{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1326,"total_is_capped":false,"direct_labels_cover":35,"predictions_cover":1326,"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":"e802a3299282","filters":{"topic":"Advanced Causal Inference Techniques"}},"results":[{"id":"W2036193982","doi":"10.1080/00273171.2011.568786","title":"An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11884,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Observational study; Covariate; Confounding; Statistics; Inverse probability weighting; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8974226593536919,"gpt":0.6794649079660394,"spread":0.2179577513876525,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006753378,0.0001320362,0.0003260467,0.0002465841,0.0001889317,0.00002330101,0.0003384725,0.0000790503,0.000009914063],"category_scores_gemma":[0.0108523,0.00009296784,0.00003991782,0.0005005787,0.0002033273,0.0003066678,0.0002007345,0.0003656098,0.000001178264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002581883,"about_ca_system_score_gemma":0.0000841354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006518969,"about_ca_topic_score_gemma":0.0001046212,"domain_scores_codex":[0.997631,0.0009212406,0.0003871311,0.0003592734,0.0003259058,0.0003754889],"domain_scores_gemma":[0.9958278,0.00237814,0.0001111007,0.0004914185,0.001128237,0.00006328556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000355599,0.0006330891,0.005786605,0.0003384953,0.00002239347,0.000003529305,0.0159094,0.000005958023,0.8450568,0.09410986,0.0001776686,0.03760062],"study_design_scores_gemma":[0.0004309722,0.001504177,0.04700927,0.0002973234,0.00003366003,0.000001921406,0.001437723,0.0002981351,0.7497191,0.1989969,0.00007734635,0.000193416],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9202135,0.0000221448,0.07665904,0.0002019576,0.0001653342,0.002659545,0.00000324145,0.00006038761,0.00001484027],"genre_scores_gemma":[0.5802438,0.000003987337,0.4189482,0.000005200957,0.00007632076,0.0006432403,0.000003197924,0.00001906868,0.00005701225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3422891,"threshold_uncertainty_score":0.9974797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126049444","doi":"10.1002/sim.3697","title":"Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity‐score matched samples","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6487,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Matching (statistics); Quantile; Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2114497428934903,"gpt":0.4202548380162484,"spread":0.208805095122758,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009551875,0.0001872629,0.0006860506,0.00006476622,0.00004160957,0.00000616034,0.0001698366,0.00006288834,0.00000838171],"category_scores_gemma":[0.006444343,0.0001218774,0.00001977777,0.0002163665,0.0001741788,0.00004066479,0.00002553759,0.0001542706,3.799494e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000198718,"about_ca_system_score_gemma":0.00003672248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001853483,"about_ca_topic_score_gemma":0.0003548727,"domain_scores_codex":[0.9985509,0.00009937034,0.0006959968,0.0001959466,0.0002076686,0.0002501206],"domain_scores_gemma":[0.9933268,0.005925904,0.0002621044,0.0002891535,0.0001563732,0.00003959509],"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":[0.0001324537,0.0003430188,0.2419266,0.0002418274,0.0000312567,0.00001988727,0.00142743,0.0001053988,0.0004952129,0.7422302,0.002213802,0.0108329],"study_design_scores_gemma":[0.001332351,0.0007929642,0.1568467,0.0005623271,0.00008464915,0.00000172501,0.0001909562,0.003155827,0.001849565,0.8349497,0.00009535121,0.0001378101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1523039,0.00009847339,0.845264,0.0006051103,0.00003874826,0.0009897766,0.0006280991,0.00004157511,0.00003033468],"genre_scores_gemma":[0.8582994,0.0002804627,0.1404751,0.00004249367,0.00008786792,0.00006643381,0.0007270477,0.00001230141,0.000008812349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7059955,"threshold_uncertainty_score":0.7714946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110818436","doi":"10.1002/sim.6607","title":"Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies","year":2015,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4309,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; National Institute of Mental Health; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Inverse probability weighting; Observational study; Inverse probability; Weighting; Average treatment effect; Statistics; Treatment and control groups; Econometrics; Sample size determination; Baseline (sea); Mathematics; Selection bias; Computer science; Posterior probability; Medicine; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.6765608631638398,"gpt":0.5702584500397571,"spread":0.1063024131240827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00269643,0.0007237854,0.003190661,0.0002977274,0.0001094442,0.0000176138,0.0002717285,0.0001882616,0.000006667016],"category_scores_gemma":[0.02305184,0.0004198938,0.00007812036,0.0005697595,0.0004174566,0.0001784264,0.0002624058,0.0004139525,0.00000116138],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007056866,"about_ca_system_score_gemma":0.001585657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002149459,"about_ca_topic_score_gemma":0.001972817,"domain_scores_codex":[0.9956156,0.0009921558,0.00168086,0.0006061625,0.0006564941,0.0004487299],"domain_scores_gemma":[0.9908638,0.00617586,0.001314674,0.0006982357,0.0008240381,0.0001233895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000205423,0.002060927,0.001547596,0.07049702,0.001410804,0.0009908285,0.02753251,0.001659376,0.00006021765,0.06116321,0.0004119571,0.8324602],"study_design_scores_gemma":[0.003798125,0.00917749,0.00008317934,0.2304193,0.01296473,0.000320958,0.002960537,0.01344947,0.0001140571,0.6956356,0.02888222,0.002194393],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.01180621,0.798593,0.1680657,0.0002591576,0.000776616,0.01947474,0.0005742618,0.0001727917,0.0002775343],"genre_scores_gemma":[0.0000461117,0.2281866,0.7710488,0.00002837804,0.0001326816,0.000385034,0.00006793877,0.00007215919,0.00003233563],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8302658,"threshold_uncertainty_score":0.9998253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111635289","doi":"10.1002/pst.433","title":"Optimal caliper widths for propensity‐score matching when estimating differences in means and differences in proportions in observational studies","year":2010,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3895,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Calipers; Statistics; Estimator; Mathematics; Logit; Matching (statistics); Observational study; Econometrics; Standard deviation; Confidence interval; Logistic regression; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5850172035475715,"gpt":0.5093227869028153,"spread":0.07569441664475618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006720899,0.0002721575,0.000583042,0.0001505903,0.0001075048,0.00006419125,0.0001836351,0.0001083669,0.0001427266],"category_scores_gemma":[0.005333425,0.0002261091,0.00002354665,0.0001715965,0.0003457131,0.0002603874,0.0001534025,0.0007175928,0.000001075164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009149244,"about_ca_system_score_gemma":0.00009509872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006342919,"about_ca_topic_score_gemma":0.001813236,"domain_scores_codex":[0.9979894,0.0001014118,0.0007628911,0.0003947499,0.0002937372,0.0004578818],"domain_scores_gemma":[0.9959605,0.003444055,0.0001689809,0.0001376953,0.0001649313,0.0001237755],"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":[0.0001183315,0.0005895928,0.4410522,0.001163657,0.00004771452,0.00006528252,0.005470528,0.00007393833,0.001791756,0.540161,0.0004508555,0.009015203],"study_design_scores_gemma":[0.0006265716,0.00007762445,0.05886068,0.0003398299,0.00003392851,0.000008525208,0.000424386,0.0989402,0.000253933,0.8400614,0.00003384267,0.0003391106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7048489,0.00003927316,0.2931017,0.0004205741,0.0001053669,0.0009971044,0.0003752409,0.00007291753,0.00003893017],"genre_scores_gemma":[0.4761547,0.00002361761,0.5233449,0.00006316978,0.00003287132,0.0003163916,0.00002635588,0.00001677382,0.00002113672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3821915,"threshold_uncertainty_score":0.9220461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3122958054","doi":"10.1016/j.jeconom.2007.05.001","title":"Regression discontinuity designs: A guide to practice","year":2007,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3773,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Regression discontinuity design; Covariate; Econometrics; Discontinuity (linguistics); Regression; Value (mathematics); Regression analysis; Statistics; Mathematics; Computer science; Economics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.4194458121712126,"gpt":0.4801592340539934,"spread":0.06071342188278078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005315716,0.0001429653,0.0003805149,0.001176416,0.00004894099,0.00005495838,0.0003442246,0.00009493118,0.00007026763],"category_scores_gemma":[0.03189541,0.0001109915,0.0001180619,0.001099334,0.00002536188,0.0008873572,0.00008957015,0.0003379597,0.00001668652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003704425,"about_ca_system_score_gemma":0.00007656212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003454623,"about_ca_topic_score_gemma":0.000008660762,"domain_scores_codex":[0.9981894,0.00005674998,0.001061765,0.0001318824,0.0002849409,0.0002752457],"domain_scores_gemma":[0.9940033,0.00352545,0.001307349,0.0002779932,0.0006339265,0.0002519838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001172606,0.001970619,0.007994942,0.0001908063,0.0003635727,0.001097759,0.002699766,0.00008320905,0.009012998,0.2118557,0.2899019,0.4736561],"study_design_scores_gemma":[0.001128342,0.00220552,0.002314247,0.0005276523,0.0001986093,0.0009612329,0.00255389,0.00002920457,0.04869323,0.3753513,0.565304,0.0007328794],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03525117,0.0002326627,0.949561,0.0006057757,0.0003323214,0.0001809718,0.000002401257,0.00004383642,0.01378983],"genre_scores_gemma":[0.1464581,0.0001366029,0.8518707,0.0004220831,0.0002608105,0.000001823679,2.476488e-7,0.00002596804,0.0008237192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4729232,"threshold_uncertainty_score":0.9762594,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2264767503","doi":"10.1161/circulationaha.115.017719","title":"Introduction to the Analysis of Survival Data in the Presence of Competing Risks","year":2016,"lang":"en","type":"article","venue":"Circulation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2536,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University Health Network; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Covariate; Medicine; Proportional hazards model; Survival analysis; Cumulative incidence; Incidence (geometry); Survival function; Event (particle physics); Statistics; Hazard ratio; Outcome (game theory); Hazard; Demography; Accelerated failure time model; Econometrics; Confidence interval; Internal medicine; Cohort; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2664686297936992,"gpt":0.4426291158539977,"spread":0.1761604860602985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001584616,0.00004413999,0.0001372609,0.00010388,0.00002149896,0.000004865493,0.0003466294,0.00002309122,0.00002232791],"category_scores_gemma":[0.002529238,0.00002228824,0.00002377733,0.0006560491,0.00004063454,0.000135915,0.00007476932,0.00004195216,0.000001160102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002053902,"about_ca_system_score_gemma":0.000008219667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007646727,"about_ca_topic_score_gemma":0.000228061,"domain_scores_codex":[0.9991515,0.0001854325,0.000258124,0.0001358247,0.0002047534,0.00006439219],"domain_scores_gemma":[0.9978166,0.00101744,0.0001886962,0.0008795899,0.00009084983,0.000006783838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005264811,0.0002123681,0.4892606,0.0001050861,0.0003157068,5.923145e-7,0.007567714,0.01028328,0.1384201,0.2885939,0.0009820153,0.06420599],"study_design_scores_gemma":[0.0001181882,0.00001818539,0.9054275,0.00007443727,0.0003039908,7.556611e-7,0.0008910385,0.01446155,0.005933315,0.07231374,0.0003493053,0.0001080546],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5953732,0.000007360289,0.402934,0.001292401,0.0000314275,0.0002026053,0.0000172302,0.00001723244,0.00012451],"genre_scores_gemma":[0.9961413,0.000004387137,0.003749407,0.000006660375,0.00007023314,0.000007703508,0.00001364634,0.00000360874,0.000003118221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4161668,"threshold_uncertainty_score":0.3027917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004722883","doi":"10.1097/ede.0b013e3181a819a1","title":"Overadjustment Bias and Unnecessary Adjustment in Epidemiologic Studies","year":2009,"lang":"en","type":"article","venue":"Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1947,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Selection bias; Omitted-variable bias; Confounding; Information bias; Econometrics; Statistics; Proxy (statistics); Causal structure; Sampling bias; Non-response bias; Outcome (game theory); Causal inference; Sample size