{"meta":{"query_hash":"9890b73406e3","filters":{"venue":"Statistical Methods in Medical Research"},"cohort_total":233,"direct_labels_cover":2,"predictions_cover":233,"exported":233,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/9890b73406e3","api":"https://metacan.xera.ac/api/v1/cohort?venue=Statistical+Methods+in+Medical+Research"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7388653050513273,"score_gpt":0.6767105014196586,"score_spread":0.0621548036316687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1829168467","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027721745,0.001785707,0.9649975,0.028784528,0.00014654855,0.00372231,0.000070454145,0.000007060383,0.00020869287],"genre_scores_gemma":[0.015296034,0.0023716572,0.98125136,0.00058862905,0.000065816195,0.00027002313,0.0000013574527,0.000010426617,0.00014468501],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9661128,0.017477801,0.003102248,0.0013736129,0.0110077765,0.0009257876],"domain_scores_gemma":[0.21180284,0.78199196,0.00036175098,0.002526177,0.002214304,0.0011029821],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30590615,0.00015862181,0.0007157914,0.00011922534,0.00023461602,0.00008057058,0.001493691,0.000117325944,0.0012308691],"category_scores_gemma":[0.88523096,0.0000838829,0.000066337685,0.0013711544,0.0012729593,0.00008711299,0.00051170145,0.0007985488,0.000010978118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089007017,0.000996033,0.0010864048,0.0003816549,0.0000367946,0.000009792651,0.0006431302,0.000101561694,0.00006885325,0.012304317,0.016762849,0.96671855],"study_design_scores_gemma":[0.0025577268,0.0015834908,0.01666613,0.00047584344,0.000043431966,9.721886e-7,0.00070483703,0.0013848571,0.000087738874,0.9667127,0.009666867,0.00011539585],"about_ca_topic_score_codex":0.00096829666,"about_ca_topic_score_gemma":0.000085926986,"teacher_disagreement_score":0.96660316,"about_ca_system_score_codex":0.00015765542,"about_ca_system_score_gemma":0.0010248302,"threshold_uncertainty_score":0.9996821},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6971779961484548,"score_gpt":0.6699345220452536,"score_spread":0.02724347410320116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1943072312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30852887,0.000012049287,0.6874759,0.0012521023,0.000090524576,0.0011017129,0.000012006993,0.000046423975,0.0014803944],"genre_scores_gemma":[0.2363228,0.0000033606143,0.7633068,0.00008807884,0.000056063807,0.00016187373,0.0000014987636,0.000030286963,0.000029241142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9861241,0.010468535,0.0005467013,0.00034571582,0.001954377,0.0005605708],"domain_scores_gemma":[0.8822498,0.11657819,0.00010253715,0.0006339161,0.00018393842,0.00025166865],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031775344,0.0002205368,0.0006044999,0.0001432155,0.0001896427,0.000033755066,0.0005569948,0.00014536107,0.00019163908],"category_scores_gemma":[0.21381381,0.00009117789,0.000057957554,0.00041551472,0.0010135589,0.000040630726,0.00034095204,0.0014564457,0.00001033692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094333943,0.00039903933,0.0017209318,0.0002995991,0.00007124452,0.00026286775,0.0010463175,0.0002492619,0.0012640089,0.5229602,0.00067906175,0.47010416],"study_design_scores_gemma":[0.0005502939,0.005235471,0.0005014024,0.0005647065,0.000022429756,0.000009918723,0.00016591964,0.058201082,0.005692456,0.9288896,0.000035514557,0.00013125682],"about_ca_topic_score_codex":0.00021770815,"about_ca_topic_score_gemma":0.00002069738,"teacher_disagreement_score":0.4699729,"about_ca_system_score_codex":0.0005297126,"about_ca_system_score_gemma":0.0003075837,"threshold_uncertainty_score":0.99699104},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5286679617407478,"score_gpt":0.6699203937793321,"score_spread":0.14125243