{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":708,"total_is_capped":false,"direct_labels_cover":5,"predictions_cover":708,"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":"e941b4fc72db","filters":{"venue":"Statistics in Medicine"}},"results":[{"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":"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":"W2157347940","doi":"10.1002/sim.698","title":"A comparison of methods to detect publication bias in meta‐analysis","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1297,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Statistics; Publication bias; Funnel plot; Sample size determination; Meta-analysis; Type I and type II errors; Nominal level; Linear regression; Mathematics; Econometrics; Censoring (clinical trials); Logistic regression; Meta-regression; Statistical power; Logit; Confidence interval; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.8953613622891847,"gpt":0.6824856965509237,"spread":0.212875665738261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.180884,0.0002091828,0.007175386,0.00294699,0.00002660089,0.00008083197,0.001079068,0.00005978642,0.01701467],"category_scores_gemma":[0.1887139,0.0001003784,0.0006662896,0.01181131,0.00008300998,0.0000687596,0.00007520962,0.0001692537,0.0001772328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003969517,"about_ca_system_score_gemma":0.00003648966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003757007,"about_ca_topic_score_gemma":0.002864133,"domain_scores_codex":[0.9651464,0.01546937,0.0143306,0.0008700597,0.003904541,0.0002791013],"domain_scores_gemma":[0.9749687,0.01743129,0.003683685,0.002385736,0.001372534,0.0001580715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005091603,0.0002726703,0.4828337,0.0001410674,0.02992861,0.00002268782,0.008033151,0.006777737,0.000389673,0.03057922,0.1414376,0.2995329],"study_design_scores_gemma":[0.00109098,0.0005034874,0.3142297,0.00006316178,0.1199377,0.000007261413,0.005323763,0.2989049,0.0001818233,0.1066047,0.1525327,0.000619885],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002920446,0.00202808,0.9884496,0.001903088,0.00008262603,0.0004736607,0.00003187508,0.000002218338,0.004108423],"genre_scores_gemma":[0.3721851,0.0000460154,0.625703,0.0003409669,0.00002368107,0.00006128823,0.00002631119,0.000006763404,0.001606863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3692646,"threshold_uncertainty_score":0.9838839,"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":"W2754160328","doi":"10.1002/sim.7501","title":"Practical recommendations for reporting<scp>F</scp>ine‐<scp>G</scp>ray model analyses for competing risk data","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1176,"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; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Regression analysis; Econometrics; Regression; Event (particle physics); Hazard; Mathematics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.7862327183202007,"gpt":0.6125248362078489,"spread":0.1737078821123518,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04726753,0.0003092443,0.001682477,0.0004096859,0.001004574,0.0001753887,0.000867067,0.000194842,0.00004023663],"category_scores_gemma":[0.6004921,0.0003551218,0.00008559827,0.00012476,0.0002809259,0.0006327703,0.000248041,0.0004482993,0.0000735041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003208352,"about_ca_system_score_gemma":0.0003778379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001199161,"about_ca_topic_score_gemma":0.0009100792,"domain_scores_codex":[0.9897964,0.0002706279,0.007963895,0.00107686,0.0001851122,0.0007070967],"domain_scores_gemma":[0.94915,0.0325522,0.01555038,0.002113698,0.0003456499,0.0002880897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006728931,0.0001261321,0.01680045,0.0005337979,0.00015886,0.000003799454,0.002341896,0.001406271,0.000003277862,0.1211279,0.8570197,0.00047113],"study_design_scores_gemma":[0.001806317,0.0001412208,0.004702933,0.000204595,0.00009969169,0.000005644085,0.004555591,0.7099326,0.000002508944,0.09595138,0.1824918,0.0001057605],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004036563,0.0004653516,0.9418402,0.03236541,0.001231421,0.001556076,0.01449039,0.00004706723,0.003967512],"genre_scores_gemma":[0.03772511,0.0007363761,0.9485192,0.003814131,0.001532129,0.0004144505,0.00454492,0.0001035324,0.00261012],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7085263,"threshold_uncertainty_score":0.9998901,"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":"W2135029321","doi":"10.1002/sim.1301","title":"Issues in the meta‐analysis of cluster randomized trials","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":731,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Cancer Care Ontario; Western University","funders":"","keywords":"Meta-analysis; Randomization; Randomized controlled trial; Cluster (spacecraft); Computer science; Research design; Econometrics; Statistics; Medicine; Mathematics; Surgery","retraction":null,"screen_n_in":null,"score":{"opus":0.8482658612698941,"gpt":0.6110797934992076,"spread":0.2371860677706865,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5379483,0.0002234539,0.02008259,0.00149506,0.00002888149,0.0000866799,0.001319803,0.00005493853,0.0758016],"category_scores_gemma":[0.444272,0.00006784457,0.002560659,0.004466992,0.000295457,0.00005040154,0.00004064606,0.0001658541,0.0001791769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001040776,"about_ca_system_score_gemma":0.000008638802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002436647,"about_ca_topic_score_gemma":0.0006489371,"domain_scores_codex":[0.8262555,0.1306951,0.03218506,0.0009077555,0.00962906,0.0003275742],"domain_scores_gemma":[0.8213107,0.169677,0.005924548,0.002437599,0.0005973385,0.0000528232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.001047981,0.0002457454,0.002215322,0.0001236995,0.1286283,0.00006001136,0.02434051,0.001768907,0.000009266652,0.0955433,0.7370014,0.009015528],"study_design_scores_gemma":[0.03982675,0.00008846244,0.001703109,0.0000427542,0.5040606,0.000003168155,0.004821441,0.2712018,0.000002670316,0.1521066,0.02589251,0.0002501744],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003935752,0.08432114,0.8266863,0.04061342,0.0006968162,0.006325928,0.0004383724,0.000005261544,0.03697701],"genre_scores_gemma":[0.9092833,0.00290179,0.06599886,0.003710126,0.0002136462,0.0003356868,0.0000584103,0.00001777616,0.01748045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9053475,"threshold_uncertainty_score":0.9944653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144420447","doi":"10.1002/sim.1099","title":"Properties of the summary receiver operating characteristic (SROC) curve for diagnostic test data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Ovarian cancer diagnosis and treatment","field":"Medicine","cited_by":694,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Receiver operating characteristic; Diagnostic odds ratio; Area under the curve; Statistics; Homogeneous; Meta-analysis; Odds ratio; Area under curve; Coverage probability; Standard error; Mathematics; Medicine; Confidence interval; Internal medicine; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.08867909890496116,"gpt":0.319686173518747,"spread":0.2310070746137858,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003383328,0.0001654045,0.0004501326,0.00006071466,0.00007632808,0.000008002486,0.0002421602,0.00004789052,0.0002976994],"category_scores_gemma":[0.01352281,0.00009538262,0.00002261397,0.0001812926,0.0002610673,0.00005132256,0.0001004158,0.0001653288,0.000006695923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009507182,"about_ca_system_score_gemma":0.00006965039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002160947,"about_ca_topic_score_gemma":0.0001383186,"domain_scores_codex":[0.998605,0.00004711904,0.0005081047,0.0003158824,0.0002987784,0.0002250972],"domain_scores_gemma":[0.9967051,0.002182841,0.0001558264,0.0007278759,0.0001560841,0.00007230721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001621128,0.002443464,0.5697895,0.003396224,0.0004012484,0.0002893626,0.004857919,0.00001907015,0.003415035,0.002963561,0.3327908,0.07947169],"study_design_scores_gemma":[0.02124543,0.004456701,0.849469,0.0214268,0.002499169,0.0001461799,0.001316464,0.04372391,0.002596763,0.001149572,0.05118731,0.0007827186],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5195694,0.1144572,0.03302924,0.2072562,0.01580622,0.04032709,0.04683264,0.0004269275,0.02229511],"genre_scores_gemma":[0.9895924,0.002597771,0.005223891,0.0007785183,0.0004102909,0.0001487965,0.0003211671,0.00003292648,0.0008942402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.470023,"threshold_uncertainty_score":0.9947867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2618058430","doi":"10.1002/sim.7336","title":"Intermediate and advanced topics in multilevel logistic regression analysis","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":657,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Hospital; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Vetenskapsrådet; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Marginal model; Logistic regression; Covariate; Multilevel model; Statistics; Hierarchical clustering; Econometrics; Regression analysis; Population; Odds ratio; Regression; Cluster analysis; Computer science; Mathematics; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.1141231773850907,"gpt":0.4782803494377693,"spread":0.3641571720526786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007417856,0.0001655243,0.0006113496,0.0002487255,0.00009099644,0.00002700602,0.0002408098,0.00007906852,0.0001525876],"category_scores_gemma":[0.02324446,0.0001205914,0.00001686387,0.0001295237,0.0004990573,0.00005300714,0.0001149757,0.0002833541,0.000001824644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004516376,"about_ca_system_score_gemma":0.00002129416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002118792,"about_ca_topic_score_gemma":0.0009492463,"domain_scores_codex":[0.998592,0.0001187662,0.0005108292,0.0003010044,0.0002274729,0.0002499479],"domain_scores_gemma":[0.9969254,0.002163521,0.0002552666,0.0004885613,0.00006779583,0.00009948996],"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":[0.00005892026,0.00006520665,0.07124351,0.000214306,0.00004261253,0.0003053071,0.00089358,0.000001845389,0.00004839401,0.5168502,0.000439163,0.4098369],"study_design_scores_gemma":[0.0008455173,0.00007113545,0.3587915,0.0003048706,0.00009436935,0.000001386816,0.00009716185,0.01334464,0.000008733343,0.626288,0.00004762696,0.0001050439],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01492543,0.00007295243,0.9828474,0.0003974565,0.0002591764,0.0001724363,0.0001134776,0.00001258844,0.001199091],"genre_scores_gemma":[0.3864107,0.0001723577,0.6131126,0.00005077052,0.00006029159,0.00001312711,0.00001160717,0.000009490599,0.0001589875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4097319,"threshold_uncertainty_score":0.9849831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3191796027","doi":"10.1002/sim.9133","title":"Testing