{"meta":{"query_hash":"33f071fc94ed","filters":{"venue":"Collection of Biostatistics Research Archive"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/33f071fc94ed","api":"https://metacan.xera.ac/api/v1/cohort?venue=Collection+of+Biostatistics+Research+Archive"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Bayesian probability; Confounding; Parametric statistics; Flexibility (engineering); Random effects model; Econometrics; Bayesian inference; Computer science; Mixed model; Mathematics; Statistics; Medicine","score_opus":0.17403837553126464,"score_gpt":0.3308276810665618,"score_spread":0.15678930553529716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1501606210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5176382,0.0002292942,0.46767002,0.00012694145,0.00012791205,0.0010507745,0.00042218255,0.000013357344,0.012721297],"genre_scores_gemma":[0.91801196,0.000088550216,0.08053479,0.000011000145,0.000044412984,0.00007560255,0.000044798322,0.00001761144,0.0011712526],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99837565,0.00014970782,0.0007055829,0.00032128056,0.00012944767,0.00031831182],"domain_scores_gemma":[0.9967203,0.0025048156,0.00028737562,0.0003167159,0.00005600993,0.000114751856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00270894,0.00011606618,0.00027099598,0.0010907145,0.0003476216,0.000028482329,0.00017327383,0.000055460783,0.000053717384],"category_scores_gemma":[0.0017017875,0.00010966597,0.0000803084,0.0013119522,0.00023125735,0.0000601559,0.000053046737,0.00015321028,0.00010756602],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004569343,0.008644633,0.42831203,0.00025180329,0.0006617367,0.000005681415,0.054276895,0.06541731,0.0019850244,0.39876777,0.012208063,0.024899716],"study_design_scores_gemma":[0.0010430613,0.0021033913,0.9150166,0.000019602854,0.000009794336,0.0000050233875,0.00089999463,0.044064414,0.0013629677,0.033454437,0.0018672533,0.00015347883],"about_ca_topic_score_codex":0.0004353973,"about_ca_topic_score_gemma":0.000034560067,"teacher_disagreement_score":0.48670456,"about_ca_system_score_codex":0.00045156345,"about_ca_system_score_gemma":0.00007629644,"threshold_uncertainty_score":0.44720483},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.28194825680009084,"score_gpt":0.5662719691961757,"score_spread":0.2843237123960849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601916447","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008759673,0.000083785344,0.98186535,0.00009112567,0.0005936541,0.0030319653,0.013537801,0.00008870563,0.00062004355],"genre_scores_gemma":[0.0031655524,0.000035530884,0.9946259,0.000009396144,0.00022086059,0.0006267285,0.00066009135,0.00014673016,0.00050918607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949657,0.0012872086,0.001027003,0.0010398625,0.0008298625,0.0008503775],"domain_scores_gemma":[0.9656875,0.030467426,0.0006504416,0.00075959705,0.0021201128,0.00031491532],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024695762,0.00048571697,0.001002232,0.0008843918,0.00093494676,0.000125211,0.00042828353,0.00029289196,0.00006785689],"category_scores_gemma":[0.031196037,0.00043193682,0.00014376147,0.0007069596,0.0008842091,0.00005678162,0.00053041236,0.0019381628,0.000001312489],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021342507,0.00041294174,0.000012028958,0.009868418,0.0008055762,0.000027360009,0.0028728324,0.07413004,0.0045660473,0.7864239,0.0089673875,0.109779194],"study_design_scores_gemma":[0.0007277433,0.00082776113,0.000018407334,0.0008056045,0.0001515632,0.000014241337,0.00021564163,0.25410053,0.00078541593,0.7417471,0.00028698606,0.00031900767],"about_ca_topic_score_codex":0.0002068869,"about_ca_topic_score_gemma":0.0002831566,"teacher_disagreement_score":0.1799705,"about_ca_system_score_codex":0.0004