{"meta":{"query_hash":"805c37b54ad1","filters":{"venue":"Biostatistics & Epidemiology"},"cohort_total":7,"direct_labels_cover":0,"predictions_cover":7,"exported":7,"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/805c37b54ad1","api":"https://metacan.xera.ac/api/v1/cohort?venue=Biostatistics+%26+Epidemiology"},"results":[{"id":"W2760713401","doi":"10.1080/24709360.2017.1359356","title":"Analysis of progressive multi-state models with misclassified states: likelihood and pairwise likelihood methods","year":2017,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","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":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Inference; Computer science; Maximum likelihood; State (computer science); Data mining; Artificial intelligence; Machine learning; Econometrics; Statistics; Mathematics; Algorithm","score_opus":0.19242330087441353,"score_gpt":0.4705267785926885,"score_spread":0.2781034777182749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760713401","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":[0.0065030716,0.00028948663,0.99259126,0.00026910982,0.000023182893,0.000049496328,0.000056693134,0.00004890522,0.0001689105],"genre_scores_gemma":[0.4363988,0.0014756852,0.5564958,0.0003396647,0.00030847877,0.0008701027,0.00082675397,0.00016097608,0.0031237588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98029697,0.014842065,0.0006341262,0.0023397547,0.0015197005,0.00036753085],"domain_scores_gemma":[0.81832707,0.16498704,0.0072347797,0.0061913193,0.002301898,0.0009578791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052806962,0.0017583057,0.0029346352,0.002459469,0.00082516123,0.0026604927,0.005806346,0.0026610494,0.0029320342],"category_scores_gemma":[0.16559592,0.0013114087,0.0036589873,0.0024593626,0.0034986224,0.0045985365,0.0041857623,0.005258273,0.00041560887],"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":[0.0002430041,0.00015302576,0.016906923,0.0003879428,0.0011735618,0.00062750105,0.00083594787,0.5736148,0.0005792502,0.3069158,0.0013757381,0.097186536],"study_design_scores_gemma":[0.000041092142,0.00008237202,0.0015297673,0.00007576086,0.00011127346,0.00016277788,0.00006169231,0.7792315,0.00030602916,0.21737218,0.0009768215,0.000048737103],"about_ca_topic_score_codex":0.0041884286,"about_ca_topic_score_gemma":0.0031220526,"teacher_disagreement_score":0.052806962,"about_ca_system_score_codex":0.0015030417,"about_ca_system_score_gemma":0.0024549726,"threshold_uncertainty_score":0.2792732},"labels":[],"label_agreement":null},{"id":"W2971936035","doi":"10.1080/24709360.2019.1660110","title":"A frequentist mixture modeling of stop signal reaction times","year":2019,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"","keywords":"Frequentist inference; SIGNAL (programming language); Computer science; Econometrics; Statistics; Algorithm; Mathematics; Bayesian probability; Bayesian inference","score_opus":0.035524784508415765,"score_gpt":0.3131540366445244,"score_spread":0.2776292521361086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971936035","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":[0.103420034,0.00046296412,0.8913403,0.0006479516,0.00012513445,0.0002493758,0.000841113,0.0006911856,0.0022218456],"genre_scores_gemma":[0.7969844,0.0006306889,0.1810214,0.00030217975,0.00023747761,0.000983448,0.002373471,0.00030192194,0.017164987],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973907,0.0010524888,0.00012715085,0.00080412376,0.00035577826,0.00026986774],"domain_scores_gemma":[0.9953342,0.0031559712,0.00043148798,0.00047257266,0.00047242217,0.0001332524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005596126,0.0012933643,0.0022305325,0.0018840734,0.00076146325,0.0021459034,0.0040076617,0.0023621707,0.004400888],"category_scores_gemma":[0.012660722,0.0011929611,0.0031896147,0.0017227674,0.0011779296,0.002039211,0.001587838,0.0027164733,0.0013109766],"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