and correcting for weak and pleiotropic instruments in two‐sample multivariable Mendelian randomization","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":630,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Wellcome Trust","keywords":"Mendelian randomization; Statistics; Pleiotropy; Test statistic; Instrumental variable; Statistic; Mathematics; Econometrics; Sample size determination; Resampling; Statistical hypothesis testing; Biology; Genetics; Genetic variants","retraction":null,"screen_n_in":null,"score":{"opus":0.02197166481314274,"gpt":0.3276798526833534,"spread":0.3057081878702106,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004909669,0.0000771569,0.0002020055,0.00004337115,0.00005187411,0.00000538103,0.00002595974,0.00005144109,0.000007084159],"category_scores_gemma":[0.01196105,0.00007413078,0.000005232571,0.00009456128,0.00004934265,0.000001717758,0.00004218733,0.00006118504,8.456791e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001743631,"about_ca_system_score_gemma":0.00004434914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005883351,"about_ca_topic_score_gemma":0.001129487,"domain_scores_codex":[0.9992065,0.00009280526,0.0002742624,0.0002200067,0.00004374765,0.0001626532],"domain_scores_gemma":[0.9990808,0.0006423067,0.00008234581,0.00007369662,0.00008518641,0.00003567409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007350538,0.00002790729,0.9256311,0.00005383932,0.00001972257,0.000002280868,0.0002026793,0.0005628993,0.03097269,0.0007440008,0.0005314591,0.04117791],"study_design_scores_gemma":[0.04575028,0.0007945669,0.7237576,0.0003616213,0.0001034548,0.00006235721,0.003286714,0.1793782,0.003219463,0.03961495,0.003111756,0.0005590969],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7063362,0.0004052228,0.2921721,0.0002590891,0.0002076209,0.000259456,0.00008114259,0.000003343205,0.0002758651],"genre_scores_gemma":[0.7954559,0.0001641072,0.2038095,0.0001360683,0.00008218998,0.00002483041,0.000244969,0.000008150273,0.00007421497],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2018735,"threshold_uncertainty_score":0.9963616,"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":"W2091019309","doi":"10.1002/sim.5466","title":"Sample size formulas for estimating intraclass correlation coefficients with precision and assurance","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":467,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Intraclass correlation; Confidence interval; Reliability (semiconductor); Sample size determination; Statistics; Interval (graph theory); Mathematics; Coverage probability; Limit (mathematics); Interval estimation; Sample (material); Correlation coefficient; Correlation; Computer science; Reproducibility; Power (physics); Mathematical analysis; Combinatorics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.0854428886232476,"gpt":0.3958068923931848,"spread":0.3103640037699372,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00701403,0.0001294434,0.0002927156,0.00009737493,0.0001445583,0.00004037315,0.0001777118,0.00004867782,0.0001137755],"category_scores_gemma":[0.05895115,0.00007927259,0.00001140496,0.0003191426,0.0001817037,0.0001946525,0.00003749401,0.000128265,0.000007101997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006403356,"about_ca_system_score_gemma":0.00003125366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003909961,"about_ca_topic_score_gemma":0.0000768278,"domain_scores_codex":[0.9972705,0.000117423,0.0006695832,0.0002901726,0.001354668,0.0002976892],"domain_scores_gemma":[0.9771791,0.02183926,0.0002568303,0.0002580502,0.000351443,0.0001153645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004922879,0.0003229198,0.4425733,0.0001626575,0.00002307319,0.000002307115,0.005014019,0.02067447,0.000284349,0.02675664,0.02059298,0.483101],"study_design_scores_gemma":[0.003485309,0.0009511887,0.2150431,0.0005213569,0.00005061744,0.000006225203,0.001208445,0.5956204,0.00005170642,0.1763625,0.006426179,0.00027296],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03243521,0.0001012836,0.9651323,0.0006145685,0.0007373785,0.0006140475,0.00008665168,0.00001027044,0.000268267],"genre_scores_gemma":[0.5394728,0.000008728366,0.4602003,0.00008952562,0.0001099004,0.00002323863,0.00001157251,0.000005826205,0.00007804557],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5749459,"threshold_uncertainty_score":0.9489757,"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":"W1987973071","doi":"10.1002/sim.5941","title":"Graphical assessment of internal and external calibration of logistic regression models by using loess smoothers","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":357,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Sciences Centre; University of Toronto; Public Health Ontario; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","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":"Overfitting; Calibration; Logistic regression; Statistics; Computer science; Covariate; Loess; Econometrics; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.4241021929435487,"gpt":0.5779164790022724,"spread":0.1538142860587237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001924642,0.000172031,0.0008074914,0.0001359013,0.00002160374,0.000008488657,0.0001675667,0.0001309255,0.0003523325],"category_scores_gemma":[0.01609883,0.0001224345,0.00002708841,0.000154647,0.0008586697,0.00007046431,0.00007646738,0.0003080148,1.303527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004063725,"about_ca_system_score_gemma":0.00004377491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000464574,"about_ca_topic_score_gemma":0.000007696043,"domain_scores_codex":[0.9969909,0.0005794904,0.001403392,0.000257527,0.0005775525,0.0001911781],"domain_scores_gemma":[0.9824188,0.01641773,0.0006209838,0.0002440667,0.0001815258,0.0001169259],"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":[0.0001705808,0.0004979622,0.01797379,0.001314293,0.00009745445,0.00002710582,0.0005407127,0.0001936103,0.03140313,0.9221156,0.003781611,0.02188419],"study_design_scores_gemma":[0.001005949,0.0002396711,0.001508164,0.0008931746,0.00006183166,0.000003085052,0.00009869772,0.259879,0.0002744701,0.7359542,8.227699e-7,0.00008094367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04975117,0.00008036116,0.9491192,0.00007728522,0.0002367592,0.0003428982,0.0001713458,0.000008486106,0.0002124999],"genre_scores_gemma":[0.4347288,0.00005514966,0.5650991,0.00003954291,0.00004062224,0.000007485965,0.000002692556,0.0000145768,0.00001207678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3849776,"threshold_uncertainty_score":0.992189,"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":"W2954707123","doi":"10.1002/sim.8281","title":"The Integrated Calibration Index (ICI) and related metrics for quantifying the calibration of logistic regression models","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":313,"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; Institute of Health Services and Policy Research; Sunnybrook Hospital; University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; National Institutes of Health; Ontario Ministry of Health and Long-Term Care; Canadian Institutes of Health Research; Patient-Centered Outcomes Research Institute; Heart and Stroke Foundation of Canada","keywords":"Calibration; Statistics; Percentile; Logistic regression; Mathematics; Range (aeronautics); Smoothing; Regression; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2038005309243087,"gpt":0.4336053912476601,"spread":0.2298048603233514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00213575,0.0001456502,0.0003520928,0.0001079696,0.0001219727,0.00002416828,0.0001629847,0.0001050627,0.00004109528],"category_scores_gemma":[0.01684236,0.00006934835,0.00001701868,0.0004390411,0.0003415779,0.0000630884,0.00004171377,0.0002769512,3.157174e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003445659,"about_ca_system_score_gemma":0.00006078697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001449155,"about_ca_topic_score_gemma":0.00007036505,"domain_scores_codex":[0.9982336,0.0003063456,0.0007370912,0.0002000932,0.0003344023,0.0001884883],"domain_scores_gemma":[0.9826381,0.01647005,0.0003487299,0.0002789285,0.0002217455,0.00004242313],"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":[0.00008500093,0.00002075999,0.0006365391,0.000182959,0.00001760534,0.000001397548,0.0007378232,0.0001689314,0.0003265337,0.9858239,0.001107258,0.01089129],"study_design_scores_gemma":[0.0004012694,0.0001349277,0.0003656265,0.0001770129,0.00002923034,0.000001511892,0.0005956407,0.5078098,0.00005090443,0.4903607,0.00002540589,0.00004802622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005599792,0.0002957331,0.9920734,0.0005499726,0.0003581065,0.0007081809,0.0001120803,0.00001599633,0.0002867017],"genre_scores_gemma":[0.8627844,0.0002434043,0.1365797,0.00005798993,0.00002926998,0.00002981876,0.00004731016,0.00002093622,0.0002071809],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8571846,"threshold_uncertainty_score":0.9914392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169425545","doi":"10.1002/sim.6276","title":"The use of bootstrapping when using propensity‐score matching without replacement: a simulation study","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":278,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Health Services and Policy Research; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Bootstrapping (finance); Statistics; Resampling; Standard error; Matching (statistics); Confidence interval; Sample size determination; Standard deviation; Sampling distribution; Observational study; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3885413863266839,"gpt":0.4667305653599856,"spread":0.07818917903330169,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001554607,0.0001487087,0.000373402,0.00009781491,0.0001142302,0.00002014366,0.0001427852,0.000037873,0.00001455394],"category_scores_gemma":[0.005391769,0.00009968238,0.00001090305,0.0001253245,0.0001730461,0.0001164248,0.0000767536,0.0002275064,3.882496e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007613562,"about_ca_system_score_gemma":0.00002530242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002305582,"about_ca_topic_score_gemma":0.0002849462,"domain_scores_codex":[0.9982763,0.0002454444,0.0006665422,0.0001971884,0.0004172755,0.0001972772],"domain_scores_gemma":[0.995978,0.002935601,0.0004056042,0.0004443667,0.0002007968,0.00003562573],"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":[0.001027624,0.001083299,0.2644673,0.001321241,0.0003142329,0.00006763865,0.05405121,0.05883328,0.01238253,0.5664105,0.001654613,0.03838659],"study_design_scores_gemma":[0.001002178,0.0007180276,0.004290229,0.0008882358,0.0001038814,0.000003660412,0.001268077,0.1875128,0.0001858077,0.8036195,0.0002156431,0.0001919498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3198702,0.000006119692,0.6793033,0.00002631334,0.00004853178,0.0006330695,0.000004784818,0.0000396364,0.00006794722],"genre_scores_gemma":[0.7771273,0.000005420867,0.222706,0.00003370039,0.00004019514,0.00001178463,0.000004000333,0.00002140587,0.00005013562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4572571,"threshold_uncertainty_score":0.645484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138393952","doi":"10.1002/sim.3095","title":"Construction