950608,"about_ca_system_score_gemma":0.0018076166,"threshold_uncertainty_score":0.99981326},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4378421577236633,"score_gpt":0.5507619228625688,"score_spread":0.11291976513890545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097814090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012322962,0.000013199043,0.9834594,0.00006886528,0.00007353565,0.0009964624,0.0020932592,0.000059420003,0.00091289735],"genre_scores_gemma":[0.4432726,0.000013759425,0.55602473,0.0000017612253,0.000023776285,0.000041687,0.00018856033,0.000018182825,0.000414944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979635,0.0002622196,0.00057394645,0.0003100997,0.0005575646,0.00033267646],"domain_scores_gemma":[0.9827357,0.015349765,0.0002477206,0.00068570033,0.00088170706,0.000099416524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004880608,0.00011406826,0.00024578127,0.0007949265,0.00025555003,0.000015506714,0.00036288792,0.00006671187,0.00003876959],"category_scores_gemma":[0.023393342,0.00011519617,0.00004239948,0.00084071717,0.0005090968,0.00014143813,0.00022952248,0.00024752237,0.000003631226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.020659875,0.0014810507,0.0006941205,0.0014229887,0.00031157196,0.000018981167,0.001952516,0.00047569402,0.17760153,0.5013472,0.21125603,0.08277846],"study_design_scores_gemma":[0.0007288287,0.0020170368,0.0035577295,0.00013839173,0.000039946994,0.000011436088,0.0004154645,0.06706213,0.062047634,0.8628831,0.00093617395,0.00016211023],"about_ca_topic_score_codex":0.00007302505,"about_ca_topic_score_gemma":0.00027659058,"teacher_disagreement_score":0.43094963,"about_ca_system_score_codex":0.00012355729,"about_ca_system_score_gemma":0.00034125184,"threshold_uncertainty_score":0.984833},"labels":[],"label_agreement":null},{"id":"W7014010608","doi":"","title":"OPTIMIZED ADAPTIVE ENRICHMENT DESIGNS FOR MULTI-ARM TRIALS: LEARNING WHICH SUBPOPULATIONS BENEFIT FROM DIFFERENT TREATMENTS","year":2018,"lang":"en","type":"article","venue":"Collection of Biostatistics Research Archive","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Sample size determination; Adaptive design; Type I and type II errors; Sample (material); Disjoint sets; Adaptive control; Computerized adaptive testing; Interim analysis","score_opus":0.8219072492581264,"score_gpt":0.6271974068010037,"score_spread":0.19470984245712275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7014010608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005644624,0.000027327611,0.9850083,0.000092547074,0.00052442536,0.0037142541,0.0043718945,0.000070139,0.0005465119],"genre_scores_gemma":[0.06781724,0.0001407403,0.92925215,0.000008031409,0.00036372436,0.00080512045,0.00015215135,0.00006658682,0.001394232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990072,0.0056994343,0.0018078283,0.00074673374,0.0009939797,0.0006800272],"domain_scores_gemma":[0.80710214,0.1896021,0.00069747417,0.00043189246,0.0018513502,0.0003150165],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006932391,0.00033326633,0.0013633431,0.00056411454,0.0009023541,0.00008553618,0.00034198267,0.0001948274,0.0005891737],"category_scores_gemma":[0.26612014,0.0002786685,0.00026207475,0.0007866484,0.00060825,0.0000528723,0.00020969893,0.0005657766,0.000022175876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.061054848,0.01690121,0.0049689873,0.00071950455,0.009847881,0.000030144522,0.013958499,0.00102008,0.0313544,0.6592631,0.044683423,0.15619797],"study_design_scores_gemma":[0.006831061,0.0049772644,0.0032304307,0.00016245985,0.00034286478,7.232444e-7,0.00041807897,0.13971092,0.008136091,0.8358158,0.00012002999,0.00025430924],"about_ca_topic_score_codex":0.00042665875,"about_ca_topic_score_gemma":0.00042917108,"teacher_disagreement_score