":[0.001003771,0.00034566858,0.014435592,0.00024796405,0.00079035526,0.0005104321,0.0009724081,0.7607659,0.0049177133,0.12916774,0.004049176,0.08279334],"study_design_scores_gemma":[0.00002536741,0.000045948727,0.0016339491,0.000010601085,0.000050837913,0.00005868609,0.00001998195,0.9821177,0.00017883957,0.015208245,0.0006193136,0.000030507068],"about_ca_topic_score_codex":0.011390449,"about_ca_topic_score_gemma":0.00931157,"teacher_disagreement_score":0.011390449,"about_ca_system_score_codex":0.0011341982,"about_ca_system_score_gemma":0.0009955291,"threshold_uncertainty_score":0.029595494},"labels":[],"label_agreement":null},{"id":"W2997098473","doi":"10.1080/24709360.2019.1699341","title":"Cohort study design for illness-death processes with disease status under intermittent observation","year":2019,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"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; University of Toronto","funders":"","keywords":"Censoring (clinical trials); Cohort; Medicine; Cohort study; Sample size determination; Prospective cohort study; Disease; Incidence (geometry); Confidence interval; Event (particle physics); Demography; Statistics; Internal medicine; Mathematics; Pathology","score_opus":0.25519801630112465,"score_gpt":0.4321040283620619,"score_spread":0.17690601206093726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997098473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015712082,0.0016457556,0.9673935,0.0010544615,0.0011429108,0.008871267,0.0018996383,0.00024982865,0.0020304914],"genre_scores_gemma":[0.19229925,0.004570465,0.7145315,0.0016157412,0.0011879149,0.07598013,0.0024648383,0.000102708786,0.0072474885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95250666,0.03900289,0.0015452651,0.004010374,0.0022984783,0.0006363947],"domain_scores_gemma":[0.9403328,0.043822348,0.004981468,0.007854248,0.002245286,0.0007639326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07755016,0.0013178994,0.002076796,0.0018358339,0.0011063878,0.0018405049,0.004098156,0.0029019034,0.009417197],"category_scores_gemma":[0.091297664,0.00073474646,0.0019777054,0.0029216544,0.0018688295,0.0021946286,0.003060699,0.003408845,0.0012623287],"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":[0.0026926857,0.0007687104,0.036824454,0.0027165934,0.002358316,0.00075859186,0.0018125742,0.029963681,0.0022952813,0.8005115,0.011159605,0.10813806],"study_design_scores_gemma":[0.004083075,0.011014419,0.016093075,0.0014758206,0.002794628,0.0014897627,0.00096730475,0.33156428,0.0017971203,0.5340964,0.09431005,0.00031405975],"about_ca_topic_score_codex":0.0017326897,"about_ca_topic_score_gemma":0.0018765285,"teacher_disagreement_score":0.9224498,"about_ca_system_score_codex":0.0011843154,"about_ca_system_score_gemma":0.0036489242,"threshold_uncertainty_score":0.4101293},"labels":[],"label_agreement":null},{"id":"W3047938449","doi":"10.1080/24709360.2020.1796176","title":"Number needed to test: quantifying risk stratification provided by diagnostic tests and risk predictions","year":2020,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"BRCA gene mutations in cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"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":"Division of Cancer Epidemiology and Genetics, National Cancer Institute; Fonds de Recherche du Québec-Société et Culture; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Risk stratification; Genetic testing; Medicine; Risk assessment; Psychological intervention; Disease; Metric (unit); Test (biology); Actuarial science; Econometrics; Computer science; Risk analysis (engineering); Mathematics; Internal medicine; Economics; Biology; Operations