{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":233,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":233,"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":"9890b73406e3","filters":{"venue":"Statistical Methods in Medical Research"}},"results":[{"id":"W2130845266","doi":"10.1177/0962280211427759","title":"Extension of the modified Poisson regression model to prospective studies with correlated binary data","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":745,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Binary data; Estimator; Poisson distribution; Mathematics; Poisson regression; Logistic regression; Econometrics; Variance (accounting); Regression analysis; Cluster (spacecraft); Binary number; Computer science; Population; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6529093814670139,"gpt":0.6393137010129344,"spread":0.01359568045407955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01804409,0.0002438039,0.0007742554,0.0002338764,0.0001828236,0.00001471166,0.001411315,0.0002439995,0.0003916312],"category_scores_gemma":[0.2318256,0.0001231512,0.00003222159,0.001482217,0.001774276,0.00007994386,0.001934842,0.001680538,0.000006429558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001239034,"about_ca_system_score_gemma":0.0004903477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001341799,"about_ca_topic_score_gemma":0.0000511098,"domain_scores_codex":[0.9895895,0.005487652,0.0008293383,0.0008817919,0.002484043,0.0007276913],"domain_scores_gemma":[0.9634731,0.03325433,0.0001385084,0.001703592,0.0009118504,0.0005186638],"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":[0.001092283,0.0004988915,0.0003371124,0.0002681276,0.00005212335,0.0001540343,0.001803915,0.000003086187,0.0005184634,0.7806562,0.001982179,0.2126336],"study_design_scores_gemma":[0.0005317297,0.0005402137,0.006427182,0.001379739,0.00003351434,0.00001032996,0.0006000091,0.1362593,0.0009272619,0.8531279,0.000008963104,0.0001539076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003359865,0.0001131653,0.9917343,0.0006589983,0.0001323839,0.0009387397,0.0001216951,0.00002758097,0.002913261],"genre_scores_gemma":[0.07525264,0.00006772597,0.9243379,0.00007285537,0.00002435081,0.0000927905,0.000003575194,0.00003390488,0.0001142694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2137815,"threshold_uncertainty_score":0.7746451,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2613408792","doi":"10.1177/0962280217710835","title":"Compositional data analysis for physical activity, sedentary time and sleep research","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":547,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Children's Hospital of Eastern Ontario","funders":"Ministerio de Economía y Competitividad; Australian Government; Coca-Cola Foundation","keywords":"Compositional data; Multicollinearity; Physical activity; Statistical inference; Causal inference; Statistics; Econometrics; Inference; Psychology; Regression analysis; Computer science; Mathematics; Medicine; Physical therapy; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3791836015499943,"gpt":0.623165077965462,"spread":0.2439814764154677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03256501,0.0001252237,0.0004193577,0.000303962,0.001001383,0.0004319698,0.004086102,0.0001696761,0.0004053116],"category_scores_gemma":[0.05682416,0.0001074836,0.00004594064,0.0006568397,0.00205114,0.0003077844,0.006361615,0.001525064,0.00002318117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005940281,"about_ca_system_score_gemma":0.0002779812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002760847,"about_ca_topic_score_gemma":0.00005046165,"domain_scores_codex":[0.9921122,0.003323092,0.0002279852,0.001099764,0.002351378,0.0008855515],"domain_scores_gemma":[0.9652452,0.03185216,0.00004706464,0.00188147,0.0004251078,0.0005489645],"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":[0.0001595706,0.0005533941,0.00113155,0.0001277346,0.000196021,0.0002695168,0.0001433172,0.00001033362,0.002140614,0.1474275,0.005619561,0.8422209],"study_design_scores_gemma":[0.0003642389,0.0001368441,0.02884987,0.00002916828,0.00001693825,0.000007684821,0.00001318863,0.7599959,0.0005219453,0.2061946,0.003762396,0.0001072075],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00353029,0.000036106,0.9651938,0.02412332,0.00005649734,0.0003497107,0.000185547,0.0000184336,0.006506309],"genre_scores_gemma":[0.2628785,0.00001986235,0.7360466,0.00005574971,0.0002286394,0.00008843834,0.00009066907,0.000003919041,0.0005876122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8421137,"threshold_uncertainty_score":0.9961779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157235443","doi":"10.1177/0962280214521348","title":"Multiple imputation of covariates by fully conditional specification: Accommodating the substantive model","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":491,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; Economic and Social Research Council; University of California, San Diego; National Institutes of Health; Genentech; IXICO; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Novartis Pharmaceuticals Corporation; Synarc; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"Covariate; Imputation (statistics); Missing data; Econometrics; Computer science; Statistics; Specification; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2276033325385271,"gpt":0.5725945814759557,"spread":0.3449912489374286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02596157,0.0001796809,0.0005060642,0.0001539499,0.0002184502,0.00005549985,0.0006583232,0.0002181217,0.001526929],"category_scores_gemma":[0.2358185,0.0001242444,0.00005063929,0.0006987746,0.0015557,0.0000741524,0.0002030862,0.001291321,0.00001417664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008742861,"about_ca_system_score_gemma":0.0002843665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008356349,"about_ca_topic_score_gemma":0.00001958056,"domain_scores_codex":[0.9880795,0.007631482,0.00104557,0.0004722243,0.002164097,0.0006071259],"domain_scores_gemma":[0.8324588,0.1660668,0.0001726439,0.0004097353,0.0006027401,0.0002892961],"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":[0.00006642779,0.0001549998,0.0002055723,0.00008632043,0.00001330623,0.000003468845,0.0002095876,0.000006489765,0.001112429,0.7763035,0.002001504,0.2198364],"study_design_scores_gemma":[0.0003629684,0.00008012106,0.001167596,0.00006291507,0.000007657975,0.000002065339,0.0001435594,0.3583513,0.0008803408,0.638704,0.0001503216,0.00008720977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007212588,0.00003499243,0.9940387,0.001389893,0.00006699164,0.0004053279,0.0003252042,0.00002249679,0.002995135],"genre_scores_gemma":[0.1717995,0.00002314458,0.827825,0.00007907413,0.00007182942,0.0001005712,0.00005609067,0.00002177292,0.00002306485],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3583448,"threshold_uncertainty_score":0.9993858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100697007","doi":"10.1177/0962280214558972","title":"Events per variable (EPV) and the relative performance of different strategies for estimating the out-of-sample validity of logistic regression models","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":484,"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 Neurological Disorders and Stroke; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Statistics; Sample size determination; Logistic regression; Sample (material); Mathematics; Regression analysis; Econometrics; Mean squared error; Regression; Linear regression; Variance (accounting); Variables; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3934446952715054,"gpt":0.579674810655022,"spread":0.1862301153835166,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03290375,0.000177432,0.0008481187,0.00009037222,0.0001726553,0.00001930212,0.0005253757,0.000176754,0.0002047556],"category_scores_gemma":[0.2396518,0.00008294976,0.00006006138,0.0002394961,0.002994153,0.00007345768,0.0003285731,0.000897509,2.885302e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000322099,"about_ca_system_score_gemma":0.0002409571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001186971,"about_ca_topic_score_gemma":0.000009171365,"domain_scores_codex":[0.9878017,0.0088264,0.001088635,0.0003376075,0.001465856,0.0004797842],"domain_scores_gemma":[0.7031545,0.2955875,0.0002611755,0.0004110624,0.0004396992,0.0001460556],"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":[0.0003435344,0.0001197633,0.0001946041,0.00114782,0.00002272686,3.494843e-7,0.0006867333,0.00001395549,0.00006043642,0.8486877,0.00003172585,0.1486906],"study_design_scores_gemma":[0.0005507544,0.0002831066,0.0003452689,0.0004619404,0.00002867048,5.841314e-7,0.0001652232,0.4218926,0.0001462419,0.576071,0.000004828064,0.00004983165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003192432,0.00003326925,0.9945339,0.0002634128,0.00013959,0.0006872028,0.0001167371,0.000006094737,0.001027356],"genre_scores_gemma":[0.2263138,0.00003373444,0.7734734,0.00001004326,0.00003644657,0.0001068403,0.000002983891,0.00001315596,0.000009568374],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4218786,"threshold_uncertainty_score":0.9997191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1829168467","doi":"10.1191/0962280204sm365ra","title":"Sample size requirements for the design of reliability study: review and new results","year":2004,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":468,"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":"Intraclass correlation; Sample size determination; Reliability (semiconductor); Variance (accounting); Statistics; Sample (material); Computer science; Mathematics; Reliability engineering; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.7388653050513273,"gpt":0.6767105014196586,"spread":0.0621548036316687,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3059061,0.0001586218,0.0007157914,0.0001192253,0.000234616,0.00008057058,0.001493691,0.0001173259,0.001230869],"category_scores_gemma":[0.885231,0.0000838829,0.00006633768,0.001371154,0.001272959,0.00008711299,0.0005117015,0.0007985488,0.00001097812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001576554,"about_ca_system_score_gemma":0.00102483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009682967,"about_ca_topic_score_gemma":0.00008592699,"domain_scores_codex":[0.9661128,0.0174778,0.003102248,0.001373613,0.01100778,0.0009257876],"domain_scores_gemma":[0.2118028,0.781992,0.000361751,0.002526177,0.002214304,0.001102982],"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":[0.0008900702,0.000996033,0.001086405,0.0003816549,0.0000367946,0.000009792651,0.0006431302,0.0001015617,0.00006885325,0.01230432,0.01676285,0.9667186],"study_design_scores_gemma":[0.002557727,0.001583491,0.01666613,0.0004758434,0.00004343197,9.721886e-7,0.000704837,0.001384857,0.00008773887,0.9667127,0.009666867,0.0001153959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002772174,0.001785707,0.9649975,0.02878453,0.0001465486,0.00372231,0.00007045415,0.000007060383,0.0002086929],"genre_scores_gemma":[0.01529603,0.002371657,0.9812514,0.000588629,0.0000658162,0.0002700231,0.000001357453,0.00001042662,0.000144685],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9666032,"threshold_uncertainty_score":0.9996821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2035404753","doi":"10.1177/0962280215584401","title":"The performance of inverse probability of treatment weighting and full matching on the propensity score in the presence of model misspecification when estimating the effect of treatment on survival outcomes","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":325,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Mental Health","keywords":"Propensity score matching; Observational study; Matching (statistics); Statistics; Inverse probability weighting; Hazard ratio; Inverse probability; Covariate; Average treatment effect; Selection bias; Confounding; Weighting; Marginal structural model; Econometrics; Selection (genetic algorithm); Mathematics; Computer science; Medicine; Confidence interval; Posterior probability; Bayesian probability; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5863130353224311,"gpt":0.5806095152849405,"spread":0.005703520037490528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03236401,0.0001566107,0.0005199593,0.00006370126,0.0001098177,0.00001232008,0.0005161812,0.00007924562,0.000008713187],"category_scores_gemma":[0.06968031,0.000054903,0.00003950169,0.0002428548,0.001570897,0.0000422767,0.0001626837,0.000552514,2.337649e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002633104,"about_ca_system_score_gemma":0.0002628237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003791909,"about_ca_topic_score_gemma":0.0001795942,"domain_scores_codex":[0.9894098,0.00790736,0.0007768646,0.0002580839,0.001348078,0.0002998223],"domain_scores_gemma":[0.9058805,0.09295272,0.0002342446,0.0006519073,0.0002093207,0.0000713251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001898006,0.0007830943,0.02241156,0.0010132,0.00006780739,0.000005805091,0.01435558,0.001310393,0.002071896,0.5593496,0.00003823464,0.3966948],"study_design_scores_gemma":[0.0005410898,0.004361697,0.00345757,0.0005499005,0.00002042718,0.000001347536,0.0008051294,0.3389878,0.01417914,0.6370296,0.000002825288,0.00006343971],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8596705,0.00001747117,0.1373769,0.0008245812,0.00001758315,0.001688166,0.00001422496,0.000006837027,0.0003836697],"genre_scores_gemma":[0.6752847,0.00002944264,0.3244692,0.000004152506,0.000007124584,0.0001890841,8.499148e-7,0.000007601799,0.000007764232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3966314,"threshold_uncertainty_score":0.9963849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171446894","doi":"10.1177/0962280211402548","title":"Confidence