{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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":"33f071fc94ed","filters":{"venue":"Collection of Biostatistics Research Archive"}},"results":[{"id":"W2097814090","doi":"","title":"Estimation of Dose-Response Functions for Longitudinal Data","year":2007,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"","keywords":"Propensity score matching; Statistics; Estimation; Confounding; Regression; Global Positioning System; Generalization; Longitudinal study; Binary data; Mathematics; Regression analysis; Computer science; Econometrics; Medicine; Binary number","retraction":null,"screen_n_in":null,"score":{"opus":0.4378421577236633,"gpt":0.5507619228625688,"spread":0.1129197651389054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004880608,0.0001140683,0.0002457813,0.0007949265,0.00025555,0.00001550671,0.0003628879,0.00006671187,0.00003876959],"category_scores_gemma":[0.02339334,0.0001151962,0.00004239948,0.0008407172,0.0005090968,0.0001414381,0.0002295225,0.0002475224,0.000003631226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001235573,"about_ca_system_score_gemma":0.0003412518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007302505,"about_ca_topic_score_gemma":0.0002765906,"domain_scores_codex":[0.9979635,0.0002622196,0.0005739465,0.0003100997,0.0005575646,0.0003326765],"domain_scores_gemma":[0.9827357,0.01534977,0.0002477206,0.0006857003,0.0008817071,0.00009941652],"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":[0.02065988,0.001481051,0.0006941205,0.001422989,0.000311572,0.00001898117,0.001952516,0.000475694,0.1776015,0.5013472,0.211256,0.08277846],"study_design_scores_gemma":[0.0007288287,0.002017037,0.00355773,0.0001383917,0.00003994699,0.00001143609,0.0004154645,0.06706213,0.06204763,0.8628831,0.000936174,0.0001621102],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01232296,0.00001319904,0.9834594,0.00006886528,0.00007353565,0.0009964624,0.002093259,0.00005942,0.0009128973],"genre_scores_gemma":[0.4432726,0.00001375943,0.5560247,0.000001761225,0.00002377629,0.000041687,0.0001885603,0.00001818283,0.000414944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4309496,"threshold_uncertainty_score":0.984833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1601916447","doi":"","title":"Resampling methods for estimating functions with U-statistic structure","year":2004,"lang":"en","type":"preprint","venue":"Collection of Biostatistics Research Archive","topic":"Advanced Statistical Methods and Models","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":"University of Waterloo","funders":"","keywords":"Studentized range; Resampling; Mathematics; Jackknife resampling; Statistic; Inference; Statistics; Studentized residual; Applied mathematics; Computer science; Artificial intelligence; Standard error; Estimator","retraction":null,"screen_n_in":null,"score":{"opus":0.2819482568000908,"gpt":0.5662719691961757,"spread":0.2843237123960849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002469576,0.000485717,0.001002232,0.0008843918,0.0009349468,0.000125211,0.0004282835,0.000292892,0.00006785689],"category_scores_gemma":[0.03119604,0.0004319368,0.0001437615,0.0007069596,0.0008842091,0.00005678162,0.0005304124,0.001938163,0.000001312489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004950608,"about_ca_system_score_gemma":0.001807617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002068869,"about_ca_topic_score_gemma":0.0002831566,"domain_scores_codex":[0.9949657,0.001287209,0.001027003,0.001039863,0.0008298625,0.0008503775],"domain_scores_gemma":[0.9656875,0.03046743,0.0006504416,0.0007595971,0.002120113,0.0003149153],"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":[0.002134251,0.0004129417,0.00001202896,0.009868418,0.0008055762,0.00002736001,0.002872832,0.07413004,0.004566047,0.7864239,0.008967387,0.1097792],"study_design_scores_gemma":[0.0007277433,0.0008277611,0.00001840733,0.0008056045,0.0001515632,0.00001424134,0.0002156416,0.2541005,0.0007854159,0.7417471,0.0002869861,0.0003190077],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008759673,0.00008378534,0.9818653,0.00009112567,0.0005936541,0.003031965,0.0135378,0.00008870563,0.0006200435],"genre_scores_gemma":[0.003165552,0.00003553088,0.9946259,0.000009396144,0.0002208606,0.0006267285,0.0006600913,0.0001467302,0.0005091861],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1799705,"threshold_uncertainty_score":0.9998133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7066205105","doi":"","title":"IMPROVING