{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":55,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":55,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"65f19e95c375","filters":{"venue":"Pharmaceutical Statistics"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5850172035475715,"gpt":0.5093227869028153,"spread":0.07569441664475618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006720899,0.0002721575,0.000583042,0.0001505903,0.0001075048,0.00006419125,0.0001836351,0.0001083669,0.0001427266],"category_scores_gemma":[0.005333425,0.0002261091,0.00002354665,0.0001715965,0.0003457131,0.0002603874,0.0001534025,0.0007175928,0.000001075164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009149244,"about_ca_system_score_gemma":0.00009509872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006342919,"about_ca_topic_score_gemma":0.001813236,"domain_scores_codex":[0.9979894,0.0001014118,0.0007628911,0.0003947499,0.0002937372,0.0004578818],"domain_scores_gemma":[0.9959605,0.003444055,0.0001689809,0.0001376953,0.0001649313,0.0001237755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001183315,0.0005895928,0.4410522,0.001163657,0.00004771452,0.00006528252,0.005470528,0.00007393833,0.001791756,0.540161,0.0004508555,0.009015203],"study_design_scores_gemma":[0.0006265716,0.00007762445,0.05886068,0.0003398299,0.00003392851,0.000008525208,0.000424386,0.0989402,0.000253933,0.8400614,0.00003384267,0.0003391106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7048489,0.00003927316,0.2931017,0.0004205741,0.0001053669,0.0009971044,0.0003752409,0.00007291753,0.00003893017],"genre_scores_gemma":[0.4761547,0.00002361761,0.5233449,0.00006316978,0.00003287132,0.0003163916,0.00002635588,0.00001677382,0.00002113672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3821915,"threshold_uncertainty_score":0.9220461,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.996400707501376,"gpt":0.8337696602368216,"spread":0.1626310472645544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5529103,0.0009388931,0.02119238,0.0002398086,0.0003874848,0.00124995,0.004588531,0.0001539664,0.003689583],"category_scores_gemma":[0.5636719,0.0002841019,0.004065914,0.00449125,0.0008625996,0.0001879772,0.00102435,0.002300273,0.0004406181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002564943,"about_ca_system_score_gemma":0.0009374197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004093528,"about_ca_topic_score_gemma":0.00003147609,"domain_scores_codex":[0.6569226,0.2501513,0.06218917,0.002758909,0.02686369,0.001114399],"domain_scores_gemma":[0.5374619,0.4189918,0.02525914,0.007834525,0.009922951,0.0005296677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003059473,0.0001338943,0.00004362269,0.04116113,0.00449906,0.00002794572,0.00008406862,0.000004173489,3.491135e-7,0.08413507,0.125315,0.7445926],"study_design_scores_gemma":[0.00007195571,0.00002663454,0.00004647048,0.008181733,0.007882097,0.000003362045,0.0005439174,0.000918482,3.69766e-7,0.008913156,0.9731182,0.0002935599],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001349057,0.9796069,0.00619727,0.007194105,0.0003924206,0.004253914,0.001198827,0.000005420069,0.00114978],"genre_scores_gemma":[0.00002625975,0.9884336,0.007619636,0.00275683,0.0001735587,0.0006353392,0.00004905193,0.00003381306,0.0002719298],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8478032,"threshold_uncertainty_score":0.9999611,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9499294280480977,"gpt":0.6769455700599387,"spread":0.2729838579881589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007773739,0.0004404078,0.0008799425,0.00007936053,0.0002833068,0.00009160008,0.0003865692,0.0001839101,0.0001679321],"category_scores_gemma":[0.06072364,0.0003310314,0.000113928,0.0002938384,0.001238706,0.0000778929,0.0001335064,0.0004333362,0.00002683979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000168583,"about_ca_system_score_gemma":0.0001201792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001727023,"about_ca_topic_score_gemma":0.000004849627,"domain_scores_codex":[0.9957122,0.0005995682,0.00119074,0.0007026183,0.0007320321,0.001062832],"domain_scores_gemma":[0.8775157,0.1209517,0.0002961455,0.000367069,0.0004354459,0.0004339083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004778831,0.0006209284,0.0001382913,0.001039028,0.0007884573,0.0001395825,0.0003240432,0.00009763594,0.0006094719,0.902356,0.008539382,0.08056831],"study_design_scores_gemma":[0.003362035,0.0007173656,0.00005089609,0.0000796646,0.0009265163,0.00002295237,0.0001257416,0.008321926,0.0192227,0.9645975,0.002000994,0.0005717041],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005018375,0.0002385377,0.9954823,0.0001911178,0.0006009637,0.001803115,0.0007165315,0.0001729519,0.0002926923],"genre_scores_gemma":[0.02612049,0.00009018419,0.9723901,0.0003840389,0.0005180414,0.0001531814,0.000006064628,0.00009516204,0.0002427419],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1203521,"threshold_uncertainty_score":0.9999142,"prediction_status":"machine_predicted_unvalidated"},"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":"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8455461255403379,"gpt":0.7076831575087411,"spread":0.1378629680315968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01653172,0.0004893036,0.001970381,0.0001801216,0.00008295218,0.0001788937,0.0004660169,0.0004326135,0.002609106],"category_scores_gemma":[0.3703019,0.0004075653,0.0001645569,0.0005794367,0.002427883,0.000194562,0.0003571604,0.001322138,0.00004917832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003927972,"about_ca_system_score_gemma":0.0002734379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006921551,"about_ca_topic_score_gemma":0.00004277629,"domain_scores_codex":[0.9898248,0.00384467,0.003238529,0.001000574,0.001042993,0.001048445],"domain_scores_gemma":[0.8341656,0.1644225,0.0003205223,0.0004117452,0.0001234493,0.0005562234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0011848,0.0005418724,0.04391392,0.0003907324,0.00004911109,0.0004052828,0.0003225573,0.00003067122,0.0002566106,0.9439052,0.0007428338,0.00825638],"study_design_scores_gemma":[0.006882178,0.0002203107,0.02256575,0.0004481715,0.0001873217,0.00001201265,0.00002710451,0.003303359,0.0007603347,0.9647604,0.0003326411,0.000500416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4267278,0.0009468248,0.5627643,0.003018793,0.001421724,0.002486307,0.001710244,0.0001677177,0.0007563233],"genre_scores_gemma":[0.6306677,0.0007929573,0.366963,0.001062404,0.0003616544,0.00007459628,0.000002844305,0.00005526907,0.00001955992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3537702,"threshold_uncertainty_score":0.9998376,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8859019112477156,"gpt":0.5762477195149607,"spread":0.3096541917327549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003572407,0.0003287175,0.0004718461,0.0001207598,0.0003945016,0.0001903087,0.0006521198,0.00009237118,0.002965274],"category_scores_gemma":[0.01371136,0.0002311937,0.0001159436,0.0003384704,0.001055186,0.0002676624,0.0001299261,0.0001544623,0.00008714548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059012,"about_ca_system_score_gemma":0.0001771452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000218801,"about_ca_topic_score_gemma":0.000001783932,"domain_scores_codex":[0.9960055,0.0004802803,0.0008702521,0.0009015109,0.001092489,0.0006500178],"domain_scores_gemma":[0.9745771,0.02361286,0.0003139712,0.0003507526,0.0008409287,0.0003043883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.02612999,0.0007628513,0.0000266126,0.0001057121,0.0004658889,0.00004089857,0.001869147,0.0007008105,0.001747026,0.1159482,0.7650716,0.08713125],"study_design_scores_gemma":[0.01020024,0.004330629,0.0002301054,0.00009376231,0.0004897055,0.0000561542,0.001300187,0.2287255,0.11606,0.4899949,0.147058,0.001460892],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004112441,0.0002288968,0.947814,0.00008327632,0.0003020517,0.001498242,0.04912106,0.00005460373,0.0008567678],"genre_scores_gemma":[0.01161774,0.00001882546,0.9854012,0.0003040605,0.0001802599,0.001099433,0.0003465071,0.0000403833,0.0009915975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6180137,"threshold_uncertainty_score":0.9979461,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6731853966455711,"gpt":0.6174407262752281,"spread":0.05574467037034303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002377775,0.0002053739,0.000439348,0.00007267571,0.0004041483,0.00005589055,0.0001862883,0.00006187963,0.007100018],"category_scores_gemma":[0.01472986,0.0002041113,0.00004577581,0.0001912638,0.0003269003,0.00004239453,0.0002060868,0.0006723935,0.0000204555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001627459,"about_ca_system_score_gemma":0.0001331246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004413636,"about_ca_topic_score_gemma":0.000002018378,"domain_scores_codex":[0.9963514,0.001181323,0.0007319804,0.0004169096,0.0009426817,0.0003757357],"domain_scores_gemma":[0.9646532,0.03448611,0.0001905149,0.0001892673,0.0001648313,0.0003161095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004635285,0.0001951652,0.0002307217,0.0001200868,0.00005617508,0.00005639077,0.00005571207,0.00007420139,0.00009741197,0.958324,0.01339494,0.02693174],"study_design_scores_gemma":[0.002016998,0.0003287974,0.0003030619,0.000006778095,0.0001713026,0.00001418226,0.00004750125,0.02586359,0.0002853734,0.9508915,0.01982024,0.0002506862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002581211,0.00003776214,0.9832269,0.0007958927,0.0003715942,0.0004619886,0.01118767,0.000127627,0.001209377],"genre_scores_gemma":[0.2238766,0.00001341191,0.774563,0.001114018,0.0001013494,0.0001081094,0.0001196899,0.00003546109,0.00006839646],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2212954,"threshold_uncertainty_score":0.9938076,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7673059866440124,"gpt":0.6597566135267552,"spread":0.1075493731172572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01081928,0.0002036861,0.001244715,0.0001513399,0.0001369779,0.00003844549,0.0003261454,0.00009752358,0.0005001162],"category_scores