203858429,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967858306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008326338,0.000056520166,0.9584727,0.00027087505,0.00012856316,0.0004455917,0.00002742499,0.00006844218,0.032203496],"genre_scores_gemma":[0.050201938,0.000021582742,0.94927657,0.00013520516,0.000089748326,0.00011944454,0.00000594543,0.000059647362,0.00008989547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9697017,0.02361649,0.0010533442,0.0008835181,0.0031968653,0.0015480475],"domain_scores_gemma":[0.8611915,0.13610366,0.00011418607,0.0006981274,0.00051598303,0.0013765261],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.056560613,0.00029159928,0.00079963467,0.0002955517,0.00030236092,0.00011270244,0.0006255316,0.00033781957,0.007873846],"category_scores_gemma":[0.44589433,0.00021425512,0.000039682138,0.0011365818,0.0013860476,0.00008110744,0.00017745033,0.003018359,0.00003683284],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007908092,0.00024743035,0.0016984326,0.0001267277,0.000013196248,0.00030212925,0.00016332559,5.838345e-7,0.00006477842,0.66978294,0.00014555379,0.32737583],"study_design_scores_gemma":[0.0010561838,0.00078026036,0.004097033,0.00040141543,0.000017621622,0.000051498835,0.0010850576,0.018685583,0.0004502991,0.9713578,0.0016800209,0.00033718778],"about_ca_topic_score_codex":0.00026267962,"about_ca_topic_score_gemma":0.000097447686,"teacher_disagreement_score":0.38933372,"about_ca_system_score_codex":0.00015251535,"about_ca_system_score_gemma":0.00060385454,"threshold_uncertainty_score":0.9992817},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3234065665027732,"score_gpt":0.6439255386965067,"score_spread":0.3205189721937335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974493848","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004381192,0.9110173,0.086964175,0.000046156252,0.00011942951,0.0002677686,0.00018370958,0.000008887146,0.001388179],"genre_scores_gemma":[0.000007906288,0.8810972,0.11772788,0.000018865656,0.00009305478,0.00009269732,0.0003901587,0.000028772916,0.00054347364],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874562,0.008023242,0.0012558863,0.0008672555,0.0016546405,0.00074275956],"domain_scores_gemma":[0.9918714,0.0065299557,0.00016398465,0.0007627661,0.00019065269,0.0004812125],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012861054,0.00028725324,0.0022066487,0.0010062555,0.00004858003,0.000009986809,0.0009815005,0.0014574146,0.002330281],"category_scores_gemma":[0.07452188,0.00020933892,0.0004303181,0.0029243901,0.0012723038,8.086699e-7,0.0006206868,0.0016079582,0.00002109715],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016504324,0.00015434086,0.000029865354,0.001964403,0.00080127065,0.00007671796,0.000010471892,1.3262388e-7,0.000004127715,0.00023590736,0.0014081514,0.9952981],"study_design_scores_gemma":[0.00019112631,0.0003086672,0.00010179834,0.0019966187,0.00068788516,0.0000090333915,0.000019057172,0.00038394364,0.000007001878,0.00044291443,0.99563664,0.00021533352],"about_ca_topic_score_codex":0.000061959945,"about_ca_topic_score_gemma":0.000027919947,"teacher_disagreement_score":0.9950828,"about_ca_system_score_codex":0.000059848895,"about_ca_system_score_gemma":0.0005540831,"threshold_uncertainty_score":0.9998389},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.640358640075248,"score_gpt":0.6721812143614034,"score_spread":0.031822574286155425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977586926","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012230799,0.000115815325,0.98678416,0.000521398,0.000041712763,0.00025569342,0.00037753631,0.000022346108,0.010658235],"genre_scores_gemma":[0.029189954,0.000120767414,0.97032887,0.000060221915,0.000042738677,0.000041505922,0.000023566741,0.000025399055,0.00016698833],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