PRECISION BY ADJUSTING FOR BASELINE VARIABLES IN RANDOMIZED TRIALS WITH BINARY OUTCOMES, WITHOUT REGRESSION MODEL ASSUMPTIONS","year":2016,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Atomic and Molecular Physics","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Covariate; Baseline (sea); Sample size determination; Regression; Regression analysis; Randomized controlled trial; Binary number; Sample (material); Binary data","retraction":null,"screen_n_in":null,"score":{"opus":0.06071523194507317,"gpt":0.3847473783563576,"spread":0.3240321464112845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004904581,0.0001758277,0.000821168,0.0003400651,0.0002780448,0.00002862636,0.0001457425,0.00004460529,0.00003032439],"category_scores_gemma":[0.003619877,0.0001032492,0.0001487165,0.0003235681,0.000252684,0.00009625386,0.00009649063,0.000196875,0.000001676165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007897591,"about_ca_system_score_gemma":0.0005226999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003640856,"about_ca_topic_score_gemma":0.00002337392,"domain_scores_codex":[0.9968368,0.001347403,0.0006902763,0.0003560103,0.0004059791,0.0003635741],"domain_scores_gemma":[0.9880947,0.01077079,0.0003861338,0.0002277947,0.000415363,0.0001051448],"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":[0.1092217,0.001382041,0.008635463,0.0003120087,0.000768367,0.000003915141,0.001129624,0.004849002,0.5646411,0.06776375,0.04775064,0.1935423],"study_design_scores_gemma":[0.07757349,0.0003469043,0.0001183078,0.0006520231,0.0001133375,4.802955e-7,0.0002305783,0.8101248,0.02042814,0.08997831,0.0001598168,0.0002738057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008609385,0.00003057099,0.9871775,0.0001404814,0.00004233322,0.001816411,0.00166985,0.00001313653,0.0005003614],"genre_scores_gemma":[0.8281034,0.00004355457,0.1691032,0.000006775149,0.00006031005,0.0005073491,0.0002572793,0.00003788252,0.001880233],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.819494,"threshold_uncertainty_score":0.4333592,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7053292768","doi":"","title":"Using Multilevel Outcomes to Construct and Select Biomarker Combinations for Single-level Prediction","year":2017,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Abbott Diagnostics; Pritzker School of Medicine; University of California, San Francisco; National Institutes of Health; Institute for Clinical Evaluative Sciences; U.S. Department of Veterans Affairs","keywords":"Outcome (game theory); Logistic regression; Biomarker; Context (archaeology); Construct (python library); Selection (genetic algorithm); Regression","retraction":null,"screen_n_in":null,"score":{"opus":0.204276076903986,"gpt":0.4232211065717832,"spread":0.2189450296677973,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006005944,0.0001263355,0.0002094451,0.0005657964,0.00149682,0.0002002231,0.0002345649,0.00003143877,0.001184039],"category_scores_gemma":[0.001289994,0.0001269153,0.00004965482,0.0002069491,0.0004955999,0.0000496733,0.0002874536,0.0001651129,0.000003402692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003196624,"about_ca_system_score_gemma":0.0002958808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886865,"about_ca_topic_score_gemma":0.0002517534,"domain_scores_codex":[0.9983886,0.0001478757,0.0003083726,0.0003164216,0.0004639712,0.0003746953],"domain_scores_gemma":[0.9971109,0.00130861,0.0001386809,0.0003334052,0.0009129717,0.0001954357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005365806,0.0009084518,0.126688,0.0002062263,0.0003738659,0.000002821364,0.0009148678,0.00002085481,0.3332396,0.05836316,0.03797207,0.4407735],"study_design_scores_gemma":[0.00628254,0.00176262,0.6464623,0.0001739392,0.00006670239,0.000005442222,0.001164892,0.2783843,0.02399322,0.03270414,0.00856528,0.000434673],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0997522,0.000008530471,0.8545695,0.001204492,0.0002798565,0.003441192,0.008433714,0.00002107359,0.03228944],"genre_scores_gemma":[0.9271734,0.000004069097,0.07003137,0.000005935136,0.00003601805,0.0001576888,0.00008655433,0.0000164817,0.0024885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8274212,"threshold_uncertainty_score":0.9998031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7014010608","doi":"","title":"OPTIMIZED