determination; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6176038876181804,"gpt":0.5397161510959915,"spread":0.07788773652218894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00494286,0.0003125956,0.001288739,0.0001689442,0.00005382099,0.000002067691,0.0001762378,0.0002362393,0.00003051063],"category_scores_gemma":[0.02941776,0.0002334642,0.00007725751,0.0001618202,0.0002283733,0.0001277703,0.0001227597,0.000367969,0.00001012724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000219135,"about_ca_system_score_gemma":0.00002005558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002379907,"about_ca_topic_score_gemma":0.00003541876,"domain_scores_codex":[0.9962081,0.001485003,0.001067367,0.0005440801,0.00007643207,0.0006190116],"domain_scores_gemma":[0.9830894,0.01597509,0.0003749245,0.0004088301,0.00005018404,0.0001015583],"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":[0.00003724899,0.0001445859,0.01937161,0.0000534154,0.00004425518,0.00002818719,0.0002953323,0.00006091745,0.0001608376,0.9363624,0.01369524,0.02974592],"study_design_scores_gemma":[0.0002767082,0.0004674071,0.06190481,0.00009346961,0.00001823697,0.00002610527,0.0001946438,0.0001863189,0.0001468317,0.9357155,0.0007547453,0.0002152401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8449751,0.07231061,0.03387222,0.03963155,0.0006065691,0.002048211,0.00001611194,0.001260217,0.005279379],"genre_scores_gemma":[0.7615846,0.01706808,0.206382,0.01431604,0.0001957927,0.0001735499,0.000009686608,0.00002491743,0.0002452794],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1725098,"threshold_uncertainty_score":0.9787579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029059557","doi":"10.1080/03610911003650383","title":"How Big is a Big Odds Ratio? Interpreting the Magnitudes of Odds Ratios in Epidemiological Studies","year":2010,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1932,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Canada; Columbia College","funders":"","keywords":"Odds ratio; Odds; Epidemiology; Index (typography); Statistics; Medicine; Demography; Psychology; Mathematics; Computer science; Internal medicine; Sociology; Logistic regression","retraction":null,"screen_n_in":null,"score":{"opus":0.5103286940819939,"gpt":0.559314319333483,"spread":0.04898562525148908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001153322,0.0001613631,0.0003336882,0.0001992794,0.0001604884,0.00005960737,0.000322747,0.0001041885,0.000004225817],"category_scores_gemma":[0.008766515,0.0001288171,0.00002730185,0.0003655516,0.0004757952,0.000141291,0.0002538961,0.0004590303,6.633155e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005039937,"about_ca_system_score_gemma":0.00003916079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002145288,"about_ca_topic_score_gemma":0.0007133313,"domain_scores_codex":[0.9982825,0.0004937297,0.0007367767,0.0001924902,0.0001536669,0.000140861],"domain_scores_gemma":[0.984515,0.0140644,0.0004261698,0.0005663136,0.0004019486,0.00002623212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003175835,0.0002278086,0.008732584,0.0001325806,0.0000352222,0.000001040164,0.009354492,0.0116647,0.001094798,0.7634559,0.0001244877,0.2051447],"study_design_scores_gemma":[0.0002271184,0.00004638456,0.004260319,0.0001156057,0.00001418996,0.000001197273,0.001105689,0.5572912,0.0001191374,0.4366294,0.00008152588,0.0001082973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07716683,0.0002803683,0.9203379,0.001460396,0.00008520175,0.000468629,0.00003104009,0.00005890314,0.0001108047],"genre_scores_gemma":[0.7898632,0.0003009265,0.2095784,0.0001129176,0.00001575719,0.00006749013,0.00003547783,0.0000110001,0.00001481078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7126964,"threshold_uncertainty_score":0.9995831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056621649","doi":"10.1214/10-sts321","title":"Identification, Inference and Sensitivity Analysis for Causal Mediation Effects","year":2010,"lang":"en","type":"article","venue":"Statistical Science","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1558,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University; University of Wisconsin-Madison; University of Pennsylvania; Harvard University; National Science Foundation","keywords":"Causal inference; Estimator; Robustness (evolution); Identification (biology); Sensitivity (control systems); Randomized experiment; Inference; Causal model; Parametric statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05207382361030993,"gpt":0.4371451219746848,"spread":0.3850712983643749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001660729,0.00009853551,0.0001816581,0.0001477086,0.000221455,0.0001046541,0.0001011503,0.00005145481,0.00001976052],"category_scores_gemma":[0.02338552,0.00008530857,0.00002013267,0.0006903958,0.0008409185,0.0003148485,0.00006430526,0.0001376496,0.000003759839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003014099,"about_ca_system_score_gemma":0.00008030736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002195275,"about_ca_topic_score_gemma":0.0003468886,"domain_scores_codex":[0.9987804,0.00004071716,0.000211477,0.0003792304,0.0003348849,0.0002532369],"domain_scores_gemma":[0.994081,0.005082025,0.0001044769,0.0002622528,0.0003178483,0.0001524456],"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":[0.000003121358,0.00002262102,0.003487406,0.00002810704,0.000008956951,0.000001887837,0.00008474752,0.000001966675,0.1490913,0.8422166,0.00003918402,0.005014085],"study_design_scores_gemma":[0.00007720503,0.00004452207,0.09991317,0.000004183416,0.00009859279,0.000002692269,0.00001111456,0.02203145,0.03630024,0.8413563,0.00001894185,0.0001415759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1819675,0.000001050317,0.8173853,0.0000817254,0.00008277083,0.0002584593,0.00005706969,0.00009072391,0.00007535482],"genre_scores_gemma":[0.7764116,0.000001463465,0.2234689,0.00002332559,0.000022455,0.00004510211,0.000007246261,0.000004362346,0.00001557555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5944441,"threshold_uncertainty_score":0.9848409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144168223","doi":"10.1002/sim.5984","title":"The use of propensity score methods with survival or time‐to‐event outcomes: reporting measures of effect similar to those used in randomized experiments","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1441,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Observational study; Marginal structural model; Inverse probability weighting; Medicine; Covariate; Randomized controlled trial; Confounding; Average treatment effect; Statistics; Hazard ratio; Selection bias; Population; Survival analysis; Matching (statistics); Proportional hazards model; Confidence interval; Internal medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4544700176042719,"gpt":0.5290019207742545,"spread":0.0745319031699826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01029026,0.0002563637,0.00198025,0.0001833278,0.0000350234,0.00001110843,0.0002248454,0.00005974404,0.00008089279],"category_scores_gemma":[0.11958,0.0001196134,0.00004162958,0.0003649259,0.0003061056,0.00007398292,0.000121427,0.0002229984,0.000001968204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009655355,"about_ca_system_score_gemma":0.0000781067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006107939,"about_ca_topic_score_gemma":0.0003401974,"domain_scores_codex":[0.9951426,0.001510572,0.002093985,0.0002701264,0.0006896854,0.0002929952],"domain_scores_gemma":[0.9798867,0.01777242,0.00125029,0.0005895777,0.0004021251,0.00009893163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.1520505,0.002317576,0.2100007,0.004554696,0.002069088,0.0008961363,0.05569208,0.002101875,0.3038575,0.04768069,0.01561762,0.2031615],"study_design_scores_gemma":[0.1845281,0.01163768,0.04100255,0.02006637,0.001053832,0.00003748071,0.003192708,0.009401509,0.4417945,0.2845741,0.0004097036,0.002301513],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2638102,0.0000207472,0.7315506,0.0001922975,0.00006227529,0.004237083,0.0000131762,0.00003879833,0.00007485471],"genre_scores_gemma":[0.1291616,0.00001364471,0.8699784,0.00007559598,0.00001119781,0.000459102,0.000004933001,0.00003945955,0.0002560995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2368934,"threshold_uncertainty_score":0.8878361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089198100","doi":"10.1186/1471-2288-8-70","title":"Reducing bias through directed acyclic graphs","year":2008,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1410,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Jewish General Hospital","funders":"McGill University Health Centre; McGill University","keywords":"Directed acyclic graph; Confounding; Causal inference; Selection bias; Computer science; Outcome (game theory); Econometrics; Simple (philosophy); Causality (physics); Statistics; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.9122827611924192,"gpt":0.6583154278917019,"spread":0.2539673333007173,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02556201,0.0002524107,0.0008368503,0.0004186552,0.0003921919,0.00001390556,0.0009846976,0.0006212333,0.001962332],"category_scores_gemma":[0.4471436,0.0002013016,0.0001693329,0.001285538,0.002179991,0.00018524,0.0005874144,0.002021387,0.0001116958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001392263,"about_ca_system_score_gemma":0.00110775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005361075,"about_ca_topic_score_gemma":0.0002615557,"domain_scores_codex":[0.9764681,0.01825425,0.0008217107,0.0007357324,0.00238709,0.00133309],"domain_scores_gemma":[0.8679871,0.1298494,0.0001531977,0.0009571065,0.000520641,0.0005325641],"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":[0.0003792783,0.0005769926,0.003275793,0.0004784398,0.0001194597,0.0008872838,0.004181597,0.000002167448,0.01398497,0.8552887,0.07480704,0.04601822],"study_design_scores_gemma":[0.0004231975,0.0002794605,0.000663108,0.0001834521,0.000009799307,0.0003634564,0.000269678,0.000240079,0.023843,0.9677824,0.00571103,0.0002313476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2453303,0.0004719148,0.7387174,0.0009721924,0.0002521286,0.0006140576,0.000003739343,0.001254038,0.01238432],"genre_scores_gemma":[0.05889649,0.001936481,0.9370844,0.0002279868,0.0002520871,0.0002443778,0.000007158642,0.00006499829,0.001285967],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4215816,"threshold_uncertainty_score":0.99895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964475341","doi":"10.1002/sim.3150","title":"A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003","year":2007,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1250,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Wilcoxon signed-rank test; Statistics; Observational study; Matching (statistics); Selection bias; Logistic regression; Sample size determination; Statistical significance; Medicine; Mathematics; Mann–Whitney U test","retraction":null,"screen_n_in":null,"score":{"opus":0.2610013184506083,"gpt":0.5385518179316583,"spread":0.27755049948105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004457467,0.0004290472,0.002410291,0.0004083482,0.000032494,0.00001425073,0.000513162,0.0005737967,0.00005300863],"category_scores_gemma":[0.04742031,0.000246532,0.00003858292,0.0009533892,0.0008578071,0.00006270395,0.0001562753,0.002370442,0.000001137493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006538287,"about_ca_system_score_gemma":0.0002337297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005021322,"about_ca_topic_score_gemma":0.0001134154,"domain_scores_codex":[0.9960502,0.0005756262,0.001539771,0.0003873369,0.001048189,0.0003988229],"domain_scores_gemma":[0.9787021,0.0201453,0.0003354331,0.0004579554,0.0002300681,0.0001291921],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007285114,0.00008025152,0.0001514409,0.035944,0.00003000337,0.001268713,0.002018572,9.882061e-9,1.762265e-7,0.3921306,0.002840202,0.5655288],"study_design_scores_gemma":[0.0005263903,0.000417791,0.0002226761,0.1696646,0.0006087758,0.0004870286,0.000338661,0.000009597476,7.240726e-7,0.7095591,0.1176234,0.0005413498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002389785,0.8471528,0.1505251,0.0001359911,0.0001819448,0.001004999,0.0002986965,0.00003714857,0.0006393584],"genre_scores_gemma":[0.00009246635,0.8832279,0.1159296,0.00008253232,0.0003303008,0.00005889398,0.0002129339,0.00005266278,0.00001279583],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5649874,"threshold_uncertainty_score":0.9999987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2026656096","doi":"10.1136/bmj.b5087","title":"Problem of immortal time bias in cohort studies: example using statins for preventing progression of diabetes","year":2010,"lang":"en","type":"article","venue":"BMJ","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1155,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Jewish General Hospital; Kingston Health Sciences Centre; McGill University; Queen's University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Diabetes mellitus; Cohort; Internal