.70043","title":"Nonparametric Inference for the Covariate‐Adjusted Youden Index and Associated Cut‐Off Points for Three Ordinal Diagnostic Groups","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"DoD Alzheimer's Disease Neuroimaging Initiative; National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Takeda Pharmaceutical Company; Bristol-Myers Squibb; Eli Lilly and Company; Northern California Institute for Research and Education; Alzheimer's Drug Discovery Foundation; Simons Foundation; Foundation for the National Institutes of Health","keywords":"Estimator; Confidence interval; Heteroscedasticity; Youden's J statistic; Context (archaeology); Nonparametric statistics; Inference; Point estimation; Statistical inference","score_opus":0.19714102671591952,"score_gpt":0.45609796827218,"score_spread":0.2589569415562605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415152696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033938198,0.00036260101,0.98961496,0.0009348581,0.00056276313,0.0021467886,0.0026683484,0.000085466854,0.00023041318],"genre_scores_gemma":[0.5998835,0.0003071126,0.3972635,0.0011317959,0.00014268864,0.0009053586,0.00008139881,0.00006245215,0.0002221627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751014,0.00021179365,0.0007233183,0.00048738648,0.0003644077,0.0007029858],"domain_scores_gemma":[0.875106,0.123689175,0.0001899755,0.00027607748,0.00052916503,0.00020962933],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014277704,0.00035552905,0.00059247157,0.0001293781,0.000433692,0.00019699693,0.00041076812,0.00019404739,0.00014995536],"category_scores_gemma":[0.11905252,0.0002651247,0.0000869352,0.0006246299,0.00035697035,0.000064004584,0.00020733879,0.00041266912,0.0000062621248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026923412,0.00026582315,0.0075492896,0.00039547845,0.00028820807,0.000005029538,0.000056247616,0.00001090913,0.000014280912,0.84980506,0.0072021373,0.13413832],"study_design_scores_gemma":[0.0021505286,0.00017292377,0.022464478,0.00008847413,0.000768828,0.0000020979576,0.000027386977,0.31164297,0.00006649651,0.65981954,0.002538038,0.00025825115],"about_ca_topic_score_codex":0.00004294477,"about_ca_topic_score_gemma":0.00013013081,"teacher_disagreement_score":0.5964897,"about_ca_system_score_codex":0.000119686316,"about_ca_system_score_gemma":0.00015303526,"threshold_uncertainty_score":0.9999801},"labels":[],"label_agreement":null},{"id":"W4416257149","doi":"10.1002/pst.70049","title":"Great Wall: A Generalized Dose Optimization Design for Drug Combination Trials Maximizing Survival Benefit","year":2025,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Advancing Translational Sciences; Ralph W. and Grace M. Showalter Research Trust Fund; National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; Indiana Clinical and Translational Sciences Institute","keywords":"Clinical trial; Modular design; Clinical study design; Maximum tolerated dose; Set (abstract data type); Randomization; Optimal design","score_opus":0.7105486185993154,"score_gpt":0.606923267544355,"score_spread":0.1036253510549604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416257149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015316112,0.00012439316,0.9907375,0.0016448032,0.0020685655,0.003339022,0.0011363853,0.00024779967,0.00054835435],"genre_scores_gemma":[0.0018307318,0.0002723443,0.9950361,0.0008576047,0.00024350904,0.00050244416,0.00008856695,0.000085839594,0.001082815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9920381,0.003348417,0.0025339732,0.00071837846,0.00064931606,0.00071185996],"domain_scores_gemma":[0.83318067,0.16494568,0.0005349164,0.00040254733,0.00064945035,0.00028674625],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.014297856,0.00046415252,0.0017138852,0.00019175066,0.00032165417,0.00020834846,0.00044087516,0.00025690816,0.0008153568],"category_scores_gemma":[0.17915553,0.00042005823,0.0002822408,0.00047684138,0.00021832781,0.00011036002,0.00014683187,0.00040177998,0.000016116837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019963542,0.00050588895,0.000052062303,0.00051504135,0.00038464836,0.000009352721,0.00005265288,0.0041004303,0.00014372908,0.9350118,0.016947659,0.040280387],"study_design_scores_gemma":[0.006591571,0.00008043539,0.000023242248,0.00007590482,0.00094271306,9.2798626e-7,0.000010484402,0.34201205,0.0014786478,0.64663,0.0018638221,0.00029020393],"about_ca_topic_score_codex":0.00001445199,"about_ca_topic_score_gemma":0.0000038295393,"teacher_disagreement_score":0.3379116,"about_ca_system_score_codex":0.00024265384,"about_ca_system_score_gemma":0.00015711243,"threshold_uncertainty_score":0.9998251},"labels":[],"label_agreement":null}]}