interval estimation for the Bland–Altman limits of agreement with multiple observations per individual","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":262,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation","keywords":"Confidence interval; Statistics; Quantile; Point estimation; Limits of agreement; Bland–Altman plot; Mathematics; Robust confidence intervals; Standard error; Interval estimation; Interval (graph theory); Econometrics; Level of measurement; Medicine; Nuclear medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.4464294343882807,"gpt":0.573171685688689,"spread":0.1267422513004083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009546593,0.0001001147,0.0002878129,0.000131565,0.0001012557,0.00001213275,0.0002778321,0.0001144526,0.0006562506],"category_scores_gemma":[0.02325095,0.00005744169,0.00003378151,0.0002799362,0.0007654647,0.00003376994,0.00006142422,0.0006817441,0.00000502328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006167578,"about_ca_system_score_gemma":0.0004127353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004661519,"about_ca_topic_score_gemma":0.0001024374,"domain_scores_codex":[0.9967114,0.0008299563,0.0004240978,0.000252482,0.001395402,0.0003866888],"domain_scores_gemma":[0.9818776,0.01708759,0.00005105976,0.0003096777,0.0004014309,0.0002726588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001503317,0.0005956877,0.02553037,0.000342424,0.0001612421,0.00004106218,0.003392449,0.000007507574,0.0005820809,0.0885487,0.0003282924,0.8789669],"study_design_scores_gemma":[0.005111304,0.003823267,0.6180181,0.00117222,0.000113356,0.00003206488,0.00201965,0.310664,0.005283707,0.05193586,0.001621343,0.0002051562],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02864034,0.00007640354,0.9685049,0.001337623,0.0001112163,0.0007933694,0.0000383242,0.00001114765,0.0004866475],"genre_scores_gemma":[0.4347582,0.00004152457,0.564775,0.0000694605,0.00005585395,0.0001871564,0.00001581639,0.00001021223,0.00008675085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8787617,"threshold_uncertainty_score":0.9849766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115308689","doi":"10.1191/0962280202sm304ra","title":"Analysis of uncertainty in health care cost-effectiveness studies: an introduction to statistical issues and methods","year":2002,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":251,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; St. Joseph's Hospital","funders":"","keywords":"Bootstrapping (finance); Computer science; Cost effectiveness; Health care; Statistic; Confidence interval; Econometrics; Statistics; Actuarial science; Risk analysis (engineering); Medicine; Mathematics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.6888032750728122,"gpt":0.7167444363492629,"spread":0.02794116127645063,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2061612,0.000206715,0.002476229,0.002207467,0.0001456807,0.00004449554,0.000356465,0.0002284903,0.002376234],"category_scores_gemma":[0.2838238,0.0002250658,0.00005461395,0.002571655,0.0007813663,0.0001583304,0.0002028543,0.0009240477,0.00003880172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001673103,"about_ca_system_score_gemma":0.0002389001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005717036,"about_ca_topic_score_gemma":0.002085791,"domain_scores_codex":[0.9562998,0.03576047,0.004853297,0.001384177,0.0006842504,0.001017931],"domain_scores_gemma":[0.9403105,0.05745054,0.0004182266,0.0005975872,0.0003245573,0.0008986168],"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":[0.0001695661,0.0004417213,0.01581112,0.002406035,0.0003469394,0.00001553268,0.01575603,0.001402779,0.000004290335,0.5764005,0.003323002,0.3839225],"study_design_scores_gemma":[0.002639194,0.002288371,0.2139026,0.0005349517,0.00006175959,0.000005692493,0.03446702,0.5126504,0.00001490068,0.177256,0.05536839,0.0008106609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01242128,0.009118079,0.9220251,0.05326129,0.0003648377,0.001937506,0.0006377089,0.00002133508,0.0002128597],"genre_scores_gemma":[0.05070716,0.001588116,0.9450152,0.00163428,0.0002891133,0.0006017981,0.00008321714,0.00003495263,0.00004616408],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5112476,"threshold_uncertainty_score":0.9985358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3041396397","doi":"10.1177/0962280220932962","title":"Mixed-effects models for the design and analysis of stepped wedge cluster randomized trials: An overview","year":2020,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"National Center for Advancing Translational Sciences; National Institute on Drug Abuse; National Institute for Health and Care Research","keywords":"Computer science; Confounding; Research design; Cluster (spacecraft); Clinical study design; Econometrics; Management science; Risk analysis (engineering); Data science; Operations research; Medicine; Statistics; Mathematics; Clinical trial; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.9463831388066777,"gpt":0.7778418496968618,"spread":0.1685412891098159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5551415,0.0009410062,0.0260746,0.001227283,0.0002129987,0.000166126,0.002211444,0.001768083,0.001011599],"category_scores_gemma":[0.9736168,0.0005055639,0.002429883,0.004074937,0.004184239,0.00008597986,0.00109363,0.004243182,0.000006155733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002059849,"about_ca_system_score_gemma":0.001498848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004566109,"about_ca_topic_score_gemma":0.00001128985,"domain_scores_codex":[0.510965,0.4708693,0.009951133,0.002088987,0.004582991,0.00154251],"domain_scores_gemma":[0.04442916,0.9503744,0.0015042,0.001542133,0.0007138472,0.001436248],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00658107,0.0001948246,2.579657e-8,0.01889027,0.003266099,0.00003722822,0.00005871476,0.000002707367,8.033118e-8,0.3820854,0.0006756268,0.5882079],"study_design_scores_gemma":[0.0196732,0.0003341664,3.260747e-7,0.00525555,0.02015654,0.000003361065,0.00002529548,0.2544487,0.00000111479,0.680052,0.01971435,0.0003352986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.147023e-8,0.4587681,0.5290315,0.000218344,0.0003186032,0.01104832,0.000546974,0.00002315518,0.00004499701],"genre_scores_gemma":[9.028888e-8,0.4911679,0.5047529,0.00006965491,0.0002022741,0.003678867,0.00002127306,0.0000884597,0.00001852195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5878726,"threshold_uncertainty_score":0.9999016,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147254563","doi":"10.1177/0962280213503925","title":"Linear spline multilevel models for summarising childhood growth trajectories: A guide to their application using examples from five birth cohorts","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Birth, Development, and Health","field":"Medicine","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canadian Institutes of Health Research; Wellcome Trust","keywords":"Spline (mechanical); Multilevel model; Smoothing spline; Computer science; Econometrics; Linear model; Generalized linear mixed model; Mathematics; Statistics; Spline interpolation","retraction":null,"screen_n_in":null,"score":{"opus":0.180160078655825,"gpt":0.53160055665824,"spread":0.3514404780024151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009190721,0.0002910166,0.0008925395,0.00044313,0.0002754299,0.00005233381,0.0003607018,0.0004076116,0.0005760578],"category_scores_gemma":[0.03286105,0.0002275575,0.00006905307,0.0007244959,0.000413049,0.0001095711,0.0002401816,0.001336808,0.00002654854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000450023,"about_ca_system_score_gemma":0.001896341,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01103508,"about_ca_topic_score_gemma":0.0003220483,"domain_scores_codex":[0.9938238,0.001213661,0.001117013,0.0009507271,0.001687941,0.001206901],"domain_scores_gemma":[0.9813813,0.01538202,0.00009005651,0.0004911749,0.001059649,0.001595823],"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":[0.0006213397,0.001007488,0.005080075,0.0008827281,0.0001517018,0.00005106307,0.005278321,0.00003253913,0.005807086,0.1211519,0.00402822,0.8559075],"study_design_scores_gemma":[0.002268619,0.0003861057,0.05346469,0.000601379,0.00002459342,0.0000105293,0.001110299,0.4525572,0.001253678,0.4867864,0.001240871,0.0002956396],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03250522,0.0001508446,0.9606826,0.002403554,0.0001333415,0.003277344,0.0003412067,0.00005716657,0.000448688],"genre_scores_gemma":[0.0641417,0.001198857,0.9319421,0.001070094,0.0005572042,0.0007703269,0.0002107409,0.00007204409,0.00003691453],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8556119,"threshold_uncertainty_score":0.9955505,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140873752","doi":"10.1177/0962280213519716","title":"The performance of different propensity score methods for estimating absolute effects of treatments on survival outcomes: A simulation study","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Jewish General Hospital; 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":"Propensity score matching; Observational study; Inverse probability weighting; Statistics; Hazard ratio; Weighting; Average treatment effect; Medicine; Absolute risk reduction; Matching (statistics); Marginal structural model; Inverse probability; Mathematics; Confidence interval; Bayesian probability; Posterior probability","retraction":null,"screen_n_in":null,"score":{"opus":0.5155792263631098,"gpt":0.6760756832121154,"spread":0.1604964568490056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02892184,0.0002121482,0.0009099345,0.0001625275,0.0001792101,0.00001862807,0.0004834592,0.000141453,0.00002224333],"category_scores_gemma":[0.3092251,0.0001182037,0.00006544749,0.0003132129,0.0006179622,0.00004865502,0.0002742928,0.0007385795,7.114722e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001408108,"about_ca_system_score_gemma":0.00009677532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003060788,"about_ca_topic_score_gemma":0.00001928198,"domain_scores_codex":[0.9869672,0.009475101,0.0009907219,0.0004020311,0.001588093,0.0005768436],"domain_scores_gemma":[0.7662256,0.2325187,0.0001870626,0.0005034197,0.0004052861,0.0001598825],"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":[0.000361047,0.001209656,0.005778417,0.0009499553,0.00007101773,0.000003224329,0.0003153097,0.00004922558,0.0004464423,0.06942978,0.000007484675,0.9213784],"study_design_scores_gemma":[0.001258885,0.004514739,0.04489089,0.000533442,0.00004362926,2.973388e-7,0.00007096007,0.5025642,0.006999071,0.4389927,0.000007327891,0.0001238892],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2137835,0.000006116392,0.7838694,0.00004635727,0.0001152112,0.002037703,0.000004956453,0.00002621928,0.0001105314],"genre_scores_gemma":[0.3764388,0.000006235473,0.6231458,0.000005187999,0.00001850184,0.0003411435,0.000001535035,0.00001965828,0.0000230797],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9212546,"threshold_uncertainty_score":0.9999293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2484604119","doi":"10.1177/0962280216658920","title":"Propensity score matching and complex surveys","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Covariate; Statistics; Confounding; Matching (statistics); Sample size determination; Medicine; Population; Demography; Econometrics; Mathematics; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.7553058634596144,"gpt":0.6754228526511649,"spread":0.0798830108084495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04732967,0.0001526485,0.00046832,0.0001913246,0.0001136459,0.00003516933,0.0003910556,0.0002029175,0.002603762],"category_scores_gemma":[0.1596704,0.00009138939,0.00001927575,0.000349031,0.001642695,0.0001012541,0.0006510787,0.001041517,0.00002154282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001369862,"about_ca_system_score_gemma":0.0001890827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000135022,"about_ca_topic_score_gemma":0.0001419505,"domain_scores_codex":[0.984878,0.0116207,0.0005447335,0.0005137769,0.001647729,0.0007950766],"domain_scores_gemma":[0.9347618,0.06406335,0.0000431977,0.0003717596,0.0002496466,0.0005102865],"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":[0.0000190565,0.00005328102,0.001373879,0.00007912275,0.000004138551,0.0001097993,0.00004977355,4.306601e-9,0.002658465,0.4401305,0.0005615331,0.5549604],"study_design_scores_gemma":[0.0003006932,0.0001305195,0.03487192,0.0003406953,0.000002297766,0.00001753813,0.00003454367,0.0001107093,0.0008863888,0.9627134,0.0004616707,0.000129608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0172148,0.00002032209,0.9775504,0.001633163,0.00004070385,0.0004047685,0.00002171097,0.00009795216,0.003016127],"genre_scores_gemma":[0.1537364,0.00009587079,0.8458018,0.00006209577,0.00004358263,0.00006311195,0.000001900764,0.00002590527,0.0001693582],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5548308,"threshold_uncertainty_score":0.998308,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123033778","doi":"10.1177/0962280210383082","title":"Closed-form confidence intervals for functions of the normal mean and standard deviation","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Standard