medicine; Endocrinology","retraction":null,"screen_n_in":null,"score":{"opus":0.2976455350419575,"gpt":0.5009101891130961,"spread":0.2032646540711386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001272051,0.0001088903,0.0003747984,0.00007959049,0.00002487438,0.000004204511,0.0001017828,0.00006309821,0.00001426568],"category_scores_gemma":[0.001331244,0.0000907308,0.00005022518,0.0001218573,0.00008610208,0.0001172951,0.00008495228,0.0001040465,2.83233e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002097135,"about_ca_system_score_gemma":0.00004283669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000015213,"about_ca_topic_score_gemma":0.00004413509,"domain_scores_codex":[0.9988357,0.00004022558,0.0006147408,0.0001523263,0.000163801,0.0001931599],"domain_scores_gemma":[0.9982124,0.0007696557,0.0005863747,0.0002174673,0.0001943766,0.00001971041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002398263,0.0004590472,0.2347204,0.002432319,0.000155881,0.000001389958,0.002113235,0.00003079858,0.7404705,0.007650676,0.0004964605,0.01144527],"study_design_scores_gemma":[0.0005950251,0.0004413583,0.003300564,0.002091522,0.0001138785,0.000001759045,0.0004889728,0.007764402,0.6873403,0.2974395,0.0000895154,0.0003332571],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950122,0.0000307188,0.002873946,0.0000122303,0.00002364144,0.001833592,0.00001471338,0.00005760372,0.000141317],"genre_scores_gemma":[0.5050166,0.000001469437,0.4947321,0.000001802294,0.00001876194,0.0001775902,0.00000387308,0.00001733858,0.0000305698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4918581,"threshold_uncertainty_score":0.3699895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164498941","doi":"10.1002/sim.2580","title":"A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Outcome (game theory); Statistics; Matching (statistics); Medicine; Average treatment effect; Variables; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2043349314626578,"gpt":0.4063998310840797,"spread":0.2020648996214219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005536152,0.00022124,0.001050444,0.0000942553,0.00004009755,0.000004250564,0.0002079884,0.00006638189,0.000005034816],"category_scores_gemma":[0.001339533,0.0001347208,0.00001687129,0.0003598006,0.0003018177,0.00003709603,0.0001091193,0.0002048519,5.270307e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091782,"about_ca_system_score_gemma":0.00003258875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004236729,"about_ca_topic_score_gemma":0.003110834,"domain_scores_codex":[0.9979088,0.0002742489,0.00086632,0.0002780284,0.0004722729,0.0002002989],"domain_scores_gemma":[0.9976801,0.001033451,0.0003561664,0.0005111599,0.0003652949,0.00005382825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001052001,0.0006317322,0.9803109,0.0003217201,0.00004533335,0.000004212744,0.003110252,0.0001714252,0.005874513,0.008849548,0.0002345956,0.0003405868],"study_design_scores_gemma":[0.001400583,0.0009609634,0.6867701,0.0007422187,0.0002353319,6.824714e-7,0.0005533664,0.00375957,0.01028509,0.2951308,6.144638e-7,0.0001606024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9213251,0.00005099085,0.07656187,0.00003576731,0.00002073529,0.001686519,0.0001751684,0.0000431576,0.0001007148],"genre_scores_gemma":[0.9868041,0.000005662152,0.01307546,0.000005283802,0.00001612681,0.00004804089,0.000008825689,0.00001791994,0.00001858672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2935407,"threshold_uncertainty_score":0.6404696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103371988","doi":"10.1002/sim.5705","title":"The performance of different propensity score methods for estimating marginal hazard ratios","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":995,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Odds ratio; Estimator; Matching (statistics); Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.220207531187187,"gpt":0.4904911441960751,"spread":0.2702836130088881,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238949,0.0001514908,0.0003968481,0.00005268499,0.0001149006,0.000005728927,0.0001813139,0.00004535697,0.00002308958],"category_scores_gemma":[0.006526079,0.00008779509,0.00001731552,0.00009666391,0.0002996201,0.00008154345,0.00006211945,0.0002099996,5.209366e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007045359,"about_ca_system_score_gemma":0.00002840429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005186673,"about_ca_topic_score_gemma":0.00001888416,"domain_scores_codex":[0.998678,0.0001365724,0.0005378662,0.0001177051,0.0002152649,0.0003146451],"domain_scores_gemma":[0.9950841,0.004075878,0.0002993941,0.0002889437,0.0001929272,0.00005876641],"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":[0.0001415097,0.0001310219,0.02683964,0.001189853,0.00003550294,0.000001166249,0.00178377,0.00001416456,0.005966098,0.7812556,0.003408749,0.1792329],"study_design_scores_gemma":[0.0009979375,0.0009844513,0.012969,0.00101758,0.0001281161,0.00001373897,0.0002930119,0.08898605,0.02950362,0.8643796,0.0004199635,0.0003068998],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06839165,0.00009420794,0.9301739,0.0001203102,0.0002656203,0.0007133104,0.00001670286,0.00003677284,0.0001874982],"genre_scores_gemma":[0.1917724,0.00004180599,0.807808,0.00002542271,0.0001250119,0.0001122633,0.00001057819,0.00001759673,0.00008695062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.178926,"threshold_uncertainty_score":0.7812798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2404984931","doi":"10.1016/j.jclinepi.2016.04.014","title":"Specifying a target trial prevents immortal time bias and other self-inflicted injuries in observational analyses","year":2016,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":974,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"National Center for Advancing Translational Sciences; National Cancer Institute","keywords":"Observational study; Emulation; Randomized controlled trial; Computer science; Medical physics; Research design; Simple (philosophy); Clinical trial; Medicine; Psychology; Statistics; Social psychology; Surgery; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8894193828691276,"gpt":0.6870352047744127,"spread":0.2023841780947149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03209012,0.0005453135,0.01091304,0.0004618366,0.00003850229,0.0000140979,0.0005590029,0.001273811,0.0003493402],"category_scores_gemma":[0.1817413,0.0003221478,0.00164865,0.0002685804,0.0003237695,0.000255146,0.0002018199,0.0018237,0.00002003887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001367519,"about_ca_system_score_gemma":0.0006435767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004273882,"about_ca_topic_score_gemma":0.000003027041,"domain_scores_codex":[0.975041,0.01126213,0.01241356,0.0004828413,0.0003222349,0.0004781997],"domain_scores_gemma":[0.8614943,0.1249712,0.0126586,0.0004081633,0.0002218118,0.0002458826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.009361404,0.002869226,0.02738507,0.01051036,0.006798446,0.0002627368,0.0001654081,0.000006508214,0.000003683149,0.0641276,0.01662694,0.8618826],"study_design_scores_gemma":[0.005144324,0.001130475,0.0004353772,0.01155969,0.0007072682,0.0001061902,0.000003410881,0.00003764535,6.229564e-7,0.3657453,0.6146924,0.0004372375],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.003012915,0.9862737,0.007548017,0.0003645431,0.0008503029,0.001386047,0.0001015147,0.0001103379,0.0003526204],"genre_scores_gemma":[0.00001609266,0.8535389,0.1441202,0.0003103035,0.001753426,0.00003521402,0.000008386639,0.00006459206,0.0001529369],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8614454,"threshold_uncertainty_score":0.9999231,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2132557528","doi":"10.3386/w13039","title":"Regression Discontinuity Designs: A Guide to Practice","year":2007,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":888,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Regression discontinuity design; Discontinuity (linguistics); Regression; Computer science; Econometrics; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.7507059545647676,"gpt":0.6941272470872978,"spread":0.05657870747746985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02445607,0.0003337458,0.0007965141,0.001347893,0.0001314643,0.00007266113,0.0008627385,0.0006257439,0.0004412702],"category_scores_gemma":[0.06483965,0.0003031183,0.0001837189,0.0003301679,0.0002334309,0.0004412656,0.000522326,0.001303376,0.0001690454],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004997009,"about_ca_system_score_gemma":0.00478812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008760396,"about_ca_topic_score_gemma":0.0003015001,"domain_scores_codex":[0.9936811,0.0004024412,0.001435754,0.0007354275,0.003119947,0.0006252917],"domain_scores_gemma":[0.9806991,0.01071965,0.0008849268,0.0007478274,0.006725609,0.0002228638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001188849,0.0001329405,0.00002947833,0.0001864643,0.00009513156,0.00001631859,0.00007748792,0.00001069608,0.0004451977,0.4108363,0.5822608,0.005790293],"study_design_scores_gemma":[0.0001373151,0.0001624188,0.00001493664,0.0006222129,0.00002027394,0.00004268993,0.0001034387,0.0000160697,0.004538856,0.7317032,0.2623844,0.0002541874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.0001663278,0.0002833837,0.01216034,0.001094357,0.0003606461,0.001642371,0.00009442776,0.0001202532,0.9840779],"genre_scores_gemma":[0.0369756,0.002913467,0.7851505,0.0002316828,0.003513223,0.001009534,0.0004886449,0.0003892405,0.1693282],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8147497,"threshold_uncertainty_score":0.9999421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127992265","doi":"10.1093/ije/dyp334","title":"Illustrating bias due to conditioning on a collider","year":2009,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":823,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism","keywords":"Collider; Conditioning; Selection bias; Outcome (game theory); Selection (genetic algorithm); Association (psychology); Confounding; Computer science; Physics; Statistics; Psychology; Mathematics; Artificial intelligence; Particle physics; Mathematical economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3891479896255752,"gpt":0.5215592792262753,"spread":0.1324112896007001,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002267123,0.0001235073,0.0004270769,0.0002662922,0.00003654045,0.00001346743,0.0003678046,0.00009397934,0.0001619618],"category_scores_gemma":[0.03014813,0.000100953,0.0001217743,0.00007992604,0.00004520576,0.000154669,0.00002730338,0.0003367775,0.00001985266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001721342,"about_ca_system_score_gemma":0.00005303048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004813162,"about_ca_topic_score_gemma":0.000004773176,"domain_scores_codex":[0.9981607,0.0002907715,0.0009883657,0.0001338982,0.0002227035,0.0002035948],"domain_scores_gemma":[0.9928593,0.005490249,0.000834112,0.0001198326,0.0005848572,0.0001116413],"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":[0.0001499207,0.0001209402,0.001022933,0.000002747648,0.00009592211,0.0002884699,0.0001953756,0.001167174,0.002382269,0.9505446,0.02412483,0.01990483],"study_design_scores_gemma":[0.000259519,0.0007999248,0.002707277,0.0002309211,0.00001068895,0.0008067984,0.00006541292,0.0001538278,0.002603756,0.9889048,0.003342835,0.0001142691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3230953,0.00005061262,0.6410537,0.02683116,0.0009044595,0.0001916931,0.0000158373,0.00009165047,0.007765565],"genre_scores_gemma":[0.7786908,0.000011827,0.2121663,0.008557294,0.0004680119,0.000003297201,0.000002752326,0.000008623457,0.00009107568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4555955,"threshold_uncertainty_score":0.9780213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393132304","doi":"10.1016/j.envint.2024.108602","title":"A tool to assess risk of bias in non-randomized follow-up studies of exposure effects (ROBINS-E)","year":2024,"lang":"en","type":"article","venue":"Environment International","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":806,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Cochrane; McMaster University; Ottawa Hospital; Impact","funders":"Medical Research Council; National Institute of Environmental Health Sciences; National Institute for Health and Care Research; National Institutes of Health; Cancer Research UK; CHDI Foundation; National Council for Air and Stream Improvement; NIHR Bristol Biomedical Research Centre; United Soybean Board","keywords":"Randomized controlled trial; Environmental health; Environmental science; Medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1252290287888377,"gpt":0.4028231892404779,"spread":0.2775941604516402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009781662,0.0001513708,0.000486065,0.0002050435,0.00001051445,0.000008858913,0.0001941314,0.00005443869,0.0001242803],"category_scores_gemma":[0.001942199,0.0001227698,0.0001466754,0.00008213105,0.0001120224,0.00008927067,0.0001590995,0.0001382894,0.00001927942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001687247,"about_ca_system_score_gemma":0.00001300076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001222278,"about_ca_topic_score_gemma":0.000006916503,"domain_scores_codex":[0.9986017,0.0001346604,0.0005435788,0.0002115305,0.0003960261,0.0001125427],"domain_scores_gemma":[0.9968545,0.00272239,0.0001744265,0.0001979189,0.00002847739,0.00002222618],"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":[0.01433589,0.002666828,0.03174265,0.003935367,0.007156226,0.0001795169,0.03528987,0.007473036,0.2299486,0.6161821,0.008145136,0.04294479],"study_design_scores_gemma":[0.03230687,0.0006607444,0.005584974,0.003252706,0.0003583632,0.000005187832,0.0008200507,0.002783343,0.3658728,0.5863158,0.001368406,0.00067073],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9409434,0.0002154607,0.05709168,0.0000870427,0.0003431297,0.0007042056,0.00004554579,0.00004736227,0.0005222074],"genre_scores_gemma":[0.9564459,0.0003662582,0.04219811,0.00001979987,0.00003322241,0.0002753848,0.000006648548,0.00001998069,0.0006346928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1359242,"threshold_uncertainty_score":0.5006406,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142912667","doi":"10.1001/jama.297.3.278","title":"Analysis