of confidence limits about effect measures: A general approach","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":252,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Confidence interval; Computer science; Statistics; Log-normal distribution; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5277622902536679,"gpt":0.527346483686242,"spread":0.0004158065674259026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1521486,0.0002077423,0.002763194,0.0005257517,0.00004589814,0.00004661769,0.0007148599,0.00007783472,0.001440495],"category_scores_gemma":[0.09823371,0.00009885066,0.0001929397,0.001242397,0.000424111,0.00005459094,0.00002881916,0.0001940657,0.00009033976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003316298,"about_ca_system_score_gemma":0.00005114455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008218842,"about_ca_topic_score_gemma":0.00009667105,"domain_scores_codex":[0.9811692,0.004131633,0.008130901,0.0006438741,0.005650942,0.0002734537],"domain_scores_gemma":[0.9853996,0.009228762,0.002788549,0.001390992,0.001060577,0.0001315445],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001007752,0.000089904,0.186051,0.0005140846,0.0002521593,0.00006097518,0.002989484,0.0002193888,0.001785962,0.4207374,0.05795018,0.3292487],"study_design_scores_gemma":[0.007241348,0.002291575,0.5188615,0.001702542,0.002020494,0.0004476147,0.01025845,0.08886697,0.002277093,0.3099205,0.05473572,0.001376264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03724565,0.0009940348,0.9411585,0.00006795296,0.000481499,0.0005124364,0.00002810303,0.000002795697,0.01950904],"genre_scores_gemma":[0.773428,0.00008979943,0.2246438,0.0001323996,0.0002011045,0.00001305906,0.00002052417,0.000009698619,0.001461563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7361824,"threshold_uncertainty_score":0.9994723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084292194","doi":"10.1002/sim.2731","title":"Developments in cluster randomized trials and <i>Statistics in Medicine</i>","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":248,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Royal Society","keywords":"Sample size determination; Medical statistics; Statistics; Cluster (spacecraft); Cluster analysis; Randomized controlled trial; Computer science; Population; Psychological intervention; Research design; Medicine; Econometrics; Data science; Mathematics; Surgery","retraction":null,"screen_n_in":null,"score":{"opus":0.08618382227126765,"gpt":0.4329159356107219,"spread":0.3467321133394543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01372133,0.0003807597,0.003001541,0.0005611365,0.00004190807,0.00001869381,0.0001940343,0.000169865,0.0003504821],"category_scores_gemma":[0.07601936,0.0002714275,0.00002504262,0.000527877,0.0009022726,0.00005169497,0.00007354252,0.000502421,0.000005772247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355855,"about_ca_system_score_gemma":0.0001038868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001657652,"about_ca_topic_score_gemma":0.002642845,"domain_scores_codex":[0.9930974,0.002153914,0.003073928,0.000486027,0.0006442686,0.0005445118],"domain_scores_gemma":[0.9511223,0.04789391,0.0004818187,0.0002482797,0.0001302867,0.0001234177],"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":[0.002809743,0.0001136997,0.003322797,0.0003514935,0.00002204618,0.0003077955,0.001001249,0.000001884221,0.00004421327,0.9458554,0.01991514,0.02625452],"study_design_scores_gemma":[0.08762998,0.00009352931,0.006297548,0.001018479,0.00009503439,0.00001247236,0.0002116868,0.002544212,0.00001093846,0.901451,0.0003681415,0.0002669675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008020336,0.0004212901,0.9891431,0.000768577,0.0004356507,0.001210886,0.0002415548,0.00002212751,0.006954772],"genre_scores_gemma":[0.02428333,0.0004587295,0.9740484,0.0005040952,0.0002070984,0.000128123,0.00009529198,0.00003975461,0.0002351789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08482024,"threshold_uncertainty_score":0.9999738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089415104","doi":"10.1002/sim.1687","title":"Inflation of the type I error rate when a continuous confounding variable is categorized in logistic regression analyses","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":248,"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":"Confounding; Statistics; Categorical variable; Type I and type II errors; Logistic regression; Mathematics; Inflation (cosmology); Sample size determination; Econometrics; Variable (mathematics); Regression analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.5624346742081207,"gpt":0.6001798666323802,"spread":0.03774519242425955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004747816,0.0002088345,0.001023645,0.00018084,0.00004978231,0.0000108188,0.000296851,0.0001643093,0.0005797995],"category_scores_gemma":[0.2249355,0.00012904,0.00003423355,0.0007293968,0.0005066833,0.00003807149,0.00008817995,0.0004530701,0.00000585902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001744657,"about_ca_system_score_gemma":0.000198628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006772228,"about_ca_topic_score_gemma":0.0001384239,"domain_scores_codex":[0.9963841,0.0009272852,0.001595113,0.0003081833,0.0004924686,0.0002928249],"domain_scores_gemma":[0.970709,0.02773507,0.0007021452,0.000486944,0.000295038,0.00007186142],"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":[0.0006070863,0.0002602652,0.004528323,0.0006208214,0.00009215776,0.00007515206,0.003629701,0.0004233468,0.008536065,0.975642,0.00334475,0.002240334],"study_design_scores_gemma":[0.003756336,0.0002083429,0.003439062,0.001253103,0.0001588075,0.000002525094,0.0003699273,0.001777568,0.0005391135,0.9882916,0.00007056141,0.0001330174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02909794,0.0001363408,0.9628906,0.001250949,0.002045406,0.001187174,0.0001965385,0.00003915855,0.00315594],"genre_scores_gemma":[0.3235398,0.00004757665,0.6757451,0.0002629384,0.0001239902,0.00001580211,0.00000951733,0.0000262091,0.0002291229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2944418,"threshold_uncertainty_score":0.7815932,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130728435","doi":"10.1002/sim.2103","title":"The partial area under the summary ROC curve","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":246,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Receiver operating characteristic; Truncation (statistics); Measure (data warehouse); Sensitivity (control systems); Statistics; Area under the curve; Area under curve; Mathematics; Computer science; Medicine; Data mining; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6102396939187572,"gpt":0.5384282700556492,"spread":0.07181142386310801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.1004645,0.0001867629,0.001325256,0.000104567,0.000273411,0.0002314496,0.001581619,0.00004134166,0.008326954],"category_scores_gemma":[0.04811865,0.00005371215,0.0001869729,0.0007846904,0.0003737549,0.00005722587,0.00009702093,0.0002660495,0.0009364803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003757421,"about_ca_system_score_gemma":0.00005606766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004002558,"about_ca_topic_score_gemma":0.001615317,"domain_scores_codex":[0.9833971,0.005445833,0.005695122,0.0004804736,0.004678444,0.0003030691],"domain_scores_gemma":[0.9729427,0.02256125,0.001558236,0.002370871,0.0004699112,0.00009707197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005686937,0.0000142534,0.003200575,0.000004768255,0.00005034828,0.000005635098,0.0005625327,0.0003749952,0.000003658657,0.09399304,0.8508113,0.05097319],"study_design_scores_gemma":[0.0002486625,0.00003691652,0.009802543,0.00003640742,0.0001118268,0.000006239889,0.002602255,0.04357054,0.000001839456,0.08010708,0.8633882,0.00008746216],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005738049,0.01017329,0.8486532,0.08049479,0.001927969,0.001298071,0.0001176309,0.000009594609,0.05158743],"genre_scores_gemma":[0.9181996,0.001104356,0.01165505,0.006597226,0.001639527,0.0000969372,0.00004095528,0.0000266669,0.06063969],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9124615,"threshold_uncertainty_score":0.9998414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4234921364","doi":"10.1002/sim.2781","title":"The performance of different propensity score methods for estimating marginal odds ratios","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":244,"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; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Statistics; Odds ratio; Odds; Estimator; Matching (statistics); Medicine; Mathematics; Logistic regression","retraction":null,"screen_n_in":null,"score":{"opus":0.1636371954417831,"gpt":0.4737266236584863,"spread":0.3100894282167033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001440583,0.0001533055,0.0003956063,0.00005870846,0.0001196971,0.00000786383,0.0001879101,0.00004498881,0.00001675221],"category_scores_gemma":[0.003346611,0.00009087888,0.00001741449,0.0001144231,0.0003333985,0.00004524119,0.00004891106,0.0001915706,2.69258e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007043953,"about_ca_system_score_gemma":0.00003465485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000300062,"about_ca_topic_score_gemma":0.00008847591,"domain_scores_codex":[0.998661,0.0001105302,0.0006178968,0.0001558654,0.0002195026,0.0002352355],"domain_scores_gemma":[0.9954485,0.003698763,0.000315655,0.0002784863,0.0002315271,0.00002707009],"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":[0.00009186043,0.00007759775,0.004458784,0.0007301857,0.0000139113,0.000002843605,0.000260542,0.00006668358,0.006183057,0.9101394,0.003094376,0.0748807],"study_design_scores_gemma":[0.0005251256,0.0005000319,0.004005472,0.0004443988,0.00004303695,0.000004917463,0.00005520105,0.1104467,0.01335285,0.8703821,0.0001108719,0.0001293549],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05286114,0.00005312101,0.9456895,0.0001375669,0.0001436716,0.0007104615,0.0000210877,0.00004277977,0.0003406586],"genre_scores_gemma":[0.1438901,0.00002468122,0.8556389,0.00001751047,0.000103859,0.0001050498,0.00002077667,0.00001821366,0.0001808416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.11038,"threshold_uncertainty_score":0.4006448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061407842","doi":"10.1002/sim.2618","title":"Conditioning on the propensity score can result in biased estimation of common measures of treatment effect: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":227,"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; Covariate; Hazard ratio; Observational