_gemma":[0.0751076,0.0001227722,0.0005013766,0.001137353,0.0003827279,0.00002508287,0.0001117231,0.0003328147,0.0000285143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001162505,"about_ca_system_score_gemma":0.00005854381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001009067,"about_ca_topic_score_gemma":0.000007784642,"domain_scores_codex":[0.9959847,0.001030732,0.001824359,0.0003184614,0.0004248139,0.0004168783],"domain_scores_gemma":[0.8797943,0.118998,0.0003943516,0.00031972,0.0003278174,0.0001658636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001943584,0.0001460034,0.000571083,0.0001120269,0.00544855,0.000005894638,0.00006336491,0.00004254296,0.0001994294,0.6993443,0.02893129,0.2649411],"study_design_scores_gemma":[0.0007661236,0.00007174139,0.006799551,0.00001290837,0.01590907,6.700812e-7,0.00004745727,0.6654125,0.000602329,0.3037853,0.006402642,0.000189678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002663204,0.0004839989,0.99067,0.0007392496,0.001089941,0.0007975679,0.003366314,0.00009645125,0.00009322417],"genre_scores_gemma":[0.2561326,0.0007918415,0.741388,0.0004939911,0.0005787912,0.0001691552,0.0001639185,0.0000561262,0.0002256214],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.66537,"threshold_uncertainty_score":0.9326832,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8262700275298006,"gpt":0.64127193821718,"spread":0.1849980893126206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004662915,0.0003150142,0.0005407823,0.0001244765,0.0002348986,0.0003199013,0.0007730286,0.00009518306,0.0004835556],"category_scores_gemma":[0.01868592,0.0002466039,0.0001255622,0.0004657091,0.0009427216,0.0004023016,0.0003885938,0.0002319075,0.0004562385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002686265,"about_ca_system_score_gemma":0.0002874721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007343349,"about_ca_topic_score_gemma":0.000001395312,"domain_scores_codex":[0.9952837,0.0006494634,0.0008466383,0.0007643317,0.001755355,0.0007004713],"domain_scores_gemma":[0.9903796,0.006696524,0.0002202506,0.0003751384,0.001470114,0.0008584304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01044693,0.001078376,0.0007848894,0.00009035785,0.0007808664,0.0003267597,0.006874461,0.01382151,0.03570293,0.3807734,0.4178489,0.1314707],"study_design_scores_gemma":[0.006762294,0.002414656,0.0001385718,0.0000324527,0.0003628141,0.00006083501,0.004822372,0.4878848,0.1206402,0.2744123,0.1011669,0.001301795],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003036842,0.00141792,0.9911149,0.0002582355,0.00145793,0.0006916271,0.000976675,0.00007369261,0.0009721798],"genre_scores_gemma":[0.1532418,0.00004373063,0.8444121,0.0006857688,0.0002551273,0.00009835631,0.000009271241,0.00003422445,0.001219669],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4740633,"threshold_uncertainty_score":0.9999986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030706697","doi":"10.1002/pst.368","title":"The Rheumatoid Arthritis Drug Development Model: a case study in Bayesian clinical trial simulation","year":2009,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6679110266087562,"gpt":0.6478830317170668,"spread":0.02002799489168938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01329871,0.0004150511,0.001044861,0.00008379267,0.0004608106,0.0001873684,0.0004322139,0.0001872957,0.0001108599],"category_scores_gemma":[0.08118486,0.0003180431,0.0001389224,0.0003519382,0.0002921747,0.00009065886,0.0001495605,0.001187027,0.00003731838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001668797,"about_ca_system_score_gemma":0.0002828459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000143867,"about_ca_topic_score_gemma":0.0002250095,"domain_scores_codex":[0.9902754,0.003272009,0.003931766,0.000742495,0.0009548604,0.0008235017],"domain_scores_gemma":[0.8979982,0.1003335,0.0004183316,0.0005546691,0.0002074855,0.0004878668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01189464,0.005833738,0.000813237,0.00003198018,0.0001438348,0.004102661,0.001161354,0.001662389,9.488361e-7,0.08434432,0.001950173,0.8880607],"study_design_scores_gemma":[0.03465933,0.0004839977,0.0001665773,0.00004492221,0.00006126784,0.00005927126,0.0002516071,0.424531,0.00001031264,0.538469,0.0008897886,0.0003729073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1240817,0.00009341335,0.8708831,0.0003644762,0.000908428,0.003208913,0.00008994668,0.000144744,0.0002253072],"genre_scores_gemma":[0.5625781,0.0001652772,0.4366957,0.0002367371,0.0001692617,0.00008167545,0.000002162534,0.00003286587,0.00003822729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8876878,"threshold_uncertainty_score":0.9999272,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. John’s Health Sciences Centre","funders":"","keywords":"Randomized controlled trial; Medicine; Statistics; Medical physics; Mathematics; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.4516716274172117,"gpt":0.5365292550014282,"spread":0.0848576275842165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03731491,0.0003436398,0.003131338,0.0001231868,0.0002379649,0.0003424099,0.0002923451,0.0001102857,0.0002016645],"category_scores_gemma":[0.01894831,0.0001820728,0.0002595341,0.0002143218,0.0003992127,0.0002206989,0.0000327856,0.0003711517,0.0004098507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007783106,"about_ca_system_score_gemma":0.0004854554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006316378,"about_ca_topic_score_gemma":0.00009426605,"domain_scores_codex":[0.9912612,0.00369562,0.00376545,0.0004830643,0.0002550669,0.0005395879],"domain_scores_gemma":[0.9667867,0.03061626,0.001748945,0.0004222222,0.0001503323,0.0002755009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.9720802,0.0004006524,0.0003794364,0.00003850081,0.0004182664,0.00001109227,0.001981014,0.0002937863,2.021807e-7,0.01957448,0.004065335,0.0007570733],"study_design_scores_gemma":[0.8886463,0.001392444,0.00008636787,0.00003074689,0.0001854028,0.000002673049,0.000471155,0.09636537,0.000002127533,0.009167182,0.003437179,0.0002130246],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7630785,0.005346132,0.1196329,0.03595849,0.006298592,0.06164442,0.0005349623,0.000101242,0.007404817],"genre_scores_gemma":[0.9815328,0.0002943322,0.003290991,0.006213708,0.00133635,0.006775715,0.00004148008,0.00005459131,0.0004600315],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2184543,"threshold_uncertainty_score":0.9912869,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.863855780924001,"gpt":0.6504602847221514,"spread":0.2133954962018495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2881328,0.0003962508,0.006430179,0.0004309264,0.0003119165,0.0008453489,0.001015316,0.00007097115,0.0006221132],"category_scores_gemma":[0.5918576,0.0002178885,0.0003139086,0.001655036,0.0004003568,0.0002360102,0.0007088796,0.0003193214,0.000001799265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000497653,"about_ca_system_score_gemma":0.00007737108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000562484,"about_ca_topic_score_gemma":0.00002084429,"domain_scores_codex":[0.9584158,0.02902875,0.008138851,0.001957799,0.001906923,0.0005518547],"domain_scores_gemma":[0.2499841,0.7436123,0.003415593,0.001889291,0.0005985558,0.0005001583],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.06344173,0.0008890522,0.06647411,0.002727659,0.00204725,0.00001829045,0.00242379,0.0008956501,0.0001083317,0.02035682,0.01722578,0.8233916],"study_design_scores_gemma":[0.03140155,0.000296217,0.001739141,0.00004229405,0.001490655,0.00002642028,0.0003595544,0.7898223,0.00001059333,0.1445553,0.02990826,0.0003477625],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01843637,0.006755784,0.9647508,0.0004909609,0.000134758,0.007262008,0.002142644,0.000007937199,0.00001876639],"genre_scores_gemma":[0.1090284,0.0002694166,0.8887963,0.0003980416,0.0000313495,0.001297508,0.00006489455,0.00002065881,0.00009341646],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8230438,"threshold_uncertainty_score":0.8885235,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6618107269419979,"gpt":0.6408193264275303,"spread":0.02099140051446768,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02299781,0.0003462344,0.001637403,0.00006813225,0.0001828272,0.0001346233,0.0001341827,0.0002159653,0.002481508],"category_scores_gemma":[0.7308038,0.0002714751,0.0001184242,0.0002108392,0.0007889185,0.00006494996,0.0001292901,0.001091812,0.00002632577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005624519,"about_ca_system_score_gemma":0.0001123737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009201864,"about_ca_topic_score_gemma":0.0001153098,"domain_scores_codex":[0.9863247,0.008303151,0.00356644,0.0006618543,0.0005418964,0.0006019303],"domain_scores_gemma":[0.362777,0.6357737,0.0006596732,0.0002924069,0.0001739751,0.0003233023],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008322189,0.001384046,0.1155766,0.0001762984,0.0002285996,0.0002684898,0.0001107145,0.00002411416,0.00007553922,0.8552109,0.006867427,0.01924509],"study_design_scores_gemma":[0.00467783,0.0002058837,0.02973726,0.00006745265,0.0003469853,0.0000193608,0.00004264142,0.003072724,0.0001513326,0.9605337,0.0007938568,0.0003509184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05259555,0.00009637736,0.9373134,0.0007738231,0.0005972385,0.001512505,0.00457074,0.000159504,0.002380879],"genre_scores_gemma":[0.2516844,0.00007993384,0.7475139,0.0003804666,0.0002359063,0.0000343012,0.000003272401,0.00004311347,0.00002470843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7078059,"threshold_uncertainty_score":0.9999737,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Health Canada","keywords":"Baseline (sea); Medicine; QT interval; Replicate; Time point; Statistics; Internal medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08796446487793805,"gpt":0.4388097362429016,"spread":0.3508452713649636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000600513,0.00009570231,0.0005492996,0.0001140909,0.00006224596,0.000002169411,0.00002361625,0.00004860177,0.000217981],"category_scores_gemma":[0.001738667,0.00005820686,0.0001921429,0.0003781553,0.0001929907,0.00001502084,0.00001163265,0.0001802046,0.000002086167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003430027,"about_ca_system_score_gemma":0.0000637971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003236729,"about_ca_topic_score_gemma":0.000001029088,"domain_scores_codex":[0.9988397,0.0003783485,0.000383717,0.00012408,0.0001563132,0.0001178907],"domain_scores_gemma":[0.9970667,0.002470568,0.0001652875,0.0001036737,0.0001238951,0.00006986539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.08172446,0.003102128,0.4154205,0.0008100571,0.03917854,0.001074115,0.006735893,0.02843919,0.1903669,0.009677843,0.05557971,0.1678907],"study_design_scores_gemma":[0.00286214,0.002616867,0.3527665,0.00006729543,0.006305695,0.0001751851,0.00004042102,0.5999336,0.03402511,0.0008854585,0.0001380892,0.0001836642],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8700707,0.0002214086,0.128869,0.0001457005,0.00004306235,0.0002437243,0.0002121271,0.000009138561,0.0001851603],"genre_scores_gemma":[0.9976679,0.0003731724,0.001652175,0.0001222,0.00006102334,0.000006823435,0.00006261081,0.000006358911,0.00004771799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5714944,"threshold_uncertainty_score":0.2386739,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7492670943859359,"gpt":0.6880764956332216,"spread":0.06119059875271426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007103716,0.000428235,0.005102172,0.0002268911,0.00004201826,0.0001140015,0.00138591,0.0002473658,0.00009396841],"category_scores_gemma":[0.05815197,0.0003396095,0.00108374,0.00151432,0.0002588628,0.000150217,0.0003697826,0.0006864758,0.00003235498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004635685,"about_ca_system_score_gemma":0.0006357933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002438209,"about_ca_topic_score_gemma":0.000001276998,"domain_scores_codex":[0.9902108,0.003136919,0.004913683,0.0007481274,0.0005765975,0.000413836],"domain_scores_gemma":[0.9753796,0.02220289,0.0009630944,0.0005654152,0.0004081547,0.0004808181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003577038,0.0001562291,7.96024e-7,0.1034376,0.0001121277,0.00002548073,0.000003279105,6.377206e-8,2.852286e-8,0.3066756,0.01148992,0.5780954],"study_design_scores_gemma":[0.0003391115,0.00009238059,4.700682e-7,0.0246794,0.002216188,0.000007002977,7.603175e-7,0.03415899,5.71772e-7,0.003085865,0.9351,0.0003192241],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.315873e-10,0.5135837,0.4835107,0.0002335251,0.000227704,0.0005912197,0.001804848,0.00002376441,0.00002453651],"genre_scores_gemma":[2.995639e-7,0.9256588,0.07136103,0.002138882,0.000177838,0.00007160734,0.000552147,0.00003103326,0.000008332101],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9236101,"threshold_uncertainty_score":0.9999056,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5327868823583967,"gpt":0.6279960254321367,"spread":0.09520914307374007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00212493,0.0002452244,0.0005933605,0.0000255554,0.0001649075,0.00004283931,0.0003775141,0.0001527416,0.0005132151],"category_scores_gemma":[0.1703386,0.0001747674,0.0001647354,0.000260114,0.0003536447,0.00004308192,0.00012204,0.0003609811,0.000004111914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001127653,"about_ca_system_score_gemma":0.0001700215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002467498,"about_ca_topic_score_gemma":0.00001318846,"domain_scores_codex":[0.9967411,0.0005075143,0.001276417,0.0003667678,0.0006734951,0.0004347018],"domain_scores_gemma":[0.8578741,0.1408698,0.0004424395,0.0003809409,0.0003096705,0.0001230626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008968214,0.0005502626,0.002398493,0.0009819178,0.0000630573,0.000001538343,0.00001923898,0.0001361366,0.0007403013,0.968522,0.0200244,0.006472972],"study_design_scores_gemma":[0.00130002,0.0001015437,0.01013579,0.0000676439,0.0003686824,0.000001821217,0.000009164891,0.09176667,0.002119762,0.8922796,0.001658687,0.0001906403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002104831,0.00001505184,0.9894403,0.0008521285,0.0005780656,0.001663634,0.004128759,0.00007066782,0.001146566],"genre_scores_gemma":[0.1861445,0.000006491156,0.812988,0.0002850648,0.0002185808,0.0001528095,0.00001100402,0.00004196957,0.0001515678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1840397,"threshold_uncertainty_score":0.83665,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Boehringer Ingelheim (Canada)","funders":"","keywords":"Clinical trial; Medical physics; Computer science; Medicine; Econometrics; Mathematics; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.8294575017396123,"gpt":0.6433639861404327,"spread":0.1860935155991796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09645499,0.000230788,0.001717085,0.00007548184,0.0005632091,0.0003661037,0.0002501183,0.0001861372,0.0001342039],"category_scores_gemma":[0.1326519,0.0002202164,0.0001871962,0.0002128,0.0003120085,0.0001589308,0.0001724785,0.0006264959,0.0005071389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001565678,"about_ca_system_score_gemma":0.000279456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001938341,"about_ca_topic_score_gemma":0.00001443764,"domain_scores_codex":[0.9856188,0.004993844,0.007780553,0.000869622,0.0001505786,0.0005866406],"domain_scores_gemma":[0.955682,0.04151449,0.001436256,0.0004291403,0.0001701611,0.0007679359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003577164,0.0008085269,0.2655171,0.0003852574,0.000825997,0.00001815119,0.001081357,0.0001891756,0.000009075387,0.5874598,0.07500792,0.06833997],"study_design_scores_gemma":[0.006457338,0.0003948956,0.187417,0.0001347821,0.0002932724,0.00005291504,0.001597376,0.3490658,0.00005415608,0.09746888,0.3557665,0.001297138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01280952,0.005360463,0.9615884,0.01321637,0.001817256,0.001015504,0.0005084434,0.00006208356,0.003621939],"genre_scores_gemma":[0.3449967,0.004430264,0.6128348,0.03363767,0.002638123,0.0002512388,0.00009655146,0.0001148106,0.0009998608],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4899909,"threshold_uncertainty_score":0.9303897,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Roche (Canada)","funders":"Genentech","keywords":"Truncation (statistics); Mathematics; Computer science; Left behind; Statistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1304051742352185,"gpt":0.4019486621779917,"spread":0.2715434879427732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007742847,0.0001579517,0.000164881,0.00006772125,0.000279415,0.00009211175,0.0001111152,0.00008101584,0.00001983158],"category_scores_gemma":[0.0003922333,0.0001768454,0.00001314866,0.00009118399,0.00008447299,0.0000201118,0.0006403173,0.000287708,0.000001871317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223647,"about_ca_system_score_gemma":0.0001179913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002462963,"about_ca_topic_score_gemma":0.00006348736,"domain_scores_codex":[0.9985878,0.0001067565,0.0003920448,0.0003783572,0.0002086231,0.0003264294],"domain_scores_gemma":[0.9992052,0.000222662,0.0001010707,0.0002458135,0.00003088814,0.0001943314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001475902,0.001727411,0.04456559,0.002008089,0.001172571,0.0003555144,0.01367972,0.02918394,0.3666532,0.1587842,0.2650756,0.1153183],"study_design_scores_gemma":[0.001478279,0.0001848677,0.0009033086,0.00002211392,0.0001290758,0.0003029131,0.002143604,0.6886213,0.0005769439,0.003604397,0.3017828,0.0002503616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07569867,0.0003887991,0.9212047,0.0009846608,0.0002134867,0.000672798,0.0004013504,0.00001285976,0.0004226309],"genre_scores_gemma":[0.9166467,0.0004486469,0.07941524,0.002232198,0.0001759512,0.0000230527,0.0009026576,0.00003404423,0.0001215703],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8417895,"threshold_uncertainty_score":0.7211548,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.620705524597161,"gpt":0.6302486008024275,"spread":0.00954307620526651,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003537914,0.0002411077,0.0006116077,0.00008430226,0.00006663129,0.00006954826,0.0004020049,0.0000991919,0.0004176266],"category_scores_gemma":[0.01024467,0.0001548471,0.0001189047,0.000251251,0.0001583527,0.00009877673,0.0001191277,0.0005108578,0.000007523352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007463858,"about_ca_system_score_gemma":0.0001038054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001941526,"about_ca_topic_score_gemma":0.000002908415,"domain_scores_codex":[0.9959903,0.001098355,0.00132052,0.0003934336,0.0008612642,0.0003361429],"domain_scores_gemma":[0.9496598,0.04944662,0.0001931599,0.0003578938,0.0001460217,0.0001964693],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003607734,0.001113321,0.00396829,0.01037287,0.0004596955,0.0000215301,0.0008265578,0.004615426,0.01727126,0.4596574,0.000650346,0.5006826],"study_design_scores_gemma":[0.0003930823,0.0001960902,0.001199282,0.0006716483,0.0004257342,0.000001572131,0.00005259466,0.886557,0.01219659,0.09804442,0.00007763699,0.0001843016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09073558,0.00007821642,0.9071457,0.0002215443,0.0006160474,0.0004710272,0.0006203146,0.00005112013,0.00006044019],"genre_scores_gemma":[0.5211497,0.00002925788,0.4785616,0.0001004633,0.00008566624,0.00003495572,0.000005477207,0.00002536257,0.000007547335],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8819416,"threshold_uncertainty_score":0.9980925,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7041238095391115,"gpt":0.6470359725829649,"spread":0.05708783695614661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003973074,0.0003105127,0.0006097646,0.0001058836,0.0002553481,0.0001031646,0.0002211531,0.0001281215,0.001163431],"category_scores_gemma":[0.03129907,0.0002991394,0.00005935398,0.0002120463,0.0006694726,0.0001371692,0.0002339648,0.0006834608,0.0000465216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001840328,"about_ca_system_score_gemma":0.0001092284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002650529,"about_ca_topic_score_gemma":0.00002789263,"domain_scores_codex":[0.9963754,0.0004130678