management","score_opus":0.04071876991350831,"score_gpt":0.3399215882456961,"score_spread":0.2992028183321878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047938449","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5512115,0.0061050155,0.38414997,0.013791552,0.0005687849,0.00042963546,0.004604788,0.0022147514,0.036924012],"genre_scores_gemma":[0.94787216,0.00044447498,0.048453767,0.0006685436,0.00011483742,0.00014646024,0.0009821423,0.00016336888,0.0011542148],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98583823,0.0075259334,0.00072431675,0.0018661491,0.0033981004,0.00064728345],"domain_scores_gemma":[0.83514696,0.1421274,0.00864901,0.007415411,0.005114721,0.0015464097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020081474,0.0016472883,0.0012580412,0.0030110704,0.0007525259,0.0035302492,0.0013824195,0.0030642338,0.006142885],"category_scores_gemma":[0.16203213,0.0006732614,0.0015846677,0.0016468822,0.0024720456,0.0055277282,0.002465329,0.0027901996,0.0008566203],"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":[0.0031643168,0.00043117232,0.23152922,0.0007160156,0.0009742102,0.0005986557,0.0009209916,0.504871,0.0031856725,0.050621692,0.006138662,0.1968483],"study_design_scores_gemma":[0.00025266883,0.0012970751,0.07388232,0.0005414124,0.0004992886,0.0015803003,0.0006777217,0.69626325,0.00600891,0.209235,0.009398481,0.0003635795],"about_ca_topic_score_codex":0.004804189,"about_ca_topic_score_gemma":0.0027512726,"teacher_disagreement_score":0.020081474,"about_ca_system_score_codex":0.0023755864,"about_ca_system_score_gemma":0.0013280135,"threshold_uncertainty_score":0.106202245},"labels":[],"label_agreement":null},{"id":"W4280498397","doi":"10.1080/24709360.2022.2069457","title":"Doubly weighted estimating equations and weighted multiple imputation for causal inference with an incomplete subgroup variable","year":2022,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Missing data; Statistics; Observational study; Mathematics; Estimator; Causal inference; Inference; Imputation (statistics); Subgroup analysis; Variable (mathematics); Propensity score matching; Econometrics; Medicine; Computer science; Artificial intelligence","score_opus":0.18093787325331165,"score_gpt":0.4283506853874128,"score_spread":0.24741281213410113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280498397","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":[0.0009204439,0.00023751172,0.99822444,0.00015650477,0.000024460904,0.0000664773,0.000110339926,0.00007766005,0.0001822518],"genre_scores_gemma":[0.05255783,0.0012079512,0.9428252,0.0002064416,0.00015048092,0.0011442676,0.00068884547,0.00008945382,0.0011294802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96314824,0.03198755,0.0010913241,0.0015532878,0.0018904402,0.00032918854],"domain_scores_gemma":[0.9233024,0.06291646,0.004631321,0.0066688736,0.0022252137,0.0002556799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037176948,0.0014989104,0.0028480673,0.0034392232,0.0006042957,0.001797065,0.0045069614,0.002216105,0.005063281],"category_scores_gemma":[0.1340474,0.0011827699,0.003379401,0.0059550167,0.0013532734,0.00296492,0.0029731987,0.004042274,0.0011216091],"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":[0.0001804425,0.00013518076,0.0069983737,0.00071468076,0.0017901644,0.00038661444,0.0005115935,0.18009755,0.0005517682,0.6010912,0.004110471,0.20343189],"study_design_scores_gemma":[0.00012885065,0.00010607235,0.0010951511,0.0001759827,0.0002474633,0.00014636044,0.00005149532,0.4723447,0.0003892964,0.51891446,0.006339387,0.00006070873],"about_ca_topic_score_codex":0.005871609,"about_ca_topic_score_gemma":0.005448453,"teacher_disagreement_score":0.037176948,"about_ca_system_score_codex":0.0012729015,"about_ca_system_score_gemma":0.0029657024,"threshold_uncertainty_score":0.19661283},"labels":[],"label_agreement":null},{"id":"W4406596694","doi":"10.1080/24709360.2025.2451519","title":"Finite Markov chains with absorbing states and mis-specified random effects: application to cognitive data","year":2025,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"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":"National Center for Advancing Translational Sciences; National Institute on Aging","keywords":"Markov