{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Erica E. M. Moodie","is_ca":true},{"name":"David A. Stephens","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1770003,0.002457424,0.004684078,0.007228294,0.001291477,0.002606797,0.004485893,0.005946002,0.006832434],"category_scores_gemma":[0.296421,0.001890102,0.005615958,0.005523125,0.004243167,0.004750917,0.004701176,0.005649597,0.001369291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003177354,"about_ca_system_score_gemma":0.002244257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00304231,"about_ca_topic_score_gemma":0.001669672,"domain_scores_codex":[0.8764197,0.1122269,0.001989825,0.005779651,0.002692927,0.0008909987],"domain_scores_gemma":[0.6251821,0.3332326,0.01615047,0.02184146,0.002916699,0.0006766966],"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":[0.001828353,0.0007466474,0.09508365,0.002491214,0.00851639,0.00118685,0.002277238,0.3061999,0.001566595,0.3559998,0.006655313,0.2174482],"study_design_scores_gemma":[0.0005670993,0.0009768986,0.01583881,0.0005167924,0.001097538,0.0005733752,0.0004102071,0.6051826,0.001081463,0.364889,0.008689371,0.0001767475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02220288,0.001455507,0.9721056,0.001313158,0.00009764258,0.0008617848,0.0007617273,0.000558992,0.0006428353],"genre_scores_gemma":[0.4169983,0.003677083,0.5604938,0.001584655,0.0002964762,0.009062377,0.002793448,0.0002942184,0.00479966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1770003,"threshold_uncertainty_score":0.9360784,"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","authors":[{"name":"Wenyu Jiang","is_ca":true},{"name":"J. G. Kalbfleisch","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0218442,0.001533666,0.001651681,0.00312418,0.0006806157,0.001709483,0.002552266,0.002183243,0.003245783],"category_scores_gemma":[0.09692165,0.0007725797,0.002013226,0.00223612,0.002189347,0.003009709,0.002090888,0.002716561,0.001074995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001116868,"about_ca_system_score_gemma":0.001272143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002296686,"about_ca_topic_score_gemma":0.002001393,"domain_scores_codex":[0.9861602,0.01109411,0.000348813,0.0007021875,0.001473997,0.0002207069],"domain_scores_gemma":[0.9498256,0.04217907,0.002105646,0.003483495,0.002117711,0.0002884348],"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":[0.0001811748,0.0001106633,0.001965621,0.0003386996,0.000264981,0.0003026564,0.0003962127,0.1088288,0.001938883,0.721767,0.003395104,0.1605102],"study_design_scores_gemma":[0.00006190351,0.0001355798,0.0005384499,0.0001112587,0.0000523737,0.0001329658,0.00006034659,0.6382923,0.001774889,0.352604,0.006190612,0.00004532994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008761189,0.0001548413,0.9984604,0.00006155448,0.00001851936,0.00003478917,0.00002338251,0.00008065322,0.0002897412],"genre_scores_gemma":[0.06121229,0.0008427727,0.9345444,0.0002389359,0.0002307896,0.0008586642,0.0003480105,0.0001660756,0.001557971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0218442,"threshold_uncertainty_score":0.1155245,"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","authors":[],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5389328,0.003153539,0.007324685,0.006947192,0.001706344,0.006782604,0.005458749,0.006730033,0.007502116],"category_scores_gemma":[0.8206995,0.003225826,0.01051928,0.0122941,0.005347193,0.00666061,0.005903419,0.01003651,0.002803433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002910384,"about_ca_system_score_gemma":0.008808065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003140977,"about_ca_topic_score_gemma":0.003064445,"domain_scores_codex":[0.3441895,0.5786317,0.03555624,0.01917686,0.02081154,0.001634166],"domain_scores_gemma":[0.2028287,0.6424546,0.04450689,0.09822277,0.01109487,0.0008921154],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.008177296,0.0004457877,0.03062542,0.0200586,0.02345843,0.0006027927,0.004310752,0.04896123,0.002246398,0.139945,0.0582485,0.6629198],"study_design_scores_gemma":[0.01130752,0.002447069,0.02410934,0.009864652,0.01476828,0.0008750025,0.0003934257,0.08883017,0.00827851,0.7262198,0.1120541,0.0008520774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004448938,0.008488293,0.9637646,0.008079291,0.001847127,0.003885783,0.002074295,0.002771772,0.004639859],"genre_scores_gemma":[0.1247407,0.002920312,0.8448231,0.007097458,0.001400677,0.01468841,0.001663866,0.0009718323,0.001693698],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4610672,"threshold_uncertainty_score":0.568578,"