9872776,0.0066879173,0.0010203823,0.00081922655,0.0033413304,0.0008535431],"domain_scores_gemma":[0.8879992,0.109447986,0.00010194239,0.0014402026,0.0003971854,0.00061350816],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025706545,0.00019211747,0.0010589528,0.00074750104,0.00008296291,0.00003922754,0.0016209724,0.00022788964,0.026376141],"category_scores_gemma":[0.19945356,0.0001327116,0.000047207603,0.0040379036,0.0018187627,0.000090338945,0.0007456067,0.0014424219,0.00001929496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054465283,0.0003735489,0.001261994,0.000147192,0.00020994521,0.00014546512,0.00014055788,6.857373e-7,0.000038236405,0.3914808,0.0012704254,0.6048767],"study_design_scores_gemma":[0.0007166402,0.0004279678,0.008828228,0.00021505068,0.00034670637,0.000007050845,0.00022824552,0.4091017,0.0001284525,0.5784771,0.0012632251,0.00025964287],"about_ca_topic_score_codex":0.00020700699,"about_ca_topic_score_gemma":0.00010471437,"teacher_disagreement_score":0.60461706,"about_ca_system_score_codex":0.000056996305,"about_ca_system_score_gemma":0.00014989893,"threshold_uncertainty_score":0.9745139},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.827207652661658,"score_gpt":0.7242513774061305,"score_spread":0.10295627525552742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982070055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001213007,0.00036058578,0.9842229,0.0008861416,0.0006028701,0.01107603,0.0010807456,0.000023867284,0.00053384143],"genre_scores_gemma":[0.04953331,0.00010080273,0.9475149,0.00007887181,0.00045442284,0.002218741,0.000013709121,0.00005531492,0.000029912682],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.79726344,0.18429825,0.01021785,0.0007470228,0.005648953,0.0018245107],"domain_scores_gemma":[0.064326316,0.9314025,0.0010606188,0.0007064674,0.0013118023,0.0011922686],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.45671725,0.0004317575,0.010750865,0.0006219715,0.00016362777,0.000043260578,0.0011633472,0.0004537111,0.0050471216],"category_scores_gemma":[0.9295541,0.00022211329,0.0015569119,0.0010599477,0.003116478,0.00006365185,0.00027845608,0.0014411467,0.00001101192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.33648917,0.0024111308,0.00012871771,0.0003698778,0.0024132342,0.000009441438,0.00041775705,0.000031824504,0.0041279765,0.5692559,0.003918586,0.08042636],"study_design_scores_gemma":[0.13795595,0.00062962744,0.0014294084,0.00042254393,0.00062051124,0.0000054979278,0.000044086257,0.04565442,0.0015875868,0.8114254,0.000022025592,0.00020295155],"about_ca_topic_score_codex":0.00008007299,"about_ca_topic_score_gemma":0.0000015669681,"teacher_disagreement_score":0.7471043,"about_ca_system_score_codex":0.00020935175,"about_ca_system_score_gemma":0.00068731495,"threshold_uncertainty_score":0.9995965},"labels":[],"label_agreement":null},{"id":"W1993762614","doi":"10.1177/0962280212448974","title":"A Skew-t space-varying regression model for the spectral analysis of resting state brain activity","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Down Syndrome Research Foundation; Simon Fraser University; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Skew; Resting state fMRI; Regression analysis; State space; Regression; Mathematics; Computer science; Statistics; Econometrics; Statistical