of Observational Studies in the Presence of Treatment Selection Bias","year":2007,"lang":"en","type":"article","venue":"JAMA","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":788,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Sciences Centre; St. Michael's Hospital; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; University of Toronto; York University","funders":"National Institute on Aging; Institute for Clinical Evaluative Sciences; Canadian Institutes of Health Research; Dartmouth College","keywords":"Medicine; Propensity score matching; Relative risk; Observational study; Confidence interval; Cardiac catheterization; Myocardial infarction; Selection bias; Internal medicine; Proportional hazards model; Cohort study; Emergency medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5264523418573861,"gpt":0.503462976493724,"spread":0.02298936536366214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006521916,0.00005280942,0.0001950491,0.000155193,0.00001358131,0.000002300932,0.00007424925,0.00003020831,0.000009711655],"category_scores_gemma":[0.001106905,0.00003276918,0.00005379601,0.0008318945,0.00005410615,0.00007312596,0.00001222766,0.00003794679,1.895984e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008873458,"about_ca_system_score_gemma":0.00001609191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006307025,"about_ca_topic_score_gemma":0.000705148,"domain_scores_codex":[0.9994014,0.00004853404,0.0002672725,0.00006925028,0.0001435633,0.00007000498],"domain_scores_gemma":[0.9976583,0.001870205,0.0001647002,0.0001309093,0.0001699297,0.000005996869],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000134595,0.0008956597,0.6313767,0.0001659741,0.001820646,0.000006226914,0.0323463,0.001429483,0.01197232,0.2937399,0.0006182211,0.02549391],"study_design_scores_gemma":[0.0005323663,0.0007298699,0.5832627,0.0001241828,0.0008384659,0.000002747142,0.004968049,0.003462856,0.1540957,0.251352,0.0004573271,0.0001737361],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895404,0.00005252231,0.009656651,0.00009145017,0.00000842369,0.0001392275,0.000003948313,0.00001891008,0.0004884882],"genre_scores_gemma":[0.982464,0.00004884345,0.0173675,0.00001885438,0.00001264261,0.00001765943,0.000002762561,0.000002589169,0.00006514241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1421234,"threshold_uncertainty_score":0.1336288,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016403661","doi":"10.1002/bimj.200810488","title":"Some Methods of Propensity‐Score Matching had Superior Performance to Others: Results of an Empirical Investigation and Monte Carlo simulations","year":2009,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":769,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Statistics; Monte Carlo method; Matching (statistics); Standard deviation; Logit; Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.374473599393049,"gpt":0.4837530024844751,"spread":0.109279403091426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143927,0.0001441752,0.000403316,0.001016668,0.00009120425,0.0000436814,0.0001857574,0.0001115364,0.000003976335],"category_scores_gemma":[0.002274567,0.000112685,0.00005423292,0.001500137,0.00009686274,0.0006140191,0.0000514174,0.0002613492,3.768705e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007911846,"about_ca_system_score_gemma":0.00006110704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001297406,"about_ca_topic_score_gemma":0.000001674067,"domain_scores_codex":[0.9982947,0.0002146791,0.0007475152,0.0001862461,0.0003594303,0.0001974513],"domain_scores_gemma":[0.9983543,0.0005239095,0.0003485568,0.0002251543,0.000304389,0.0002437187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007675074,0.0007556958,0.02281027,0.0001920886,0.00009058374,0.00002144319,0.007186863,0.001493972,0.6800453,0.002094366,0.0003360543,0.2842058],"study_design_scores_gemma":[0.001950689,0.006273846,0.2810068,0.0007031971,0.0001385465,0.000245674,0.0003950355,0.01346501,0.4268679,0.2680264,0.0002131896,0.0007136629],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9511,0.00007823835,0.04814072,0.0003427393,0.00002936921,0.0002271633,0.00001521762,0.00004474408,0.00002184542],"genre_scores_gemma":[0.6206691,0.00001876545,0.3791653,0.00007651695,0.00005013349,0.000001039903,7.898624e-7,0.00000890998,0.000009400995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3310246,"threshold_uncertainty_score":0.4595162,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013188809","doi":"10.1023/b:ejep.0000036568.02655.f8","title":"Loss to Follow-Up in Cohort Studies: How Much is Too Much?","year":2004,"lang":"en","type":"article","venue":"European Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":732,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Institute for Work & Health; University of Toronto","funders":"","keywords":"Medicine; Confounding; Cohort; Logistic regression; Missing data; Cohort study; Odds; Statistics; Demography; Internal medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3441335696772531,"gpt":0.4711298412925512,"spread":0.1269962716152981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01025339,0.0002846857,0.001242563,0.0003170093,0.00005618238,0.000009558556,0.0005831398,0.00007461091,0.00003650262],"category_scores_gemma":[0.03556694,0.0002236029,0.0002168634,0.000275594,0.0001906999,0.000211053,0.0002071498,0.0006850924,0.00006671785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003161662,"about_ca_system_score_gemma":0.00006776921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005607847,"about_ca_topic_score_gemma":0.00001517928,"domain_scores_codex":[0.9955139,0.001760663,0.001619036,0.0003326263,0.0001881159,0.0005856175],"domain_scores_gemma":[0.9951249,0.002784078,0.0009817587,0.0004643176,0.0004086884,0.0002362992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007762179,0.0006620988,0.09914224,0.0002998969,0.001623353,0.007088516,0.01595753,0.0006341856,0.004587366,0.3639541,0.488837,0.01643752],"study_design_scores_gemma":[0.001887667,0.00178103,0.006773563,0.0006704708,0.00009847148,0.0006945743,0.001519997,0.000005992219,0.002252488,0.959958,0.02388141,0.0004763966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7380667,0.001138664,0.2298757,0.02672141,0.0007697392,0.0004171177,0.000007579254,0.0001133914,0.002889652],"genre_scores_gemma":[0.7644584,0.0009640883,0.2272648,0.006252035,0.0003373348,0.00000653146,9.494098e-7,0.00006926597,0.0006466151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5960038,"threshold_uncertainty_score":0.9725569,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891367027","doi":"10.1513/annalsats.201808-564ps","title":"Control of Confounding and Reporting of Results in Causal Inference Studies. Guidance for Authors from Editors of Respiratory, Sleep, and Critical Care Journals","year":2018,"lang":"en","type":"article","venue":"Annals of the American Thoracic Society","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":722,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; McGill University; Queen's University","funders":"","keywords":"Confounding; Causal inference; Fallacy; Medicine; Statistics; Econometrics; Computer science; Mathematics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.4090745820242512,"gpt":0.5752142049379743,"spread":0.166139622913723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003244587,0.0001678961,0.001087546,0.00005316755,0.00007526111,0.000007802851,0.0002218462,0.00008316092,0.000001114901],"category_scores_gemma":[0.03851728,0.0001283726,0.0001680779,0.0002962493,0.002606359,0.000131612,0.0001633045,0.0001896224,2.063223e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002541624,"about_ca_system_score_gemma":0.00008959942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001817961,"about_ca_topic_score_gemma":0.00002942735,"domain_scores_codex":[0.996946,0.0002322928,0.002008077,0.0002525848,0.0003251634,0.0002359265],"domain_scores_gemma":[0.9878831,0.004551752,0.005291191,0.0004241725,0.001791494,0.00005829768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00314799,0.0005016191,0.3777197,0.00667416,0.001763653,0.000007256651,0.1005853,0.00003928516,0.4189281,0.01381814,0.01064688,0.06616782],"study_design_scores_gemma":[0.0009826,0.002172706,0.04006404,0.00449541,0.0003023242,0.000003541043,0.04275474,0.0006633901,0.7377562,0.1701538,0.0001956394,0.000455638],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862588,0.0011631,0.01132954,0.0004897464,0.0001558401,0.000350454,0.0002059409,0.00001788526,0.00002870082],"genre_scores_gemma":[0.9644642,0.0001322245,0.03506736,0.0001144199,0.0001854881,0.00001730054,5.731508e-7,0.0000163811,0.000001981089],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3376557,"threshold_uncertainty_score":0.9695817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024692342","doi":"10.1016/j.jeconom.2003.10.006","title":"How robust is the evidence on the effects of college quality? Evidence from matching","year":2004,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":690,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Propensity score matching; Matching (statistics); Regression; Quality (philosophy); Linear regression; Econometrics; Statistics; Average treatment effect; Regression analysis; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4967390886913728,"gpt":0.404828367581793,"spread":0.09191072110957987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002633582,0.0001879088,0.0005086945,0.0003634958,0.0001150842,0.0001069487,0.0009565149,0.00009484625,0.00003520352],"category_scores_gemma":[0.0324829,0.0001033612,0.0002429394,0.0009733664,0.0001204733,0.0008841354,0.0001145935,0.0005768527,0.000004991183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000315695,"about_ca_system_score_gemma":0.0001353423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000471716,"about_ca_topic_score_gemma":0.00001372034,"domain_scores_codex":[0.9981328,0.0002129163,0.0007965499,0.0001635355,0.0004892945,0.0002048821],"domain_scores_gemma":[0.9650238,0.03218746,0.001786345,0.0006018748,0.0003258791,0.00007462104],"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":[0.0004860657,0.001129038,0.007403784,0.001857599,0.001036422,0.0001768603,0.0132976,0.002124763,0.02140061,0.923811,0.0148099,0.01246641],"study_design_scores_gemma":[0.0003322153,0.0007881402,0.003327922,0.003975176,0.0001157035,0.00002312917,0.001245912,0.00002191436,0.07889389,0.9109238,0.0001374817,0.0002146816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8559704,0.002966454,0.1287681,0.01137601,0.0003171454,0.0004240485,0.00001676574,0.00002559273,0.0001354523],"genre_scores_gemma":[0.9658851,0.001828101,0.03148984,0.0005393606,0.0001461765,0.000008507458,9.38438e-8,0.00002174128,0.00008107806],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1099147,"threshold_uncertainty_score":0.9756669,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160704894","doi":"10.1093/aje/kwq224","title":"Statistical Criteria for Selecting the Optimal Number of Untreated Subjects Matched to Each Treated Subject When Using Many-to-One Matching on the Propensity Score","year":2010,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":667,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; University of Toronto","keywords":"Propensity score matching; Matching (statistics); Statistics; Estimator; Mathematics; Average treatment effect; Mean squared error; Observational study; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.260989989819204,"gpt":0.4622396814012198,"spread":0.2012496915820159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005872954,0.0002873203,0.001321939,0.0001310195,0.0001778685,0.00002021042,0.0005085837,0.0001004099,0.000108376],"category_scores_gemma":[0.02034611,0.000161861,0.0001474524,0.0003321702,0.0004485101,0.00009075017,0.0001115605,0.0008208113,0.000004631846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106209,"about_ca_system_score_gemma":0.0001172874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006456391,"about_ca_topic_score_gemma":0.00008556018,"domain_scores_codex":[0.9962854,0.001423918,0.001215684,0.0002943371,0.0001874767,0.0005931241],"domain_scores_gemma":[0.9803085,0.01710488,0.001385066,0.0004552908,0.0005568991,0.0001894178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.006686277,0.0007022626,0.1190044,0.00017876,0.001055902,0.00006067632,0.008694569,0.001097197,0.5853264,0.2574809,0.003897486,0.01581523],"study_design_scores_gemma":[0.001283118,0.007743077,0.02861985,0.0009775439,0.0007506247,0.001856074,0.002565172,0.003578674,0.09145886,0.8598849,0.0002104436,0.00107168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6153524,0.000001993604,0.3826931,0.001322681,0.00005698466,0.0004749827,0.00001769432,0.0000282088,0.0000519209],"genre_scores_gemma":[0.5916402,0.000001719339,0.4075346,0.0006674203,0.00009673699,0.00001487354,0.000001812793,0.00003357015,0.000009093868],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.602404,"threshold_uncertainty_score":0.9879059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051866975","doi":"10.1016/j.jtcvs.2007.07.021","title":"Propensity-score matching in the cardiovascular surgery literature from 2004 to 2006: A systematic review and suggestions for improvement","year":2007,"lang":"en","type":"review","venue":"Journal of Thoracic and Cardiovascular Surgery","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":598,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Systematic