deviation; Confidence interval; Percentile; Mathematics; Statistics; Coefficient of variation; Robust confidence intervals; Normal distribution; Geometric standard deviation; Standard error; CDF-based nonparametric confidence interval; Variance (accounting); Mean difference; Range (aeronautics); Limits of agreement; Relative standard deviation; Medicine; Detection limit; Nuclear medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.3547369148091911,"gpt":0.6128973161725231,"spread":0.258160401363332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1100707,0.00008988532,0.000310686,0.0001826272,0.0002334441,0.00009938571,0.0008777013,0.0001570354,0.002872102],"category_scores_gemma":[0.3485041,0.00004952302,0.00006353475,0.0007182384,0.001710188,0.0001020159,0.0003706187,0.00111577,0.00001005962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004761361,"about_ca_system_score_gemma":0.0004875911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001127896,"about_ca_topic_score_gemma":0.001055198,"domain_scores_codex":[0.9890402,0.003324019,0.001047715,0.0004582904,0.005692075,0.0004377214],"domain_scores_gemma":[0.9306525,0.06664287,0.0001372804,0.0006660515,0.001538578,0.000362738],"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":[0.0001761867,0.00007759803,0.00546384,0.00004866521,0.000008367719,0.000001232246,0.0004047066,0.000001825551,0.002088815,0.1264373,0.002488403,0.8628031],"study_design_scores_gemma":[0.0006617922,0.0004105788,0.06661344,0.00009610029,0.00000979521,0.000002325616,0.0009008228,0.01095056,0.003013095,0.8975269,0.01972528,0.00008934994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05266859,0.00004051549,0.9382982,0.005628624,0.0006493448,0.0006895743,0.00009816025,0.000005139726,0.001921882],"genre_scores_gemma":[0.6721897,0.0000249475,0.3271143,0.0001489413,0.00009579927,0.0001044804,0.00000213681,0.000006607864,0.0003130741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8627138,"threshold_uncertainty_score":0.9980394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135596283","doi":"10.1177/096228020101000502","title":"Statistical methods for the meta-analysis of cluster randomization trials","year":2001,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Meta-analysis; Estimator; Randomization; Computer science; Context (archaeology); Cluster randomised controlled trial; Cluster (spacecraft); Statistics; Restricted randomization; Statistical power; Variance (accounting); Sample size determination; Econometrics; Statistical hypothesis testing; Clinical trial; Randomized controlled trial; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6678900408750544,"gpt":0.7118649138188959,"spread":0.0439748729438415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2494707,0.0004039883,0.004901627,0.0009701997,0.0002789976,0.0001158717,0.001113823,0.0004902914,0.02645232],"category_scores_gemma":[0.7434539,0.0002240313,0.001060185,0.003586345,0.002005473,0.00007551836,0.0003502112,0.001541833,0.000007939881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001136251,"about_ca_system_score_gemma":0.0004737924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002001389,"about_ca_topic_score_gemma":0.0000946673,"domain_scores_codex":[0.907059,0.08260415,0.004330214,0.001158702,0.003346206,0.001501703],"domain_scores_gemma":[0.3469341,0.6503012,0.0003729443,0.0008782746,0.0009457167,0.0005677426],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001021114,0.0002082084,0.00001895735,0.000115722,0.01102269,0.00001534962,0.000107071,0.000005562256,0.0000392067,0.5596755,0.001300982,0.4264696],"study_design_scores_gemma":[0.002093353,0.0002072083,0.000334807,0.00001841016,0.03623269,0.000005537394,0.0001359734,0.1720797,0.0001277277,0.7849769,0.003585135,0.0002025389],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000006141161,0.0007954914,0.9909407,0.003492697,0.0002279813,0.002286513,0.0006149219,0.00003039257,0.001605106],"genre_scores_gemma":[0.0007468303,0.0003375048,0.9968156,0.0003079526,0.0001383143,0.001352547,0.00004386865,0.00005357391,0.0002037991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.567697,"threshold_uncertainty_score":0.9744377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977586926","doi":"10.1191/0962280202sm289ra","title":"Analysis of data with excess zeros","year":2002,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Biometrics; Wilcoxon signed-rank test; Econometrics; Statistics; Statistical hypothesis testing; Statistical power; Test (biology); Statistical model; Computer science; Data set; Statistical analysis; Mathematics; Artificial intelligence; Mann–Whitney U test","retraction":null,"screen_n_in":null,"score":{"opus":0.640358640075248,"gpt":0.6721812143614034,"spread":0.03182257428615543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02570654,0.0001921175,0.001058953,0.000747501,0.00008296291,0.00003922754,0.001620972,0.0002278896,0.02637614],"category_scores_gemma":[0.1994536,0.0001327116,0.0000472076,0.004037904,0.001818763,0.00009033894,0.0007456067,0.001442422,0.00001929496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000569963,"about_ca_system_score_gemma":0.0001498989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000207007,"about_ca_topic_score_gemma":0.0001047144,"domain_scores_codex":[0.9872776,0.006687917,0.001020382,0.0008192266,0.00334133,0.0008535431],"domain_scores_gemma":[0.8879992,0.109448,0.0001019424,0.001440203,0.0003971854,0.0006135082],"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":[0.00005446528,0.0003735489,0.001261994,0.000147192,0.0002099452,0.0001454651,0.0001405579,6.857373e-7,0.00003823641,0.3914808,0.001270425,0.6048767],"study_design_scores_gemma":[0.0007166402,0.0004279678,0.008828228,0.0002150507,0.0003467064,0.000007050845,0.0002282455,0.4091017,0.0001284525,0.5784771,0.001263225,0.0002596429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00122308,0.0001158153,0.9867842,0.000521398,0.00004171276,0.0002556934,0.0003775363,0.00002234611,0.01065824],"genre_scores_gemma":[0.02918995,0.0001207674,0.9703289,0.00006022192,0.00004273868,0.00004150592,0.00002356674,0.00002539905,0.0001669883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6046171,"threshold_uncertainty_score":0.9745139,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993980658","doi":"10.1177/0962280213505804","title":"Studying noncollapsibility of the odds ratio with marginal structural and logistic regression models","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":144,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Health Canada; Canada Research Chairs; Thrasher Research Fund; McGill University; McGill University Health Centre; World Health Organization","keywords":"Covariate; Confounding; Observational study; Statistics; Logistic regression; Econometrics; Marginal structural model; Odds ratio; Odds; Point estimation; Regression; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4115418379409699,"gpt":0.4732199780575682,"spread":0.06167814011659828,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006791667,0.0000943556,0.0003244909,0.00009559729,0.0001153444,0.00003222328,0.0002430915,0.0001062116,0.002466867],"category_scores_gemma":[0.004503939,0.00006133804,0.00002035009,0.0002106986,0.001042399,0.0001323202,0.0002408177,0.0005343995,0.00001937677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001647561,"about_ca_system_score_gemma":0.00006621356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007495513,"about_ca_topic_score_gemma":0.00005194483,"domain_scores_codex":[0.9978445,0.0006697337,0.0005611891,0.0003723105,0.0002487949,0.0003034514],"domain_scores_gemma":[0.9970282,0.002400619,0.00010543,0.0002703345,0.00003571698,0.000159642],"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":[0.00006929175,0.00009235358,0.2848961,0.000119141,0.00002112682,0.000004659099,0.0005032364,0.0002200541,0.00005566084,0.606106,0.0001496901,0.1077627],"study_design_scores_gemma":[0.0003837302,0.00009476858,0.4917128,0.00003806402,0.000001559606,0.000002236286,0.0001979269,0.1787341,0.00002498056,0.328733,0.00001827636,0.00005856031],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5334241,0.0002877203,0.4609551,0.0009107387,0.00008650649,0.0005233501,0.00003203173,0.000003787005,0.003776659],"genre_scores_gemma":[0.8880324,0.00006405637,0.1116519,0.00004258271,0.00002103643,0.00005660914,0.000002908684,0.00000858132,0.0001198894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3546083,"threshold_uncertainty_score":0.998445,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974493848","doi":"10.1191/0962280202sm278ra","title":"Analysis of repeated events","year":2002,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Event (particle physics); Marginal model; Medicine; Machine learning; Regression analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.3234065665027732,"gpt":0.6439255386965067,"spread":0.3205189721937335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01286105,0.0002872532,0.002206649,0.001006256,0.00004858003,0.000009986809,0.0009815005,0.001457415,0.002330281],"category_scores_gemma":[0.07452188,0.0002093389,0.0004303181,0.00292439,0.001272304,8.086699e-7,0.0006206868,0.001607958,0.00002109715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000598489,"about_ca_system_score_gemma":0.0005540831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006195995,"about_ca_topic_score_gemma":0.00002791995,"domain_scores_codex":[0.9874562,0.008023242,0.001255886,0.0008672555,0.001654641,0.0007427596],"domain_scores_gemma":[0.9918714,0.006529956,0.0001639846,0.0007627661,0.0001906527,0.0004812125],"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":[0.00001650432,0.0001543409,0.00002986535,0.001964403,0.0008012707,0.00007671796,0.00001047189,1.326239e-7,0.000004127715,0.0002359074,0.001408151,0.9952981],"study_design_scores_gemma":[0.0001911263,0.0003086672,0.0001017983,0.001996619,0.0006878852,0.000009033392,0.00001905717,0.0003839436,0.000007001878,0.0004429144,0.9956366,0.0002153335],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004381192,0.9110173,0.08696418,0.00004615625,0.0001194295,0.0002677686,0.0001837096,0.000008887146,0.001388179],"genre_scores_gemma":[0.000007906288,0.8810972,0.1177279,0.00001886566,0.00009305478,0.00009269732,0.0003901587,0.00002877292,0.0005434736],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9950828,"threshold_uncertainty_score":0.9998389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1943072312","doi":"10.1177/0962280215601134","title":"Estimating the effect of treatment on binary outcomes using full matching on the propensity score","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Mental Health","keywords":"Propensity score matching; Covariate; Confounding; Matching (statistics); Average treatment effect; Inverse probability weighting; Calipers; Statistics; Weighting; Binary number; Mathematics; Computer science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6971779961484548,"gpt":0.6699345220452536,"spread":0.02724347410320116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03177534,0.0002205368,0.0006044999,0.0001432155,0.0001896427,0.00003375507,0.0005569948,0.0001453611,0.0001916391],"category_scores_gemma":[0.2138138,0.00009117789,0.00005795755,0.0004155147,0.001013559,0.00004063073,0.000340952,0.001456446,0.00001033692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005297126,"about_ca_system_score_gemma":0.0003075837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002177081,"about_ca_topic_score_gemma":0.00002069738,"domain_scores_codex":[0.9861241,0.01046854,0.0005467013,0.0003457158,0.001954377,0.0005605708],"domain_scores_gemma":[0.8822498,0.1165782,0.0001025372,0.0006339161,0.0001839384,0.0002516687],"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":[0.0009433394,0.0003990393,0.001720932,0.0002995991,0.00007124452,0.0002628677,0.001046318,0.0002492619,0.001264009,0.5229602,0.0006790617,0.4701042],"study_design_scores_gemma":[0.0005502939,0.005235471,0.0005014024,0.0005647065,0.00002242976,0.000009918723,0.0001659196,0.05820108,0.005692456,0.9288896,0.00003551456,0.0001312568],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3085289,0.00001204929,0.6874759,0.001252102,0.00009052458,0.001101713,0.00001200699,0.00004642397,0.001480394],"genre_scores_gemma":[0.2363228,0.000003360614,0.7633068,0.00008807884,0.00005606381,0.0001618737,0.000001498764,0.00003028696,0.00002924114],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4699729,"threshold_uncertainty_score":0.996991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967858306","doi":"10.1191/0962280203sm335ra","title":"Fitting competing risks with an assumed copula","year":2003,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Copula (linguistics); Identifiability; Econometrics; Marginal distribution; Parametric statistics; Bivariate analysis; Multivariate statistics; Computer science; Parametric