physics; Neuroscience; Psychology; Physics","score_opus":0.2554435893414817,"score_gpt":0.595130034201998,"score_spread":0.33968644486051625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993762614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029031204,0.00009165617,0.98919183,0.006689643,0.00005386885,0.0004046497,0.00001783871,0.000050214767,0.0005971872],"genre_scores_gemma":[0.281153,0.00002817425,0.7184916,0.00012529269,0.000029356424,0.00008269768,0.0000019581032,0.0000086147975,0.000079293306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99153036,0.004883709,0.00046641537,0.0004112985,0.0018864791,0.0008217365],"domain_scores_gemma":[0.93701714,0.061596714,0.000110430476,0.00064853724,0.00024346782,0.00038373127],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04714418,0.00012726958,0.00041369745,0.0006201415,0.00019612815,0.000075325705,0.0010382168,0.00014363547,0.00006923428],"category_scores_gemma":[0.06441677,0.00008301194,0.00009694139,0.0024647193,0.00048354137,0.00025919912,0.00058117486,0.001185734,0.0000010963217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000878768,0.00017215215,0.0005924826,0.00004519199,0.00007951612,0.0000058530018,0.0031033691,0.0006209104,0.0019927127,0.37530503,0.00074312114,0.6172518],"study_design_scores_gemma":[0.00016782292,0.000062968036,0.005216758,0.000045926656,0.000018135324,7.878035e-7,0.000030107234,0.88967806,0.0029840376,0.10156412,0.00015154212,0.00007973112],"about_ca_topic_score_codex":0.00019151937,"about_ca_topic_score_gemma":0.00006149491,"teacher_disagreement_score":0.88905716,"about_ca_system_score_codex":0.00010727195,"about_ca_system_score_gemma":0.00038956443,"threshold_uncertainty_score":0.9811656},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4115418379409699,"score_gpt":0.47321997805756816,"score_spread":0.06167814011659828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993980658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53342414,0.0002877203,0.46095508,0.00091073866,0.000086506494,0.00052335014,0.00003203173,0.0000037870054,0.0037766595],"genre_scores_gemma":[0.88803244,0.00006405637,0.11165192,0.000042582713,0.000021036427,0.00005660914,0.0000029086837,0.00000858132,0.000119889395],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9978445,0.00066973374,0.00056118914,0.00037231052,0.0002487949,0.0003034514],"domain_scores_gemma":[0.99702823,0.0024006194,0.00010543,0.00027033448,0.000035716977,0.00015964196],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0067916666,0.0000943556,0.00032449092,0.000095597294,0.0001153444,0.000032223277,0.00024309153,0.00010621161,0.0024668674],"category_scores_gemma":[0.004503939,0.00006133804,0.000020350095,0.00021069864,0.0010423992,0.00013232016,0.0002408177,0.00053439947,0.000019376772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006929175,0.00009235358,0.2848961,0.000119140976,0.000021126818,0.000004659099,0.00050323637,0.0002200541,0.00005566084,0.606106,0.00014969007,0.10776267],"study_design_scores_gemma":[0.0003837302,0.00009476858,0.49171284,0.00003806402,0.0000015596061,0.0000022362863,0.00019792689,0.17873408,0.000024980556,0.32873297,0.000018276363,0.00005856031],"about_ca_topic_score_codex":0.00074955134,"about_ca_topic_score_gemma":0.000051944826,"teacher_disagreement_score":0.3546083,"about_ca_system_score_codex":0.00016475609,"about_ca_system_score_gemma":0.000066213564,"threshold_uncertainty_score":0.99844503},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4958300143860889,"score_gpt":0.6114019961467672,"score_spread":0.11557198176067823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994201608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011174604,0.00004394705,0.95291084,0.009318216,0.00037866767,0.00047147766,0.000022086504,0.000042312407,0.025637856],"genre_scores_gemma":[0.5762991,0.000055287815,0.42194057,0.0013511906,0.00009622529,0.00010323784,0.0000041367834,0.00002644472,0.00012383693],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98248863,0.012896355,0.00044945438,0.0010366306,0.0023139128,0.00081504125],"domain_scores_gemma":[0.60504967,0.39356896,0.00004582888,0.00086418964,0.00011688501,0.00035448238],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032257672,0.00011773939,0.00026125135,0.00041983117,0.00019123619,0.000044253648,0.00068176095,0.00014776622,0.0012895879],"category_scores_gemma":[0.895532,0.00010