review; Matching (statistics); Medicine; MEDLINE; General surgery; Surgery; Political science; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.19215338945083,"gpt":0.4069807759266218,"spread":0.2148273864757918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02690726,0.0007910269,0.01030402,0.0007933798,0.0001544646,0.0002450972,0.0004244318,0.000438031,0.000002726453],"category_scores_gemma":[0.004179604,0.0004748191,0.007181368,0.0009147411,0.00006598463,0.0003424745,0.0001491945,0.001115575,0.000001295338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001862367,"about_ca_system_score_gemma":0.0003088178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002894009,"about_ca_topic_score_gemma":0.000006260065,"domain_scores_codex":[0.9931009,0.0018202,0.002819342,0.0005865056,0.001144962,0.0005280225],"domain_scores_gemma":[0.9902063,0.006190157,0.001313407,0.001457147,0.0006099101,0.0002230858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001238314,0.00004851503,0.000006044088,0.6770965,0.005447245,0.0004684678,0.0001675296,0.000002780814,2.020414e-7,0.00004481219,0.001528146,0.3151774],"study_design_scores_gemma":[0.00007293532,0.00004621126,0.000007900733,0.864713,0.03656936,0.002744074,0.0001073331,3.452639e-7,0.000003732725,0.004167664,0.09081151,0.0007559588],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001427442,0.9508514,0.04381116,0.00005606207,0.0002178087,0.004761902,0.0001156812,0.00003498262,0.000008235802],"genre_scores_gemma":[0.00006971319,0.9943367,0.004271526,0.0002316323,0.0003378306,0.0005868983,0.00003852457,0.0001075412,0.00001958776],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.3144214,"threshold_uncertainty_score":0.9997703,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117317003","doi":"10.1002/pds.1357","title":"Immortal time bias in observational studies of drug effects","year":2007,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":569,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; AstraZeneca","keywords":"Medicine; Observational study; Pharmacoepidemiology; COPD; Cohort study; Drug; Disease; Pulmonary disease; Cohort; Internal medicine; Intensive care medicine; Pharmacology; Medical prescription","retraction":null,"screen_n_in":null,"score":{"opus":0.3359460404749271,"gpt":0.5112862260978849,"spread":0.1753401856229578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008221722,0.0001970854,0.0007125695,0.0001234775,0.00006125669,0.00000114026,0.0001233038,0.00008297856,0.0000361587],"category_scores_gemma":[0.007318458,0.0001640924,0.00006685915,0.0001705037,0.0003183165,0.0001492617,0.0001163787,0.0003040052,0.000005229092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005451572,"about_ca_system_score_gemma":0.00002199397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002300269,"about_ca_topic_score_gemma":0.00004878816,"domain_scores_codex":[0.9977756,0.0006608873,0.0008602929,0.0002658547,0.0001037413,0.0003336395],"domain_scores_gemma":[0.9716604,0.02771648,0.0003157487,0.0001460195,0.00009500494,0.00006640219],"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":[0.0009593146,0.0004829973,0.4361809,0.001274171,0.0004395365,0.00009947551,0.004237107,0.0001302521,0.0226366,0.4913902,0.0220158,0.02015367],"study_design_scores_gemma":[0.001604571,0.00007407402,0.1053898,0.0002813255,0.0001098654,0.00002306991,0.0003021108,0.001498398,0.04361384,0.845219,0.001423217,0.0004606792],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9831476,0.002785048,0.01071657,0.001215755,0.0001709045,0.0004618569,0.00001332902,0.0001565503,0.001332427],"genre_scores_gemma":[0.9645533,0.000734821,0.03349514,0.0007918515,0.00007773558,0.00002672752,0.00001363172,0.00001688944,0.0002899187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3538289,"threshold_uncertainty_score":0.8761407,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102520493","doi":"10.1002/sim.2328","title":"A comparison of propensity score methods: a case‐study estimating the effectiveness of post‐AMI statin use","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":565,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Statin; Statistics; Medicine; Internal medicine; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3195657084475746,"gpt":0.5520056064708857,"spread":0.2324398980233111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005197028,0.000201513,0.0009233155,0.0001338412,0.00005890257,0.000006593456,0.0002066477,0.00005223488,0.00002329173],"category_scores_gemma":[0.01845002,0.0001294161,0.00002128836,0.000323946,0.0004314344,0.00009708928,0.000118625,0.0003791928,4.534697e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008125761,"about_ca_system_score_gemma":0.00005906859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001193474,"about_ca_topic_score_gemma":0.000830774,"domain_scores_codex":[0.9965876,0.00158168,0.001004126,0.000230627,0.0003880798,0.0002078408],"domain_scores_gemma":[0.9805859,0.01777619,0.0005787362,0.0004905913,0.0005275191,0.00004100895],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00120939,0.004826003,0.397978,0.006228888,0.000403155,0.001375217,0.08864853,0.002946229,0.0405375,0.2752811,0.0009364065,0.1796295],"study_design_scores_gemma":[0.006051955,0.009193189,0.09257529,0.006477603,0.0009334239,0.0007021175,0.04045672,0.1165814,0.05513364,0.670894,0.00002878201,0.0009719493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4748936,0.00002601211,0.5240141,0.00001521492,0.00003342237,0.0009111875,0.00003780118,0.00002742925,0.00004127967],"genre_scores_gemma":[0.5095511,0.000001223515,0.4903658,0.000009849728,0.00001583001,0.0000337941,0.0000050744,0.00001414598,0.00000318943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3956128,"threshold_uncertainty_score":0.989818,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063548620","doi":"10.1016/j.jclinepi.2004.10.016","title":"Propensity score methods gave similar results to traditional regression modeling in observational studies: a systematic review","year":2005,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":497,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences","funders":"","keywords":"Propensity score matching; Observational study; Confounding; Medicine; Odds ratio; Statistics; Regression analysis; Hazard ratio; Confidence interval; Internal medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.9794651742196404,"gpt":0.7432106376404088,"spread":0.2362545365792316,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1539406,0.0007703802,0.02802663,0.000442475,0.00006792699,0.000008690608,0.00105748,0.001108347,0.0000200442],"category_scores_gemma":[0.7218381,0.0004453543,0.00273617,0.0005585724,0.0001885702,0.0002682251,0.0002865857,0.003657988,0.00001330534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005815147,"about_ca_system_score_gemma":0.001017951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001339391,"about_ca_topic_score_gemma":0.000007855634,"domain_scores_codex":[0.9296362,0.03670861,0.03147855,0.0008736961,0.0006791626,0.0006237342],"domain_scores_gemma":[0.7050266,0.2670707,0.02424546,0.001225685,0.001889281,0.0005423374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0001443627,0.0003804039,0.000008518411,0.8017644,0.0007723976,0.0001139093,0.00005016094,0.0001886273,5.110324e-8,0.01413237,0.01195815,0.1704866],"study_design_scores_gemma":[0.0002761305,0.0004171562,0.00000324091,0.786927,0.001795257,0.0003395319,0.000008575838,0.0005853752,4.650059e-8,0.1885306,0.02076584,0.0003512391],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004944319,0.9073538,0.08646218,0.002881074,0.0004685654,0.002688844,0.00004521265,0.00004040225,0.00005503268],"genre_scores_gemma":[7.95075e-7,0.6119496,0.3849775,0.002234484,0.0006066497,0.000140476,0.00001754413,0.00003995965,0.00003304692],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5678974,"threshold_uncertainty_score":0.9997998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2609185034","doi":"10.1186/s12874-017-0338-0","title":"Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":491,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"University of Oxford; Cancer Research UK","keywords":"Covariate; Propensity score matching; Confounding; Statistics; Residual; Matching (statistics); Logistic regression; Regression; Mathematics; Regression analysis; Econometrics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.8896096151371321,"gpt":0.6436425630183503,"spread":0.2459670521187818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04284102,0.0002378853,0.001141047,0.0005774823,0.000538384,0.0001185988,0.001216027,0.0004211147,0.0001274519],"category_scores_gemma":[0.1008581,0.0001967548,0.000162395,0.0003440469,0.0009582182,0.0002617346,0.001080059,0.00141144,0.000005351801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003179928,"about_ca_system_score_gemma":0.0008763894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007958629,"about_ca_topic_score_gemma":0.01271188,"domain_scores_codex":[0.9930576,0.002807129,0.000785624,0.000777531,0.001409492,0.001162588],"domain_scores_gemma":[0.9699904,0.02756566,0.0003175496,0.00136684,0.0003975896,0.0003619612],"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":[0.003787212,0.0005952665,0.1492941,0.002255698,0.0007084965,0.0005073908,0.002677052,0.000159596,0.01300951,0.8007784,0.002010536,0.02421677],"study_design_scores_gemma":[0.00201424,0.0002091713,0.03084219,0.0006806706,0.0001047635,0.00002907747,0.0004129297,0.001847048,0.01263102,0.9508296,0.00009583295,0.0003034397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3953219,0.0001911004,0.6014486,0.0008138763,0.0001031759,0.001165744,0.000004344708,0.0001086268,0.0008426167],"genre_scores_gemma":[0.3769965,0.0001254387,0.6218768,0.00008545961,0.0002085438,0.0005257433,0.000005235831,0.00003314762,0.0001431428],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1500512,"threshold_uncertainty_score":0.9855966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119863846","doi":"10.1016/j.jclinepi.2014.12.018","title":"Interrupted time series analysis in drug utilization research is increasing: systematic review and recommendations","year":2015,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":486,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; St. Michael's Hospital; University of Toronto","funders":"","keywords":"Interrupted time series; Interrupted Time Series Analysis; Medicine; MEDLINE; Systematic review; Psychological intervention; Meta-analysis; Research design; Statistics; Pathology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8623636112980363,"gpt":0.7162576385668367,"spread":0.1461059727311996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1857933,0.0003980188,0.01983804,0.001321471,0.00005174677,0.00001927081,0.0006868938,0.0007414176,0.0001746728],"category_scores_gemma":[0.4634458,0.0002624571,0.001321071,0.00177174,0.0003906487,0.0002910451,0.0003046108,0.002848029,0.00002588388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002776845,"about_ca_system_score_gemma":0.0005551816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001996785,"about_ca_topic_score_gemma":0.00003347622,"domain_scores_codex":[0.9277359,0.05629213,0.01474017,0.0004573537,0.0003621018,0.0004123439],"domain_scores_gemma":[0.8437547,0.1411545,0.01220357,0.0008564668,0.001669757,0.0003610529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00004736955,0.0003247921,0.0002526049,0.8643678,0.003177988,0.00003295381,0.0001351225,3.338917e-7,1.444656e-8,0.01170119,0.04924131,0.07071853],"study_design_scores_gemma":[0.0001828939,0.0003678944,0.00001103792,0.579801,0.01794176,0.00035841,0.00006079323,0.00005926472,4.66222e-8,0.2225594,0.1783232,0.0003343227],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003890196,0.9927569,0.003118077,0.002465117,0.00009383719,0.001269976,0.00002504228,0.00002957967,0.0002375769],"genre_scores_gemma":[0.000004125514,0.9667422,0.03216314,0.0004649919,0.0001079019,0.00006633176,0.00003781709,0.00003800928,0.000375436],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2845668,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158460222","doi":"10.1177/0272989x09341755","title":"The Relative Ability of Different Propensity Score Methods to Balance Measured Covariates Between Treated and Untreated Subjects in Observational Studies","year":2009,"lang":"en","type":"article","venue":"Medical Decision Making","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":456,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Covariate; Statistics; Observational study; Inverse probability weighting; Weighting; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4399813510196111,"gpt":0.5151726562683904,"spread":0.07519130524877926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003171956,0.000192428,0.0006584102,0.00008431691,0.0001423613,0.00001455837,0.000233614,0.000155353,0.00001094927],"category_scores_gemma":[0.06082897,0.0001089966,0.0000436767,0.0004450858,0.0001962963,0.0001081311,0.0001788584,0.0003462847,5.832123e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001639239,"about_ca_system_score_gemma":0.00004930103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007983872,"about_ca_topic_score_gemma":0.0000727966,"domain_scores_codex":[0.9972337,0.0007146614,0.0007686635,0.000324212,0.0007173566,0.0002414251],"domain_scores_gemma":[0.9799435,0.01901354,0.0002406182,0.0003129677,0.0003964712,0.00009297119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000550431,0.0002041216,0.5170233,0.00009579607,0.000130781,0.00002638149,0.002262875,0.000004978218,0.004319331,0.07273739,0.0001806051,0.4024641],"study_design_scores_gemma":[0.0002366698,0.0001218855,0.4817345,0.0007924183,0.00001784219,7.830027e-7,0.00003355814,0.0001983079,0.002242804,0.5145416,0.000006351394,0.00007327541],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7554493,0.0001682441,0.2431628,0.0005098166,0.00002829184,0.000562806,0.000002969732,0.00006567833,0.00005006706],"genre_scores_gemma":[0.8561302,0.00006013981,0.1436714,0.00007800737,0.00001832942,0.00002335976,0.000001626554,0.000008071373,0.000008924541],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4418042,"threshold_uncertainty_score":0.947082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065417422","doi":"10.1080/00273171.2011.540480","title":"A