study; Mathematics; Econometrics; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.2038916704515713,"gpt":0.4246693777064753,"spread":0.2207777072549041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001014465,0.000149914,0.0005247193,0.0001578074,0.00003265131,0.000003041076,0.00009534074,0.00003723333,0.000007700153],"category_scores_gemma":[0.002681419,0.00008826202,0.00001303845,0.0002255354,0.0002014932,0.00002121597,0.00001664806,0.0001517469,1.89033e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002442504,"about_ca_system_score_gemma":0.00004269863,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008497692,"about_ca_topic_score_gemma":0.01650867,"domain_scores_codex":[0.9984816,0.0003205381,0.0005981983,0.0001433529,0.0003325756,0.0001236802],"domain_scores_gemma":[0.996643,0.00259557,0.0003221424,0.0003024994,0.0001192603,0.00001750358],"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":[0.001623145,0.005766741,0.4252471,0.001276648,0.0002215376,0.0004456841,0.0283285,0.03260591,0.01071192,0.4610099,0.003863116,0.02889972],"study_design_scores_gemma":[0.007982511,0.01710625,0.2619719,0.004273138,0.0003075195,0.000005993682,0.002203498,0.01780962,0.05175816,0.6361921,0.000004717701,0.0003845987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9864438,0.00001643673,0.01140314,0.00009518329,0.00002373204,0.001552348,0.0001224852,0.00002614503,0.0003167688],"genre_scores_gemma":[0.9920664,0.000005251086,0.007735792,0.00001289618,0.0000121343,0.0001068566,0.00003110289,0.0000128858,0.00001664677],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1751821,"threshold_uncertainty_score":0.9981048,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068953434","doi":"10.1002/sim.2053","title":"The use of the propensity score for estimating treatment effects: administrative versus clinical data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":225,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Women's College Hospital; University of Toronto","funders":"","keywords":"Propensity score matching; Statistics; Econometrics; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.7319400186447765,"gpt":0.5861486378777672,"spread":0.1457913807670094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001247712,0.0001454809,0.0003800348,0.00001794855,0.0001348587,0.00001069355,0.0004069194,0.0000535593,0.000005410871],"category_scores_gemma":[0.04516651,0.00006860535,0.0000234119,0.00009262591,0.0006237422,0.00008210537,0.0001473944,0.0002233639,5.887497e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001017413,"about_ca_system_score_gemma":0.0001235377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003303402,"about_ca_topic_score_gemma":0.001010622,"domain_scores_codex":[0.9984651,0.0002400161,0.0006567328,0.0002261609,0.0002275347,0.0001844278],"domain_scores_gemma":[0.9709049,0.02762097,0.0003692086,0.0009219985,0.0001422861,0.00004065039],"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":[0.00113216,0.0005726996,0.003757978,0.000390704,0.0002202971,0.00001944032,0.001607951,0.00006884433,0.0001287227,0.4461048,0.04482607,0.5011704],"study_design_scores_gemma":[0.0128478,0.01154986,0.006923924,0.002944713,0.001094058,0.00001467777,0.0007246521,0.1884885,0.004366419,0.7459511,0.02443366,0.0006605966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01549587,0.000066865,0.9797662,0.00111236,0.0005577629,0.002327585,0.0004949808,0.0000497405,0.0001286286],"genre_scores_gemma":[0.04923556,0.0000871212,0.9501311,0.0000664967,0.000217198,0.00008160062,0.00004991374,0.00001829628,0.0001127592],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5005098,"threshold_uncertainty_score":0.9628764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095752327","doi":"10.1002/(sici)1097-0258(20000315)19:5<723::aid-sim379>3.0.co;2-a","title":"Interval estimation for Cohen's kappa as a measure of agreement","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":217,"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":"Confidence interval; Statistics; Mathematics; Measure (data warehouse); Kappa; Statistic; Variance (accounting); Delta method; Coverage probability; Asymptotic analysis; Computation; Asymptotic distribution; Cohen's kappa; Applied mathematics; Computer science; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1194851870437682,"gpt":0.4260948892710158,"spread":0.3066097022272476,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007252351,0.0001381291,0.0004369779,0.000180623,0.00005625889,0.0000204042,0.0004393494,0.00005284913,0.006227912],"category_scores_gemma":[0.008945916,0.00009497673,0.00004560084,0.0003774818,0.0002492155,0.00007386786,0.00002588437,0.0001163929,0.0001100698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007963402,"about_ca_system_score_gemma":0.00007118362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001450716,"about_ca_topic_score_gemma":0.0001421121,"domain_scores_codex":[0.9958637,0.0001877172,0.001203565,0.0003503025,0.002177019,0.0002176944],"domain_scores_gemma":[0.9970811,0.001633237,0.0002395192,0.0004441712,0.0005190375,0.00008291486],"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":[0.0004506093,0.0003054597,0.003310242,0.000110228,0.0000390168,0.00000870051,0.003275936,0.004834862,0.0005035896,0.02728542,0.09017988,0.869696],"study_design_scores_gemma":[0.004283762,0.002271252,0.01531838,0.0006632088,0.00008327864,0.000004389221,0.00209458,0.08427042,0.0005615975,0.8536577,0.03650804,0.000283358],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09164632,0.0003324673,0.8774809,0.005971984,0.0009288197,0.001759466,0.0002601117,0.00002090377,0.02159907],"genre_scores_gemma":[0.934467,0.00005486016,0.06239018,0.0004828379,0.0001126822,0.00006699333,0.00004351584,0.00000935096,0.002372566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8694127,"threshold_uncertainty_score":0.9994022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098196266","doi":"10.1002/sim.6115","title":"Statistics for quantifying heterogeneity in univariate and bivariate meta-analyses of binary data: The case of meta-analyses of diagnostic accuracy","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":215,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Bivariate analysis; Univariate; Statistics; Variance (accounting); Estimator; Meta-analysis; Econometrics; Statistic; Bivariate data; Mathematics; Multivariate statistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.9168580576152456,"gpt":0.6467614652057476,"spread":0.270096592409498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1378905,0.0004463421,0.009631727,0.0008970557,0.0000858192,0.00006853336,0.001810531,0.00008298119,0.001065545],"category_scores_gemma":[0.4882441,0.0001794953,0.0007193278,0.001812748,0.0006133188,0.0001829707,0.0004015968,0.0002098002,0.000004235756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001913236,"about_ca_system_score_gemma":0.0001101315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00357029,"about_ca_topic_score_gemma":0.003975641,"domain_scores_codex":[0.9678836,0.01340825,0.01423201,0.001083559,0.003064184,0.0003283382],"domain_scores_gemma":[0.7858435,0.1966154,0.01030528,0.004894394,0.00221351,0.0001279111],"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":[0.0005044369,0.001873255,0.0333264,0.01073922,0.2112069,0.001268421,0.009073657,0.04128237,0.01982881,0.5558249,0.07409772,0.04097388],"study_design_scores_gemma":[0.002627676,0.0008722253,0.01866494,0.0002181699,0.309359,0.0001118694,0.003399297,0.5032345,0.00113825,0.1576134,0.002134763,0.0006259669],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04979129,0.00907913,0.9326586,0.0004777588,0.0001765743,0.001250821,0.006493161,0.00000206987,0.00007063737],"genre_scores_gemma":[0.8665233,0.0004098222,0.1327118,0.00007606774,0.00002870295,0.00004137409,0.0001412336,0.0000170649,0.00005063182],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.816732,"threshold_uncertainty_score":0.9998476,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034503810","doi":"10.1002/sim.8570","title":"Graphical calibration curves and the integrated calibration index (ICI) for survival models","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":214,"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; Sunnybrook Hospital; University of Toronto","funders":"National Center for Advancing Translational Sciences; Canadian Institutes of Health Research; National Institutes of Health; Ontario Ministry of Health and Long-Term Care; Georgia Clinical and Translational Science Alliance; Heart and Stroke Foundation of Canada; Institute for Clinical Evaluative Sciences; Patient-Centered Outcomes Research Institute; Vanderbilt Institute for Clinical and Translational Research; Vanderbilt University","keywords":"Calibration; Context (archaeology); Statistics; Proportional hazards model; Percentile; Regression analysis; Mathematics; Survival analysis; Regression; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.3271472948171102,"gpt":0.4229108498472749,"spread":0.09576355503016465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009051238,0.0001448755,0.0008060008,0.0001282446,0.0001066009,0.00003145447,0.0001485383,0.00009500919,0.0001060255],"category_scores_gemma":[0.01056561,0.0001244273,0.00002811628,0.000251786,0.000313666,0.0002460732,0.00002598762,0.0002208515,0.000006032262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007029159,"about_ca_system_score_gemma":0.00008302548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00111124,"about_ca_topic_score_gemma":0.0005280912,"domain_scores_codex":[0.9965912,0.0003922724,0.002336865,0.0003587071,0.0001128132,0.000208171],"domain_scores_gemma":[0.9958757,0.003021054,0.0007221018,0.0001766917,0.00007079339,0.0001336347],"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":[0.0001052841,0.00001465151,0.005006091,0.0004808626,0.00002546556,6.066991e-7,0.002569222,0.0005958277,0.00000130896,0.9467309,0.04436165,0.0001081857],"study_design_scores_gemma":[0.002248651,0.00008864408,0.00168552,0.0001091596,0.000009262071,6.591613e-7,0.0008061171,0.7407881,4.236037e-7,0.2523155,0.001838587,0.0001094174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001353175,0.002068072,0.8168408,0.1773954,0.000299575,0.0009614534,0.0007553028,0.00002380573,0.0003023768],"genre_scores_gemma":[0.9239458,0.002025149,0.01082599,0.06112044,0.0007563854,0.0002930639,0.0008644723,0.00004804085,0.0001206044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9225927,"threshold_uncertainty_score":0.9977688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756610413","doi":"10.1002/sim.7532","title":"Measures of clustering and heterogeneity in multilevel <scp>P</scp>oisson regression analyses of rates/count data","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Prince Edward Island; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Vetenskapsrådet; Heart and Stroke Foundation of Canada","keywords":"Statistics; Poisson regression; Multilevel model; Poisson distribution; Hazard ratio; Proportional hazards model; Count data; Random effects model; Regression analysis; Cluster analysis; Confidence interval; Mathematics; Odds ratio; Rate ratio; Linear regression; Hierarchical clustering; Cluster (spacecraft); Econometrics; Medicine; Meta-analysis; Computer science; Internal