561289,0.00001352509,0.0017915072,0.0007347094,0.00018832492,0.00062911387,0.002024334,0.00005228025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120564786,0.00030184875,0.0015066469,0.000072341994,0.000004082141,0.00023628071,0.00019742241,0.0000072783832,0.028988726,0.23724802,0.002334491,0.72898227],"study_design_scores_gemma":[0.0022532525,0.00042169832,0.020013575,0.00036043345,0.000004095591,0.000046153666,0.0011832773,0.05894597,0.11391679,0.7585918,0.043729845,0.0005331081],"about_ca_topic_score_codex":0.00016359662,"about_ca_topic_score_gemma":0.0002037264,"teacher_disagreement_score":0.86327434,"about_ca_system_score_codex":0.00022474297,"about_ca_system_score_gemma":0.00041943364,"threshold_uncertainty_score":0.99962336},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Medicine; Econometrics; Mathematics","score_opus":0.5884113956304523,"score_gpt":0.6665425784460107,"score_spread":0.07813118281555842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999384961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76721734,0.0073778583,0.16226064,0.03782787,0.0021470678,0.013069308,0.00012974953,0.000027407783,0.009942745],"genre_scores_gemma":[0.86712915,0.0012539891,0.12173308,0.0029711917,0.000670871,0.005990017,0.000025026282,0.000057856523,0.00016883777],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8918096,0.09859936,0.006844961,0.0007477625,0.0010873405,0.00091099954],"domain_scores_gemma":[0.33452323,0.6630692,0.0011662719,0.00077864435,0.00011853623,0.00034415862],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4318154,0.00019527758,0.0019744947,0.00035851303,0.00018956496,0.000056765413,0.0005968896,0.00021166664,0.0010290013],"category_scores_gemma":[0.70775294,0.00011082865,0.00013613286,0.00053744024,0.0007086325,0.00005959594,0.000113421396,0.00080710807,0.000101009355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010312386,0.000411838,0.0057997936,0.00090281124,0.00009943811,0.0000045734873,0.0055285287,0.000043590317,0.000023351091,0.26151162,0.0013018333,0.72334135],"study_design_scores_gemma":[0.019921897,0.0059962957,0.018198514,0.0006075024,0.000027538,0.0000019274332,0.0010098161,0.081877716,0.0002999125,0.86676663,0.005011779,0.00028049218],"about_ca_topic_score_codex":0.0016018262,"about_ca_topic_score_gemma":0.0002391469,"teacher_disagreement_score":0.7230609,"about_ca_system_score_codex":0.00046247983,"about_ca_system_score_gemma":0.00038306828,"threshold_uncertainty_score":0.9998842},"labels":[],"label_agreement":null},{"id":"W2002026546","doi":"10.1177/0962280212453891","title":"Meta-analysis using Dirichlet process","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Dirichlet process; Latent Dirichlet allocation; Hierarchical Dirichlet process; Dirichlet distribution; Generalized Dirichlet distribution; Computer science; Bayesian probability; Process (computing); Marginal likelihood; Statistics; Econometrics; Data mining; Mathematics; Topic model; Dirichlet's energy; Information retrieval","score_opus":0.4948803650150258,"score_gpt":0.630971933392843,"score_spread":0.13609156837781716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002026546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007816501,0.0018750445,0.9918189,0.0013445152,0.00015717714,0.00023650359,0.0000107406195,0.000043952394,0.0044349744],"genre_scores_gemma":[0.02442529,0.000030257506,0.9747289,0.00043941877,0.0001301363,0.000088618224,0.000002381294,0.000016741193,0.00013827636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.980588,0.013076015,0.00071644725,0.0007521882,0.0032778047,0.0015895115],"domain_scores_gemma":[0.9807393,0.016575923,0.000069323774,0.00091966754,0.00032683756,0.0013689412],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058727,0.00022494895,0.0011721717,0.0008780709,0.00017841606,0.00013225336,0.0017143138,0.00028522997,0.