chain; Statistical physics; Cognition; Computer science; Mathematics; Physics; Psychology; Statistics","score_opus":0.03042029286051502,"score_gpt":0.33965049095912536,"score_spread":0.30923019809861035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406596694","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":[0.018408988,0.00022437163,0.9799269,0.00034603628,0.000025539352,0.000119069264,0.00012200387,0.00021145715,0.0006158228],"genre_scores_gemma":[0.43390524,0.0007808593,0.5614521,0.00036027993,0.00013358457,0.0009444561,0.00053683214,0.00013857348,0.0017479998],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98889726,0.008650241,0.0003827405,0.0010019843,0.00074946746,0.00031816494],"domain_scores_gemma":[0.79835135,0.18742289,0.005523313,0.004957657,0.0029869128,0.0007577955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033037473,0.0009430817,0.0020180428,0.0029941509,0.0013460873,0.002548339,0.0025628374,0.0023990842,0.003393284],"category_scores_gemma":[0.12319171,0.0010635417,0.0025691434,0.0029228884,0.003014392,0.0030079617,0.0027178146,0.0037808013,0.00040728803],"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":[0.00020282839,0.00017117734,0.01704195,0.0003084547,0.00037270965,0.0007619816,0.001432063,0.48747787,0.00060931005,0.42240348,0.0014986981,0.06771949],"study_design_scores_gemma":[0.00003078807,0.000034452307,0.0012686093,0.00007567551,0.000048158003,0.00010438869,0.0000998151,0.77283573,0.0001936713,0.22424972,0.0010224548,0.000036579353],"about_ca_topic_score_codex":0.0156228095,"about_ca_topic_score_gemma":0.014631989,"teacher_disagreement_score":0.033037473,"about_ca_system_score_codex":0.002139388,"about_ca_system_score_gemma":0.00275303,"threshold_uncertainty_score":0.17472094},"labels":[],"label_agreement":null},{"id":"W4413019256","doi":"10.1080/24709360.2025.2539589","title":"Selection of mediators and dependence structure for high-dimensional mediation analysis","year":2025,"lang":"en","type":"article","venue":"Biostatistics & Epidemiology","topic":"Child and Adolescent Psychosocial and Emotional Development","field":"Psychology","cited_by":0,"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":"Mediation; Psychology; Selection (genetic algorithm); Computer science; Artificial intelligence; Political science","score_opus":0.017883454270799872,"score_gpt":0.3335996795926779,"score_spread":0.31571622532187804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413019256","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":[0.011361297,0.00008926803,0.9870703,0.00036898485,0.000021232863,0.00036534455,0.00009664583,0.00013994271,0.0004870245],"genre_scores_gemma":[0.26111057,0.00028251903,0.7329424,0.000267852,0.00009179681,0.0030153992,0.0005933368,0.000116624826,0.0015795352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9678361,0.028542819,0.0006332655,0.0013498148,0.0011234842,0.0005144237],"domain_scores_gemma":[0.94712496,0.04392151,0.002173558,0.004422078,0.0017474425,0.00061045535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042330932,0.0013397378,0.0023999515,0.0014979928,0.0017501734,0.002320038,0.0029094466,0.0018084584,0.00811728],"category_scores_gemma":[0.08709102,0.0009670762,0.0028040146,0.0016574921,0.0021583913,0.0027121517,0.005412834,0.0044335714,0.0008844887],"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":[0.0013580489,0.001537677,0.051602267,0.0011057309,0.0020000672,0.0013426387,0.0031569232,0.15832591,0.006904089,0.5394608,0.007000891,0.22620493],"study_design_scores_gemma":[0.00023613732,0.00042750052,0.0059541445,0.00014876187,0.00023387551,0.00017190285,0.00033272256,0.7750584,0.0017190246,0.21203081,0.0035946222,0.00009215392],"about_ca_topic_score_codex":0.001518602,"about_ca_topic_score_gemma":0.0019211028,"teacher_disagreement_score":0.042330932,"about_ca_system_score_codex":0.00070359383,"about_ca_system_score_gemma":0.0041188425,"threshold_uncertainty_score":0.22387004},"labels":[],"label_agreement":null}]}