medicine; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.4042531616015181,"gpt":0.5285301629397802,"spread":0.1242770013382621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001815571,0.0001650661,0.0007155885,0.0001529229,0.00005702112,0.00001388402,0.000471199,0.00007978216,0.00001518714],"category_scores_gemma":[0.04550336,0.0001187697,0.00001130118,0.00007465965,0.0004974941,0.00007783343,0.0003283753,0.0001941781,2.506839e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002212856,"about_ca_system_score_gemma":0.00003839452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001104852,"about_ca_topic_score_gemma":0.001943266,"domain_scores_codex":[0.9981558,0.0001992642,0.0007453185,0.000304192,0.0003951457,0.0002002705],"domain_scores_gemma":[0.9938189,0.004472902,0.0005664403,0.0009211642,0.0001483414,0.00007221516],"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":[0.0002651171,0.0008051959,0.3212843,0.007428375,0.000271404,0.0004213884,0.006697524,0.0000246419,0.0588426,0.1684965,0.006407223,0.4290557],"study_design_scores_gemma":[0.00244776,0.0002816924,0.4138441,0.003740715,0.0001614488,0.000009468451,0.0006479456,0.08211432,0.007656442,0.4888956,0.00006126775,0.0001392065],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07328229,0.0002937511,0.9250822,0.00004048678,0.0001251376,0.0001808646,0.0006493783,0.000005246029,0.000340628],"genre_scores_gemma":[0.5082842,0.0002253154,0.491415,0.000008362808,0.00002591371,0.000003060212,0.00001799677,0.00001011757,0.00001004181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4350019,"threshold_uncertainty_score":0.9625368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094834023","doi":"10.1002/sim.8766","title":"Minimum sample size for external validation of a clinical prediction model with a continuous outcome","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":198,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Medical Research Council; National Institute for Health and Care Research; NIHR School for Primary Care Research; NIHR Oxford Biomedical Research Centre; Medical Research Council Canada; Wellcome Trust; British Heart Foundation; Cancer Research UK","keywords":"Sample size determination; Variance (accounting); Statistics; Outcome (game theory); Calibration; Sample (material); Range (aeronautics); Cross-validation; Computer science; Mathematics; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.1267781237050936,"gpt":0.4179327851487913,"spread":0.2911546614436977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009544592,0.000133126,0.0006599664,0.00006954536,0.00002126086,0.000003554953,0.00007804234,0.00008117453,0.00005871992],"category_scores_gemma":[0.006315175,0.0001032928,0.00003975919,0.0001438602,0.0001808633,0.00003836704,0.00001566293,0.0002275858,8.446909e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003950909,"about_ca_system_score_gemma":0.000112042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002606805,"about_ca_topic_score_gemma":0.000004427293,"domain_scores_codex":[0.9979071,0.00006187077,0.001098547,0.000260235,0.000520444,0.000151801],"domain_scores_gemma":[0.9977784,0.001161373,0.0003172096,0.0001779585,0.0004157447,0.0001492959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.008982861,0.000733621,0.9074503,0.001654765,0.0001959515,0.00006388431,0.001799893,0.0004760147,0.03539501,0.008013451,0.02649726,0.008737004],"study_design_scores_gemma":[0.04521101,0.02764772,0.1683954,0.002894012,0.001667577,0.00004983499,0.0005895269,0.7112232,0.009123559,0.03158278,0.001053334,0.0005619964],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07299697,0.00002285076,0.9229719,0.002239757,0.0000904628,0.0009973532,0.0004181762,0.00007340474,0.0001891368],"genre_scores_gemma":[0.5756824,0.00001476551,0.4231483,0.0007786499,0.0002010653,0.00004021994,0.00008925958,0.0000167096,0.0000286205],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7390549,"threshold_uncertainty_score":0.756031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138986862","doi":"10.1002/sim.5452","title":"Generating survival times to simulate Cox proportional hazards models with time‐varying covariates","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":198,"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":"Covariate; Proportional hazards model; Statistics; Weibull distribution; Gompertz function; Mathematics; Statistical model; Econometrics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06665911353813758,"gpt":0.3846642828112441,"spread":0.3180051692731065,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007528662,0.0001871203,0.0003379047,0.00009996576,0.0001465651,0.00001957703,0.0001108561,0.00005275891,0.001461052],"category_scores_gemma":[0.001875781,0.0001459933,0.00001299595,0.0003335547,0.0001426199,0.0001026077,0.00003661603,0.000168377,0.0001095567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009483667,"about_ca_system_score_gemma":0.00008371026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003630147,"about_ca_topic_score_gemma":0.0000106399,"domain_scores_codex":[0.9982395,0.00007877347,0.0005464428,0.0002180781,0.0005476167,0.0003696282],"domain_scores_gemma":[0.9978829,0.001246601,0.0001436991,0.0002124768,0.0002682619,0.0002460326],"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":[0.00002977099,0.0001284076,0.0002409678,0.00004994643,0.00002302687,0.000005274624,0.0005718106,0.008439994,0.0002610009,0.9789031,0.01027937,0.001067316],"study_design_scores_gemma":[0.0009957906,0.0001081642,0.001241025,0.0001417949,0.00007476882,0.00001104772,0.0001361283,0.6938713,0.00006448283,0.3026638,0.0004208705,0.0002708215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003439303,0.00002110152,0.9908104,0.0007923851,0.00009256816,0.0004379116,0.0006797309,0.00007628495,0.003650312],"genre_scores_gemma":[0.4697669,0.000002539112,0.5286384,0.0002754672,0.0001749604,0.00007398561,0.0004958512,0.00002598608,0.0005459319],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6854313,"threshold_uncertainty_score":0.9994518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138878140","doi":"10.1002/sim.2069","title":"The value of information and optimal clinical trial design","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Population Health Research Institute; SickKids Foundation; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Sick Kids Foundation","keywords":"Type I and type II errors; Sample size determination; Null hypothesis; Value (mathematics); Sample (material); Set (abstract data type); Value of information; Computer science; Perspective (graphical); Statistics; Clinical trial; Medicine; Mathematics; Artificial intelligence; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5587308049738138,"gpt":0.6187845387614808,"spread":0.06005373378766699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01865485,0.0001318152,0.0006477474,0.00006821886,0.0000634176,0.0000145403,0.0002213538,0.0001340299,0.00008487343],"category_scores_gemma":[0.3376411,0.00008076955,0.00003089282,0.0001519213,0.0009333927,0.0000684545,0.0000707949,0.0003898998,0.000007382561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002817367,"about_ca_system_score_gemma":0.00008635099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001161245,"about_ca_topic_score_gemma":0.000007046101,"domain_scores_codex":[0.9950607,0.001457587,0.002590185,0.0001585994,0.0005026592,0.0002302093],"domain_scores_gemma":[0.8475086,0.1514656,0.0005115395,0.000281843,0.0001366871,0.00009570134],"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":[0.00653325,0.00008258587,0.00006960158,0.00005099456,0.00003150037,0.00000245476,0.0002478989,0.00002910914,0.000002312445,0.7330124,0.01336177,0.2465761],"study_design_scores_gemma":[0.02598109,0.001740946,0.0006570011,0.0001019282,0.00009625724,0.000002700716,0.0001621973,0.01439383,0.00002182247,0.9533074,0.003434558,0.000100239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002942194,0.00007956684,0.9934734,0.00114406,0.000808301,0.000795131,0.00006130837,0.00001650723,0.0006795272],"genre_scores_gemma":[0.007743992,0.0005403189,0.9908193,0.0002112728,0.0005988994,0.00002521435,0.000002594898,0.0000111811,0.00004721653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3189862,"threshold_uncertainty_score":0.6679382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016919144","doi":"10.1002/sim.2711","title":"Bayesian sensitivity analysis for unmeasured confounding in observational studies","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":184,"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; University of British Columbia Hospital","funders":"","keywords":"Confounding; Statistics; Markov chain Monte Carlo; Bayesian probability; Observational study; Econometrics; Logistic regression; Prior probability; Sample size determination; Sensitivity (control systems); Mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2203225194206481,"gpt":0.4762013753441512,"spread":0.2558788559235031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00294536,0.0001768332,0.0008009552,0.0003628785,0.00006371525,0.00001171296,0.00007116511,0.00006606093,0.00006737946],"category_scores_gemma":[0.01805763,0.0001502257,0.00003818837,0.0008277185,0.0002536201,0.00003833509,0.00002152377,0.0001678869,8.42037e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611168,"about_ca_system_score_gemma":0.00005240186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003665136,"about_ca_topic_score_gemma":0.005885283,"domain_scores_codex":[0.9979748,0.000286481,0.0007590422,0.0002980111,0.0003753425,0.0003063596],"domain_scores_gemma":[0.98395,0.01535692,0.0001767653,0.0001837016,0.0002851692,0.00004741342],"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":[0.00003397561,0.00006637172,0.05800291,0.0001833353,0.0001140439,0.00005978397,0.0003161396,0.0000754658,0.0001250078,0.9362516,0.002197913,0.002573407],"study_design_scores_gemma":[0.0008069526,0.00005678313,0.1207594,0.0001381655,0.0002324105,0.000001663247,0.0003050424,0.03279477,0.00001823679,0.8446822,0.00006386801,0.0001405755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00247425,0.00008674066,0.9955192,0.0005225808,0.0001829299,0.0003179997,0.000318397,0.00002004719,0.0005578473],"genre_scores_gemma":[0.3052233,0.00001311953,0.6943384,0.00008847916,0.0001301022,0.0000382837,0.000082087,0.00001172839,0.00007450845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.302749,"threshold_uncertainty_score":0.9902137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071109714","doi":"10.1002/sim.2655","title":"Analysing and interpreting competing risk data","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Hazard; Computer science; Event (particle physics); Population; Interpretation (philosophy); Econometrics; Statistics; Risk analysis (engineering); Mathematics; Medicine; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.1114147099766471,"gpt":0.460709521559191,"spread":0.349294811582544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00140484,0.0001232855,0.0003059004,0.0001291136,0.00006011228,0.00001312638,0.000207738,0.0000382111,0.00004983817],"category_scores_gemma":[0.006287939,0.0001053035,0.000004862316,0.0001693547,0.0002157671,0.00008150197,0.0002145456,0.0002877747,0.000001007496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004120034,"about_ca_system_score_gemma":0.00001136297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000581219,"about_ca_topic_score_gemma":0.0006890958,"domain_scores_codex":[0.9987797,0.0001077926,0.0004688413,0.0002602472,0.0001938509,0.0001895846],"domain_scores_gemma":[0.9967938,0.002452993,0.0002305615,0.0004346174,0.00005517051,0.00003285531],"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":[0.00002951048,0.00008964951,0.1007801,0.0003395611,0.00004453839,0.0001751472,0.001899589,0.00004696964,0.002490954,0.7953867,0.01646308,0.08225418],"study_design_scores_gemma":[0.0002839835,0.00005036424,0.001986134,0.0004991248,0.00006505438,0.000009054184,0.0006647958,0.04224221,0.000100934,0.9536461,0.0003144532,0.0001377498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02219973,0.0001747789,0.9734604,0.0001100909,0.00004620973,0.0001117918,0.0001234934,0.00009792814,0.003675586],"genre_scores_gemma":[0.3950902,0.00006674259,0.6045966,0.00003499829,0.00007895946,0.000002267789,0.00008952517,0.00001451631,0.00002616999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3728905,"threshold_uncertainty_score":0.7527705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2400385987","doi":"10.1002/sim.6986","title":"Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":177,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Population Health Research Institute","funders":"Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Computer science; Outcome (game theory); Ignorance; Calibration; Statistics; Econometrics; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6090490742207253,"gpt":0.5329850486829449,"spread":0.07606402553778036,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004384618,0.0002050755,0.0008513732,0.00006930033,0.00005986699,0.000004519154,0.0003525388,0.00007944301,0.00004454592],"category_scores_gemma":[0.1536168,0.00007045064,0.00008970518,0.000128932,0.0007947853,0.0000163228,0.00005394586,0.0002071665,4.573518e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005111064,"about_ca_system_score_gemma":0.0000644866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007620549,"about_ca_topic_score_gemma":0.000006848236,"domain_scores_codex":[0.997444,0.0004068706,0.001170678,0.0002246957,0.000470792,0.0002830104],"domain_scores_gemma":[0.8604295,0.1384452,0.0005214434,0.0004059188,0.0001489664,0.00004888378],"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":[0.0009997964,0.0004583304,0.03552201,0.0009509864,0.0002925588,0.000001594305,0.001593688,0.0004479432,0.00121152,0.92904,0.001633613,0.02784801],"study_design_scores_gemma":[0.002184932,0.002055496,0.009312034,0.001963553,0.0002067433,8.396643e-7,0.0002092338,0.1986456,0.0009474216,0.784352,0.000001335051,0.0001208108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3953355,0.00002455877,0.6026335,0.000290307,0.0001550652,0.001030751,0.0004163462,0.000009793811,0.0001042106],"genre_scores_gemma":[0.8511531,0.00007501791,0.1484722,0.00001389679,0.0001036638,0.0001197956,0.000002022924,0.00002547011,0.00003482617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4558177,"threshold_uncertainty_score":0.8535126,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014896206","doi":"10.1002/sim.8532","title":"STRATOS guidance document on measurement error and misclassification of variables in observational epidemiology: Part 1—Basic theory and simple methods of adjustment","year":2020,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":176,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of British Columbia","funders":"National Institutes of Health; National Cancer Institute; Medical Research Council; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Patient-Centered Outcomes Research Institute","keywords":"Covariate; Observational error; Statistics; Computer science; Observational study; Errors-in-variables models; Econometrics; Type I and type II errors; Regression; Regression analysis; Sample size determination; Extrapolation; Calibration; Linear regression; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3319225737265194,"gpt":0.4910995069651478,"spread":0.1591769332386284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005620636,0.0002607624,0.002186898,0.0001455168,0.00002290969,0.000001024182,0.00006731255,0.0001230609,0.00007745035],"category_scores_gemma":[0.007789714,0.0001863523,0.00004426187,0.0002212598,0.0003489383,0.00001286293,0.00004635724,0.0002738525,3.621134e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001999073,"about_ca_system_score_gemma":0.000209329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006651271,"about_ca_topic_score_gemma":0.00003080652,"domain_scores_codex":[0.9964949,0.0009896834,0.001535436,0.0003913878,0.000411747,0.0001768268],"domain_scores_gemma":[0.9941573,0.004721249,0.000638421,0.0001932819,0.0001944816,0.00009526229],"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":[0.0003040385,0.0002551535,0.001317019,0.03205015,0.0003398315,0.00001520876,0.0001379009,0.000003345183,0.00001560109,0.4019726,0.009904694,0.5536844],"study_design_scores_gemma":[0.003262773,0.001774345,0.03289328,0.04412734,0.00132403,0.00001300239,0.0004394328,0.0001004864,0.000005228627,0.1558093,0.7599753,0.000275393],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000129249,0.9880056,0.009210373,0.0009877735,0.0001154375,0.0009956316,0.0004495379,0.000004147426,0.0002185801],"genre_scores_gemma":[0.00009365068,0.9483869,0.05041533,0.000318059,0.0001339674,0.000218564,0.000402545,0.00001598791,0.00001500078],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7500706,"threshold_uncertainty_score":0.9325578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099844674","doi":"10.1002/sim.1115","title":"Current and future challenges in the design and analysis of cluster randomization trials","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Cancer Care Ontario","funders":"","keywords":"Randomization; Cluster (spacecraft); Cluster randomised controlled trial; Restricted randomization; Psychological intervention; Randomized controlled trial; Research design; Computer science; Medicine; Statistics; Mathematics; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.6291099124678506,"gpt":0.5903951121051839,"spread":0.03871480036266672,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02845252,0.0001407542,0.001487455,0.0003282651,0.00002201507,0.000007754959,0.0001144859,0.00009021942,0.0001039725],"category_scores_gemma":[0.1385399,0.00007918111,0.00003325487,0.0005794817,0.0002655987,0.00002049689,0.00002849376,0.0002303556,1.945375e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001478729,"about_ca_system_score_gemma":0.00001550851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000854579,"about_ca_topic_score_gemma":0.00005651923,"domain_scores_codex":[0.9924769,0.00525439,0.001489459,0.0002487189,0.0003760933,0.0001544868],"domain_scores_gemma":[0.8455071,0.1538071,0.0003568124,0.0002119372,0.00007410357,0.00004287078],"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":[0.001729383,0.000215166,0.002131017,0.0003850071,0.0003363965,0.00002522724,0.00546169,0.00004713554,0.00000878353,0.480347,0.0015454,0.5077679],"study_design_scores_gemma":[0.008749942,0.0001890102,0.0127062,0.0001706966,0.001574611,0.000003125225,0.0008593666,0.01262836,0.000002147579,0.9624972,0.000521298,0.00009805933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001715755,0.004819219,0.9892414,0.002783117,0.0002809674,0.0009104132,0.00006983995,0.000006112587,0.0001732053],"genre_scores_gemma":[0.01685627,0.0750768,0.9073563,0.0001492583,0.0004625823,0.00006380152,0.00001268237,0.00001603126,0.000006248744],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5076697,"threshold_uncertainty_score":0.9861132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159741108","doi":"10.1002/sim.1335","title":"Power and sample size for DNA microarray studies","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"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 Heart, Lung, and Blood Institute","keywords":"Sample size determination; Statistics; Computer science; Sample (material); Power (physics); Computational biology; Mathematics; Biology; Chromatography; Chemistry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03013445253274159,"gpt":0.3339330755395447,"spread":0.303798623006803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001247673,0.00007264991,0.0001136883,0.00002501748,0.00003594527,0.000003123434,0.00004824803,0.00004142431,0.0001038045],"category_scores_gemma":[0.002034053,0.00005852583,0.000008305627,0.00004131704,0.0001266452,8.4076e-7,0.00002003157,0.00003364416,9.711761e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008704134,"about_ca_system_score_gemma":0.000006615528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003477041,"about_ca_topic_score_gemma":0.00001877381,"domain_scores_codex":[0.9994848,0.00001876706,0.0001438684,0.000182977,0.00006296333,0.0001066726],"domain_scores_gemma":[0.9995223,0.0001996209,0.00004243139,0.000130415,0.00006857104,0.00003662735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005849468,0.00004113786,0.001662991,0.00007615019,0.00004071335,0.000001581373,0.001049576,0.000002071881,0.5592846,0.001660472,0.4260972,0.01002497],"study_design_scores_gemma":[0.006236137,0.00180241,0.01525531,0.0001855857,0.00006276015,0.00001268687,0.005179298,0.0003673874,0.05744839,0.02761585,0.8853046,0.0005295271],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4970315,0.06052702,0.4114495,0.01709609,0.003313938,0.002177474,0.001352027,0.00005334599,0.006999218],"genre_scores_gemma":[0.9532593,0.00399045,0.03927045,0.001055559,0.0002077999,0.00006219557,0.00004586714,0.00001564623,0.002092717],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5018362,"threshold_uncertainty_score":0.2435098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054344391","doi":"10.1002/sim.3504","title":"Age‐ and size‐related reference ranges: A case study of spirometry through childhood and adulthood","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Skewness; Kurtosis; Statistics; Spirometry; Mathematics; Generalized additive model; Linear