0027699247],"category_scores_gemma":[0.019036142,0.0001580214,0.00032917573,0.00526842,0.00052219746,0.00036979522,0.0007024528,0.0016684253,0.00002841638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010670499,0.00027689483,0.00022510887,0.00005560078,0.005549999,0.000097513155,0.0007766966,0.0000097397515,0.00007002739,0.6479138,0.00018810036,0.3448258],"study_design_scores_gemma":[0.00024497314,0.00006877726,0.00083179714,0.000009289601,0.0067778775,0.000026288648,0.000053427946,0.38855582,0.00052885804,0.60121447,0.0013259761,0.0003624685],"about_ca_topic_score_codex":0.00010646818,"about_ca_topic_score_gemma":0.000009614274,"teacher_disagreement_score":0.38854608,"about_ca_system_score_codex":0.000101010235,"about_ca_system_score_gemma":0.00039060047,"threshold_uncertainty_score":0.9981417},"labels":[],"label_agreement":null},{"id":"W2009966581","doi":"10.1177/0962280208092559","title":"Meta-analyses of safety data: a comparison of exact versus asymptotic methods","year":2008,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Health Canada","keywords":"Computer science; Statistics; Mathematics; Medicine; Econometrics","score_opus":0.9908641569893527,"score_gpt":0.8447660122197003,"score_spread":0.14609814476965244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009966581","genre_codex":"review","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.601742e-8,0.51623785,0.477406,0.00006324466,0.00027609582,0.0010192423,0.0005274967,0.000002240652,0.00446773],"genre_scores_gemma":[0.0000017548151,0.4979454,0.50124216,0.0000068416393,0.0000691978,0.0000956137,0.00011458067,0.000034488923,0.0004899759],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.1436781,0.72650546,0.0659219,0.005523716,0.056454513,0.0019163138],"domain_scores_gemma":[0.09312923,0.8691373,0.013090417,0.018502066,0.004485936,0.0016550877],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7225992,0.0011323363,0.05453356,0.0035780529,0.00019098308,0.00024402274,0.016701974,0.0012038529,0.10458129],"category_scores_gemma":[0.9024712,0.0005016897,0.007071642,0.011893148,0.0031739874,0.00019626673,0.004137435,0.004596171,0.0007416633],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057172718,0.00034482364,0.0000066324883,0.0059094606,0.010099879,0.00006207563,0.00008800904,0.000003212309,7.422864e-7,0.0063305786,0.016703904,0.9603935],"study_design_scores_gemma":[0.00038069236,0.00027151787,0.000018290935,0.0017327619,0.018282752,0.000023970766,0.00023380402,0.010779328,0.0000049340065,0.007998381,0.959889,0.0003845515],"about_ca_topic_score_codex":0.0002174914,"about_ca_topic_score_gemma":0.00005616537,"teacher_disagreement_score":0.960009,"about_ca_system_score_codex":0.00023043616,"about_ca_system_score_gemma":0.003579466,"threshold_uncertainty_score":0.99974346},"labels":[],"label_agreement":null},{"id":"W2017373633","doi":"10.1177/0962280207081866","title":"Surrogate endpoints: wishful thinking or reality?","year":2008,"lang":"en","type":"editorial","venue":"Statistical Methods in Medical Research","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wishful thinking; Surrogate endpoint; Psychology; Computer science; Medicine; Cognitive psychology; Internal medicine","score_opus":0.6801096472464887,"score_gpt":0.682748615074429,"score_spread":0.002638967827940264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017373633","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026732072,0.0042017004,0.36742094,0.03951941,0.5534466,0.0022124278,0.00473985,0.00016557999,0.028266773],"genre_scores_gemma":[0.000035223235,0.0094138915,0.5085864,0.0030435373,0.47110727,0.00079146103,0.0009480733,0.00027268997,0.00580143],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9480966,0.028518334,0.012850273,0.002976782,0.0045406213,0.0030174432],"domain_scores_gemma":[0.6282182,0.36369723,0.0024722428,0.002293051,0.