,0.001159565,0.0005039693,0.0009048405,0.0006431212],"domain_scores_gemma":[0.9389828,0.05976782,0.0002865846,0.000196144,0.0002786703,0.0004879282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002475749,0.0003530042,0.07414464,0.0001894449,0.0001414694,0.0002907981,0.00004815399,0.00006066419,0.001491235,0.9166765,0.001574981,0.004781505],"study_design_scores_gemma":[0.002053912,0.00006172802,0.04573356,0.00006911553,0.0002160735,0.0001280046,0.00002444299,0.02555066,0.002330271,0.9231454,0.0003155801,0.0003712945],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1205823,0.0000455052,0.876714,0.00007088899,0.0004295484,0.0003584235,0.001020585,0.00008369332,0.0006950882],"genre_scores_gemma":[0.4956391,0.00000807852,0.503669,0.0003452012,0.000260923,0.000006085835,0.00003067304,0.00002502731,0.00001588894],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3750569,"threshold_uncertainty_score":0.9999461,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6114267450329344,"gpt":0.5681218487714129,"spread":0.04330489626152145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05801738,0.0003094238,0.002408758,0.0003789889,0.0007473574,0.0003901269,0.0008069777,0.0002344242,0.0002677632],"category_scores_gemma":[0.03928872,0.0003921038,0.0005726679,0.0002957882,0.0002231515,0.0004326205,0.0002128051,0.000805975,0.001047412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003086666,"about_ca_system_score_gemma":0.0001250091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001538487,"about_ca_topic_score_gemma":0.001140036,"domain_scores_codex":[0.9899453,0.002128621,0.005703318,0.001068993,0.000265408,0.0008883784],"domain_scores_gemma":[0.9894356,0.005467359,0.002766785,0.001571545,0.0001187525,0.0006400085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001432407,0.0007985107,0.9678736,0.00009815887,0.001844657,0.00002233953,0.0008300522,0.0005944119,7.636262e-8,0.02533581,0.001299807,0.001159382],"study_design_scores_gemma":[0.02286999,0.0001797405,0.6507606,0.00001702402,0.0006953654,0.000001405676,0.0007194075,0.2361825,9.957664e-7,0.005520372,0.08277548,0.0002770607],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.851634,0.002025863,0.1369185,0.0008900193,0.001478549,0.001439121,0.003697821,0.00007978897,0.001836266],"genre_scores_gemma":[0.9835488,0.001085998,0.01242115,0.001798233,0.0007466744,0.00009794078,0.0001483022,0.00005479997,0.00009811905],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.317113,"threshold_uncertainty_score":0.9998531,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5404197726327826,"gpt":0.5112801002807985,"spread":0.02913967235198411,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002640902,0.0001941291,0.0006048679,0.00008690225,0.0003140394,0.0001111238,0.00006558957,0.00008395516,0.0007801967],"category_scores_gemma":[0.006780798,0.0002103939,0.00006426611,0.0002082663,0.00009025753,0.000125933,0.00004846507,0.0001439017,0.0008566207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007755033,"about_ca_system_score_gemma":0.0001382159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000135691,"about_ca_topic_score_gemma":0.0001015721,"domain_scores_codex":[0.997064,0.0004344603,0.001578716,0.0004710622,0.00008556677,0.0003661885],"domain_scores_gemma":[0.9950864,0.003863732,0.0003663227,0.0002058307,0.00007430238,0.0004033761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002644253,0.0003712028,0.06259993,0.00010768,0.0002123042,0.00001572732,0.000255506,0.00005219362,0.00003220448,0.8955689,0.03284092,0.007916984],"study_design_scores_gemma":[0.003108189,0.0004515735,0.05009127,0.00006227459,0.0001295073,0.00007190704,0.0001025095,0.06032215,0.000765498,0.0772756,0.8070099,0.0006096222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2569971,0.009057231,0.6706946,0.03704201,0.001757738,0.002020237,0.01591988,0.0002399566,0.006271232],"genre_scores_gemma":[0.8732437,0.004983284,0.09754973,0.01933631,0.0007816728,0.0005247695,0.001577191,0.00009153116,0.001911805],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8182933,"threshold_uncertainty_score":0.9999213,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4828785734049401,"gpt":0.6096617833509836,"spread":0.1267832099460435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00562678,0.0006379161,0.002662974,0.00005673921,0.0002550378,0.0001446034,0.0001564837,0.0002862361,0.0006379135],"category_scores_gemma":[0.2594135,0.0004074992,0.0002309885,0.0003248365,0.0003413034,0.00004985004,0.00007960894,0.0003750333,0.00001475453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003112077,"about_ca_system_score_gemma":0.0002499034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002180215,"about_ca_topic_score_gemma":0.0000497799,"domain_scores_codex":[0.9927377,0.003677167,0.001437812,0.0008097189,0.0005510866,0.0007865889],"domain_scores_gemma":[0.6649986,0.3335801,0.0003702053,0.0002700467,0.0003189544,0.0004621041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.02000501,0.005312126,0.01978167,0.004423532,0.01134616,0.001610047,0.0002415171,0.00001923413,0.009309866,0.139656,0.02010982,0.768185],"study_design_scores_gemma":[0.06807797,0.01660684,0.001549093,0.0008375208,0.02457095,0.0001009762,0.0000175565,0.08756047,0.1358432,0.6535324,0.009216587,0.002086433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02743126,0.0008440769,0.9466155,0.0008814103,0.0008623223,0.004798785,0.01806113,0.0002949048,0.0002106197],"genre_scores_gemma":[0.03412896,0.0005366299,0.9624125,0.0003384138,0.0004105674,0.001578439,0.0001314236,0.0001612467,0.0003017587],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7660986,"threshold_uncertainty_score":0.9998377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3092379046","doi":"10.1002/pst.2073","title":"Utilizing Bayesian predictive power in clinical trial design","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8404547068645039,"gpt":0.6558272472679741,"spread":0.1846274595965297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007148369,0.0004263998,0.001362138,0.00006987657,0.0000905986,0.00007944616,0.0005614191,0.000373247,0.002200296],"category_scores_gemma":[0.2659346,0.0003925858,0.0002198656,0.0005107569,0.0005446509,0.00009896429,0.0002668338,0.001687694,0.0001870642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013229,"about_ca_system_score_gemma":0.0002098745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002864145,"about_ca_topic_score_gemma":0.000001129822,"domain_scores_codex":[0.9896669,0.004574076,0.003074999,0.0009644861,0.0008596558,0.0008598648],"domain_scores_gemma":[0.8824727,0.1155036,0.0003823479,0.0003795533,0.000167004,0.00109482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1638341,0.003391318,0.00199515,0.0004114036,0.0004887429,0.001073197,0.0007426134,0.00006846635,0.00008118281,0.6790748,0.0532038,0.09563528],"study_design_scores_gemma":[0.05122584,0.003013958,0.0004709634,0.00006644979,0.0003311906,0.000004289274,0.00008842823,0.09578563,0.0002348478,0.8446875,0.00351141,0.0005794695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009750669,0.00004536113,0.9909415,0.00142683,0.001352785,0.002055431,0.0005335478,0.000218129,0.002451334],"genre_scores_gemma":[0.1562919,0.00008200984,0.8399673,0.002660813,0.0008012603,0.00008532997,0.000004462324,0.00008477647,0.00002213073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2587862,"threshold_uncertainty_score":0.9998526,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3163601643995426,"gpt":0.5100445254687855,"spread":0.193684361069243,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003344113,0.0002167245,0.001392219,0.0002492327,0.00005784485,0.00002247411,0.0001242058,0.0001083691,0.0001869226],"category_scores_gemma":[0.01215507,0.0001864764,0.0001044681,0.000268897,0.0005500682,0.0001360559,0.0001160415,0.0004987473,0.000008415842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007034453,"about_ca_system_score_gemma":0.0002294055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001447676,"about_ca_topic_score_gemma":0.0001498974,"domain_scores_codex":[0.9956991,0.0008248693,0.001947191,0.0003845349,0.0006128044,0.0005315054],"domain_scores_gemma":[0.99417,0.004736332,0.000117311,0.0002199496,0.0001280831,0.0006283164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001019406,0.0004622014,0.8914539,0.00008157585,0.00008381157,0.0005251844,0.0002966832,0.00001732828,0.001918955,0.0004358454,0.000198774,0.1035064],"study_design_scores_gemma":[0.01112515,0.002114514,0.9632089,0.002933912,0.00002147571,0.0003114235,0.00009007849,0.01659026,0.001383921,0.0005339403,0.001269445,0.0004169368],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9828708,0.007784199,0.00732638,0.0004692941,0.0001470973,0.001057061,0.0002810465,0.00002394037,0.00004021515],"genre_scores_gemma":[0.9244395,0.06794541,0.007309501,0.0001901642,0.00003551917,0.00003099935,0.00001099736,0.00002440247,0.00001351686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1030895,"threshold_uncertainty_score":0.996166,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Potency; Outlier; Bioassay; Statistics; Mathematics; Computer