regression; Medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01751881853312985,"gpt":0.2850192669584043,"spread":0.2675004484252745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002745934,0.0001175865,0.0003395978,0.00004162329,0.00009883197,0.000001533845,0.00006887259,0.00006867253,0.0006635091],"category_scores_gemma":[0.0003704878,0.00009223189,0.000006372407,0.0003735511,0.0007309882,0.00005245372,0.00008240667,0.000209652,0.000005634985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001633143,"about_ca_system_score_gemma":0.000005259558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004412549,"about_ca_topic_score_gemma":0.002898436,"domain_scores_codex":[0.9989222,0.0001132511,0.0003308748,0.0002739315,0.0002090918,0.0001506769],"domain_scores_gemma":[0.9992803,0.0003744899,0.00009492858,0.0001767484,0.000007780954,0.00006579891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006067939,0.0009564372,0.8184949,0.00004118104,0.0001318392,0.02348729,0.1494661,0.00007442326,0.0003394989,0.0003243714,0.0008279659,0.005795313],"study_design_scores_gemma":[0.004955043,0.001625379,0.9700427,0.00004081815,0.0002095534,0.002097339,0.01448907,0.0004679362,0.00001554604,0.005794944,0.00006326279,0.0001983877],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974462,0.0002575044,0.0004995455,0.00006872196,0.00002461511,0.0001734752,0.0000157449,0.000008266806,0.001505899],"genre_scores_gemma":[0.9955213,0.0005028989,0.00376428,0.0001091421,0.000009760242,0.000005421128,0.000006277047,0.000006376947,0.00007451944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1515478,"threshold_uncertainty_score":0.726496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970654520","doi":"10.1002/sim.3701","title":"Flexible modeling of the cumulative effects of time‐dependent exposures on the hazard","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Faculty of Medicine, McGill University; McGill University","keywords":"Covariate; Proportional hazards model; Statistics; Econometrics; Hazard; Regression analysis; Medicine; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2270755262068856,"gpt":0.4336685487184045,"spread":0.206593022511519,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008124019,0.0001188619,0.0006887708,0.0001579461,0.00006770705,0.000005079585,0.0002819092,0.0000595169,0.0001599917],"category_scores_gemma":[0.01048899,0.00008515611,0.00003807147,0.0001688321,0.0001297278,0.00004410386,0.00002486583,0.0001867553,0.00005070034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001395015,"about_ca_system_score_gemma":0.00006224096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003928462,"about_ca_topic_score_gemma":0.00004541587,"domain_scores_codex":[0.9968534,0.0003319049,0.002241321,0.0002152064,0.0001738174,0.0001844129],"domain_scores_gemma":[0.9947907,0.003477198,0.001174705,0.0004453161,0.00007032225,0.00004180211],"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":[0.00004467698,0.0001465113,0.005130142,0.0004141164,0.0000594708,0.000001547432,0.007751571,0.04034973,0.00006600343,0.9268062,0.01868472,0.000545285],"study_design_scores_gemma":[0.001949566,0.0008088883,0.02993267,0.001207561,0.00002417473,0.000001337747,0.001361091,0.355788,0.0003563038,0.6079884,0.0003485684,0.0002334897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.460369,0.005239285,0.3973918,0.08371398,0.00237736,0.004292353,0.001034799,0.00005055233,0.04553092],"genre_scores_gemma":[0.9943603,0.00009018789,0.001718276,0.003259996,0.0001146875,0.00001600185,0.000008234781,0.00001091356,0.0004214126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5339913,"threshold_uncertainty_score":0.9978461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097027506","doi":"10.1002/1097-0258(20000730)19:14<1849::aid-sim506>3.0.co;2-1","title":"Estimating treatment effects in randomized clinical trials in the presence of non-compliance","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Universiteit Leiden","keywords":"Confounding; Randomization; Randomized controlled trial; Outcome (game theory); Clinical trial; Medicine; Placebo; Estimator; Statistics; Instrumental variable; Causal inference; Econometrics; Internal medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2897409135338255,"gpt":0.5720931192616544,"spread":0.2823522057278289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0237718,0.000185358,0.002218789,0.0001315378,0.00001592135,0.000004809496,0.0002545853,0.00008334205,0.0001176372],"category_scores_gemma":[0.09670696,0.0001050537,0.00006235579,0.0002981524,0.0004613751,0.00004195685,0.00001659721,0.0003184688,0.000003080705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007681386,"about_ca_system_score_gemma":0.00005067522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000302815,"about_ca_topic_score_gemma":0.0002289232,"domain_scores_codex":[0.9925598,0.00402531,0.002568162,0.0002524985,0.0003391031,0.0002551406],"domain_scores_gemma":[0.8913952,0.1076933,0.0004710022,0.0003656458,0.00004097106,0.00003387783],"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":[0.01638176,0.00185007,0.0058649,0.001606536,0.0001066823,0.0006734867,0.01811476,0.001065722,0.0004275819,0.2066138,0.00288115,0.7444135],"study_design_scores_gemma":[0.05925073,0.0005226659,0.001544909,0.002645229,0.00006761331,0.000004011987,0.0001616525,0.07916347,0.0001521079,0.8563522,0.00001531579,0.0001200957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06532778,0.0002174212,0.9277225,0.0003510711,0.0001810141,0.003677874,0.00002769681,0.00003456976,0.002460054],"genre_scores_gemma":[0.3833678,0.0003487446,0.6156754,0.00008453342,0.00008428524,0.0003503661,0.000008801272,0.00001392176,0.00006613875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7442934,"threshold_uncertainty_score":0.9109018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071379517","doi":"10.1002/sim.2770","title":"A comparison of regression trees, logistic regression, generalized additive models, and multivariate adaptive regression splines for predicting AMI mortality","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"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":"Logistic regression; Multivariate adaptive regression splines; Statistics; Receiver operating characteristic; Multivariate statistics; Regression; Regression analysis; Logistic model tree; Predictive modelling; Mathematics; Bayesian multivariate linear regression; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1183073088240789,"gpt":0.4368427016114135,"spread":0.3185353927873346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001119848,0.0003483038,0.0009147302,0.0002614695,0.0002208814,0.00002008739,0.0004315969,0.0001729451,0.00001054972],"category_scores_gemma":[0.002224301,0.0002387051,0.00003560045,0.0003781928,0.0003477266,0.0001707715,0.0002489395,0.0004658063,3.359158e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020275,"about_ca_system_score_gemma":0.000114797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005604393,"about_ca_topic_score_gemma":0.001181507,"domain_scores_codex":[0.9965249,0.0004805751,0.001181184,0.0007271413,0.000662496,0.0004237032],"domain_scores_gemma":[0.9957686,0.002038684,0.0009922608,0.0005557586,0.0005058893,0.0001388096],"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":[0.001126822,0.0006576761,0.2602929,0.001537288,0.0001027936,0.0001704323,0.01126565,0.04093446,0.001601234,0.5615667,0.02610671,0.09463745],"study_design_scores_gemma":[0.001997193,0.0004776838,0.06557643,0.001919543,0.00003711716,0.000005203238,0.0002681814,0.8458922,0.000119953,0.08342929,0.00008349148,0.0001937142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0234952,0.001492643,0.9725293,0.0005538188,0.0004906713,0.0007758264,0.000389742,0.00009514912,0.0001776397],"genre_scores_gemma":[0.6914147,0.00008810958,0.3078234,0.00004838814,0.000211115,0.00005861626,0.0002551503,0.00002120753,0.00007927445],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8049577,"threshold_uncertainty_score":0.9734111,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2579663487","doi":"10.1002/sim.7215","title":"Accounting for competing risks in randomized controlled trials: a review and recommendations for improvement","year":2017,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":152,"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; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Randomized controlled trial; Cumulative incidence; Incidence (geometry); Outcome (game theory); Event (particle physics); Survival analysis; Medicine; Relative risk; Actuarial science; Confidence interval; Cohort; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.8315391831852751,"gpt":0.7107421776711227,"spread":0.1207970055141524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2000932,0.0007115617,0.03982186,0.0004235818,0.0001681697,0.00006649049,0.000483893,0.000384783,0.000183716],"category_scores_gemma":[0.9416268,0.0004348069,0.0009916383,0.0001590232,0.0004564319,0.00003822746,0.0001355614,0.0007843678,0.000001232019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001754492,"about_ca_system_score_gemma":0.0002948626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006427499,"about_ca_topic_score_gemma":0.00005271671,"domain_scores_codex":[0.9755104,0.008749117,0.01383447,0.0008662472,0.0004337368,0.0006060323],"domain_scores_gemma":[0.4135163,0.5783305,0.007198615,0.000532572,0.000321333,0.0001006024],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002834314,0.00006227433,2.230432e-7,0.1212955,0.000597849,0.000002868482,0.00004053859,1.631567e-8,2.783328e-8,0.08028455,0.005893324,0.7889885],"study_design_scores_gemma":[0.1798318,0.0001403165,6.98928e-8,0.1361159,0.01499806,0.000001725539,0.00003064282,0.0002643671,1.842363e-8,0.5131682,0.1551688,0.000280026],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.171178e-8,0.6325012,0.3363447,0.0008899962,0.0008931131,0.02712273,0.00208654,0.00001522812,0.0001463854],"genre_scores_gemma":[5.440304e-8,0.5287631,0.4613141,0.0001783038,0.0004230543,0.009068119,0.0001280612,0.0000561188,0.00006906847],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7887084,"threshold_uncertainty_score":0.9998104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162274668","doi":"10.1002/sim.2624","title":"Using mixed treatment comparisons and meta‐regression to perform indirect comparisons to estimate the efficacy of biologic treatments in rheumatoid arthritis","year":2006,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital","funders":"","keywords":"Meta-analysis; Medicine; Odds ratio; Rheumatoid arthritis; Internal medicine; Random effects model; Meta-regression; Placebo; Randomized controlled trial; Sample size determination; Statistics; Pathology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1452751148105242,"gpt":0.4591348507660336,"spread":0.3138597359555093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000679768,0.0006925463,0.005021826,0.0008761782,0.0001428469,0.00002167683,0.0002042648,0.0001772635,0.0001108391],"category_scores_gemma":[0.0007087594,0.0003429558,0.0001668962,0.0008008598,0.0004433136,0.0000267963,0.0001200253,0.0004444276,0.00001195657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003774171,"about_ca_system_score_gemma":0.0002797903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003141108,"about_ca_topic_score_gemma":0.004781723,"domain_scores_codex":[0.996403,0.0004598492,0.001428401,0.0005700712,0.0005204785,0.0006181842],"domain_scores_gemma":[0.9970987,0.00162219,0.0003534362,0.0005034067,0.0000910451,0.0003311805],"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":[0.0002456621,0.0008054816,0.006257115,0.001580808,0.001622364,0.0002926978,0.0007945517,0.00005538485,0.000009723011,0.0003701435,0.002886333,0.9850798],"study_design_scores_gemma":[0.01912236,0.01072478,0.0308052,0.1008394,0.003296525,0.0007439642,0.000696897,0.001427436,0.00004763242,0.0003106163,0.8306381,0.001347036],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01019188,0.9843983,0.0009172701,0.0001981651,0.00013413,0.003330284,0.0006809526,0.00002281196,0.0001261757],"genre_scores_gemma":[0.0070601,0.9738185,0.01807155,0.0000250608,0.00003769598,0.0003219893,0.000557314,0.00005456248,0.00005324684],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9837327,"threshold_uncertainty_score":0.9999022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982693598","doi":"10.1002/sim.8399","title":"A