00090871716,0.0024105955],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.3441978,0.0006157302,0.003942048,0.0016842141,0.0005741282,0.00025972616,0.002406936,0.0031222757,0.016869187],"category_scores_gemma":[0.7871143,0.0006417688,0.0002197598,0.0012830099,0.0018429632,0.00032565414,0.00089192804,0.009015192,0.0032569354],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001638507,0.00020311227,0.00009129323,0.0013317982,0.000076375356,0.00035719282,0.0008945697,0.0000018429749,8.897964e-8,0.10090314,0.88787055,0.00810618],"study_design_scores_gemma":[0.0010500213,0.00020781555,0.00016298788,0.0008065044,0.000005228282,0.0000103666325,0.00033998713,0.0019672299,7.5854877e-7,0.23891775,0.75604874,0.00048258895],"about_ca_topic_score_codex":0.006264033,"about_ca_topic_score_gemma":0.0014035217,"teacher_disagreement_score":0.4429165,"about_ca_system_score_codex":0.0029658624,"about_ca_system_score_gemma":0.005875044,"threshold_uncertainty_score":0.99976075},"labels":[],"label_agreement":null},{"id":"W2019366647","doi":"10.1177/0962280213503924","title":"Robust inference for mixed censored and binary response models with missing covariates","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Covariate; Estimator; Outlier; Inference; Computer science; Monte Carlo method; Missing data; Econometrics; Statistics; M-estimator; Robust statistics; Mathematics; Artificial intelligence","score_opus":0.41380458300558887,"score_gpt":0.5995737200556673,"score_spread":0.18576913705007847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019366647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002900698,0.00011478439,0.9921945,0.002786641,0.00006024507,0.0012609317,0.00009512865,0.00004933637,0.0005377353],"genre_scores_gemma":[0.013463242,0.00006742657,0.9853715,0.00011526383,0.000047438738,0.0006563281,0.000008251809,0.00006264324,0.00020794966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885453,0.007291494,0.0007591798,0.0008053418,0.0014200526,0.0011786099],"domain_scores_gemma":[0.79374415,0.20411481,0.000077463876,0.00042490722,0.00065559254,0.0009830655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021072246,0.00028234322,0.00074709876,0.00030317076,0.0002642263,0.00012122868,0.0003716079,0.00031421537,0.0006580327],"category_scores_gemma":[0.23038816,0.0002024852,0.000034347875,0.00051848125,0.0014961826,0.00020592478,0.0002899273,0.001254566,0.0000053156114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012619374,0.000162183,0.00001758522,0.00030923894,0.000018810495,0.000074948635,0.0002028808,0.00005574818,0.0007731797,0.65968376,0.0005805424,0.33685917],"study_design_scores_gemma":[0.00089471985,0.00049654633,0.0004948386,0.00022314757,0.00001191381,0.000009751521,0.00021167229,0.35338873,0.00010230236,0.64384633,0.00014500794,0.00017505251],"about_ca_topic_score_codex":0.00011688092,"about_ca_topic_score_gemma":0.000017786906,"teacher_disagreement_score":0.35333297,"about_ca_system_score_codex":0.00011070961,"about_ca_system_score_gemma":0.00046301127,"threshold_uncertainty_score":0.82571065},"labels":[],"label_agreement":null},{"id":"W2020953180","doi":"10.1177/0962280210391443","title":"A Bayesian destructive weighted Poisson cure rate model and an application to a cutaneous melanoma data","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Markov chain Monte Carlo; Poisson distribution; Bayesian inference; Bayesian probability; Mathematics; Statistics; Cure rate; Applied