model; Mathematics; Statistics; Random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.5286679617407478,"gpt":0.6699203937793321,"spread":0.1412524320385843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05656061,0.0002915993,0.0007996347,0.0002955517,0.0003023609,0.0001127024,0.0006255316,0.0003378196,0.007873846],"category_scores_gemma":[0.4458943,0.0002142551,0.00003968214,0.001136582,0.001386048,0.00008110744,0.0001774503,0.003018359,0.00003683284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001525153,"about_ca_system_score_gemma":0.0006038545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002626796,"about_ca_topic_score_gemma":0.00009744769,"domain_scores_codex":[0.9697017,0.02361649,0.001053344,0.0008835181,0.003196865,0.001548048],"domain_scores_gemma":[0.8611915,0.1361037,0.0001141861,0.0006981274,0.000515983,0.001376526],"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":[0.00007908092,0.0002474303,0.001698433,0.0001267277,0.00001319625,0.0003021293,0.0001633256,5.838345e-7,0.00006477842,0.6697829,0.0001455538,0.3273758],"study_design_scores_gemma":[0.001056184,0.0007802604,0.004097033,0.0004014154,0.00001762162,0.00005149884,0.001085058,0.01868558,0.0004502991,0.9713578,0.001680021,0.0003371878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008326338,0.00005652017,0.9584727,0.0002708751,0.0001285632,0.0004455917,0.00002742499,0.00006844218,0.0322035],"genre_scores_gemma":[0.05020194,0.00002158274,0.9492766,0.0001352052,0.00008974833,0.0001194445,0.00000594543,0.00005964736,0.00008989547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3893337,"threshold_uncertainty_score":0.9992817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792390571","doi":"10.1177/0962280218756159","title":"Assessing covariate balance when using the generalized propensity score with quantitative or continuous exposures","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":118,"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","keywords":"Propensity score matching; Covariate; Statistics; Observational study; Logistic regression; Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.7850233477568593,"gpt":0.6838532647255835,"spread":0.1011700830312758,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02332576,0.0002440697,0.0007010302,0.0001674886,0.0004007889,0.0002165595,0.0007234432,0.0002213296,0.00160307],"category_scores_gemma":[0.1328984,0.0001253128,0.00002881345,0.000777058,0.004053392,0.0002426311,0.0004469262,0.001702034,0.000007986716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001986211,"about_ca_system_score_gemma":0.0009573112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003652579,"about_ca_topic_score_gemma":0.0003997687,"domain_scores_codex":[0.9866934,0.008907622,0.000686778,0.0005996983,0.002161039,0.0009514026],"domain_scores_gemma":[0.957516,0.04011943,0.0001698823,0.0006620935,0.001177462,0.0003551694],"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":[0.001434995,0.0002660063,0.002135453,0.0002141202,0.00007240154,0.0006319301,0.001790146,0.000001228283,0.006442675,0.8662613,0.001449412,0.1193003],"study_design_scores_gemma":[0.0007966979,0.0010566,0.00172782,0.000841493,0.00002441164,0.00005387779,0.0008253125,0.02021024,0.005693028,0.9680012,0.0005041746,0.0002651429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0458698,0.00004428426,0.9510462,0.0006271966,0.0000790448,0.0008735818,0.0000137432,0.00009631469,0.001349789],"genre_scores_gemma":[0.04423176,0.00002463553,0.9551132,0.0002011067,0.0001336225,0.0001190684,0.000002793264,0.00004722536,0.0001265777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1190352,"threshold_uncertainty_score":0.9993096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096206421","doi":"10.1177/0962280208092346","title":"The case-crossover study design in pharmacoepidemiology","year":2008,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Pharmacoepidemiology; Crossover study; Crossover; Medicine; Computer science; Pharmacology; Alternative medicine; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.9107676203454614,"gpt":0.7895228873335225,"spread":0.1212447330119389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2773042,0.0003685841,0.001572237,0.0003903304,0.0006623239,0.00005577492,0.001416867,0.0005746383,0.003329212],"category_scores_gemma":[0.9292687,0.0002383286,0.0001092983,0.00189609,0.004822175,0.00006528135,0.0008757352,0.005873616,0.0000988882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000344003,"about_ca_system_score_gemma":0.0008148605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005609316,"about_ca_topic_score_gemma":0.0003286399,"domain_scores_codex":[0.7452556,0.2394007,0.00528938,0.00197901,0.004492835,0.003582447],"domain_scores_gemma":[0.1970287,0.8006013,0.0001643539,0.0009501172,0.0003492163,0.000906271],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001703532,0.00227804,0.003624882,0.00008416734,0.00008737249,0.06516936,0.0007901061,0.000005573584,0.00002772323,0.3232525,0.01669045,0.5862863],"study_design_scores_gemma":[0.00350169,0.0007441092,0.003880845,0.00006740793,0.00001934542,0.0007532061,0.0007650864,0.01293433,0.00004907775,0.9759517,0.001075819,0.0002574041],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007578008,0.0002051976,0.98474,0.002052604,0.0007756311,0.002492466,0.0000313148,0.0000579808,0.00206679],"genre_scores_gemma":[0.04136191,0.0004112491,0.9565368,0.0002760998,0.0003178461,0.0007832706,5.983648e-7,0.00006583877,0.0002463505],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6526992,"threshold_uncertainty_score":0.9978861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994201608","doi":"10.1191/0962280203sm340ra","title":"Detecting activation in fMRI data","year":2003,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Excursion; Computer science; Artificial intelligence; Pattern recognition (psychology); Key (lock); Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4958300143860889,"gpt":0.6114019961467672,"spread":0.1155719817606782,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03225767,0.0001177394,0.0002612513,0.0004198312,0.0001912362,0.00004425365,0.000681761,0.0001477662,0.001289588],"category_scores_gemma":[0.895532,0.0001056129,0.00001352509,0.001791507,0.0007347094,0.0001883249,0.0006291139,0.002024334,0.00005228025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000224743,"about_ca_system_score_gemma":0.0004194336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001635966,"about_ca_topic_score_gemma":0.0002037264,"domain_scores_codex":[0.9824886,0.01289636,0.0004494544,0.001036631,0.002313913,0.0008150412],"domain_scores_gemma":[0.6050497,0.393569,0.00004582888,0.0008641896,0.000116885,0.0003544824],"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":[0.0001205648,0.0003018487,0.001506647,0.00007234199,0.000004082141,0.0002362807,0.0001974224,0.000007278383,0.02898873,0.237248,0.002334491,0.7289823],"study_design_scores_gemma":[0.002253253,0.0004216983,0.02001357,0.0003604334,0.000004095591,0.00004615367,0.001183277,0.05894597,0.1139168,0.7585918,0.04372985,0.0005331081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0111746,0.00004394705,0.9529108,0.009318216,0.0003786677,0.0004714777,0.0000220865,0.00004231241,0.02563786],"genre_scores_gemma":[0.5762991,0.00005528782,0.4219406,0.001351191,0.00009622529,0.0001032378,0.000004136783,0.00002644472,0.0001238369],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8632743,"threshold_uncertainty_score":0.9996234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098775098","doi":"10.1177/0962280210371561","title":"On Gaussian Markov random fields and Bayesian disease mapping","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Indian Council of Agricultural Research; Canadian Institutes of Health Research; Gallipoli Medical Research Foundation","keywords":"Bayesian probability; Univariate; Prior probability; Multivariate statistics; Computer science; Bayesian linear regression; Artificial intelligence; Autoregressive model; Bayesian inference; Bayes' theorem; Mathematics; Statistics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1232595716132747,"gpt":0.5478868605346664,"spread":0.4246272889213917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02191614,0.0002714344,0.0006526818,0.0004110206,0.0002375567,0.0001234959,0.0005264054,0.0004026912,0.01081525],"category_scores_gemma":[0.3368435,0.0002071757,0.00005817711,0.0006188618,0.001524249,0.00005443992,0.0003219637,0.003967457,0.00002779794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004533359,"about_ca_system_score_gemma":0.0003556439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006485998,"about_ca_topic_score_gemma":0.00007351935,"domain_scores_codex":[0.9898753,0.005495141,0.0007747012,0.0007841011,0.002003125,0.001067696],"domain_scores_gemma":[0.8763109,0.1210516,0.00005682083,0.0006100881,0.0001510252,0.001819539],"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":[0.0002101228,0.000124549,0.0002183896,0.0001530583,0.000007587892,0.0003600368,0.00007652908,1.154258e-8,0.00005512107,0.5465245,0.001159168,0.4511109],"study_design_scores_gemma":[0.00124708,0.0001557289,0.007943009,0.0002817612,0.0000112852,0.00001364975,0.00007462451,0.01675708,0.00003945466,0.9720637,0.001175101,0.0002375778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001246384,0.00003527765,0.9778917,0.004208371,0.0003487558,0.0004979888,0.00005982761,0.00004588971,0.01566575],"genre_scores_gemma":[0.05314071,0.00005576058,0.9458799,0.0003789202,0.0001991514,0.0001411805,0.000004937903,0.00003809613,0.0001613588],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4508733,"threshold_uncertainty_score":0.9983304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124612672","doi":"10.1177/0962280212436447","title":"Minimal sufficient balance—a new strategy to balance baseline covariates and preserve randomness of treatment allocation","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hotchkiss Brain Institute; University of Calgary","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Covariate; Categorical variable; Randomization; Baseline (sea); Restricted randomization; Randomness; Statistics; Randomized controlled trial; Medicine; Mathematics; Surgery","retraction":null,"screen_n_in":null,"score":{"opus":0.6337766155694683,"gpt":0.6851863314577871,"spread":0.05140971588831877,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06395736,0.0003257114,0.001449456,0.0003053347,0.00009822025,0.00004615737,0.0005434441,0.0004030735,0.003274916],"category_scores_gemma":[0.6190102,0.0002440893,0.00008284411,0.001013301,0.0009153388,0.00008585429,0.0003883537,0.0009167476,0.00002608506],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002664528,"about_ca_system_score_gemma":0.0007917726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005197541,"about_ca_topic_score_gemma":0.00004041615,"domain_scores_codex":[0.9753352,0.01776009,0.002183851,0.0008307165,0.002407557,0.001482527],"domain_scores_gemma":[0.617313,0.3791383,0.0001935879,0.0007179911,0.0004782811,0.002158897],"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":[0.001942781,0.001416553,0.003127117,0.0004181518,0.00007947448,0.00003148187,0.0005654806,0.000008107209,0.001005912,0.5222213,0.002337544,0.4668461],"study_design_scores_gemma":[0.007352473,0.003174561,0.01259861,0.0005483106,0.0000990958,0.00001447553,0.0003791582,0.026819,0.00369023,0.9432756,0.001602287,0.0004462277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01213346,0.0004032011,0.9828664,0.001471446,0.0003715387,0.001438272,0.0001924127,0.00003296987,0.001090273],"genre_scores_gemma":[0.08928806,0.0002361249,0.9094471,0.00008432268,0.0004552401,0.0002195575,0.00000869457,0.00004156276,0.0002193211],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5550528,"threshold_uncertainty_score":0.9976362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130892140","doi":"10.1177/0962280214543508","title":"Double propensity-score adjustment: A solution to design bias or bias due to incomplete matching","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":90,"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":"Propensity score matching; Matching (statistics); Covariate; Statistics; Confounding; Average treatment effect; Mathematics; Selection bias; Observational study; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.8048558980284114,"gpt":0.6387257078840167,"spread":0.1661301901443947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04425421,0.0003058909,0.0008699326,0.0006580444,0.000225556,0.00009867826,0.0009060192,0.0003073219,0.001615717],"category_scores_gemma":[0.2138022,0.0002234423,0.00004516722,0.001507136,0.000435686,0.0001254625,0.001145282,0.001838264,0.0002097276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000486659,"about_ca_system_score_gemma":0.0004919599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004679479,"about_ca_topic_score_gemma":0.0004269103,"domain_scores_codex":[0.984615,0.009178501,0.00101455,0.0008633208,0.002881132,0.001447475],"domain_scores_gemma":[0.9449784,0.05233754,0.00008479368,0.0007590652,0.0004855469,0.001354641],"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":[0.0009454069,0.0002210628,0.00002308703,0.0002475203,0.00001389409,0.0002401442,0.0006627156,0.00001452514,0.001841603,0.4668708,0.005612906,0.5233064],"study_design_scores_gemma":[0.0006863254,0.001407177,0.000555835,0.0008127429,0.0000111908,0.00004142322,0.0001087074,0.007398613,0.005157198,0.9802011,0.003283373,0.0003363366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002844078,0.00001187145,0.9903134,0.002389695,0.0001297254,0.002195125,0.00001594272,0.000212565,0.00188756],"genre_scores_gemma":[0.01541343,0.0000145197,0.9825085,0.0007007367,0.0001843691,0.0007766915,0.000006102607,0.00006940301,0.0003261957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.52297,"threshold_uncertainty_score":0.999297,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124200703","doi":"10.1177/0962280213502437","title":"A comparison of machine learning methods for classification using simulation with multiple real data examples from mental health studies","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Menzies Centre for Australian Studies, King's College