review of the use of time‐varying covariates in the Fine‐Gray subdistribution hazard competing risk regression model","year":2019,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":151,"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; International Council for the Exploration of the Sea; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Gray (unit); Regression analysis; Econometrics; Regression; Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.2756750443033474,"gpt":0.4708426292700219,"spread":0.1951675849666745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005033984,0.0003621984,0.002621033,0.0001206777,0.00004920385,0.000008172225,0.0005708532,0.0001738443,0.0001088691],"category_scores_gemma":[0.06329907,0.0001648509,0.0001374415,0.0006725626,0.0003171012,0.00002620911,0.0001516632,0.0009437075,0.000003697644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009066478,"about_ca_system_score_gemma":0.0002494781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000157985,"about_ca_topic_score_gemma":0.00003279379,"domain_scores_codex":[0.9943098,0.002422311,0.002085901,0.000301069,0.0006214374,0.0002594253],"domain_scores_gemma":[0.9728578,0.02399315,0.002049703,0.0008162266,0.0002486029,0.00003445812],"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":[0.00001705498,0.0001364625,0.00006668438,0.3164381,0.00006626635,0.000008777268,0.000507909,0.00003818265,0.000002339761,0.2077515,0.01346192,0.4615048],"study_design_scores_gemma":[0.0004974267,0.0001307349,0.00003361755,0.7757645,0.001927356,0.00001310717,0.00002796713,0.03811998,0.000001052028,0.15772,0.02546721,0.000297046],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001976419,0.6782525,0.3179381,0.00005339064,0.0001196164,0.001173251,0.002311844,0.000005204232,0.0001441491],"genre_scores_gemma":[0.000008119365,0.7926552,0.2069769,0.00006743996,0.00003109814,0.00003392589,0.0001809307,0.00002380623,0.00002253241],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4612077,"threshold_uncertainty_score":0.9445912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2896981660","doi":"10.1002/sim.8008","title":"Propensity‐score matching with competing risks in survival analysis","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":147,"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 Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Covariate; Observational study; Matching (statistics); Hazard ratio; Confounding; Sample size determination; Medicine; Absolute risk reduction; Confidence interval; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2384664040620321,"gpt":0.4583996193977982,"spread":0.2199332153357661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001356391,0.0001828698,0.0006399223,0.0004041283,0.00005302934,0.00001106962,0.0001833503,0.00005705481,0.0001815781],"category_scores_gemma":[0.001528044,0.0001342208,0.00001328933,0.0009958131,0.0003917107,0.00006452746,0.00007041612,0.0003785256,0.00000458181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001082927,"about_ca_system_score_gemma":0.00003677035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001285666,"about_ca_topic_score_gemma":0.01293503,"domain_scores_codex":[0.9983619,0.000150369,0.0005061423,0.0002815475,0.000396811,0.0003031802],"domain_scores_gemma":[0.9980394,0.001155309,0.0002106536,0.000337415,0.0001971812,0.00006005298],"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":[0.0001646355,0.0001549616,0.594779,0.0002350136,0.0001877082,0.000470114,0.007737148,0.0001266187,0.00086593,0.3898057,0.0003330047,0.005140123],"study_design_scores_gemma":[0.001050162,0.000599377,0.1665393,0.0008578853,0.0002909161,0.000009614103,0.0020042,0.002799703,0.0004367973,0.8250068,0.00003797758,0.0003672669],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3842071,0.000008850707,0.6120987,0.00008011199,0.0000445546,0.0002167269,0.00001741795,0.00007107168,0.003255508],"genre_scores_gemma":[0.679157,0.00001142733,0.3206189,0.00005121932,0.00007424379,0.00001163854,0.00002110249,0.00001913894,0.0000353833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4352011,"threshold_uncertainty_score":0.7218051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2055260064","doi":"10.1002/sim.1442","title":"A comparison of several regression models for analysing cost of CABG surgery","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Health Sciences Centre; Institute for Clinical Evaluative Sciences; University of Calgary; Sunnybrook Health Science Centre; Women's College Hospital; University of Toronto","funders":"","keywords":"Linear regression; Statistics; Poisson regression; Generalized linear model; Regression analysis; Regression; Proportional hazards model; Medicine; Linear model; Negative binomial distribution; Mathematics; Poisson distribution; Econometrics; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.5450433319250734,"gpt":0.5321256663837163,"spread":0.01291766554135709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01362454,0.0001183213,0.001629085,0.0004772914,0.00004596612,0.000004054012,0.0000970144,0.00008169579,0.000150879],"category_scores_gemma":[0.01187282,0.0001286821,0.00005435314,0.0002378867,0.0001314058,0.00009767392,0.00001028196,0.0001041838,0.000005745246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001895245,"about_ca_system_score_gemma":0.0001356133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006645215,"about_ca_topic_score_gemma":0.0002018071,"domain_scores_codex":[0.9948333,0.0002333881,0.004338871,0.000256362,0.0001090239,0.0002290689],"domain_scores_gemma":[0.9926246,0.004366081,0.002514121,0.0002800678,0.0001356977,0.00007945779],"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":[0.00006333464,0.0002035815,0.1886486,0.001858993,0.00008511452,0.000001164253,0.005486358,0.02052904,0.00001225393,0.7018703,0.08047863,0.0007626469],"study_design_scores_gemma":[0.002440492,0.0001973661,0.01183304,0.00112943,0.00003854051,0.000002122513,0.003563143,0.6995084,0.00006642706,0.2753469,0.005552415,0.0003217151],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02948574,0.002164297,0.9631422,0.001596836,0.0005295366,0.0006130224,0.0008731805,0.000006923282,0.001588275],"genre_scores_gemma":[0.9412047,0.0001263778,0.0578457,0.0004487112,0.00006816105,0.00003471282,0.000128813,0.0000180797,0.0001247832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9117189,"threshold_uncertainty_score":0.9964506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092848201","doi":"10.1002/sim.2680","title":"Modelling smoking history using a comprehensive smoking index: application to lung cancer","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":139,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Montreal General Hospital; Université de Montréal; McGill University; Queen's University","funders":"","keywords":"Lung cancer; Statistics; Smoking history; Covariate; Econometrics; Regression analysis; Medicine; Index (typography); Demography; Computer science; Mathematics; Oncology; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.05194383189967641,"gpt":0.3575085325930135,"spread":0.3055647006933371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002585605,0.0001950439,0.0003921768,0.0004067781,0.00007306112,0.000006624313,0.00008125422,0.0001164309,0.0001578221],"category_scores_gemma":[0.00004734908,0.0001931188,0.00002301142,0.0003423715,0.00009925691,0.00005055972,0.00002753144,0.0003573014,5.707504e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00187602,"about_ca_system_score_gemma":0.0001501462,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01396667,"about_ca_topic_score_gemma":0.0001686659,"domain_scores_codex":[0.998184,0.00003742677,0.0005053676,0.0003623012,0.0006049979,0.0003058597],"domain_scores_gemma":[0.9990836,0.0001175158,0.0001669673,0.000260086,0.0002696207,0.0001022475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00013525,0.0001089474,0.7264822,0.0003381424,0.00004079278,0.00009986271,0.001981806,0.2473487,0.005802266,0.004065532,0.005994101,0.007602456],"study_design_scores_gemma":[0.002738719,0.00009747292,0.2137201,0.001358254,0.0004986178,0.0000302804,0.0004249511,0.7748002,0.0001693242,0.001339303,0.00447345,0.0003493694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3844754,0.0006874887,0.6133339,0.0001517849,0.0004547207,0.00041563,0.00001735176,0.00004265971,0.0004210068],"genre_scores_gemma":[0.9909188,0.00004639137,0.007481016,0.0005932321,0.0005730691,0.00007564524,0.0001503726,0.0000443895,0.000117141],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6064433,"threshold_uncertainty_score":0.9925994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139017261","doi":"10.1002/sim.6265","title":"STRengthening Analytical Thinking for Observational Studies: the STRATOS initiative","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Economic and Social Research Council; Medical Research Council; Cancer Research UK; McGill University","keywords":"Observational study; Computer science; Econometrics; Data science; Management science; Statistics; Mathematics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.8755938676556354,"gpt":0.6135030834304239,"spread":0.2620907842252115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1250455,0.0001950515,0.002040097,0.0001957232,0.0002175932,0.0001375415,0.0009993659,0.00004108747,0.00141388],"category_scores_gemma":[0.3467949,0.00007409384,0.0001965036,0.000818087,0.0002728683,0.00007804228,0.00007196482,0.0002041211,0.00007020008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003798013,"about_ca_system_score_gemma":0.00005937068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005981417,"about_ca_topic_score_gemma":0.0001179423,"domain_scores_codex":[0.9850941,0.003946467,0.00623451,0.0005418327,0.003952259,0.0002308588],"domain_scores_gemma":[0.9058325,0.08852912,0.00241627,0.001285744,0.001858182,0.00007815054],"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":[0.000005970073,0.00001321702,0.008360719,0.00003886233,0.00016929,0.000001690608,0.004573979,0.000272386,0.000002121468,0.8301748,0.1447542,0.01163275],"study_design_scores_gemma":[0.0004455966,0.0001270383,0.01569497,0.00012537,0.0002276731,0.000001785669,0.01052548,0.2409527,0.000001091362,0.696734,0.03505871,0.0001056922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005553451,0.0004166736,0.982564,0.006251001,0.0004188188,0.0006359779,0.00009084037,0.000003634903,0.004065555],"genre_scores_gemma":[0.8458551,0.00004608135,0.1473355,0.00409363,0.0007100831,0.0001163205,0.00007242542,0.00001655073,0.001754357],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8403016,"threshold_uncertainty_score":0.999499,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}