science; Chemistry; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.2950893604694196,"gpt":0.5342374065051462,"spread":0.2391480460357266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001081468,0.0002025854,0.0005288773,0.0001238738,0.0001014059,0.00007373132,0.0006452125,0.00007514343,0.0009306726],"category_scores_gemma":[0.009890947,0.0001631717,0.00008133856,0.0004517563,0.0002548961,0.0001682725,0.0001592278,0.0002503989,0.0005645279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004970619,"about_ca_system_score_gemma":0.00008089744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000531711,"about_ca_topic_score_gemma":0.000003228784,"domain_scores_codex":[0.9966193,0.00009952806,0.0009832056,0.0005295727,0.001261593,0.0005067284],"domain_scores_gemma":[0.9873189,0.01086072,0.0002789258,0.0003953085,0.000836447,0.0003096729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003942401,0.0005148463,0.0609971,0.0002637565,0.00007368188,0.0000158106,0.0001853197,0.001586245,0.004038841,0.6177305,0.03181211,0.2823876],"study_design_scores_gemma":[0.002355815,0.0003987118,0.01055466,0.00004181417,0.0001164258,0.000007886086,0.0002676157,0.2913906,0.005793937,0.496431,0.1920385,0.0006030342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003460288,0.0001671424,0.9900839,0.0002366295,0.0009142841,0.0005211452,0.001821252,0.00004067992,0.002754703],"genre_scores_gemma":[0.6873971,0.00001211607,0.3114745,0.000111168,0.00007961639,0.00001817704,0.00001509828,0.00002234562,0.000869792],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6839368,"threshold_uncertainty_score":0.9999826,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6908497330030037,"gpt":0.6098577142060511,"spread":0.08099201879695261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00477959,0.0008557026,0.002442916,0.0001035292,0.0004596034,0.0001662475,0.0008865992,0.0003524349,0.0007576511],"category_scores_gemma":[0.4436412,0.0007284728,0.0005564381,0.0004551866,0.0006340509,0.0001199811,0.0004112943,0.001072107,0.000171477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001198375,"about_ca_system_score_gemma":0.0003171499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001872825,"about_ca_topic_score_gemma":4.506743e-7,"domain_scores_codex":[0.9912089,0.00203594,0.002836871,0.001219553,0.001245479,0.001453217],"domain_scores_gemma":[0.743468,0.2536289,0.0005294688,0.0004584414,0.0004518689,0.00146326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1998041,0.007338885,0.00002592354,0.001078478,0.001683142,0.0002620668,0.0006714025,0.0002290762,0.002547823,0.643594,0.1166934,0.0260718],"study_design_scores_gemma":[0.3167506,0.004908776,0.000003079233,0.0000375405,0.001555033,0.000003551345,0.00003493621,0.1364043,0.001845374,0.5323464,0.005748519,0.0003618765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002343198,0.00006197752,0.9812223,0.001888893,0.001641425,0.008352775,0.003585791,0.0004779356,0.0004256511],"genre_scores_gemma":[0.0177057,0.00003787483,0.9752558,0.003760206,0.001571249,0.001190268,0.00005037618,0.0002170554,0.0002114328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4388616,"threshold_uncertainty_score":0.9995166,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4221457347332742,"gpt":0.4370171898770877,"spread":0.01487145514381355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005152631,0.0002420978,0.0006701364,0.000151717,0.00007665189,0.00003913121,0.00007489895,0.00007716873,0.0001949364],"category_scores_gemma":[0.002034324,0.0001886749,0.00004800007,0.0007885688,0.0001830388,0.00005851013,0.00004455625,0.0003290508,0.000002059291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002869468,"about_ca_system_score_gemma":0.00004355941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001610043,"about_ca_topic_score_gemma":0.000005216112,"domain_scores_codex":[0.9979406,0.0002795719,0.0004435459,0.0003998696,0.0006743211,0.000262117],"domain_scores_gemma":[0.9963652,0.002654711,0.0001864867,0.0001514241,0.0002634699,0.0003786453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.006481982,0.003821142,0.1897069,0.005628312,0.009366835,0.0002340423,0.00129516,0.04526397,0.002320679,0.6281647,0.007323066,0.1003932],"study_design_scores_gemma":[0.0009206456,0.0004364444,0.004347664,0.0000448156,0.002516685,9.844018e-7,0.0000374127,0.9696825,0.001008946,0.02071316,0.00006575611,0.0002249861],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02260536,0.00007450688,0.9756697,0.0003619236,0.00003361625,0.0002336049,0.0007061118,0.00003156426,0.0002836028],"genre_scores_gemma":[0.64284,0.00005538814,0.3568517,0.0001747468,0.00002771195,0.000008666851,0.00002079653,0.00001750034,0.000003469739],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9244185,"threshold_uncertainty_score":0.7693939,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7394911056247505,"gpt":0.6836660418249617,"spread":0.0558250637997888,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00996171,0.0005064131,0.002347785,0.0002437182,0.0001212056,0.00004252936,0.0004716846,0.0002584127,0.0006451946],"category_scores_gemma":[0.03112828,0.000398866,0.00008660834,0.0007855755,0.001471299,0.0001001603,0.0002423826,0.0009429301,0.00000531176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001209998,"about_ca_system_score_gemma":0.0004533974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001350364,"about_ca_topic_score_gemma":0.0003988556,"domain_scores_codex":[0.9815742,0.01130718,0.004128879,0.001155521,0.001127577,0.0007066465],"domain_scores_gemma":[0.9232951,0.07293544,0.0008981401,0.001016949,0.001015445,0.0008389584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.6675031,0.04372193,0.003086101,0.0001525235,0.0003270078,0.0003660334,0.0005930169,0.000002832663,0.00000451345,0.01445526,0.00006969189,0.269718],"study_design_scores_gemma":[0.604518,0.3114415,0.001064669,0.00007771495,0.001281945,0.0000333108,0.0009280349,0.002585992,0.00006802182,0.0773544,0.00007786984,0.0005685773],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.356373,0.000001373465,0.6333556,0.00001528622,0.0003129471,0.008425682,0.00145284,0.00003328842,0.00002996254],"genre_scores_gemma":[0.4581712,7.205667e-7,0.5408816,0.00004891062,0.0002177506,0.0006188423,0.00001377087,0.00004516936,0.000002073183],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2691494,"threshold_uncertainty_score":0.9998463,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9531832501912486,"gpt":0.7584745799826099,"spread":0.1947086702086387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1051456,0.0005949279,0.002818358,0.0003708984,0.0003013822,0.0001375709,0.0006977348,0.0003222419,0.0007320004],"category_scores_gemma":[0.8400598,0.0004281533,0.0003307745,0.001091784,0.0004464553,0.00006453421,0.0002427964,0.001745844,0.0003367996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003248276,"about_ca_system_score_gemma":0.0003733801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002670312,"about_ca_topic_score_gemma":0.00001010252,"domain_scores_codex":[0.9294053,0.06163962,0.004665924,0.001166704,0.001789627,0.001332824],"domain_scores_gemma":[0.4205358,0.5774817,0.0008332641,0.000575019,0.0002721116,0.0003020693],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.1084602,0.03054625,0.000974042,0.0005206689,0.001935159,0.00240755,0.003249234,0.05543685,0.002059599,0.2164469,0.01850704,0.5594565],"study_design_scores_gemma":[0.08352025,0.005016913,0.000154702,0.00003311015,0.0007128906,0.000001387572,0.0002049088,0.5616187,0.0001709765,0.3475836,0.0008484786,0.000134048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2242595,0.00001508748,0.7627189,0.0006380573,0.002222839,0.008394783,0.001169137,0.0002888949,0.000292755],"genre_scores_gemma":[0.4404687,0.00001581167,0.555485,0.001371695,0.001032256,0.001377036,0.00002958966,0.0001265364,0.00009341635],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7349142,"threshold_uncertainty_score":0.999817,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.9480752190546133,"gpt":0.7157514049968547,"spread":0.2323238140577586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02216669,0.0005353402,0.002443877,0.00007371628,0.0003072273,0.0001286629,0.0005190884,0.0003650037,0.00196165],"category_scores_gemma":[0.319788,0.0004796264,0.0005242293,0.0004232185,0.000337453,0.0001008826,0.0001552027,0.0008156238,0.000185635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009776677,"about_ca_system_score_gemma":0.0001783876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001493836,"about_ca_topic_score_gemma":5.685975e-7,"domain_scores_codex":[0.9876317,0.004905534,0.004552674,0.001089256,0.0008534717,0.0009673483],"domain_scores_gemma":[0.8068024,0.1898465,0.00058544,0.0003967541,0.0004611614,0.001907825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.03096101,0.009319725,0.000004128763,0.0008970521,0.0007612547,0.00009895299,0.001015142,0.0001553969,0.005775302,0.3656887,0.2058811,0.3794422],"study_design_scores_gemma":[0.03184917,0.01217728,0.000001764219,0.00007601994,0.001999335,0.000004351514,0.00005476513,0.08089796,0.01939208,0.7969835,0.05574078,0.0008229328],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006861018,0.00003976919,0.9785313,0.008933083,0.001326423,0.005234835,0.004671003,0.0003164529,0.0002610309],"genre_scores_gemma":[0.01848029,0.00005091447,0.9701976,0.008428275,0.002238593,0.0003548023,0.0000462862,0.000138577,0.00006465007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4312949,"threshold_uncertainty_score":0.9997655,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Statistics; Regression; Regression analysis; Linear regression; Bayesian probability; Variance (accounting); Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5672172281859323,"gpt":0.5016580102366126,"spread":0.06555921794931974,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01103993,0.0006048362,0.001720186,0.0004033201,0.0003649513,0.0003511207,0.001492037,0.000320783,0.0008844922],"category_scores_gemma":[0.0272375,0.0007728397,0.00007754461,0.0005233143,0.0005778597,0.0008460656,0.0008145072,0.0007483317,0.005367334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006157868,"about_ca_system_score_gemma":0.0003901797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002487799,"about_ca_topic_score_gemma":0.001654865,"domain_scores_codex":[0.9900258,0.0008190713,0.005100667,0.001968919,0.000441803,0.001643763],"domain_scores_gemma":[0.9823632,0.01303158,0.001069181,0.001821595,0.0002152827,0.001499136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005525909,0.000849743,0.1110053,0.000659813,0.0003012542,0.0000888261,0.004756473,0.0009083782,0.00001781519,0.4698921,0.4042447,0.00722032],"study_design_scores_gemma":[0.001134139,0.0001282148,0.06477757,0.00007984402,0.00004558088,0.000005574806,0.0002604113,0.6639238,0.00003445329,0.1674893,0.1019139,0.0002072137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07481653,0.0007392331,0.8532458,0.002030628,0.001133577,0.00130706,0.06211789,0.0001561409,0.004453168],"genre_scores_gemma":[0.7171763,0.0001616454,0.2673259,0.01060006,0.00106763,0.0001542549,0.00298389,0.0001534075,0.0003769001],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6630154,"threshold_uncertainty_score":0.9994723,