{"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011939015,0.0014717116,0.9834939,0.0011473501,0.000054720098,0.00031187598,0.0004503308,0.00019877164,0.00093229895],"genre_scores_gemma":[0.40494785,0.0019281836,0.5843619,0.0013233343,0.00017287915,0.0032158326,0.00084508106,0.00013675619,0.003068269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9429366,0.051376082,0.0006726143,0.0021553843,0.0024468326,0.00041247776],"domain_scores_gemma":[0.9033629,0.08350811,0.0048947046,0.0066641434,0.0009995105,0.00057070924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047705468,0.0014043815,0.0029269576,0.0023010734,0.00065101596,0.0018248352,0.003933206,0.002949964,0.0030586787],"category_scores_gemma":[0.113923706,0.0014352526,0.0043597985,0.00205287,0.0024988092,0.0016680697,0.00345594,0.0051490506,0.00045507768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022063851,0.0007932778,0.017217448,0.0015969526,0.007136046,0.00085317815,0.0010907322,0.36995366,0.0039050935,0.239314,0.006422699,0.34951055],"study_design_scores_gemma":[0.0005271783,0.0014865982,0.007948386,0.00023474252,0.0011481387,0.00086700526,0.00015317234,0.60726404,0.0018133537,0.3694501,0.008930311,0.00017694404],"about_ca_topic_score_codex":0.0025659183,"about_ca_topic_score_gemma":0.0026553986,"teacher_disagreement_score":0.047705468,"about_ca_system_score_codex":0.0016586706,"about_ca_system_score_gemma":0.0022705477,"threshold_uncertainty_score":0.25229365},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008761189,0.00015484127,0.9984604,0.00006155448,0.00001851936,0.00003478917,0.000023382507,0.00008065322,0.00028974123],"genre_scores_gemma":[0.061212294,0.0008427727,0.9345444,0.00023893593,0.00023078962,0.00085866416,0.00034801048,0.0001660756,0.0015579711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9861602,0.011094111,0.00034881296,0.0007021875,0.0014739973,0.0002207069],"domain_scores_gemma":[0.9498256,0.042179074,0.0021056456,0.0034834954,0.0021177107,0.0002884348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0218442,0.0015336659,0.0016516808,0.00312418,0.00068061566,0.0017094829,0.0025522655,0.002183243,0.003245783],"category_scores_gemma":[0.09692165,0.00077257975,0.0020132256,0.0022361204,0.002189347,0.0030097093,0.0020908883,0.002716561,0.0010749953],"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":[0.00018117481,0.00011066327,0.0019656206,0.00033869964,0.00026498098,0.00030265644,0.00039621274,0.10882879,0.0019388834,0.721767,0.0033951043,0.16051017],"study_design_scores_gemma":[0.00006190351,0.00013557977,0.0005384499,0.00011125867,0.0000523737,0.0001329658,0.000060346585,0.63829225,0.0017748888,0.352604,0.0061906124,0.00004532994],"about_ca_topic_score_codex":0.0022966857,"about_ca_topic_score_gemma":0.0020013931,"teacher_disagreement_score":0.0218442,"about_ca_system_score_codex":0.0011168678,"about_ca_system_score_gemma":0.0012721434,"threshold_uncertainty_score":0.11552453},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022202875,0.0014555065,0.97210556,0.001313158,0.00009764258,0.0008617848,0.00076172734,0.00055899203,0.00064283534],"genre_scores_gemma":[0.41699833,0.0036770834,0.56049377,0.0015846553,0.00029647624,0.009062377,0.002793448,0.0002942184,0.00479966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87641966,0.11222686,0.0019898254,0.0057796515,0.002692927,0.0008909987],"domain_scores_gemma":[0.6251821,0.33323264,0.016150473,0.021841457,0.0029166988,0.0006766966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17700033,0.0024574238,0.004684078,0.007228294,0.0012914767,0.0026067968,0.0044858926,0.0059460024,0.006832434],"category_scores_gemma":[0.29642102,0.0018901016,0.005615958,0.005523125,0.0042431667,0.0047509167,0.0047011757,0.005649597,0.0013692909],"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":[0.0018283533,0.0007466474,0.095083654,0.0024912136,0.00851639,0.0011868497,0.0022772383,0.30619988,0.0015665954,0.3559998,0.006655313,0.21744823],"study_design_scores_gemma":[0.00056709925,0.0009768986,0.015838815,0.0005167924,0.0010975384,0.0005733752,0.0004102071,0.60518265,0.0010814628,0.364889,0.008689371,0.00017674753],"about_ca_topic_score_codex":0.0030423095,"about_ca_topic_score_gemma":0.0016696723,"teacher_disagreement_score":0.17700033,"about_ca_system_score_codex":0.0031773536,"about_ca_system_score_gemma":0.0022442567,"threshold_uncertainty_score":0.9360784},