London, University of London; University of California, San Diego; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Genentech; IXICO; Servier; King's College London; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Eisai; Synarc; South London and Maudsley NHS Foundation Trust; Pfizer; Biogen; BioClinica; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Alzheimer's Association; Amorfix Life Sciences; Bayer HealthCare; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation","keywords":"Computer science; Sample size determination; Support vector machine; Artificial intelligence; Linear discriminant analysis; Machine learning; Random forest; Kernel (algebra); Sample (material); Stability (learning theory); Feature (linguistics); Kernel method; Pattern recognition (psychology); Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8484463315588613,"gpt":0.7874845120641984,"spread":0.06096181949466284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02994441,0.0001874213,0.0008433367,0.0003373449,0.0003524427,0.00003397942,0.0007122235,0.000208303,0.00191312],"category_scores_gemma":[0.0526082,0.0001467853,0.00002555148,0.0006037927,0.001090869,0.00013184,0.0005644981,0.001552958,0.00001206277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004584335,"about_ca_system_score_gemma":0.0005302451,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01887414,"about_ca_topic_score_gemma":0.001057188,"domain_scores_codex":[0.9747983,0.02037212,0.001271574,0.0008796236,0.001645405,0.001033036],"domain_scores_gemma":[0.9087705,0.08910696,0.0002572823,0.0007655952,0.0004743043,0.0006253733],"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":[0.0007296202,0.0004899923,0.02216776,0.0004170019,0.00009760774,0.000002972297,0.003535705,0.00003776604,0.001048041,0.005128173,0.0006264671,0.9657189],"study_design_scores_gemma":[0.001620232,0.001017769,0.03238528,0.0002423136,0.000008909223,0.000001254573,0.008283837,0.9455897,0.00009184272,0.007027495,0.00360817,0.0001231686],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01195155,0.001891722,0.9812484,0.001815532,0.0002058464,0.002293427,0.0003744306,0.00002597066,0.0001931242],"genre_scores_gemma":[0.0931351,0.0002676569,0.9053603,0.00005452193,0.0001048889,0.0002843631,0.0006924045,0.00003733836,0.0000633898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9655957,"threshold_uncertainty_score":0.9989992,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2923957350","doi":"10.1177/0962280219889080","title":"Estimating the sample mean and standard deviation from commonly reported quantiles in meta-analysis","year":2020,"lang":"en","type":"preprint","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Jewish General Hospital; McGill University; McGill University Health Centre","funders":"National Institute on Minority Health and Health Disparities; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Fonds de Recherche du Québec - Santé; National Center for Research Resources; National Institute of General Medical Sciences; National Institute of Mental Health; Agency for Healthcare Research and Quality; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Centers for Disease Control and Prevention","keywords":"Standard deviation; Quartile; Statistics; Quantile; Sample mean and sample covariance; Sample size determination; Meta-analysis; Standard error; Normal distribution; Sample (material); Econometrics; Outcome (game theory); Mathematics; Pooled variance; Absolute deviation; Confidence interval; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5909202286661872,"gpt":0.6355710282862124,"spread":0.04465079962002516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05253502,0.0005217831,0.003578335,0.0006114612,0.0002212414,0.000340528,0.001131188,0.0007337678,0.004485128],"category_scores_gemma":[0.4879542,0.0003402421,0.0003784739,0.001963156,0.001496387,0.00005116817,0.002122386,0.006405634,0.000004610439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067972,"about_ca_system_score_gemma":0.0008653528,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007705352,"about_ca_topic_score_gemma":0.004483876,"domain_scores_codex":[0.9629133,0.02732696,0.002786812,0.001696899,0.004264077,0.001011967],"domain_scores_gemma":[0.6833035,0.3134693,0.0005192623,0.001369071,0.0005316926,0.0008072051],"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":[0.000218467,0.0001807485,0.001251539,0.0006975657,0.01296843,0.0006602444,0.00157429,0.0000296539,0.00001172205,0.6804383,0.0004748252,0.3014943],"study_design_scores_gemma":[0.0002262395,0.00006915385,0.003085614,0.0001118381,0.009219206,0.000002142423,0.0001877694,0.2585057,0.00001541477,0.7282733,0.00006213551,0.0002414926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007927972,0.00063879,0.9887173,0.006295281,0.0001541149,0.001006595,0.002049774,0.00005068649,0.0002946275],"genre_scores_gemma":[0.02280295,0.00008277015,0.976168,0.0001929995,0.0001319473,0.0003892481,0.0001732679,0.00005427102,0.000004481479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4354192,"threshold_uncertainty_score":0.9999049,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770711354","doi":"10.1177/0962280217737566","title":"Bayesian latent time joint mixed effect models for multicohort longitudinal data","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Bayesian probability; Mixed model; Longitudinal data; Latent variable; Econometrics; Computer science; Statistics; Event data; Mathematics; Data mining; Covariate","retraction":null,"screen_n_in":null,"score":{"opus":0.5151171744634669,"gpt":0.6288287204909679,"spread":0.113711546027501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06050645,0.0004003992,0.001348764,0.000279968,0.0007475367,0.000369794,0.002982328,0.0004961239,0.002868692],"category_scores_gemma":[0.4838183,0.0003040305,0.000112516,0.0002337591,0.002193979,0.0002649884,0.00221746,0.001963654,0.00007902505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713867,"about_ca_system_score_gemma":0.000474871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002478127,"about_ca_topic_score_gemma":0.00007286959,"domain_scores_codex":[0.9856184,0.007046818,0.001275244,0.001511526,0.002830969,0.001717045],"domain_scores_gemma":[0.8881384,0.106839,0.0001920569,0.003123953,0.0004507793,0.001255748],"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":[0.0002417039,0.0002448501,0.0003202807,0.0004545764,0.00005416217,0.0002178387,0.00003365071,4.622212e-7,0.0001213393,0.4142254,0.005189246,0.5788965],"study_design_scores_gemma":[0.0009497844,0.0003360134,0.002704668,0.000289773,0.00004005249,0.000011966,0.000008418804,0.4096709,0.0002025263,0.5853413,0.0002306704,0.0002139117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000165214,0.00005078594,0.9914626,0.001593706,0.000376787,0.001559483,0.0006962534,0.00005626072,0.004038847],"genre_scores_gemma":[0.01355632,0.000044854,0.9853024,0.00004285725,0.000291591,0.0003934043,0.00006953711,0.00007801619,0.0002210461],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5786825,"threshold_uncertainty_score":0.9999412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2093541024","doi":"10.1177/0962280214536537","title":"Longitudinal data subject to irregular observation: A review of methods with a focus on visit processes, assumptions, and study design","year":2014,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Outcome (game theory); Computer science; Focus (optics); Set (abstract data type); Process (computing); Subject (documents); Chart; Data science; Management science; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.738749131992883,"gpt":0.6926737143409845,"spread":0.04607541765189849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1304724,0.0007764693,0.005417142,0.00076094,0.0001764631,0.000106636,0.002386424,0.000532508,0.001229938],"category_scores_gemma":[0.5777086,0.0005041399,0.00009303742,0.003629226,0.0009758025,0.0000834555,0.00153255,0.003255595,0.00002132925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002109283,"about_ca_system_score_gemma":0.002740805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001030903,"about_ca_topic_score_gemma":0.00004394306,"domain_scores_codex":[0.9285965,0.06086383,0.003037243,0.002249393,0.004080705,0.001172354],"domain_scores_gemma":[0.6671864,0.3263926,0.0005959125,0.003104097,0.001382851,0.001338167],"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":[0.00009463321,0.0005935467,0.00001006371,0.140558,0.0001501379,0.0001228636,0.00003660742,3.257295e-8,9.822122e-8,0.05905841,0.001666851,0.7977087],"study_design_scores_gemma":[0.001080594,0.007044042,0.0002267097,0.400109,0.00187403,0.0001288864,0.00009225783,0.001118114,0.000003387827,0.3206255,0.2664562,0.001241282],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.29747e-7,0.4339816,0.5621131,0.0002285557,0.00004468035,0.003234772,0.0001956014,0.00002040626,0.0001811283],"genre_scores_gemma":[2.083607e-7,0.4780119,0.5209906,0.00005366076,0.00007339095,0.0007500855,0.00003122763,0.00006406453,0.00002481765],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7964675,"threshold_uncertainty_score":0.999741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082197682","doi":"10.1177/0962280213491641","title":"Expectation maximization-based likelihood inference for flexible cure rate models with Weibull lifetimes","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advancements in Photolithography Techniques","field":"Engineering","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Weibull distribution; Maximization; Expectation–maximization algorithm; Computer science; Maximum likelihood; Econometrics; Statistics; Artificial intelligence; Mathematics; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.06775448943020891,"gpt":0.4855262341241343,"spread":0.4177717446939254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003614374,0.000204706,0.0003246964,0.0004438928,0.00009651009,0.00007262595,0.0003985185,0.0002077525,0.001405313],"category_scores_gemma":[0.006952267,0.0001695469,0.00003040251,0.0008966268,0.0004419171,0.0002178946,0.00006006207,0.0008123331,0.00001121848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189759,"about_ca_system_score_gemma":0.0002396512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005649881,"about_ca_topic_score_gemma":0.00001398726,"domain_scores_codex":[0.9963962,0.0008747172,0.0004765292,0.0004021841,0.001047013,0.0008033884],"domain_scores_gemma":[0.9882261,0.01053848,0.00003035416,0.0003290358,0.0004697655,0.0004062967],"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":[0.0002116299,0.0002710963,0.0007326051,0.0007737014,0.00006269818,0.00002901701,0.0002867305,0.01590714,0.001213727,0.09655102,0.006044538,0.8779161],"study_design_scores_gemma":[0.000522824,0.0002225752,0.0003350789,0.0001698601,0.000004823401,6.125061e-7,0.00008170772,0.7064664,0.004725651,0.2864805,0.0008168314,0.0001731242],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002035266,0.0001277931,0.9937761,0.0003516739,0.00007063479,0.001284219,0.00004539223,0.0003224222,0.003818262],"genre_scores_gemma":[0.03403563,0.0001561163,0.9626302,0.00009632073,0.0000443094,0.00287298,0.00005292422,0.00005951698,0.00005201789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.877743,"threshold_uncertainty_score":0.9995075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3156127058","doi":"10.1177/09622802211002867","title":"Predictive performance of machine and statistical learning methods: Impact of data-generating processes on external validity in the “large N, small p” setting","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","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","keywords":"Brier score; Machine learning; Random forest; Artificial intelligence; Logistic regression; Lasso (programming language); Computer science; Regression; Statistic; Gradient boosting; Sample size determination; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2592234766623989,"gpt":0.6037200504579326,"spread":0.3444965737955338,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06806692,0.0002061644,0.0006111187,0.0002901477,0.0002102243,0.00008883937,0.001676679,0.0001757152,0.0002010857],"category_scores_gemma":[0.2542945,0.0001419788,0.00002963809,0.001547309,0.0005495522,0.0001898645,0.001721896,0.003882219,0.000001009939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001095174,"about_ca_system_score_gemma":0.001790955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007247403,"about_ca_topic_score_gemma":0.0001443783,"domain_scores_codex":[0.9592489,0.0352787,0.001145539,0.0009992928,0.002382144,0.0009454454],"domain_scores_gemma":[0.8993601,0.09861114,0.0001996778,0.000868896,0.0006125816,0.0003476097],"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":[0.0001456158,0.0003091747,0.1024609,0.001394478,0.00001961118,0.0002774361,0.002241821,0.0005965804,0.0003110035,0.01890256,0.0000311166,0.8733097],"study_design_scores_gemma":[0.0004521105,0.001123192,0.09781223,0.0005791854,0.000005503387,0.00004924404,0.0002797451,0.8923295,0.0003424877,0.00685678,0.00005617685,0.0001138025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0452567,0.0005145753,0.9528596,0.0006181676,0.00005702348,0.0002817626,0.0001419163,0.00001695063,0.0002533468],"genre_scores_gemma":[0.2884543,0.0001788273,0.7111826,0.00005537251,0.00005217911,0.00002608935,0.00003208412,0.00001225139,0.000006274106],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.891733,"threshold_uncertainty_score":0.9984159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982070055","doi":"10.1177/0962280211436004","title":"Impact