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","authors":[],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02167948,0.002108308,0.002885985,0.006633128,0.00118086,0.002909333,0.001517418,0.001081299,0.003732212],"category_scores_gemma":[0.0599291,0.0008185125,0.003107696,0.004711426,0.000719962,0.002028575,0.003767707,0.003034166,0.001063332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008223939,"about_ca_system_score_gemma":0.002296149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002306314,"about_ca_topic_score_gemma":0.003831786,"domain_scores_codex":[0.9906317,0.005171034,0.000857117,0.001447646,0.001525721,0.0003667279],"domain_scores_gemma":[0.965219,0.02228572,0.004247041,0.003986916,0.003432033,0.0008293687],"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":[0.002143026,0.0006354129,0.3443795,0.0008507127,0.003744071,0.0006153982,0.0008769195,0.1504999,0.00995213,0.01257607,0.008352746,0.4653742],"study_design_scores_gemma":[0.0004709698,0.001131071,0.05767483,0.0002575144,0.001371064,0.0004101557,0.0003865631,0.8285549,0.01063913,0.08971279,0.009130097,0.0002609047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08605032,0.0004267716,0.9074648,0.0007607842,0.00009592262,0.0006765668,0.002011635,0.001352445,0.001160698],"genre_scores_gemma":[0.3562222,0.0002069294,0.638161,0.0001640297,0.0001124768,0.0009448642,0.003376806,0.0002395285,0.0005721509],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02167948,"threshold_uncertainty_score":0.1146534,"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","authors":[],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04692917,0.001593022,0.002372983,0.001230181,0.0003973985,0.001423059,0.001861042,0.001767106,0.004078841],"category_scores_gemma":[0.1012132,0.00102219,0.00208059,0.000785913,0.001797973,0.001330639,0.001948081,0.002366806,0.0005244676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107776,"about_ca_system_score_gemma":0.002682456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005230465,"about_ca_topic_score_gemma":0.0005681934,"domain_scores_codex":[0.9649252,0.03091542,0.0008491976,0.001593162,0.001310727,0.0004062162],"domain_scores_gemma":[0.9178042,0.07068041,0.004245605,0.00449022,0.002137595,0.0006420067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008730697,0.0006191091,0.006392883,0.002101637,0.001879226,0.0002569527,0.0003222074,0.593999,0.00441866,0.0705093,0.003657162,0.3071131],"study_design_scores_gemma":[0.004952943,0.003717605,0.002588074,0.0004281387,0.0008470472,0.0001403894,0.00005380492,0.7991492,0.006150446,0.1742568,0.007601827,0.0001137064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02286679,0.00074205,0.9720148,0.0004537225,0.00008704005,0.002085309,0.000252499,0.0004147885,0.001082975],"genre_scores_gemma":[0.2044783,0.0004359336,0.7863876,0.0006150553,0.00007929672,0.006426444,0.0003538486,0.000137192,0.001086378],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04692917,"threshold_uncertainty_score":0.2481881,"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","authors":[{"name":"David A. Stephens","is_ca":true},{"name":"Erica E. M. Moodie","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04770547,0.001404381,0.002926958,0.002301073,0.000651016,0.001824835,0.003933206,0.002949964,0.003058679],"category_scores_gemma":[0.1139237,0.001435253,0.004359799,0.00205287,0.002498809,0.00166807,0.00345594,0.005149051,0.0004550777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001658671,"about_ca_system_score_gemma":0.002270548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002565918,"about_ca_topic_score_gemma":0.002655399,"domain_scores_codex":[0.9429366,0.05137608,0.0006726143,0.002155384,0.002446833,0.0004124778],"domain_scores_gemma":[0.9033629,0.08350811,0.004894705,0.006664143,0.0009995105,0.0005707092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002206385,0.0007932778,0.01721745,0.001596953,0.007136046,0.0008531781,0.001090732,0.3699537,0.003905094,0.239314,0.006422699,0.3495106],"study_design_scores_gemma":[0.0005271783,0.001486598,0.007948386,0.0002347425,0.001148139,0.0008670053,0.0001531723,0.607264,0.001813354,0.3694501,0.008930311,0.000176944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01193902,0.001471712,0.9834939,0.00114735,0.0000547201,0.000311876,0.0004503308,0.0001987716,0.0009322989],"genre_scores_gemma":[0.4049478,0.001928184,0.5843619,0.001323334,0.0001728792,0.003215833,0.0008450811,0.0001367562,0.003068269],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04770547,"threshold_uncertainty_score":0.2522936,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}