Tutorial and Case Study in Propensity Score Analysis: An Application to Estimating the Effect of In-Hospital Smoking Cessation Counseling on Mortality","year":2011,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":421,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; U.S. Public Health Service; Ontario Ministry of Health and Long-Term Care","keywords":"Propensity score matching; Covariate; Medicine; Inverse probability weighting; Observational study; Matching (statistics); Statistics; Internal medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4995694276247035,"gpt":0.5544291490721748,"spread":0.05485972144747131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006843336,0.0001506863,0.0003569563,0.0004244487,0.0001368357,0.00004745501,0.0002113471,0.00008689401,0.000003528379],"category_scores_gemma":[0.0008383679,0.0001084102,0.00002990818,0.001062818,0.00008308078,0.0002450204,0.000151126,0.0005047229,5.081051e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001890487,"about_ca_system_score_gemma":0.00003247305,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03805458,"about_ca_topic_score_gemma":0.009327245,"domain_scores_codex":[0.9972368,0.001003776,0.0004588662,0.000428029,0.0005897137,0.0002828545],"domain_scores_gemma":[0.998486,0.0005390567,0.0001426994,0.0005233588,0.000242203,0.00006671725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002331233,0.001100667,0.967175,0.00003574015,0.00002447813,0.0001711283,0.02317357,0.0002554865,0.001802423,0.0002598886,2.673197e-7,0.005768243],"study_design_scores_gemma":[0.001454871,0.005623821,0.9465007,0.0001685695,0.0002674859,0.000006815613,0.004069903,0.02841226,0.008239657,0.004967135,1.105142e-7,0.0002886671],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893692,0.000001259569,0.007351854,0.000003693949,0.00002982535,0.003186126,0.000004877449,0.00004452715,0.000008693598],"genre_scores_gemma":[0.9944463,2.407144e-7,0.004876202,7.645751e-7,0.00002559479,0.0006285615,0.000004531065,0.00001695239,8.096209e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02872733,"threshold_uncertainty_score":0.9683511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153434255","doi":"10.1111/j.1524-4733.2009.00600.x","title":"Good Research Practices for Comparative Effectiveness Research: Defining, Reporting and Interpreting Nonrandomized Studies of Treatment Effects Using Secondary Data Sources: The ISPOR Good Research Practices for Retrospective Database Analysis Task Force Report—Part I","year":2009,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":410,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"","keywords":"Comparative effectiveness research; Observational study; Medicine; Outcomes research; Research design; MEDLINE; Management science; Medical education; Alternative medicine; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.827067872307364,"gpt":0.6782163137175784,"spread":0.1488515585897856,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1703659,0.0004028337,0.002290116,0.001218444,0.00163522,0.0002028625,0.0007549578,0.0001686395,0.000002235931],"category_scores_gemma":[0.3116762,0.0002900872,0.0001837129,0.00250928,0.0008320709,0.001152952,0.0007538841,0.001557724,3.187793e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001761146,"about_ca_system_score_gemma":0.001718913,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006890359,"about_ca_topic_score_gemma":0.001891243,"domain_scores_codex":[0.9762794,0.01559413,0.003201846,0.001880003,0.001538016,0.001506551],"domain_scores_gemma":[0.7264202,0.252839,0.01340293,0.003115965,0.003969515,0.0002524306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.09459944,0.0143994,0.1040188,0.0687189,0.02872767,0.001376814,0.3522241,0.007810514,0.05414745,0.2380055,0.004931037,0.03104039],"study_design_scores_gemma":[0.0207829,0.03176702,0.002918644,0.02324623,0.00267985,0.0003799964,0.1511343,0.1918347,0.05089434,0.520071,0.002648391,0.001642618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9424095,0.008197349,0.03010726,0.001198715,0.0001127337,0.01694829,0.0004557657,0.0001266617,0.000443727],"genre_scores_gemma":[0.8918738,0.0009105022,0.1052569,0.00002053708,0.0001224908,0.001512845,0.0001695108,0.00005444955,0.00007896379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2820656,"threshold_uncertainty_score":0.9999551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133554893","doi":"10.1111/j.1467-985x.2012.01032.x","title":"Experimental Designs for Identifying Causal Mechanisms","year":2012,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":407,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Causality (physics); Imperfect; Causation; Computer science; Causal model; Causal inference; Process (computing); Criticism; Key (lock); Natural (archaeology); Black box; Data science; Cognitive psychology; Psychology; Management science; Artificial intelligence; Epistemology; Econometrics; Engineering; Mathematics; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1689160987547828,"gpt":0.425026705623513,"spread":0.2561106068687302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001624352,0.0003421501,0.0006187377,0.00002260399,0.0003537333,0.00009851739,0.0005149151,0.0002338986,0.000162631],"category_scores_gemma":[0.001484004,0.0002589815,0.000504908,0.0002155457,0.0004340156,0.0003764905,0.0002309766,0.0007144209,0.000002191134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006703763,"about_ca_system_score_gemma":0.0001432532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001155401,"about_ca_topic_score_gemma":0.000007733289,"domain_scores_codex":[0.9970366,0.0001677057,0.001083239,0.0002052313,0.0007328879,0.0007742786],"domain_scores_gemma":[0.9959007,0.002540703,0.0007461417,0.0002715101,0.0003059574,0.0002349947],"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":[0.0000866391,0.0003974056,0.0002371911,0.0002252517,0.0001822136,0.000005756658,0.003814473,0.00005277342,0.003902301,0.9099831,0.0806622,0.0004507175],"study_design_scores_gemma":[0.0009192352,0.0004094917,0.0004265309,0.0001573003,0.0001970395,0.00004761825,0.00621684,0.002398155,0.01684838,0.9703245,0.001626989,0.0004279215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00254904,0.0002646489,0.9952503,0.0001592401,0.0007716513,0.0004961493,0.000376495,0.00004581081,0.00008666205],"genre_scores_gemma":[0.1740871,0.00003849527,0.8248705,0.0002512932,0.0002777925,0.000051086,0.000007020929,0.00006517523,0.00035152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.171538,"threshold_uncertainty_score":0.9999862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1988221738","doi":"10.1080/00273171.2010.498292","title":"Assessing Mediational Models: Testing and Interval Estimation for Indirect Effects","year":2010,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":398,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov chain Monte Carlo; Bootstrapping (finance); Computer science; Type I and type II errors; Bayesian probability; Statistics; Confidence interval; Statistical hypothesis testing; Econometrics; Null hypothesis; Prior probability; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6989123915737223,"gpt":0.608930368580515,"spread":0.08998202299320734,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002547896,0.000163244,0.0002347694,0.0002633694,0.0003216194,0.0002638392,0.0001990188,0.0001909368,0.00001228137],"category_scores_gemma":[0.01057296,0.0001489689,0.00003627328,0.0002627974,0.0001671424,0.0009648094,0.0001951366,0.000788292,0.000003011144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009869297,"about_ca_system_score_gemma":0.0001238706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001657966,"about_ca_topic_score_gemma":0.00004773002,"domain_scores_codex":[0.9981856,0.0001802267,0.0002944986,0.0003525856,0.000536491,0.0004506408],"domain_scores_gemma":[0.9920731,0.006798242,0.0001081352,0.0002416299,0.0006490943,0.0001297579],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006368414,0.0004916356,0.003210707,0.0003180658,0.00001570698,0.00001430029,0.001273153,0.00004110442,0.5571062,0.05426313,0.00012891,0.3830734],"study_design_scores_gemma":[0.0005746021,0.0002501782,0.006332192,0.0001690842,0.00002604408,0.000008552565,0.00008772517,0.2331191,0.04802514,0.7111719,0.00001032125,0.000225178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7655777,0.000005899952,0.2328521,0.00005662563,0.000100254,0.0009465636,0.00001151534,0.0002347219,0.0002147216],"genre_scores_gemma":[0.5518578,4.866892e-7,0.4477169,0.000003121895,0.00005106341,0.0003092022,0.000009895136,0.0000262121,0.00002533031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6569088,"threshold_uncertainty_score":0.9977614,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366992020","doi":"10.1001/jama.2023.4221","title":"Emulation of Randomized Clinical Trials With Nonrandomized Database Analyses","year":2023,"lang":"en","type":"article","venue":"JAMA","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":379,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute on Aging; National Heart, Lung, and Blood Institute; U.S. Food and Drug Administration","keywords":"Medicine; Emulation; Randomized controlled trial; Clinical trial; MEDLINE; Database; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5650319051167182,"gpt":0.5950935289172615,"spread":0.03006162380054334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02600308,0.0001525706,0.002380434,0.0001970239,0.00003085884,0.00002363115,0.0001499205,0.0001184015,0.0001410135],"category_scores_gemma":[0.09353598,0.00009265228,0.0004287101,0.0004420285,0.0001724055,0.0002278244,0.00006046017,0.0001732434,0.00002088034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001287297,"about_ca_system_score_gemma":0.00005317908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002095048,"about_ca_topic_score_gemma":0.00000961412,"domain_scores_codex":[0.9941141,0.003303535,0.001836806,0.0002309633,0.000347329,0.0001672921],"domain_scores_gemma":[0.9553498,0.04275981,0.001085396,0.0004742552,0.0002676274,0.00006309569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.7526855,0.0007032449,0.000595504,0.000428691,0.002199129,0.00006386151,0.0007847962,0.0002046402,0.02699479,0.160288,0.01772637,0.03732551],"study_design_scores_gemma":[0.6489458,0.0001805039,0.000124522,0.0003678557,0.001187566,0.00000295601,0.0001373507,0.01489255,0.0403019,0.2933661,0.0001918868,0.0003009566],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.187965,0.0000575241,0.8069181,0.0003679145,0.0001001842,0.002249887,0.0000507169,0.0007237386,0.001566973],"genre_scores_gemma":[0.8491168,0.0002251393,0.1497254,0.0000609737,0.0001818837,0.0002186016,0.0001082211,0.00003552566,0.000327471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6611518,"threshold_uncertainty_score":0.9140996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1975994236","doi":"10.1002/sim.3854","title":"The performance of different propensity-score methods for estimating differences in proportions (risk differences or absolute risk reductions) in observational studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":359,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Confidence interval; Observational study; Estimator; Mean squared error; Relative risk; Matching (statistics); Inverse probability weighting; Mathematics; Econometrics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.4011751616883879,"gpt":0.5200551633034011,"spread":0.1188800016150132,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002631738,0.0002643031,0.0008062118,0.0002353378,0.0002441914,0.00001417905,0.0003253413,0.00009620264,0.00005521493],"category_scores_gemma":[0.03792186,0.000143284,0.00002722164,0.0004320852,0.0009272676,0.0001196024,0.0001023196,0.0008582094,2.497175e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009533988,"about_ca_system_score_gemma":0.0001214929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001364446,"about_ca_topic_score_gemma":0.007370234,"domain_scores_codex":[0.9973568,0.000315674,0.001313239,0.000327436,0.0003375704,0.0003493356],"domain_scores_gemma":[0.9852414,0.01307567,0.0008802807,0.0003620829,0.000393974,0.00004661301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000309543,0.0004624946,0.7223801,0.001047106,0.0001127273,0.000006667992,0.006077092,0.0000578094,0.001407905,0.1472827,0.001209045,0.1196468],"study_design_scores_gemma":[0.0005530612,0.0005105432,0.3495131,0.0008738831,0.00006327072,0.000004079663,0.001196729,0.04699414,0.0003690312,0.5997149,0.00001943077,0.0001878482],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7761584,0.00008380621,0.2216749,0.0002329681,0.0004197104,0.001163151,0.0002083824,0.00003962277,0.00001906395],"genre_scores_gemma":[0.3462323,0.0007670073,0.6521072,0.000006848166,0.00007758733,0.0006567338,0.00002579235,0.00001655622,0.000109973],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4524322,"threshold_uncertainty_score":0.9701821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050419204","doi":"10.1111/1468-2354.t01-1-00074","title":"2001 