of weighted composite compared to traditional composite endpoints for the design of randomized controlled trials","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"","keywords":"Discriminative model; Composite number; Weighting; Statistics; Event (particle physics); Clinical endpoint; Sample size determination; Component (thermodynamics); Mathematics; Clinical trial; Medicine; Computer science; Econometrics; Algorithm; Artificial intelligence; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.827207652661658,"gpt":0.7242513774061305,"spread":0.1029562752555274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4567173,0.0004317575,0.01075086,0.0006219715,0.0001636278,0.00004326058,0.001163347,0.0004537111,0.005047122],"category_scores_gemma":[0.9295541,0.0002221133,0.001556912,0.001059948,0.003116478,0.00006365185,0.0002784561,0.001441147,0.00001101192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002093518,"about_ca_system_score_gemma":0.000687315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008007299,"about_ca_topic_score_gemma":0.000001566968,"domain_scores_codex":[0.7972634,0.1842982,0.01021785,0.0007470228,0.005648953,0.001824511],"domain_scores_gemma":[0.06432632,0.9314025,0.001060619,0.0007064674,0.001311802,0.001192269],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.3364892,0.002411131,0.0001287177,0.0003698778,0.002413234,0.000009441438,0.0004177571,0.0000318245,0.004127976,0.5692559,0.003918586,0.08042636],"study_design_scores_gemma":[0.1379559,0.0006296274,0.001429408,0.0004225439,0.0006205112,0.000005497928,0.00004408626,0.04565442,0.001587587,0.8114254,0.00002202559,0.0002029515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001213007,0.0003605858,0.9842229,0.0008861416,0.0006028701,0.01107603,0.001080746,0.00002386728,0.0005338414],"genre_scores_gemma":[0.04953331,0.0001008027,0.9475149,0.00007887181,0.0004544228,0.002218741,0.00001370912,0.00005531492,0.00002991268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7471043,"threshold_uncertainty_score":0.9995965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3202627776","doi":"10.1177/09622802211037079","title":"Commentary on the use of the reproduction number <i>R</i> during the COVID-19 pandemic","year":2021,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Fields Institute for Research in Mathematical Sciences; York University","funders":"Marsden Fund; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Medical Research Council; Wellcome; Royal Society; Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research; National Institute for Health and Care Research; Wellcome Trust; James S. McDonnell Foundation","keywords":"Value (mathematics); Basic reproduction number; Metric (unit); Coronavirus disease 2019 (COVID-19); Statistics; Computer science; Mathematics; Population; Medicine; Sociology; Demography; Disease","retraction":null,"screen_n_in":null,"score":{"opus":0.8608263610088677,"gpt":0.7112668188145757,"spread":0.149559542194292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07663086,0.0004390717,0.002301473,0.0001012044,0.0007484148,0.00005632314,0.001877393,0.0005731452,0.003083267],"category_scores_gemma":[0.8132775,0.0001673818,0.0004795189,0.001767006,0.004007096,0.00002816202,0.002937051,0.00712323,0.00002362154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001163078,"about_ca_system_score_gemma":0.0009725683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007029774,"about_ca_topic_score_gemma":0.0001549864,"domain_scores_codex":[0.9131244,0.07945184,0.002001151,0.001162862,0.003288612,0.0009711604],"domain_scores_gemma":[0.4771889,0.5197455,0.0003790523,0.002117341,0.0002098997,0.0003592464],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003778822,0.0002366506,0.0003893369,0.009456234,0.0002081172,0.00008391228,0.0001507987,0.000001651533,3.627627e-7,0.07566547,0.2092967,0.704473],"study_design_scores_gemma":[0.0001423986,0.00003487349,0.00007089466,0.003865443,0.0001279238,0.00004934398,0.00008891054,0.00004091068,8.696306e-7,0.1137877,0.8816352,0.0001554232],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000277468,0.7879218,0.08103129,0.124515,0.0008255036,0.004760219,0.0003868466,0.00007853316,0.0004530076],"genre_scores_gemma":[0.000004392932,0.9416707,0.04908225,0.007616272,0.0004301069,0.0007908564,0.00001231438,0.00005359166,0.000339477],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7366466,"threshold_uncertainty_score":0.9987034,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099077995","doi":"10.1177/0962280215601133","title":"Assessing agreement between two measurement systems: An alternative to the limits of agreement approach","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Interchangeability; Agreement; Metric (unit); Limits of agreement; Computer science; Units of measurement; Physics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.8455312682296875,"gpt":0.6788734831139276,"spread":0.1666577851157599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3749643,0.0003073855,0.0009721339,0.0006872685,0.0002732591,0.000609609,0.003568112,0.0001736044,0.0006258779],"category_scores_gemma":[0.2304376,0.0001750129,0.00009620861,0.002449658,0.0009993035,0.0003155131,0.0009649156,0.001505947,0.0001720804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001002482,"about_ca_system_score_gemma":0.001365161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001354066,"about_ca_topic_score_gemma":0.0002028967,"domain_scores_codex":[0.9017674,0.04603641,0.003419851,0.001767464,0.0454216,0.00158723],"domain_scores_gemma":[0.9661933,0.02439417,0.0003365949,0.001891713,0.005061493,0.002122768],"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":[0.0001650629,0.001129789,0.007303854,0.00009439813,0.00009324845,0.00003767438,0.003018375,0.002225057,0.0002898197,0.0350492,0.007562968,0.9430305],"study_design_scores_gemma":[0.00698043,0.006074854,0.08956563,0.001806341,0.0001365812,0.00001517509,0.0811056,0.2376251,0.003379,0.4907228,0.08113442,0.001454089],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0114914,0.0003286806,0.9649674,0.004965167,0.0006921373,0.001886587,0.00003972745,0.00001259065,0.01561636],"genre_scores_gemma":[0.6608213,0.00001554669,0.3380594,0.0001872084,0.0004664141,0.0003149985,0.000007411359,0.00001721429,0.0001105187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9415765,"threshold_uncertainty_score":0.7760447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057830194","doi":"10.1191/0962280202sm308ra","title":"Using inverse-weighting in cost-effectiveness analysis with censored data","year":2002,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Censoring (clinical trials); Weighting; Statistics; Covariance; Survival analysis; Mathematics; Econometrics; Inverse probability weighting; Duration (music); Medicine; Propensity score matching","retraction":null,"screen_n_in":null,"score":{"opus":0.8657958110574773,"gpt":0.6909467344486384,"spread":0.1748490766088389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.173803,0.0001848765,0.001456086,0.001706219,0.0001630739,0.00008777699,0.0008925429,0.0002756744,0.006053111],"category_scores_gemma":[0.1694519,0.0001935242,0.00004618592,0.003067514,0.0006083784,0.0003199579,0.0003827312,0.001336818,0.0002708496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051163,"about_ca_system_score_gemma":0.0002640229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005053329,"about_ca_topic_score_gemma":0.001865477,"domain_scores_codex":[0.9801155,0.01353456,0.003227109,0.001260867,0.0007522085,0.001109789],"domain_scores_gemma":[0.9483814,0.04931445,0.0004263758,0.001119788,0.0001262362,0.0006318151],"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":[0.000189316,0.0008253492,0.4880652,0.001144132,0.0004749376,0.0003522135,0.001859962,0.001563431,0.000009191648,0.4517593,0.002668662,0.05108823],"study_design_scores_gemma":[0.001184204,0.00006895226,0.04847097,0.0002149018,0.0000160291,0.000005002364,0.0006172298,0.9212367,0.000002892324,0.02372445,0.004215135,0.0002435673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02585671,0.0006585826,0.9611034,0.005559365,0.0001492202,0.00112888,0.0004164769,0.00002190719,0.00510549],"genre_scores_gemma":[0.1193238,0.000178452,0.8789865,0.001006886,0.0001501268,0.0001569425,0.00008647029,0.00004048866,0.00007034424],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9196732,"threshold_uncertainty_score":0.9948555,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387033650","doi":"10.1177/09622802231198795","title":"Logistic regression vs. predictive mean matching for imputing binary covariates","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":54,"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","funders":"Canadian Institutes of Health Research","keywords":"Missing data; Imputation (statistics); Logistic regression; Statistics; Binary data; Parametric statistics; Covariate; Mathematics; Regression analysis; Multivariate statistics; Matching (statistics); Computer science; Binary number","retraction":null,"screen_n_in":null,"score":{"opus":0.3427619520314442,"gpt":0.6290504285419702,"spread":0.286288476510526,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04866503,0.0003277476,0.0009266122,0.0006482294,0.0004455985,0.0001095089,0.0008068896,0.0004780886,0.001265004],"category_scores_gemma":[0.3711766,0.0002464591,0.00009998311,0.001807796,0.001171873,0.0000793388,0.0007539204,0.002094712,0.00006444401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002218141,"about_ca_system_score_gemma":0.0005370024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001167195,"about_ca_topic_score_gemma":0.00002122374,"domain_scores_codex":[0.9854252,0.008072033,0.001216689,0.001012848,0.002503737,0.001769457],"domain_scores_gemma":[0.7849909,0.2132833,0.0001153566,0.0004754674,0.0004167323,0.0007182531],"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":[0.0003311399,0.0001367114,0.00008317323,0.0005679818,0.00002433638,0.0003192099,0.0004942674,0.000002031184,0.0004133483,0.6767855,0.004554574,0.3162877],"study_design_scores_gemma":[0.0007468029,0.0005415145,0.002835386,0.0008166996,0.0000218435,0.0000106195,0.0006706323,0.1400488,0.0001480298,0.8536108,0.0003176219,0.0002312359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005778818,0.00006206441,0.9938787,0.001628981,0.0004734411,0.0009854945,0.0002344668,0.0002230596,0.001935947],"genre_scores_gemma":[0.01251858,0.0001143235,0.9862471,0.0001045476,0.0003138483,0.0004252698,0.00004536784,0.00007739198,0.0001536071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3225116,"threshold_uncertainty_score":0.9999987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2916199673","doi":"10.1177/0962280219829885","title":"Prediction intervals with random forests","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Random forest; Computer science; Covariate; Prediction interval; Calibration; Tree (set theory); Data mining; Regression; Interval (graph theory); Parametric statistics; Cart; Statistics; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1173314666053891,"gpt":0.5295953286551724,"spread":0.4122638620497834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01875815,0.0001011238,0.0002478553,0.0002772204,0.00007220577,0.0001182646,0.0009863201,0.0001311031,0.001038131],"category_scores_gemma":[0.0351016,0.00006973299,0.0000199875,0.0008507797,0.0002703496,0.0001991362,0.0003670312,0.001356473,0.0002289204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007493543,"about_ca_system_score_gemma":0.000293399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062266,"about_ca_topic_score_gemma":0.00005631314,"domain_scores_codex":[0.9920716,0.004554745,0.0003598821,0.0005768149,0.001924221,0.0005127052],"domain_scores_gemma":[0.9864148,0.01225812,0.00003911432,0.0006622503,0.0002665578,0.0003591541],"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":[0.0001292124,0.00007905403,0.01559756,0.00005518777,0.000006980357,0.00003724471,0.0001120492,0.00001267389,0.0000563817,0.1994792,0.001416404,0.7830181],"study_design_scores_gemma":[0.002334074,0.000737239,0.1926035,0.0002394943,0.000002639514,0.00001907707,0.00006376723,0.7150648,0.000102072,0.06212782,0.02655454,0.0001509761],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001231846,0.00004630238,0.9858146,0.002326978,0.0002431104,0.0003206654,0.000008275831,0.00006817348,0.009940035],"genre_scores_gemma":[0.1561617,0.0000335232,0.8430324,0.0001281727,0.00008906431,0.00008072532,0.00002528014,0.0000118444,0.0004372376],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7828671,"threshold_uncertainty_score":0.9998751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2047330460","doi":"10.1177/0962280212446326","title":"Log Gaussian Cox processes and spatially aggregated disease incidence data","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Cancer Care Ontario; Public Health Ontario; University of Toronto","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Cox process; Markov chain Monte Carlo; Inference; Computer science; Gaussian; Statistics; Mixture model; Econometrics; Gaussian network model; Gaussian process; Data mining; Mathematics; Monte Carlo method; Poisson