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7099022599683399,"gpt":0.6160788559671313,"spread":0.09382340400120859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.03768592,0.001221391,0.004061324,0.000751467,0.000832633,0.0002732665,0.001634592,0.0003617206,0.02837721],"category_scores_gemma":[0.05984899,0.001267728,0.0005334694,0.001675173,0.0004964345,0.0002456032,0.001033242,0.002154903,0.001668989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002514348,"about_ca_system_score_gemma":0.0005066221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002495303,"about_ca_topic_score_gemma":0.00001407126,"domain_scores_codex":[0.9715206,0.0160848,0.005470898,0.002436978,0.001959093,0.002527655],"domain_scores_gemma":[0.8396204,0.1558236,0.001180996,0.001116942,0.0004082999,0.001849761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.05659872,0.01837696,0.00002758436,0.0004679793,0.0008105575,0.001696773,0.001739242,0.009113785,0.08250885,0.4223673,0.08931594,0.3169763],"study_design_scores_gemma":[0.04565733,0.01334544,0.00003814922,0.0001572315,0.0009392126,0.00004133399,0.0004373696,0.232789,0.02155168,0.4767767,0.2051003,0.003166273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0108895,0.0001231648,0.9530342,0.0006359888,0.001391852,0.01025372,0.02258696,0.0003299665,0.000754697],"genre_scores_gemma":[0.01978178,0.00006819906,0.9722874,0.001608449,0.001182128,0.002751334,0.0002705881,0.0003826056,0.001667507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3138101,"threshold_uncertainty_score":0.9991083,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7951823931859413,"gpt":0.6931044078284545,"spread":0.1020779853574868,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1313839,0.0003142049,0.00253388,0.0001662906,0.00007550101,0.00009401798,0.0006438875,0.0002342787,0.002313004],"category_scores_gemma":[0.9009176,0.0001893955,0.0002279266,0.0005426999,0.001025982,0.00008533974,0.0002339855,0.001439482,0.00002843375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006612264,"about_ca_system_score_gemma":0.0002725744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002066071,"about_ca_topic_score_gemma":0.00002762921,"domain_scores_codex":[0.9601973,0.03132057,0.004623937,0.0006313407,0.002547906,0.0006789388],"domain_scores_gemma":[0.3788939,0.6189498,0.0009234143,0.0006959104,0.0003614369,0.0001755697],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01216632,0.001302646,0.0006157302,0.0002191956,0.0001226435,0.00003775379,0.0002141895,0.00007227167,0.001453719,0.8917318,0.001975792,0.09008792],"study_design_scores_gemma":[0.05567032,0.00004856218,0.0005783744,0.0001696272,0.0003112423,0.000001782924,0.00001637683,0.1108564,0.001538857,0.8305727,0.00005418604,0.0001816348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1777921,0.0002601287,0.7785403,0.005350485,0.00697784,0.01784914,0.001722448,0.0001791767,0.01132833],"genre_scores_gemma":[0.2991373,0.0000406067,0.6999807,0.0001456291,0.000226568,0.0003756092,0.000007167492,0.00004655996,0.00003983224],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7695337,"threshold_uncertainty_score":0.998599,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8261641552162479,"gpt":0.618695554779733,"spread":0.2074686004365148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006444635,0.0004896733,0.001505495,0.0001115318,0.0003500099,0.0002572754,0.0002846155,0.0002032595,0.0002039261],"category_scores_gemma":[0.05134819,0.0003937728,0.0001644437,0.0004863907,0.0001719712,0.0001173634,0.00007842117,0.0003009833,0.00002477064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002654804,"about_ca_system_score_gemma":0.0002857134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002547863,"about_ca_topic_score_gemma":0.000009263332,"domain_scores_codex":[0.9927463,0.002174608,0.00220975,0.001165172,0.0009030569,0.0008011424],"domain_scores_gemma":[0.9176236,0.07918989,0.000758583,0.0006983806,0.001007634,0.0007218735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1645316,0.004528998,0.00001830992,0.0008951019,0.0008307406,0.00004119465,0.0006509121,0.0007000673,0.009681208,0.4478247,0.004725292,0.3655719],"study_design_scores_gemma":[0.08488569,0.01066827,0.00007005586,0.000287736,0.003017275,0.00002057722,0.000314902,0.0193224,0.08636992,0.7580529,0.03549572,0.001494487],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00377152,0.00005341326,0.9795985,0.0006277207,0.000576871,0.01221669,0.002969774,0.0001469539,0.00003855111],"genre_scores_gemma":[0.02064484,0.00008003296,0.9718991,0.0004909877,0.0007967579,0.005657903,0.0002123559,0.0001506194,0.00006739939],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3640774,"threshold_uncertainty_score":0.9998514,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.09480981289805816,"gpt":0.4347240200643359,"spread":0.3399142071662777,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008164458,0.0001804208,0.0002059782,0.0000295236,0.0002743573,0.0002913732,0.000520568,0.00004076645,0.00007800209],"category_scores_gemma":[0.003258451,0.000146034,0.00007259647,0.0003093087,0.00007635954,0.0001163327,0.0005782428,0.0004747273,0.0001426393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007764423,"about_ca_system_score_gemma":0.000355758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005379674,"about_ca_topic_score_gemma":0.00006316425,"domain_scores_codex":[0.9974148,0.0006274701,0.0003098468,0.0005694524,0.0004839371,0.0005945477],"domain_scores_gemma":[0.9953823,0.002736028,0.00005894737,0.0005891175,0.000428332,0.0008052622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003705503,0.0005482141,0.06330568,0.0008147028,0.0001168531,0.002208958,0.00364912,0.001957748,0.0004418124,0.6265705,0.04200983,0.2580061],"study_design_scores_gemma":[0.0004362653,0.0001346241,0.06180479,0.00003739405,0.00003972007,0.00002323065,0.00002581563,0.7636022,0.0005658274,0.008327715,0.1646816,0.0003208709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005422954,0.0001196689,0.9553177,0.03719966,0.0006734719,0.0004381419,0.0006411132,0.0001218491,0.00006544579],"genre_scores_gemma":[0.8114731,0.00001219216,0.1720966,0.01565668,0.0002676231,0.0000683527,0.00002584407,0.0000225994,0.0003770009],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8060501,"threshold_uncertainty_score":0.5955095,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8703654930178174,"gpt":0.7163172398238357,"spread":0.1540482531939817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01183941,0.0002182021,0.001587962,0.00005814801,0.00004687268,0.00003987027,0.0002946145,0.0001345288,0.0001282308],"category_scores_gemma":[0.2869825,0.0001481312,0.0002297535,0.0003531744,0.0003485173,0.0000436882,0.00005744108,0.0001776464,0.000001296908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005586753,"about_ca_system_score_gemma":0.0002565307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003509854,"about_ca_topic_score_gemma":0.00003085542,"domain_scores_codex":[0.9875901,0.008542736,0.002797165,0.0003565204,0.0003898857,0.0003235751],"domain_scores_gemma":[0.6510043,0.3476676,0.0006078456,0.0003259863,0.0003216188,0.00007262942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001148048,0.002825758,0.0009004755,0.001387123,0.0004920107,0.000008999194,0.001452315,0.0000880845,0.01560786,0.7596883,0.001680288,0.2147207],"study_design_scores_gemma":[0.003529466,0.0004367386,0.0002590501,0.00009306623,0.0007382586,0.000003100659,0.001626502,0.08186059,0.08109551,0.8284833,0.001708227,0.0001661318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002206247,0.0004518136,0.9935834,0.0003535691,0.0003122615,0.001413954,0.001403629,0.00001507436,0.0002599929],"genre_scores_gemma":[0.1761048,0.0001796267,0.8233975,0.00003709034,0.00006447841,0.0001673453,0.00001883641,0.00001843316,0.00001186888],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3391248,"threshold_uncertainty_score":0.7190235,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5750052390768035,"gpt":0.5987650466759101,"spread":0.02375980759910667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001448051,0.0003057349,0.0006582622,0.000095833,0.0001588217,0.00006254589,0.0001201172,0.00007534843,0.00004577811],"category_scores_gemma":[0.007882001,0.0002556607,0.00004757116,0.0003162821,0.0002733345,0.00005373446,0.0001471048,0.0002060081,0.00001359883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000128025,"about_ca_system_score_gemma":0.0001045181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001539938,"about_ca_topic_score_gemma":0.00005344619,"domain_scores_codex":[0.9974052,0.0001719679,0.0007335701,0.0006947013,0.0004043367,0.0005901936],"domain_scores_gemma":[0.9892689,0.009518442,0.0001689337,0.0002689647,0.0001865818,0.0005881876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01259554,0.0005411404,0.001633672,0.003107641,0.0005450329,0.0001545396,0.0006215404,0.001981415,0.002902566,0.4020708,0.01807943,0.5557667],"study_design_scores_gemma":[0.004296116,0.000267085,0.001003829,0.0001339139,0.0003003794,0.00002120658,0.0000176595,0.6380239,0.0001526121,0.3529813,0.002490993,0.000311042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02869845,0.00003826592,0.9661779,0.001060959,0.0001143082,0.002046582,0.001684171,0.0001244696,0.00005490657],"genre_scores_gemma":[0.06579154,0.000100654,0.9321871,0.0004231549,0.00009613832,0.001085725,0.00002108726,0.00006475433,0.0002298127],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6360424,"threshold_uncertainty_score":0.9999896,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4606261912846036,"gpt":0.6514265736967599,"spread":0.1908003824121564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002450337,0.0002533007,0.001178889,0.00008753611,0.0002828644,0.00000818955,0.0003641882,0.00007137471,0.001912986],"category_scores_gemma":[0.01266785,0.000228513,0.00009882104,0.0001992455,0.0006115005,0.00002501198,0.0004811475,0.0005371305,0.000008460016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002434308,"about_ca_system_score_gemma":0.0001515452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001469303,"about_ca_topic_score_gemma":0.00000117522,"domain_scores_codex":[0.9964015,0.001179726,0.001132915,0.0003866581,0.0003483078,0.0005508811],"domain_scores_gemma":[0.9688438,0.03005765,0.0003483579,0.0002439657,0.0002500547,0.0002562256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005723192,0.001284865,0.0002352918,0.0008585325,0.0003070473,0.00001469822,0.0009479269,0.000004393486,0.002383906,0.9406106,0.02971805,0.02306235],"study_design_scores_gemma":[0.001446595,0.002175858,0.00004550087,0.000009791938,0.0005805675,0.00003808137,0.001179207,0.05208888,0.00566939,0.8803281,0.05613451,0.0003035403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003321745,0.0006273504,0.9910457,0.0005639301,0.000376187,0.0009199024,0.002191166,0.00008705394,0.0008669862],"genre_scores_gemma":[0.179829,0.00001561711,0.8192698,0.0002586116,0.00005329371,0.0004044701,0.00005260915,0.00003872409,0.00007788544],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1765072,"threshold_uncertainty_score":0.9989994,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Bayesian