Lawrence R. Klein Lecture Estimating Distributions of Treatment Effects with an Application to the Returns to Schooling and Measurement of the Effects of Uncertainty on College Choice*","year":2003,"lang":"en","type":"article","venue":"International Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":351,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Counterfactual conditional; LISREL; Veil of ignorance; Econometrics; Economics; Matching (statistics); Pairwise comparison; Probit model; Actuarial science; Mathematics; Statistics; Psychology; Microeconomics; Structural equation modeling; Counterfactual thinking; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.05282705166160347,"gpt":0.3680734952222458,"spread":0.3152464435606424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000439132,0.0001209872,0.000284629,0.00002893776,0.00003815224,0.000005980643,0.0002104383,0.00002332175,0.000006669942],"category_scores_gemma":[0.001630393,0.00006803751,0.0000472581,0.00008653223,0.00003601829,0.00004975188,0.00002700789,0.00005981169,0.000001286659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004442162,"about_ca_system_score_gemma":0.00008585671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009215679,"about_ca_topic_score_gemma":0.0004514112,"domain_scores_codex":[0.9991562,0.0001047237,0.0003470147,0.0001684972,0.0001371727,0.00008643863],"domain_scores_gemma":[0.9985707,0.0005454564,0.0003497517,0.0003460058,0.0001509704,0.00003709441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001627296,0.0008846162,0.003239325,0.009574544,0.0007808701,0.000001402091,0.0008668784,0.03286328,0.02798419,0.8523043,0.003093671,0.06824417],"study_design_scores_gemma":[0.003043088,0.007688483,0.006760483,0.08370168,0.001170224,0.00006113772,0.0001250634,0.01529667,0.6252404,0.221905,0.0337151,0.001292602],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6051443,0.004910938,0.3707908,0.003955335,0.000404331,0.01297098,0.0003734686,0.00008344744,0.001366329],"genre_scores_gemma":[0.9785174,0.0004962344,0.02037333,0.0001305873,0.00002044064,0.0004394957,0.000004677648,0.00000983517,0.000007982449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6303993,"threshold_uncertainty_score":0.2774489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766207844","doi":"10.1136/bmj.j4587","title":"Handling time varying confounding in observational research","year":2017,"lang":"en","type":"review","venue":"BMJ","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":346,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Confounding; Observational study; Weighting; Marginal structural model; Statistics; Econometrics; Parametric statistics; Inverse probability weighting; Estimation; Causal inference; Medicine; Computer science; Mathematics; Propensity score matching; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.8963818942939966,"gpt":0.6776851293144192,"spread":0.2186967649795775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005131851,0.000264395,0.001280269,0.0004151467,0.000226684,0.000145736,0.0006872892,0.0003554173,0.0001529021],"category_scores_gemma":[0.009013413,0.000236411,0.0001621693,0.000225993,0.0001077276,0.000238804,0.0003159374,0.001041874,0.0002710431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004153458,"about_ca_system_score_gemma":0.0005517724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001747862,"about_ca_topic_score_gemma":0.000007682411,"domain_scores_codex":[0.9974645,0.0003578124,0.0008457888,0.0003616484,0.0005358509,0.0004344214],"domain_scores_gemma":[0.9944647,0.003920513,0.0005552822,0.0008088139,0.0001953537,0.00005535824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003839339,0.00004592575,0.000009756267,0.0143621,0.00005695825,0.00009667074,0.00009458343,5.691294e-7,0.000004834371,0.1154447,0.008779071,0.861101],"study_design_scores_gemma":[0.00005485341,0.0000129987,8.004371e-7,0.03599876,0.00003262861,0.00001958787,0.000003328673,0.00004538201,0.000002611425,0.169972,0.7936146,0.0002423954],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002444345,0.9629158,0.001747613,0.00007197478,0.0001219856,0.001938558,0.00001609578,0.0001968692,0.0329886],"genre_scores_gemma":[0.00000279723,0.9457101,0.04813024,0.00000843508,0.0004204837,0.0005476066,0.00005586049,0.00007727404,0.005047185],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8608586,"threshold_uncertainty_score":0.9993341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1995875958","doi":"10.1257/aer.91.2.112","title":"Reconciling Conflicting Evidence on the Performance of Propensity-Score Matching Methods","year":2001,"lang":"en","type":"article","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":336,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Propensity score matching; Economics; Matching (statistics); Econometrics; Actuarial science; Positive economics; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4399859587587839,"gpt":0.4966393531473604,"spread":0.05665339438857642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003068012,0.0001936873,0.0007632904,0.00003719233,0.00008598855,0.00001598692,0.0004257487,0.00002187088,0.0001454716],"category_scores_gemma":[0.001340908,0.0001321653,0.0001166546,0.0001464211,0.0002205306,0.0002442515,0.00009822082,0.0002654356,0.00004693481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001431998,"about_ca_system_score_gemma":0.00006440406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007649188,"about_ca_topic_score_gemma":0.000009837152,"domain_scores_codex":[0.9983347,0.000350144,0.000721952,0.0002791739,0.00008288622,0.0002311202],"domain_scores_gemma":[0.9954023,0.002761456,0.001013426,0.0007189006,0.00005960102,0.00004435009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00003111943,0.00003182619,0.005573479,0.002224792,0.00007622454,0.000003328118,0.0004237679,0.00005331538,0.002602928,0.02307706,0.0007508332,0.9651513],"study_design_scores_gemma":[0.0009516475,0.006146652,0.01033671,0.3299316,0.001606744,0.001258413,0.002902393,0.008132525,0.2294514,0.1651963,0.237329,0.006756635],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977187,0.004808565,0.01115541,0.001160363,0.00006337983,0.001036211,0.000001799533,0.0001435442,0.004443753],"genre_scores_gemma":[0.6258249,0.2077163,0.1620656,0.003827994,0.00009084148,0.0002115966,0.000001274471,0.00006849814,0.0001930506],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9583947,"threshold_uncertainty_score":0.5389543,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809826847","doi":"10.1080/13645579.2018.1488449","title":"Natural experiment methodology for research: a review of how different methods can support real-world research","year":2018,"lang":"en","type":"review","venue":"International Journal of Social Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":335,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Public Health Agency of Canada","keywords":"Randomized experiment; Research design; Randomized controlled trial; Natural experiment; Natural (archaeology); Intervention (counseling); Management science; Psychological intervention; Computer science; Risk analysis (engineering); Psychology; Sociology; Engineering; Medicine; Social science; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.967881105314908,"gpt":0.8051552063693992,"spread":0.1627258989455088,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2653332,0.000741149,0.006401347,0.006479979,0.0004944086,0.0001385376,0.005607758,0.001054623,0.0006229974],"category_scores_gemma":[0.2264731,0.0005581453,0.002137033,0.002164447,0.003984121,0.0002562703,0.002393619,0.007838514,0.000007852007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00339235,"about_ca_system_score_gemma":0.004485808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001463676,"about_ca_topic_score_gemma":0.0001852853,"domain_scores_codex":[0.8331965,0.1512637,0.004666631,0.001249178,0.007172415,0.002451516],"domain_scores_gemma":[0.7757276,0.1906714,0.003203094,0.00091691,0.02905664,0.0004244125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00051291,0.0003721368,6.494667e-7,0.03427367,0.002009446,0.0001251629,0.001723544,1.065723e-8,0.0007309207,0.2759714,0.1147011,0.569579],"study_design_scores_gemma":[0.0003331226,0.001290623,9.399966e-7,0.02264136,0.0002256974,0.0001389244,0.0007492899,7.328613e-7,0.002396974,0.358943,0.6129946,0.0002847328],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000008721428,0.9226694,0.06362435,0.005496579,0.002658119,0.003724973,0.000204309,0.00004958888,0.001564014],"genre_scores_gemma":[0.000004511836,0.5702764,0.4248542,0.00004365169,0.002240755,0.0006644343,0.00004475076,0.0001212003,0.001750113],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.5692943,"threshold_uncertainty_score":0.9997724,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"systematic_review","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3047016911","doi":"10.1257/aer.20190687","title":"Methods Matter: p-Hacking and Publication Bias in Causal Analysis in Economics","year":2020,"lang":"en","type":"article","venue":"American Economic Review","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":333,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Credibility; Regression discontinuity design; Instrumental variable; Publication bias; Hacker; Causal inference; Omitted-variable bias; Economics; Identification (biology); Econometrics; Randomized experiment; Selection bias; Psychology; Statistics; Political science; Computer science; Law; MEDLINE; Mathematics; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.2339322466141202,"gpt":0.4709007945413937,"spread":0.2369685479272735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001003214,0.0001690808,0.0009806332,0.0002098238,0.00001228583,0.00003586665,0.0001895665,0.00002963233,0.0001728202],"category_scores_gemma":[0.0004853432,0.0001765997,0.00008952247,0.0005069704,0.00009768053,0.00028201,0.00009597202,0.0001524577,0.00004453579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002054763,"about_ca_system_score_gemma":0.00003933249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002581341,"about_ca_topic_score_gemma":0.0004109569,"domain_scores_codex":[0.9982673,0.0002643547,0.0008471552,0.0004011278,0.00002274202,0.0001973526],"domain_scores_gemma":[0.998508,0.0004673511,0.0005791064,0.0003436438,0.00001560239,0.00008623718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009077159,0.00004035084,0.174658,0.0008578426,0.0002025134,0.00000309152,0.0004719716,0.00009647181,0.00003511131,0.02321152,0.001957395,0.7984566],"study_design_scores_gemma":[0.002409572,0.000833528,0.254577,0.004632648,0.003472651,0.00008059861,0.001803599,0.0888748,0.001750771,0.2949046,0.3400158,0.006644421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6903905,0.02807981,0.1837168,0.06497444,0.0001195552,0.004813602,0.00008601895,0.0007152694,0.02710401],"genre_scores_gemma":[0.3721414,0.1436877,0.4669022,0.01670194,0.00005762414,0.0003464272,0.00004289429,0.00008014662,0.00003962178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7918122,"threshold_uncertainty_score":0.7201529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013920814","doi":"10.1002/sim.4200","title":"Comparing paired vs non‐paired statistical methods of analyses when making inferences about absolute risk reductions in propensity‐score matched samples","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":325,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Confidence interval; Confounding; Sample size determination; Selection bias; Observational study; Statistical significance; Statistical inference; Matching (statistics); Causal inference; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6053372113795614,"gpt":0.5275261212026646,"spread":0.0778110901768968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002377219,0.0003480334,0.001425474,0.0006387852,0.00008582623,0.00001496581,0.0003881759,0.0001494669,0.0003468446],"category_scores_gemma":[0.009036527,0.0002927189,0.0000382112,0.0005980207,0.0009641722,0.0001399565,0.0001757508,0.0006378602,0.000002263764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001639272,"about_ca_system_score_gemma":0.0001360855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003637289,"about_ca_topic_score_gemma":0.004107235,"domain_scores_codex":[0.996415,0.0006600106,0.001585777,0.0004675246,0.0004049093,0.0004668253],"domain_scores_gemma":[0.9953412,0.00294716,0.0007358047,0.0005739904,0.0003085739,0.00009331571],"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":[0.0005824228,0.0007308396,0.3124541,0.001468551,0.000359229,0.0001704124,0.02755426,0.0001096009,0.006081633,0.6148992,0.003428724,0.03216105],"study_design_scores_gemma":[0.0005951396,0.0002454616,0.2365439,0.001250009,0.0001983226,0.000005713507,0.001593032,0.004142211,0.001893574,0.7532755,0.00001568038,0.0002414811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08581615,0.0001042083,0.9114445,0.0000424137,0.0001552758,0.0005861518,0.0001259834,0.0001168378,0.001608484],"genre_scores_gemma":[0.4680082,0.00009729292,0.5317352,0.00001660559,0.00002238097,0.00004679545,0.00002780639,0.00002446418,0.00002118514],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3821921,"threshold_uncertainty_score":0.9999525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035404753","doi":"10.1177/0962280215584401","title":"The performance of inverse probability of treatment weighting and full matching on the propensity score in the