distribution; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3339326463437911,"gpt":0.6084049746751412,"spread":0.2744723283313501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02848992,0.0002840563,0.0006493485,0.0002689366,0.0002126047,0.0001204916,0.001225243,0.0002666891,0.003608376],"category_scores_gemma":[0.6194571,0.0002177205,0.00001969009,0.00111639,0.002161348,0.0003001881,0.001514118,0.00168216,0.00004215434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008595233,"about_ca_system_score_gemma":0.00139057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002449813,"about_ca_topic_score_gemma":0.0001919516,"domain_scores_codex":[0.986936,0.007248594,0.0008835247,0.0008548959,0.00257838,0.001498625],"domain_scores_gemma":[0.8534924,0.1414197,0.0001263821,0.001344255,0.0004636583,0.003153666],"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":[0.0001372833,0.0003182256,0.005808508,0.001014028,0.00001367746,0.0002745402,0.0001693043,1.080106e-8,0.00002420513,0.497295,0.001353319,0.4935919],"study_design_scores_gemma":[0.0004665309,0.0001233839,0.02048381,0.0007646289,0.00003460607,0.00002926989,0.00009999269,0.006960128,0.000053838,0.969192,0.001493776,0.0002980321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005767512,0.0009652539,0.9938105,0.001729468,0.0001767211,0.0005098383,0.0003506221,0.00005567549,0.001825168],"genre_scores_gemma":[0.04175114,0.0004850067,0.9570723,0.0001894796,0.0002553312,0.00009764597,0.00004461283,0.00004278597,0.00006174795],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5909672,"threshold_uncertainty_score":0.9973025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2749556736","doi":"10.1177/0962280217727314","title":"Survival forests for data with dependent censoring","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"Russian Science Foundation","keywords":"Censoring (clinical trials); Estimator; Covariate; Survival analysis; Computer science; Accelerated failure time model; Survival function; Statistics; Kaplan–Meier estimator; Econometrics; Data mining; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.6773318042169131,"gpt":0.6953959658900677,"spread":0.01806416167315461,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04271108,0.0002343928,0.0007038013,0.0001576869,0.0006199265,0.0002675056,0.002906909,0.0002591594,0.001347007],"category_scores_gemma":[0.5166262,0.0001664274,0.00003126006,0.0001709984,0.001633335,0.0001422704,0.001586676,0.001518926,0.00001534899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009803521,"about_ca_system_score_gemma":0.000542514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003557405,"about_ca_topic_score_gemma":0.001179782,"domain_scores_codex":[0.990856,0.003314421,0.0007236952,0.001015355,0.002776684,0.001313859],"domain_scores_gemma":[0.8813134,0.1146541,0.0001368946,0.002559473,0.0004782385,0.0008577947],"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":[0.0002029554,0.0001173126,0.001867167,0.0001931342,0.00001976548,0.0001547831,0.0000293727,9.407604e-8,0.00001897267,0.5327839,0.0006892779,0.4639232],"study_design_scores_gemma":[0.001400752,0.0003798419,0.01609585,0.0003180605,0.00002268078,0.00001249969,0.0001086892,0.04231053,0.0001549956,0.9365232,0.002428559,0.0002443545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008121795,0.00003179532,0.9870389,0.001380987,0.0003246119,0.0007351151,0.0003529374,0.00003056146,0.009292979],"genre_scores_gemma":[0.01797498,0.00003795197,0.9811468,0.00003389324,0.00026384,0.0001994175,0.000021303,0.00005301804,0.000268759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4739151,"threshold_uncertainty_score":0.9995659,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049288534","doi":"10.1177/0962280214530608","title":"Penalized count data regression with application to hospital stay after pediatric cardiac surgery","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Epidemiology","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre; Montreal Children's Hospital","funders":"National Center for Advancing Translational Sciences; National Institute of Environmental Health Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Heart, Lung, and Blood Institute","keywords":"Poisson regression; Medicine; Lasso (programming language); Feature selection; Count data; Elastic net regularization; Regression; Statistics; Poisson distribution; Regression analysis; Renal function; Computer science; Internal medicine; Mathematics; Machine learning; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.2466960887406669,"gpt":0.6088668988222045,"spread":0.3621708100815376,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1057343,0.0004048298,0.001635045,0.0006210344,0.0001595204,0.00006113995,0.001535023,0.0005266236,0.001703434],"category_scores_gemma":[0.5948159,0.0002813079,0.00007217339,0.001668307,0.001084551,0.0001151146,0.001453114,0.002321317,0.0001040097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002579603,"about_ca_system_score_gemma":0.0006034957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001845674,"about_ca_topic_score_gemma":0.00004621478,"domain_scores_codex":[0.9601381,0.03071463,0.001603443,0.001827425,0.003956995,0.001759374],"domain_scores_gemma":[0.6431692,0.352008,0.0001829158,0.002503308,0.0005735903,0.001562942],"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":[0.0008911373,0.0005734306,0.02038144,0.0007023775,0.00004956122,0.0002093005,0.0001931261,7.256307e-7,0.00002362453,0.2013495,0.04169321,0.7339326],"study_design_scores_gemma":[0.0006730027,0.0006613326,0.02956389,0.0003568166,0.0001208782,0.00001295866,0.0001483872,0.02978809,0.00005092171,0.9197101,0.01822234,0.0006912713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003128004,0.0001645742,0.9911715,0.002506514,0.0004636322,0.001222596,0.0003599458,0.00008299766,0.0009001914],"genre_scores_gemma":[0.01346728,0.0001840835,0.9839566,0.0003565757,0.0007458958,0.001019731,0.0001003609,0.00009784684,0.00007157979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7332413,"threshold_uncertainty_score":0.9999804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951322845","doi":"10.1177/0962280217747054","title":"Fitting mechanistic epidemic models to data: A comparison of simple Markov chain Monte Carlo approaches","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":43,"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":"Markov chain Monte Carlo; Computer science; Markov chain; Simple (philosophy); Bayesian probability; Monte Carlo method; Approximate Bayesian computation; Data mining; Econometrics; Machine learning; Artificial intelligence; Statistics; Mathematics; Inference","retraction":null,"screen_n_in":null,"score":{"opus":0.8933866589386059,"gpt":0.704013528761424,"spread":0.1893731301771819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08411132,0.0003143999,0.001725692,0.000337954,0.0002662656,0.00002785829,0.001984188,0.0003920318,0.0009063702],"category_scores_gemma":[0.6274607,0.0002392367,0.00007231683,0.001240448,0.001759603,0.00008179315,0.003981791,0.001887987,0.00002653739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002871963,"about_ca_system_score_gemma":0.0003356521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00151029,"about_ca_topic_score_gemma":0.001134643,"domain_scores_codex":[0.9796643,0.01263292,0.002078685,0.001349748,0.002687089,0.001587279],"domain_scores_gemma":[0.7556973,0.240996,0.0002233479,0.001591576,0.0004799791,0.001011888],"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":[0.0003656327,0.0005773538,0.001270791,0.0008672319,0.00009822574,0.00005915512,0.001693986,0.00004820784,0.0001513522,0.4550656,0.02953103,0.5102714],"study_design_scores_gemma":[0.0002285014,0.0003218926,0.0002686677,0.0001579314,0.00001609622,9.877278e-7,0.0008657824,0.4937134,0.000080072,0.5034649,0.0007415359,0.0001401715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003366892,0.0002428523,0.9897487,0.003331711,0.0001121729,0.0009439769,0.0002275752,0.00005929149,0.001966886],"genre_scores_gemma":[0.3364356,0.00002990411,0.6628709,0.0002469768,0.0001976819,0.0001372181,0.00001006914,0.00003069733,0.00004092638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5433493,"threshold_uncertainty_score":0.9924118,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309662782","doi":"10.1177/09622802221139233","title":"Standard error estimation in meta-analysis of studies reporting medians","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre; McGill University","funders":"National Science Foundation","keywords":"Standard deviation; Statistics; Meta-analysis; Standard error; Sample size determination; Quartile; Weighting; Context (archaeology); Random effects model; Econometrics; Median; Pooled variance; Mathematics; Computer science; Medicine; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.9687413692421736,"gpt":0.8023260236013716,"spread":0.166415345640802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8226035,0.00024162,0.01089127,0.004058995,0.000225449,0.0001382971,0.002245609,0.0001130424,0.1453333],"category_scores_gemma":[0.9211674,0.0001289555,0.002041938,0.01698469,0.0007620064,0.00009818884,0.001154535,0.001678383,0.00005666386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002922418,"about_ca_system_score_gemma":0.0006100244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000152198,"about_ca_topic_score_gemma":0.0005916054,"domain_scores_codex":[0.4137349,0.4327883,0.06025466,0.003668221,0.08781437,0.001739461],"domain_scores_gemma":[0.2020929,0.7627286,0.01769054,0.008665496,0.007442986,0.001379526],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001799934,0.0007024795,0.0150788,0.0005084631,0.0801764,0.001002315,0.007956277,0.009951241,0.00006936155,0.102296,0.01171394,0.7703647],"study_design_scores_gemma":[0.0003816977,0.0002552432,0.01156712,0.00003228249,0.02619816,0.000009048851,0.01423692,0.4745869,0.00004199842,0.4681637,0.004251084,0.0002758505],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005077612,0.003864491,0.9815664,0.005726056,0.0001462232,0.0008617869,0.0001584629,0.000003521955,0.002595447],"genre_scores_gemma":[0.2277382,0.00004881421,0.7706894,0.0001306303,0.00001500111,0.0005637972,0.00001548928,0.0000131974,0.000785431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7700889,"threshold_uncertainty_score":0.855448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999384961","doi":"10.1177/0962280214550516","title":"Beyond the treatment effect: Evaluating the effects of patient preferences in randomised trials","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":41,"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":"Medicine; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5884113956304523,"gpt":0.6665425784460107,"spread":0.07813118281555842,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4318154,0.0001952776,0.001974495,0.000358513,0.000189565,0.00005676541,0.0005968896,0.0002116666,0.001029001],"category_scores_gemma":[0.7077529,0.0001108287,0.0001361329,0.0005374402,0.0007086325,0.00005959594,0.0001134214,0.0008071081,0.0001010094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004624798,"about_ca_system_score_gemma":0.0003830683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001601826,"about_ca_topic_score_gemma":0.0002391469,"domain_scores_codex":[0.8918096,0.09859936,0.006844961,0.0007477625,0.001087341,0.0009109995],"domain_scores_gemma":[0.3345232,0.6630692,0.001166272,0.0007786443,0.0001185362,0.0003441586],"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":[0.001031239,0.000411838,0.005799794,0.0009028112,0.00009943811,0.000004573487,0.005528529,0.00004359032,0.00002335109,0.2615116,0.001301833,0.7233413],"study_design_scores_gemma":[0.0199219,0.005996296,0.01819851,0.0006075024,0.000027538,0.000001927433,0.001009816,0.08187772,0.0002999125,0.8667666,0.005011779,0.0002804922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7672173,0.007377858,0.1622606,0.03782787,0.002147068,0.01306931,0.0001297495,0.00002740778,0.009942745],"genre_scores_gemma":[0.8671291,0.001253989,0.1217331,0.002971192,0.000670871,0.005990017,0.00002502628,0.00005785652,0.0001688378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7230609,"threshold_uncertainty_score":0.9998842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146502722","doi":"10.1177/0962280214567141","title":"Predictive accuracy of novel risk factors and markers: A simulation study of the sensitivity of different performance measures for the Cox proportional hazards regression model","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Proportional hazards model; Statistics; Concordance; Hazard ratio; Censoring (clinical trials); Medicine; Risk factor; Cohort; Regression; Population; Statistic; Econometrics; Internal medicine; Mathematics; Confidence interval; Environmental health","retraction":null,"screen_n_in":null,"score":{"opus":0.6796715167424592,"gpt":0.626117586072389,"spread":0.05355393067007019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1045211,0.0001115098,0.0007091275,0.0001710592,0.0001351806,0.00001061962,0.0002293212,0.0001276823,0.00002514881],"category_scores_gemma":[0.3226263,0.00006764787,0.00004796002,0.0002241277,0.0006970976,0.00009948146,0.0001833159,0.0004933125,3.087811e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001943312,"about_ca_system_score_gemma":0.0005452259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001166653,"about_ca_topic_score_gemma":0.0001727642,"domain_scores_codex":[0.9915701,0.004603124,0.002304288,0.0003393766,0.0009139205,0.0002692037],"domain_scores_gemma":[0.9278744,0.0699003,0.001127797,0.0003670143,0.0005393843,0.0001911322],"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":[0.002057265,0.003339462,0.8172016,0.001580354,0.0002968964,5.616211e-7,0.01511,0.05228376,0.00004270096,0.04425192,0.0007615737,0.06307396],"study_design_scores_gemma":[0.0009261368,0.00033845,0.2461605,0.0001162304,0.000008900372,2.517421e-7,0.002088018,0.7352668,0.00003679694,0.01499645,0.00001657929,0.00004492138],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4695753,0.00007009695,0.528062,0.0007760333,0.00006774432,0.001058285,0.0003648641,0.000001874239,0.00002371828],"genre_scores_gemma":[0.9690751,0.00005481821,0.03068065,0.00002830232,0.00003325205,0.0001030657,0.000004800685,0.00001019778,0.00000984594],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.682983,"threshold_uncertainty_score":0.922084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2808600279","doi":"10.1177/0962280218779408","title":"Flexible