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022866791,0.00074205,0.9720148,0.00045372246,0.000087040054,0.0020853088,0.00025249895,0.00041478852,0.0010829748],"genre_scores_gemma":[0.20447828,0.00043593365,0.7863876,0.00061505527,0.00007929672,0.0064264443,0.00035384856,0.00013719198,0.0010863785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96492517,0.030915419,0.00084919756,0.0015931621,0.001310727,0.00040621622],"domain_scores_gemma":[0.91780424,0.07068041,0.0042456053,0.0044902205,0.002137595,0.0006420067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04692917,0.0015930216,0.002372983,0.0012301813,0.0003973985,0.0014230588,0.0018610425,0.0017671055,0.0040788413],"category_scores_gemma":[0.101213194,0.00102219,0.0020805905,0.000785913,0.0017979728,0.0013306387,0.0019480814,0.0023668061,0.0005244676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008730697,0.00061910914,0.006392883,0.0021016374,0.0018792257,0.00025695266,0.0003222074,0.59399897,0.00441866,0.0705093,0.0036571624,0.30711314],"study_design_scores_gemma":[0.004952943,0.0037176046,0.0025880742,0.0004281387,0.0008470472,0.00014038937,0.000053804917,0.7991492,0.0061504464,0.17425677,0.0076018274,0.0001137064],"about_ca_topic_score_codex":0.00052304653,"about_ca_topic_score_gemma":0.0005681934,"teacher_disagreement_score":0.04692917,"about_ca_system_score_codex":0.0010777602,"about_ca_system_score_gemma":0.002682456,"threshold_uncertainty_score":0.24818814},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086050324,0.00042677164,0.9074648,0.0007607842,0.00009592262,0.0006765668,0.002011635,0.0013524452,0.0011606975],"genre_scores_gemma":[0.35622215,0.00020692943,0.638161,0.00016402971,0.000112476824,0.00094486424,0.0033768062,0.0002395285,0.0005721509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9906317,0.0051710345,0.000857117,0.0014476456,0.0015257206,0.0003667279],"domain_scores_gemma":[0.96521896,0.022285718,0.0042470414,0.003986916,0.003432033,0.0008293687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02167948,0.0021083078,0.0028859852,0.006633128,0.00118086,0.0029093332,0.0015174182,0.001081299,0.0037322117],"category_scores_gemma":[0.0599291,0.00081851246,0.0031076963,0.004711426,0.000719962,0.0020285752,0.0037677074,0.0030341663,0.001063332],"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":[0.002143026,0.0006354129,0.34437945,0.0008507127,0.0037440711,0.0006153982,0.0008769195,0.15049987,0.00995213,0.012576074,0.008352746,0.4653742],"study_design_scores_gemma":[0.00047096983,0.0011310705,0.057674833,0.0002575144,0.0013710645,0.00041015574,0.00038656313,0.8285549,0.010639128,0.08971279,0.009130097,0.00026090472],"about_ca_topic_score_codex":0.0023063142,"about_ca_topic_score_gemma":0.0038317863,"teacher_disagreement_score":0.02167948,"about_ca_system_score_codex":0.00082239386,"about_ca_system_score_gemma":0.002296149,"threshold_uncertainty_score":0.11465341},"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":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004448938,0.008488293,0.9637646,0.008079291,0.0018471271,0.0038857826,0.0020742947,0.0027717715,0.004639859],"genre_scores_gemma":[0.12474068,0.0029203123,0.84482306,0.0070974585,0.0014006768,0.014688412,0.0016638659,0.00097183225,0.0016936985],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.3441895,0.5786317,0.035556242,0.019176861,0.020811541,0.001634166],"domain_scores_gemma":[0.20282874,0.64245456,0.044506885,0.09822277,0.01109487,0.0008921154],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5389328,0.0031535386,0.007324685,0.0069471924,0.0017063438,0.0067826044,0.005458749,0.006730033,0.007502116],"category_scores_gemma":[0.82069945,0.0032258264,0.010519279,0.012294097,0.005347193,0.00666061,0.005903419,0.010036513,0.0028034332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008177296,0.00044578768,0.030625416,0.0200586,0.023458434,0.0006027927,0.004310752,0.048961226,0.0022463975,0.13994503,0.058248498,0.66291976],"study_design_scores_gemma":[0.011307522,0.002447069,0.02410934,0.009864652,0.014768285,0.0008750025,0.0003934257,0.088830166,0.00827851,0.72621983,0.11205415,0.00085207744],"about_ca_topic_score_codex":0.0031409767,"about_ca_topic_score_gemma":0.003064445,"teacher_disagreement_score":0.4610672,"about_ca_system_score_codex":0.0029103844,"about_ca_system_score_gemma":0.008808065,"threshold_uncertainty_score":0.568578},"labels":[],"label_agreement":null}]}