presence of model misspecification when estimating the effect of treatment on survival outcomes","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":325,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Mental Health","keywords":"Propensity score matching; Observational study; Matching (statistics); Statistics; Inverse probability weighting; Hazard ratio; Inverse probability; Covariate; Average treatment effect; Selection bias; Confounding; Weighting; Marginal structural model; Econometrics; Selection (genetic algorithm); Mathematics; Computer science; Medicine; Confidence interval; Posterior probability; Bayesian probability; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5863130353224311,"gpt":0.5806095152849405,"spread":0.005703520037490528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03236401,0.0001566107,0.0005199593,0.00006370126,0.0001098177,0.00001232008,0.0005161812,0.00007924562,0.000008713187],"category_scores_gemma":[0.06968031,0.000054903,0.00003950169,0.0002428548,0.001570897,0.0000422767,0.0001626837,0.000552514,2.337649e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002633104,"about_ca_system_score_gemma":0.0002628237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003791909,"about_ca_topic_score_gemma":0.0001795942,"domain_scores_codex":[0.9894098,0.00790736,0.0007768646,0.0002580839,0.001348078,0.0002998223],"domain_scores_gemma":[0.9058805,0.09295272,0.0002342446,0.0006519073,0.0002093207,0.0000713251],"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":[0.001898006,0.0007830943,0.02241156,0.0010132,0.00006780739,0.000005805091,0.01435558,0.001310393,0.002071896,0.5593496,0.00003823464,0.3966948],"study_design_scores_gemma":[0.0005410898,0.004361697,0.00345757,0.0005499005,0.00002042718,0.000001347536,0.0008051294,0.3389878,0.01417914,0.6370296,0.000002825288,0.00006343971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8596705,0.00001747117,0.1373769,0.0008245812,0.00001758315,0.001688166,0.00001422496,0.000006837027,0.0003836697],"genre_scores_gemma":[0.6752847,0.00002944264,0.3244692,0.000004152506,0.000007124584,0.0001890841,8.499148e-7,0.000007601799,0.000007764232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3966314,"threshold_uncertainty_score":0.9963849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3112964578","doi":"10.1161/circulationaha.120.051718","title":"Emulating Randomized Clinical Trials With Nonrandomized Real-World Evidence Studies","year":2020,"lang":"en","type":"article","venue":"Circulation","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":297,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; McGill University; National Institute on Aging; Harvard University; Vanderbilt University","keywords":"Medicine; Randomized controlled trial; Confounding; Propensity score matching; Hazard ratio; Placebo; Clinical trial; Clinical endpoint; Research design; Proxy (statistics); Clinical study design; Confidence interval; Internal medicine; Statistics; Alternative medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.7113316494914241,"gpt":0.5902829400891217,"spread":0.1210487094023024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01651703,0.0002407664,0.002409896,0.00007810914,0.0001047612,0.00004542826,0.0001399689,0.00009516587,0.00005584178],"category_scores_gemma":[0.1334227,0.0001646256,0.0003609207,0.000357852,0.0002093599,0.0004082329,0.00005641139,0.0002609153,0.00001402759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007746679,"about_ca_system_score_gemma":0.00006774776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000123133,"about_ca_topic_score_gemma":0.00002030799,"domain_scores_codex":[0.9928052,0.00410556,0.002068549,0.0004259321,0.0003850445,0.0002097231],"domain_scores_gemma":[0.9411392,0.05649056,0.001465579,0.0003564671,0.0004179634,0.000130216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.5219453,0.0004291354,0.0552037,0.001794162,0.003973176,0.00008136198,0.01334133,0.003691653,0.01137336,0.3356147,0.00284785,0.04970435],"study_design_scores_gemma":[0.3525926,0.0002332401,0.002031717,0.002256751,0.001954118,0.000005529316,0.0006093757,0.0691371,0.002457518,0.5677074,0.00006576315,0.0009489591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1887572,0.000438767,0.8032129,0.001574477,0.0001387657,0.003747222,0.000002272076,0.0009689491,0.001159397],"genre_scores_gemma":[0.9183198,0.0003334933,0.08049316,0.0002455975,0.0003313336,0.000211729,0.000004767242,0.0000355825,0.00002455095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7295626,"threshold_uncertainty_score":0.8738768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153012086","doi":"10.1111/j.1524-4733.2009.00602.x","title":"Good Research Practices for Comparative Effectiveness Research: Analytic Methods to Improve Causal Inference from Nonrandomized Studies of Treatment Effects Using Secondary Data Sources: The ISPOR Good Research Practices for Retrospective Database Analysis Task Force Report—Part III","year":2009,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":290,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Causal inference; Inference; Confounding; Statistical inference; Comparative effectiveness research; Marginal structural model; Medicine; Propensity score matching; Instrumental variable; Outcomes research; Research design; Computer science; Econometrics; Management science; Statistics; Machine learning; Alternative medicine; Artificial intelligence; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8166517374954501,"gpt":0.7018213479349174,"spread":0.1148303895605327,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1245983,0.0005535864,0.003031022,0.001754285,0.001352667,0.000223041,0.001507659,0.0002329345,0.000007585712],"category_scores_gemma":[0.1799678,0.0003951015,0.0002597456,0.004778909,0.0007757317,0.001311521,0.0008061209,0.001769928,0.000001245777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003183897,"about_ca_system_score_gemma":0.003212451,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03160303,"about_ca_topic_score_gemma":0.006446623,"domain_scores_codex":[0.9639859,0.02752245,0.002314429,0.002406283,0.001956847,0.001814108],"domain_scores_gemma":[0.7062866,0.2812821,0.003860109,0.003866755,0.004351499,0.0003529797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1650445,0.02365979,0.01271477,0.029129,0.0500786,0.0006806336,0.2395029,0.02155088,0.2460101,0.1605324,0.005384399,0.04571204],"study_design_scores_gemma":[0.02234323,0.03279747,0.002180052,0.006125017,0.00361243,0.00002829648,0.05708302,0.1836645,0.1302502,0.5580377,0.002362563,0.001515511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5135121,0.004568731,0.4429642,0.001916256,0.0002416289,0.03379567,0.002607129,0.0001584062,0.0002359378],"genre_scores_gemma":[0.6271013,0.000572785,0.3682908,0.0000378282,0.0002534191,0.003173406,0.0003552945,0.00006411018,0.0001509833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3975053,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162163884","doi":"10.1136/jech.55.7.508","title":"A heuristic approach to the formulas for population attributable fraction","year":2001,"lang":"en","type":"article","venue":"Journal of Epidemiology & Community Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":289,"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":"Confounding; Fraction (chemistry); Attributable risk; Medicine; Heuristic; Population; Representation (politics); Limit (mathematics); USable; Econometrics; Statistics; Public health; Distribution (mathematics); Estimation; Environmental health; Computer science; Artificial intelligence; Mathematics; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.5047912795363017,"gpt":0.5411379398954912,"spread":0.03634666035918954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0178912,0.0001470346,0.0008840103,0.0001465064,0.0006684051,0.000008284289,0.0004508066,0.000135236,0.000006628159],"category_scores_gemma":[0.02809267,0.00009881703,0.0001514126,0.0002136156,0.0000453059,0.0002096595,0.0000776244,0.00122627,0.00000222003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005320677,"about_ca_system_score_gemma":0.0001268306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001332509,"about_ca_topic_score_gemma":0.0007199256,"domain_scores_codex":[0.9954197,0.002602286,0.001312354,0.0001073726,0.0001205267,0.0004377043],"domain_scores_gemma":[0.9837133,0.01359517,0.001526663,0.000643639,0.000340046,0.0001811584],"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":[0.001295029,0.002322348,0.09412286,0.0009275347,0.000266298,0.000002036889,0.002226136,0.00660258,0.00009871135,0.635472,0.1903151,0.0663494],"study_design_scores_gemma":[0.0003205186,0.001239696,0.0181192,0.0001393902,0.00003434766,0.000206665,0.0004466955,0.001865038,0.00001079991,0.9412343,0.03626934,0.0001140403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06435415,0.0002296503,0.9269872,0.007188396,0.0001256821,0.0006354392,0.000009183831,0.00005153648,0.0004187936],"genre_scores_gemma":[0.6131034,0.0003078964,0.3823632,0.003882797,0.0002094616,0.0000408525,0.0000229797,0.00002072404,0.00004866477],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5487493,"threshold_uncertainty_score":0.9800941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052567024","doi":"10.1037/1082-989x.12.3.247","title":"Combining propensity score matching and group-based trajectory analysis in an observational study.","year":2007,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":285,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"National Institute of Mental Health","keywords":"Propensity score matching; Covariate; Observational study; Matching (statistics); Mahalanobis distance; Statistics; Trajectory; Mathematics; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.7505569186862165,"gpt":0.6029601374272204,"spread":0.1475967812589961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007139158,0.0001965381,0.000523607,0.0002834317,0.00008469209,0.00003592427,0.0002104869,0.0001473,0.00005619461],"category_scores_gemma":[0.001111004,0.0001556689,0.00006999222,0.0008631899,0.0001068295,0.0001824442,0.00005779812,0.0004400316,5.900721e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005201834,"about_ca_system_score_gemma":0.000006142534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002223558,"about_ca_topic_score_gemma":0.0001857472,"domain_scores_codex":[0.9973857,0.001048001,0.0005275923,0.0005202928,0.0002229732,0.0002954505],"domain_scores_gemma":[0.9964577,0.002817034,0.0001670512,0.0003777114,0.00006845604,0.0001120795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001882983,0.002071025,0.9289572,0.00002096488,0.00006376801,0.00005678197,0.0007329514,0.00004486023,0.01123498,0.01735886,0.000003577892,0.03926678],"study_design_scores_gemma":[0.000340238,0.0004438781,0.7458445,0.00001181483,0.00006288737,0.000001915475,0.0002085602,0.000229073,0.0003040319,0.2523876,0.000002279458,0.0001632515],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5322487,0.000008115736,0.4671167,0.00001849173,0.0000205856,0.0002803985,0.000001146544,0.0001404305,0.0001654056],"genre_scores_gemma":[0.519919,5.851282e-7,0.4798669,0.0001665996,0.000009833866,0.00002366213,0.000004598262,0.000006699965,0.00000208264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2350287,"threshold_uncertainty_score":0.6347992,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W213628847","doi":"10.1016/j.cjca.2015.05.015","title":"A Review of Propensity-Score Methods and Their Use in Cardiovascular Research","year":2015,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":283,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Sunnybrook Hospital; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Observational study; Medicine; Covariate; Matching (statistics); Weighting; Inverse probability weighting; Selection bias; Strengths and weaknesses; Randomized controlled trial; Econometrics; Statistics; Internal medicine; Mathematics; Pathology; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.7264268470364439,"gpt":0.5542337611935539,"spread":0.1721930858428899,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01992033,0.0003441676,0.006668453,0.001149558,0.0000362901,0.00001947537,0.0005898849,0.0004863784,0.000004782195],"category_scores_gemma":[0.01043472,0.0002343352,0.0009770304,0.0006325386,0.0005079892,0.0001431549,0.0001077751,0.00172524,0.000001011472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005564144,"about_ca_system_score_gemma":0.004816043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00062377,"about_ca_topic_score_gemma":0.0007958684,"domain_scores_codex":[0.991142,0.006465213,0.001382943,0.0002869354,0.0002282921,0.0004946234],"domain_scores_gemma":[0.994501,0.001815382,0.0006681123,0.0008514393,0.001648364,0.0005157312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003076207,0.000001598283,0.00002770384,0.05079683,0.0007684844,0.000252541,0.00007678917,0.000001293684,3.973491e-7,0.00139191,0.009042874,0.9376365],"study_design_scores_gemma":[0.00007475683,0.0001280639,0.000003151794,0.08807229,0.0004820773,0.001906238,0.00002252162,9.554681e-8,0.000001885489,0.01707061,0.892068,0.0001703316],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000005323147,0.9921182,0.00595461,0.00001916889,0.0001264375,0.0009759709,0.00004019627,0.000005775548,0.0007543215],"genre_scores_gemma":[0.00001125651,0.9832873,0.0163563,0.00002330722,0.000207778,0.0000353739,0.000004855642,0.00005470749,0.00001915087],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9374661,"threshold_uncertainty_score":0.9979008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}