and structured survival model for a simultaneous estimation of non-linear and non-proportional effects and complex interactions between continuous variables: Performance of this multidimensional penalized spline approach in net survival trend analysis","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"Agence Nationale de la Recherche; Cancer Research UK","keywords":"Spline (mechanical); Survival analysis; Computer science; Elastic net regularization; Estimator; Econometrics; Statistics; Parametric statistics; Smoothing; Proportional hazards model; Poisson distribution; Mathematics; Mathematical optimization; Regression","retraction":null,"screen_n_in":null,"score":{"opus":0.1000629228932853,"gpt":0.5157611724700032,"spread":0.4156982495767179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01382993,0.0001490767,0.0007545039,0.0006226755,0.000238816,0.00002507234,0.0001744952,0.0001565023,0.000111955],"category_scores_gemma":[0.009605398,0.0001308639,0.00004458708,0.001134592,0.002621508,0.00009271249,0.0001775194,0.0004289144,1.801921e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005424516,"about_ca_system_score_gemma":0.0002041297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002272667,"about_ca_topic_score_gemma":0.001479182,"domain_scores_codex":[0.9951286,0.001783521,0.0007315708,0.0004685735,0.001436968,0.0004508145],"domain_scores_gemma":[0.9849082,0.01414924,0.0001456397,0.0001568075,0.0003864644,0.0002536818],"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":[0.003285219,0.001190341,0.4754702,0.003258426,0.001085542,0.00002912033,0.0104409,0.01208114,0.000924356,0.07227068,0.0001310582,0.4198331],"study_design_scores_gemma":[0.001182221,0.0001959705,0.1970229,0.00006138372,0.00008913994,3.961281e-7,0.000296057,0.7953933,0.00002657197,0.005620405,0.00001766295,0.00009398118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3570075,0.00001816056,0.6418235,0.00005357444,0.00005176611,0.0005966015,0.0001384298,0.00000559807,0.000304872],"genre_scores_gemma":[0.563062,0.00004847374,0.4367078,0.000005257397,0.00003937889,0.00003402221,0.00007012586,0.000006411415,0.00002657496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7833121,"threshold_uncertainty_score":0.9987371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2772202324","doi":"10.1177/0962280217743777","title":"Causal inference with measurement error in outcomes: Bias analysis and estimation methods","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Actua; University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Estimator; Observational error; Statistics; Outcome (game theory); Weighting; Inverse probability weighting; Inference; Causal inference; Errors-in-variables models; Computer science; Econometrics; Estimation; Statistical inference; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.738761936625469,"gpt":0.7244365658423263,"spread":0.01432537078314267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05711018,0.0002661473,0.0009997903,0.000911619,0.0002415626,0.0001686276,0.0007505812,0.000294185,0.0005683939],"category_scores_gemma":[0.4285808,0.0001888128,0.00004425614,0.0009313176,0.001664748,0.0002301331,0.0005478048,0.001832806,0.000004073156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003678357,"about_ca_system_score_gemma":0.0004670506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001125997,"about_ca_topic_score_gemma":0.003859657,"domain_scores_codex":[0.9873966,0.007055058,0.0009058359,0.0007208243,0.003068845,0.000852857],"domain_scores_gemma":[0.9535067,0.0440363,0.0002116172,0.001123599,0.0005614213,0.000560376],"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":[0.00009716386,0.0002229546,0.04265215,0.0001831349,0.0001212768,0.0002077401,0.0003279516,0.00000704873,0.0001528375,0.2346611,0.00003646065,0.7213302],"study_design_scores_gemma":[0.0005644743,0.0002393097,0.157762,0.0003008767,0.0000759594,0.000003637905,0.0001534405,0.05635436,0.0007006119,0.7835747,0.00004562117,0.0002250059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004190836,0.00003308692,0.9923211,0.001233462,0.00003273234,0.0005417882,0.00001279588,0.00005615632,0.001578081],"genre_scores_gemma":[0.1815319,0.00004516605,0.8180809,0.00003682825,0.00001159496,0.0002346452,0.000003201837,0.00002281944,0.00003292802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7211052,"threshold_uncertainty_score":0.9709035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096814695","doi":"10.1177/0962280211432211","title":"Reflections on meta-analyses involving trials stopped early for benefit: Is there a problem and if so, what is it?","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; University of Ottawa; McMaster University","funders":"","keywords":"Meta-analysis; Randomized controlled trial; Sample size determination; Econometrics; Publication bias; Statistics; Medicine; Mathematics; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.9834534062452185,"gpt":0.7951079030339979,"spread":0.1883455032112206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6035617,0.000423268,0.006921274,0.001261628,0.0005143928,0.001876925,0.001988161,0.0003858016,0.1355433],"category_scores_gemma":[0.621998,0.0001883131,0.001754765,0.002747449,0.0008410545,0.0003647358,0.0004126031,0.001237565,0.0005546797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000076134,"about_ca_system_score_gemma":0.0003870902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003171712,"about_ca_topic_score_gemma":0.000191022,"domain_scores_codex":[0.8289838,0.1350822,0.0145192,0.002796852,0.01728763,0.001330374],"domain_scores_gemma":[0.6209893,0.3686378,0.002099671,0.003552053,0.003301954,0.001419213],"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":[0.0001964591,0.0002831745,0.000198802,0.0001991008,0.002809463,0.00003184978,0.007226302,8.711416e-7,0.0001472359,0.1796967,0.03469609,0.7745139],"study_design_scores_gemma":[0.0005606615,0.0006362103,0.001118226,0.0001874218,0.001836807,0.000005285885,0.004852049,0.006430877,0.0002885158,0.9349602,0.04886294,0.0002608249],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008672418,0.007456789,0.9630672,0.01204665,0.000212362,0.00269728,0.0001784833,0.000007115926,0.01346684],"genre_scores_gemma":[0.01058263,0.001708439,0.9759682,0.001865562,0.0001268641,0.001128489,0.000004679291,0.00003570454,0.008579441],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7742531,"threshold_uncertainty_score":0.9991592,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071412894","doi":"10.1177/0962280211416038","title":"Measuring continuous baseline covariate imbalances in clinical trial data","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Brain Institute","funders":"National Institute of Neurological Disorders and Stroke","keywords":"Covariate; Statistics; Baseline (sea); Analysis of covariance; Test statistic; Statistic; Type I and type II errors; Econometrics; Mathematics; Medicine; Statistical hypothesis testing","retraction":null,"screen_n_in":null,"score":{"opus":0.9591079010063465,"gpt":0.7651604513098256,"spread":0.1939474496965209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4092959,0.0004675223,0.002758873,0.0006180527,0.0001355337,0.0000877326,0.00393457,0.001131495,0.01118024],"category_scores_gemma":[0.9459789,0.0003800765,0.0001678815,0.001796478,0.003087607,0.0001807659,0.002640735,0.006641019,0.0001553218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001852109,"about_ca_system_score_gemma":0.001281659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005986322,"about_ca_topic_score_gemma":0.0003698638,"domain_scores_codex":[0.8460084,0.1300914,0.009853249,0.003544012,0.007201209,0.003301764],"domain_scores_gemma":[0.178115,0.8145959,0.0005616118,0.003844108,0.0007308595,0.002152493],"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":[0.01882864,0.00268076,0.002400696,0.0002126051,0.00007291404,0.001549069,0.000145685,6.433889e-8,0.0000109874,0.2713148,0.002942143,0.6998416],"study_design_scores_gemma":[0.02996452,0.001126602,0.00554166,0.0005145044,0.00004707036,0.00001227311,0.0001765991,0.01168226,0.00004902922,0.9488743,0.001595425,0.0004157783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002419557,0.000158093,0.9770606,0.0007542191,0.002421804,0.002100207,0.0003314862,0.0001067944,0.0146472],"genre_scores_gemma":[0.009394594,0.0004247708,0.9882727,0.0002611234,0.001146171,0.0002537066,0.00001898695,0.00009325169,0.000134694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6994259,"threshold_uncertainty_score":0.9998651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888226965","doi":"10.1177/0962280218795187","title":"Methods for shortening patient-reported outcome measures","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Jewish General Hospital","funders":"Canadian Arthritis Network; Canadian Institutes of Health Research; Dr. Fooke Laboratorien","keywords":"Outcome (game theory); Observational study; Medicine; Patient-reported outcome; Clinical trial; Scale (ratio); Test (biology); Physical therapy; Computer science; Quality of life (healthcare); Nursing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8985570285078743,"gpt":0.7640029906638991,"spread":0.1345540378439752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3282519,0.0002860263,0.001169978,0.001917191,0.0005335854,0.0003029181,0.002146231,0.0004716288,0.004969077],"category_scores_gemma":[0.9692004,0.0001925901,0.0001806209,0.006602324,0.002359303,0.0001417843,0.0009578181,0.001838771,0.00006134739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001564405,"about_ca_system_score_gemma":0.0005487871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001525093,"about_ca_topic_score_gemma":0.00003140828,"domain_scores_codex":[0.948854,0.03603,0.003451954,0.001800322,0.007858512,0.002005239],"domain_scores_gemma":[0.1440678,0.8487459,0.0004109763,0.001630869,0.003645804,0.001498586],"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":[0.0001910056,0.00009392485,0.01302175,0.00001529165,0.00002575182,0.00006526768,0.0002013278,7.63793e-7,0.0004984044,0.01512301,0.003951239,0.9668123],"study_design_scores_gemma":[0.0008773163,0.001050504,0.02630008,0.00006933623,0.00001554502,0.00004393475,0.001254959,0.06631203,0.001101017,0.7799944,0.1226504,0.0003304861],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00209284,0.000353149,0.9798626,0.001169108,0.001765387,0.0007323119,0.00002015954,0.00006865517,0.01393579],"genre_scores_gemma":[0.01687317,0.00002153566,0.9816599,0.0004200459,0.0004236969,0.0002146731,0.000003540314,0.0000369286,0.0003465455],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9664817,"threshold_uncertainty_score":0.9959405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906515425","doi":"10.1177/0962280218817926","title":"Covariate-adjusted survival analyses in propensity-score matched samples: Imputing potential time-to-event outcomes","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"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":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada; National Institutes of Health; National Science Foundation","keywords":"Propensity score matching; Covariate; Statistics; Proportional hazards model; Matching (statistics); Hazard ratio; Survival analysis; Observational study; Accelerated failure time model; Sample size determination; Outcome (game theory); Econometrics; Mathematics; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.7075499601632524,"gpt":0.6697690744611742,"spread":0.03778088570207827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02830803,0.0003335174,0.001239592,0.0007897614,0.0001587607,0.00008483788,0.0009422849,0.0004068882,0.006633967],"category_scores_gemma":[0.2154595,0.0002609257,0.00008072814,0.001843038,0.001167714,0.0001011842,0.00117766,0.002066738,0.0002439118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004202266,"about_ca_system_score_gemma":0.0005633226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008109504,"about_ca_topic_score_gemma":0.000436919,"domain_scores_codex":[0.9852918,0.007923195,0.001395093,0.0008988488,0.002972122,0.001518877],"domain_scores_gemma":[0.9677452,0.02993595,0.000120454,0.0007231847,0.0007033687,0.0007717808],"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":[0.001183096,0.001794988,0.01169642,0.0006811857,0.0002094922,0.002165256,0.001875644,0.00002372357,0.02680605,0.3731161,0.003617705,0.5768303],"study_design_scores_gemma":[0.001072445,0.0007273431,0.06488276,0.000591472,0.00003052805,0.00001452068,0.0004713798,0.0170595,0.004169718,0.9102369,0.0002412386,0.0005021912],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.029392,0.00001097077,0.9665058,0.001169612,0.000134154,0.001007276,0.00003887804,0.0001588029,0.00158251],"genre_scores_gemma":[0.1626612,0.000008812897,0.8365687,0.0001563168,0.0001411921,0.0001192634,0.00001472144,0.00005776083,0.0002720327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5763282,"threshold_uncertainty_score":0.9999843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}