":0.25918773,"about_ca_system_score_codex":0.00037541808,"about_ca_system_score_gemma":0.00027009047,"threshold_uncertainty_score":0.99996656},"labels":[],"label_agreement":null},{"id":"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.20427607690398597,"score_gpt":0.42322110657178325,"score_spread":0.21894502966779728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7053292768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0997522,0.000008530471,0.8545695,0.0012044916,0.00027985653,0.0034411917,0.008433714,0.000021073587,0.032289438],"genre_scores_gemma":[0.9271734,0.000004069097,0.07003137,0.000005935136,0.00003601805,0.0001576888,0.00008655433,0.000016481705,0.0024885],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99838865,0.00014787572,0.0003083726,0.00031642156,0.0004639712,0.00037469532],"domain_scores_gemma":[0.9971109,0.0013086103,0.00013868087,0.0003334052,0.00091297174,0.00019543568],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006005944,0.00012633546,0.00020944509,0.0005657964,0.0014968197,0.0002002231,0.00023456485,0.00003143877,0.0011840393],"category_scores_gemma":[0.0012899935,0.00012691526,0.000049654816,0.00020694912,0.00049559993,0.000049673297,0.00028745361,0.0001651129,0.0000034026916],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005365806,0.0009084518,0.12668802,0.00020622632,0.00037386589,0.0000028213644,0.0009148678,0.000020854808,0.3332396,0.058363162,0.037972067,0.4407735],"study_design_scores_gemma":[0.0062825396,0.0017626203,0.64646226,0.00017393925,0.00006670239,0.000005442222,0.0011648923,0.27838427,0.023993222,0.032704145,0.00856528,0.000434673],"about_ca_topic_score_codex":0.0018868655,"about_ca_topic_score_gemma":0.00025175343,"teacher_disagreement_score":0.8274212,"about_ca_system_score_codex":0.000031966236,"about_ca_system_score_gemma":0.00029588077,"threshold_uncertainty_score":0.99980307},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Covariate; Baseline (sea); Sample size determination; Regression; Regression analysis; Randomized controlled trial; Binary number; Sample (material); Binary data","score_opus":0.060715231945073174,"score_gpt":0.38474737835635764,"score_spread":0.32403214641128447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066205105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008609385,0.000030570987,0.9871775,0.00014048138,0.000042333217,0.0018164107,0.0016698503,0.000013136527,0.00050036144],"genre_scores_gemma":[0.8281034,0.000043554566,0.16910319,0.000006775149,0.00006031005,0.00050734915,0.0002572793,0.000037882517,0.0018802328],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968368,0.0013474029,0.00069027627,0.00035601034,0.0004059791,0.0003635741],"domain_scores_gemma":[0.98809475,0.010770795,0.0003861338,0.0002277947,0.000415363,0.00010514483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049045812,0.00017582768,0.00082116795,0.0003400651,0.0002780448,0.000028626357,0.00014574248,0.000044605287,0.000030324387],"category_scores_gemma":[0.0036198767,0.00010324924,0.00014871647,0.00032356806,0.000252684,0.00009625386,0.00009649063,0.00019687503,0.0000016761651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10922171,0.0013820406,0.008635463,0.00031200866,0.00076836697,0.0000039151414,0.0011296244,0.0048490018,0.5646411,0.067763746,0.04775064,0.19354235],"study_design_scores_gemma":[0.07757349,0.00034690433,0.00011830782,0.0006520231,0.00011333749,4.8029545e-7,0.00023057831,0.8101248,0.020428138,0.089978315,0.00015981683,0.00027380572],"about_ca_topic_score_codex":0.0003640856,"about_ca_topic_score_gemma":0.00002337392,"teacher_disagreement_score":0.819494,"about_ca_system_score_codex":0.000078975914,"about_ca_system_score_gemma":0.0005226999,"threshold_uncertainty_score":0.4333592},"labels":[],"label_agreement":null}]}