probability; Bayesian statistics; Bayesian inference; Medicine; Computer science; Statistics; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5640579803130207,"gpt":0.595575910905105,"spread":0.0315179305920843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02783604,0.001079208,0.002489805,0.0001190555,0.0006691111,0.000456022,0.001863437,0.0004224374,0.00008897272],"category_scores_gemma":[0.5384909,0.0007857337,0.0003447849,0.00130989,0.00286965,0.0001607459,0.00140677,0.005133635,0.00006123057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001779149,"about_ca_system_score_gemma":0.0004103252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009363052,"about_ca_topic_score_gemma":0.0003621197,"domain_scores_codex":[0.9655889,0.02098123,0.007506123,0.002079259,0.001779578,0.00206486],"domain_scores_gemma":[0.499887,0.4962047,0.001259349,0.0008607248,0.0004295913,0.001358609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007859891,0.001395589,0.01073227,0.0003423346,0.0006940117,0.0001031482,0.001524351,0.00002279514,0.0001626815,0.04639479,0.05615389,0.8816882],"study_design_scores_gemma":[0.008845013,0.0007033272,0.03031415,0.0004141786,0.001302228,0.000008551772,0.0003212487,0.1471224,0.0006653884,0.6829378,0.1269032,0.000462599],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001759788,0.001387145,0.9641647,0.003566353,0.002420326,0.002112919,0.02401392,0.0001647656,0.0004101127],"genre_scores_gemma":[0.03589484,0.006815526,0.9530812,0.002235282,0.001093683,0.0001580726,0.0004399735,0.0002261177,0.00005528771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8812255,"threshold_uncertainty_score":0.999844,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7492029465102941,"gpt":0.639858577016374,"spread":0.10934436949392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003488123,0.0009011525,0.004367819,0.0003631795,0.0002661463,0.0001559786,0.0003052455,0.0001976348,0.001927277],"category_scores_gemma":[0.01013407,0.0006864075,0.0002296556,0.0004785649,0.0001351123,0.00009048303,0.0001816782,0.0007905546,0.00002349327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001530414,"about_ca_system_score_gemma":0.001076725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004618972,"about_ca_topic_score_gemma":0.0001425024,"domain_scores_codex":[0.991904,0.003172881,0.002547407,0.0009042112,0.000599601,0.0008719164],"domain_scores_gemma":[0.9032574,0.0949738,0.0007518834,0.0004235008,0.0001447328,0.0004486629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007351906,0.0002926267,5.029554e-7,0.005501734,0.0002204485,0.0001049252,0.000182161,0.00001260176,0.00000122766,0.341226,0.001321068,0.6510631],"study_design_scores_gemma":[0.000895896,0.0009229928,1.74953e-7,0.001655837,0.002179049,0.0000913726,0.00002642321,0.001130502,0.00001040746,0.321044,0.6714199,0.0006234589],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.502516e-7,0.100548,0.8790714,0.00005510055,0.00006271984,0.008033418,0.0118448,0.0001953313,0.00018911],"genre_scores_gemma":[0.000001586405,0.2798809,0.7123267,0.0001176513,0.00007238447,0.007000573,0.0004252872,0.0001328301,0.00004201877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6700988,"threshold_uncertainty_score":0.9995587,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1905891062","doi":"10.1002/pst.1704","title":"Bayesian inference in two‐arm trials using relative belief ratios","year":2015,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8804641098560438,"gpt":0.7012657224618299,"spread":0.1791983873942139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01522162,0.0004441531,0.001721742,0.0001706306,0.00009914763,0.0001092712,0.0004074766,0.0002024827,0.001107753],"category_scores_gemma":[0.5218032,0.0003907759,0.0001382406,0.0005987338,0.0004426521,0.0002127854,0.0002385049,0.001066923,0.0001167596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003855858,"about_ca_system_score_gemma":0.0004206675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006889609,"about_ca_topic_score_gemma":0.00003887005,"domain_scores_codex":[0.9891078,0.005556908,0.002878029,0.0006577001,0.0009963049,0.0008031867],"domain_scores_gemma":[0.8246928,0.1729869,0.000607617,0.0004447649,0.0004246224,0.0008433689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005661097,0.0008102831,0.002485814,0.0001283293,0.0001403178,0.0001866777,0.0004760562,0.0003587576,0.0001894892,0.9649017,0.001461234,0.02829522],"study_design_scores_gemma":[0.004613851,0.0001555268,0.00006511564,0.00009937152,0.0003263364,0.000006442235,0.00005890613,0.1309126,0.0007252907,0.8616699,0.000953556,0.0004131444],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001483373,0.00008675235,0.9921043,0.0003331059,0.001050014,0.001178388,0.000749253,0.0001154227,0.002899412],"genre_scores_gemma":[0.1529929,0.00003603877,0.8458791,0.0004317488,0.0004291444,0.00005126508,0.000009725577,0.00006425881,0.0001057916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5065815,"threshold_uncertainty_score":0.9998544,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6329948285871682,"gpt":0.5963440292239538,"spread":0.03665079936321436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003052177,0.000531802,0.0009502904,0.0001241783,0.0001519359,0.0002914556,0.0004526748,0.0002261248,0.0008814686],"category_scores_gemma":[0.0696193,0.0003752663,0.0001473409,0.0005214558,0.0005046041,0.0001186492,0.0001543049,0.001015728,0.0007172267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001298704,"about_ca_system_score_gemma":0.0001988227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006223103,"about_ca_topic_score_gemma":0.00000266574,"domain_scores_codex":[0.9949557,0.001120719,0.001169242,0.0007869269,0.001027864,0.0009395751],"domain_scores_gemma":[0.8190125,0.1796585,0.0001198772,0.0004297248,0.0001914273,0.0005879534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001078143,0.000328533,0.0003167915,0.0005192682,0.0007400389,0.0008436135,0.0001574162,0.0000276042,0.00009705924,0.8646718,0.09624841,0.0359417],"study_design_scores_gemma":[0.001199935,0.000399295,0.0002247314,0.0001190289,0.001018735,0.00004785401,0.00003572815,0.03197156,0.001217836,0.9179447,0.04557063,0.0002499138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005819221,0.0003239795,0.9912299,0.0004442308,0.001194174,0.0008942167,0.001333008,0.0006941112,0.003304461],"genre_scores_gemma":[0.01174091,0.0001368116,0.9847422,0.0008366454,0.0003496598,0.0001209369,0.00001134867,0.0001672991,0.001894146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1785378,"threshold_uncertainty_score":0.9998699,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4838276404501285,"gpt":0.4782297378790365,"spread":0.005597902571091995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007869584,0.0001703131,0.000357964,0.00006721527,0.00006970308,0.00004445928,0.0001576551,0.00004543633,0.0001834842],"category_scores_gemma":[0.0009632595,0.00009905957,0.00004774709,0.0006556474,0.0001966064,0.00008251629,0.0001253896,0.0002745095,0.00000255996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005735418,"about_ca_system_score_gemma":0.00006110372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002442847,"about_ca_topic_score_gemma":0.0000404796,"domain_scores_codex":[0.9985611,0.0001281236,0.0003737982,0.0002489322,0.0004663509,0.0002216885],"domain_scores_gemma":[0.998556,0.0007638929,0.00008327199,0.0002739594,0.0002202078,0.0001026787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002968237,0.0003582284,0.4034584,0.0024672,0.00282396,0.00005425642,0.0003234084,0.0001283463,0.006094722,0.5673823,0.003764887,0.01284751],"study_design_scores_gemma":[0.002461731,0.0004303671,0.01613274,0.0008163691,0.02001655,0.00005236003,0.00004763489,0.1291406,0.08975075,0.733953,0.005820202,0.001377707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01806534,0.0001271427,0.9802366,0.0001289984,0.00009485927,0.0004307396,0.0002990825,0.0001384186,0.0004787592],"genre_scores_gemma":[0.7782694,0.00001828248,0.2211658,0.0001264915,0.00001932223,0.00002012221,0.000009976268,0.00002505016,0.000345553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7602041,"threshold_uncertainty_score":0.4039532,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7559694574546456,"gpt":0.6006447139559284,"spread":0.1553247434987172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002895735,0.0004520865,0.0008463656,0.0001975717,0.0002445519,0.0001876389,0.0002887828,0.0002292196,0.0007105401],"category_scores_gemma":[0.009231768,0.0004425217,0.0001008857,0.0005933045,0.0003486122,0.000115253,0.0001777113,0.0005336218,0.0001065708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001629612,"about_ca_system_score_gemma":0.00006988644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003847049,"about_ca_topic_score_gemma":0.000003262448,"domain_scores_codex":[0.9954025,0.0008772906,0.001211549,0.0007768467,0.0007620723,0.000969757],"domain_scores_gemma":[0.9748948,0.02348131,0.0001301202,0.0004011416,0.0001399209,0.0009527034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007570607,0.005059217,0.003841379,0.005177057,0.001381293,0.004045781,0.004151059,0.0009931362,0.08284415,0.2672783,0.01383781,0.6038202],"study