ADAPTIVE ENRICHMENT DESIGNS FOR MULTI-ARM TRIALS: LEARNING WHICH SUBPOPULATIONS BENEFIT FROM DIFFERENT TREATMENTS","year":2018,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Sample size determination; Adaptive design; Type I and type II errors; Sample (material); Disjoint sets; Adaptive control; Computerized adaptive testing; Interim analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.8219072492581264,"gpt":0.6271974068010037,"spread":0.1947098424571228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006932391,0.0003332663,0.001363343,0.0005641145,0.0009023541,0.00008553618,0.0003419827,0.0001948274,0.0005891737],"category_scores_gemma":[0.2661201,0.0002786685,0.0002620748,0.0007866484,0.00060825,0.0000528723,0.0002096989,0.0005657766,0.00002217588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003754181,"about_ca_system_score_gemma":0.0002700905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004266587,"about_ca_topic_score_gemma":0.0004291711,"domain_scores_codex":[0.990072,0.005699434,0.001807828,0.0007467337,0.0009939797,0.0006800272],"domain_scores_gemma":[0.8071021,0.1896021,0.0006974742,0.0004318925,0.00185135,0.0003150165],"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":[0.06105485,0.01690121,0.004968987,0.0007195045,0.009847881,0.00003014452,0.0139585,0.00102008,0.0313544,0.6592631,0.04468342,0.156198],"study_design_scores_gemma":[0.006831061,0.004977264,0.003230431,0.0001624599,0.0003428648,7.232444e-7,0.000418079,0.1397109,0.008136091,0.8358158,0.00012003,0.0002543092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005644624,0.00002732761,0.9850083,0.00009254707,0.0005244254,0.003714254,0.004371895,0.000070139,0.0005465119],"genre_scores_gemma":[0.06781724,0.0001407403,0.9292521,0.000008031409,0.0003637244,0.0008051204,0.0001521513,0.00006658682,0.001394232],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2591877,"threshold_uncertainty_score":0.9999666,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1501606210","doi":"","title":"A Flexible Semi-Parametric Approach to Estimating a Dose-Response Relationship: the Treatment of Childhood Amblyopia.","year":2007,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Bayesian probability; Confounding; Parametric statistics; Flexibility (engineering); Random effects model; Econometrics; Bayesian inference; Computer science; Mixed model; Mathematics; Statistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1740383755312646,"gpt":0.3308276810665618,"spread":0.1567893055352972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00270894,0.0001160662,0.000270996,0.001090714,0.0003476216,0.00002848233,0.0001732738,0.00005546078,0.00005371738],"category_scores_gemma":[0.001701787,0.000109666,0.0000803084,0.001311952,0.0002312573,0.0000601559,0.00005304674,0.0001532103,0.000107566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004515635,"about_ca_system_score_gemma":0.00007629644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004353973,"about_ca_topic_score_gemma":0.00003456007,"domain_scores_codex":[0.9983757,0.0001497078,0.0007055829,0.0003212806,0.0001294477,0.0003183118],"domain_scores_gemma":[0.9967203,0.002504816,0.0002873756,0.0003167159,0.00005600993,0.0001147519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004569343,0.008644633,0.428312,0.0002518033,0.0006617367,0.000005681415,0.05427689,0.06541731,0.001985024,0.3987678,0.01220806,0.02489972],"study_design_scores_gemma":[0.001043061,0.002103391,0.9150166,0.00001960285,0.000009794336,0.000005023388,0.0008999946,0.04406441,0.001362968,0.03345444,0.001867253,0.0001534788],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5176382,0.0002292942,0.46767,0.0001269414,0.000127912,0.001050774,0.0004221826,0.00001335734,0.0127213],"genre_scores_gemma":[0.918012,0.00008855022,0.08053479,0.00001100014,0.00004441298,0.00007560255,0.00004479832,0.00001761144,0.001171253],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4867046,"threshold_uncertainty_score":0.4472048,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}