_design_scores_gemma":[0.004815439,0.0009201237,0.003235457,0.000452926,0.00140921,0.0001111767,0.00006446616,0.1243755,0.02348384,0.8394352,0.0002394124,0.001457244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0175647,0.00002751063,0.9788319,0.0002973548,0.0006643889,0.001268907,0.0007541717,0.0003481895,0.0002428985],"genre_scores_gemma":[0.1809357,0.00007909397,0.8178675,0.000506862,0.0003555335,0.00005089151,0.00002126895,0.0001195222,0.00006354108],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6023629,"threshold_uncertainty_score":0.9998026,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03203732618303272,"gpt":0.3995152458703245,"spread":0.3674779196872918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007271021,0.0001276464,0.0001889499,0.00005890081,0.000144989,0.0001331736,0.0003402099,0.00005812763,0.00003417219],"category_scores_gemma":[0.0001929921,0.0001017606,0.00002879297,0.0004305765,0.0001659346,0.000136473,0.0002873729,0.0003067322,0.000005163801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003046855,"about_ca_system_score_gemma":0.000082148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002846633,"about_ca_topic_score_gemma":0.000003323551,"domain_scores_codex":[0.9987258,0.0001150982,0.0003653578,0.0002942971,0.0001678375,0.000331606],"domain_scores_gemma":[0.9988456,0.0006691689,0.00007159387,0.0002357078,0.00008195681,0.00009599526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002393051,0.00005945152,0.009803436,0.00008800824,0.00002127121,0.00002022918,0.0002924409,0.00008023412,0.0002231066,0.9321417,0.0002530978,0.0569931],"study_design_scores_gemma":[0.001606504,0.00002151482,0.01199115,0.0001166481,0.00004966691,0.00002844017,0.00001486374,0.5946018,0.004889579,0.3842366,0.002197705,0.0002456334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01313248,0.0001796446,0.9832599,0.0006163221,0.00021753,0.0001789246,0.00004049606,0.0000333309,0.0023414],"genre_scores_gemma":[0.2611647,0.00003925539,0.7384259,0.0002541282,0.00001546429,0.0000105904,0.000002587971,0.000006017354,0.00008145576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5945215,"threshold_uncertainty_score":0.4149676,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1971410267159195,"gpt":0.45609796827218,"spread":0.2589569415562605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00142777,0.000355529,0.0005924716,0.0001293781,0.000433692,0.0001969969,0.0004107681,0.0001940474,0.0001499554],"category_scores_gemma":[0.1190525,0.0002651247,0.0000869352,0.0006246299,0.0003569704,0.00006400458,0.0002073388,0.0004126691,0.000006262125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001196863,"about_ca_system_score_gemma":0.0001530353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004294477,"about_ca_topic_score_gemma":0.0001301308,"domain_scores_codex":[0.9975101,0.0002117937,0.0007233183,0.0004873865,0.0003644077,0.0007029858],"domain_scores_gemma":[0.875106,0.1236892,0.0001899755,0.0002760775,0.000529165,0.0002096293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002692341,0.0002658232,0.00754929,0.0003954784,0.0002882081,0.000005029538,0.00005624762,0.00001090913,0.00001428091,0.8498051,0.007202137,0.1341383],"study_design_scores_gemma":[0.002150529,0.0001729238,0.02246448,0.00008847413,0.000768828,0.000002097958,0.00002738698,0.311643,0.00006649651,0.6598195,0.002538038,0.0002582512],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00339382,0.000362601,0.989615,0.0009348581,0.0005627631,0.002146789,0.002668348,0.00008546685,0.0002304132],"genre_scores_gemma":[0.5998835,0.0003071126,0.3972635,0.001131796,0.0001426886,0.0009053586,0.00008139881,0.00006245215,0.0002221627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5964897,"threshold_uncertainty_score":0.9999801,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3485820478985067,"gpt":0.5624556527276947,"spread":0.213873604829188,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001818345,0.0002208922,0.0003805749,0.0002992807,0.0001177239,0.0001210094,0.0003796767,0.00007204958,0.0004176338],"category_scores_gemma":[0.002350913,0.0001682162,0.00004937275,0.0009852106,0.0002468911,0.0001975319,0.00009928531,0.0001836776,0.00002393541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228012,"about_ca_system_score_gemma":0.0002380375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001373449,"about_ca_topic_score_gemma":0.000009904795,"domain_scores_codex":[0.9971134,0.0005033089,0.0007329652,0.0005727083,0.0006763983,0.0004011833],"domain_scores_gemma":[0.9938799,0.005128669,0.0001374865,0.0002804589,0.0003826734,0.0001908455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009783573,0.003114492,0.0009588351,0.00006006447,0.000160055,0.00009209305,0.0007863194,0.1077892,0.003967307,0.35239,0.009740302,0.5111578],"study_design_scores_gemma":[0.006619748,0.0007848531,0.0003160606,0.00003752902,0.00008671457,0.000003515235,0.0003479918,0.9413635,0.005682327,0.04123591,0.003263547,0.0002583452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004937103,0.0003494297,0.9941357,0.0002729522,0.0002912201,0.00121806,0.0003067834,0.0000323118,0.002899815],"genre_scores_gemma":[0.1109876,0.00003226885,0.8874934,0.0007476104,0.00002796407,0.0002253346,0.00002130705,0.00001675459,0.000447833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8335742,"threshold_uncertainty_score":0.6859659,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8273449729662699,"gpt":0.6381815326863675,"spread":0.1891634402799024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01175389,0.0009218801,0.006034459,0.0003216196,0.0001210214,0.00007383463,0.001103049,0.0005277373,0.0009799164],"category_scores_gemma":[0.1667926,0.0005680187,0.001097806,0.001349339,0.0004008785,0.00003513862,0.0004003393,0.002301235,0.0002044603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001894763,"about_ca_system_score_gemma":0.0002589041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002044374,"about_ca_topic_score_gemma":0.0000171178,"domain_scores_codex":[0.9878164,0.00502679,0.004016462,0.0009343748,0.001233049,0.0009729073],"domain_scores_gemma":[0.7229809,0.2749053,0.0009625757,0.0007749011,0.0001232898,0.0002530232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002984027,0.0002330253,0.000001786001,0.02040976,0.003445711,0.00008473839,0.00004812747,0.00001123289,1.185982e-7,0.4842076,0.001966545,0.4895615],"study_design_scores_gemma":[0.0006519111,0.0001337922,0.000002224031,0.01219306,0.03530658,0.00001208983,0.00002582553,0.002353976,0.0000147343,0.8498337,0.0986039,0.0008681659],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001251482,0.893301,0.09223382,0.00047612,0.0009150588,0.00367808,0.007871975,0.0002003859,0.00132227],"genre_scores_gemma":[0.00000683319,0.7284784,0.2703133,0.000249664,0.000261946,0.0003229724,0.0000209683,0.0002293944,0.0001164933],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4886934,"threshold_uncertainty_score":0.9999333,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.513051299481403,"gpt":0.5578152948638562,"spread":0.04476399538245313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002295224,0.0003418627,0.0006692956,0.00008520847,0.0002453358,0.00007005839,0.001850888,0.0001264474,0.0004191578],"category_scores_gemma":[0.003924978,0.0002666071,0.00009512868,0.0006191661,0.0001348072,0.0003534307,0.000675447,0.0004179094,0.00000322287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000142379,"about_ca_system_score_gemma":0.0001007214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005067762,"about_ca_topic_score_gemma":0.0005856783,"domain_scores_codex":[0.9967419,0.0003937518,0.0009377454,0.0009909213,0.0004408203,0.0004948677],"domain_scores_gemma":[0.9880801,0.008619275,0.0002665708,0.002690393,0.000197489,0.0001461462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007383215,0.001186679,0.04588477,0.0008872828,0.005221173,0.00001849141,0.0003113698,0.0004695044,0.0005226536,0.6927812,0.1151603,0.1368183],"study_design_scores_gemma":[0.0003505172,0.00001248907,0.00433545,0.00003260692,0.002801533,2.050173e-7,0.00004345953,0.4391588,0.0007807065,0.5340106,0.01826245,0.0002110902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001609777,0.0005114742,0.9062719,0.0006918149,0.0001891001,0.001079428,0.09076774,0.0002072191,0.0001203246],"genre_scores_gemma":[0.02206435,0.0002126538,0.9460375,0.0006672596,0.00009912415,0.00008825227,0.03071651,0.00003446834,0.00007985219],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4386893,"threshold_uncertainty_score":0.9999786,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2064775652953935,"gpt":0.4342598912393333,"spread":0.2277823259439397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000424215,0.0001895225,0.000314151,0.00004988058,0.0001818514,0.00003908291,0.000185205,0.00004242148,0.00004754323],"category_scores_gemma":[0.001188668,0.0001189929,0.00002315925,0.0002366934,0.0001396583,0.00008695851,0.0002631182,0.0002788819,0.00001472806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000597638,"about_ca_system_score_gemma":0.00003882435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002965733,"about_ca_topic_score_gemma":0.0000064824,"domain_scores_codex":[0.9986292,0.0001396649,0.0003496556,0.0002336919,0.0003658358,0.0002820148],"domain_scores_gemma":[0.9979639,0.001342275,0.0002370396,0.0002430518,0.0001082115,0.0001055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004005523,0.0005963973,0.182652,0.00275152,0.0005618711,0.0001126118,0.007443841,0.0208213,0.03736865,0.5265078,0.001201789,0.2195816],"study_design_scores_gemma":[0.0003132584,0.00006799711,0.03088044,0.0003529909,0.0002224068,0.00001320931,0.00002624263,0.2698459,0.007336361,0.6906239,0.00004237546,0.0002748561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3937667,0.00000478909,0.6054475,0.0001082579,0.00002158601,0.0003952169,0.0001050959,0.0001121437,0.00003863772],"genre_scores_gemma":[0.5689193,0.00001038173,0.4308075,0.00007427399,0.00001084584,0.00001673664,0.000003729001,0.00002747666,0.0001297804],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2490246,"threshold_uncertainty_score":0.4852389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}