mathematics; Medicine; Surgery","score_opus":0.5453015859287329,"score_gpt":0.6948447323734955,"score_spread":0.14954314644476263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020953180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006384726,0.000014197655,0.98590904,0.0035096975,0.0002643053,0.001605599,0.00068525574,0.000096457305,0.0015306886],"genre_scores_gemma":[0.022421509,0.00004324741,0.97621584,0.00038074976,0.00043125649,0.0003152872,0.000036977537,0.000093748116,0.000061364226],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97760093,0.014639412,0.001690862,0.002070038,0.0026028308,0.0013959401],"domain_scores_gemma":[0.6042627,0.3879208,0.00020759417,0.0033128941,0.00073464506,0.003561376],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059343524,0.0003863122,0.0011580101,0.00043629674,0.00024345776,0.00014845925,0.0020786463,0.0008505868,0.0015147462],"category_scores_gemma":[0.66302735,0.00032192844,0.000041313877,0.0011740575,0.0017316856,0.00017130644,0.0016192851,0.0044140047,0.000037280355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004125734,0.0003003688,0.000087988534,0.00010534637,0.00002230502,0.0001821712,0.00017819116,0.0000011937051,0.002232832,0.46742418,0.0008237386,0.5282291],"study_design_scores_gemma":[0.0005424804,0.00029407753,0.00026495202,0.000061443796,0.000026545174,0.000046166217,0.0000694608,0.3684995,0.0001730421,0.6292839,0.0005151573,0.00022328451],"about_ca_topic_score_codex":0.00018029372,"about_ca_topic_score_gemma":0.0005545572,"teacher_disagreement_score":0.6036838,"about_ca_system_score_codex":0.000105549734,"about_ca_system_score_gemma":0.0006523604,"threshold_uncertainty_score":0.9999233},"labels":[],"label_agreement":null},{"id":"W2024260148","doi":"10.1191/0962280203sm350oa","title":"Comparison of methods to identify outliers observed in health services small area variation studies","year":2003,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Population Health Research Institute; Hospital for Sick Children; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Confidence interval; Statistics; Outlier; Skewness; Medicine; Demography; Statistical hypothesis testing; Mathematics; Econometrics","score_opus":0.6626424859726238,"score_gpt":0.6637911482392466,"score_spread":0.001148662266622802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024260148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005203635,0.0032108165,0.9785278,0.008732754,0.0004126497,0.000766521,0.00005263101,0.000013151819,0.0030800595],"genre_scores_gemma":[0.14029166,0.0008082623,0.8577537,0.00085236924,0.000027366248,0.00015539736,0.0000064270394,0.000018409182,0.00008639679],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98830616,0.0071899146,0.0024040365,0.00070378825,0.00036817856,0.0010279248],"domain_scores_gemma":[0.9873764,0.011249836,0.00024272042,0.0004013696,0.00014831526,0.00058139296],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07377802,0.00014991863,0.0010981227,0.0009665779,0.00009224808,0.000032517226,0.00044029826,0.00018071839,0.000506377],"category_scores_gemma":[0.057292566,0.00015627914,0.00004468459,0.0015225301,0.00021392597,0.000058363952,0.00024697263,0.00088632957,0.000040773917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040043433,0.0002801533,0.012654145,0.0014831595,0.000037839058,0.000008388553,0.005664099,0.00005198033,0.00001259692,0.83173877,0.00021503432,0.14781378],"study_design_scores_gemma":[0.0010294637,0.00052197144,0.17185444,0.0006032677,0.0000033608278,7.2806694e-7,0.0062658265,0.018590229,0.00011645495,0.75548553,0.045257654,0.00027107468],"about_ca_topic_score_codex":0.009850558,"about_ca_topic_score_gemma":0.0026705097,"teacher_disagreement_score":0.15920028,"about_ca_system_score_codex":0.00050412107,"about_ca_system_score_gemma":0.00023612165,"threshold_uncertainty_score":0.9967429},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5863130353224311,"score_gpt":0.5806095152849405,"score_spread":0.005703520037490528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035404753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8596705,0.000017471173,0.13737693,0.00082458125,0.000017583154,0.0016881657,0.000014224961,0.0000068370273,0.00038366966],"genre_scores_gemma":[0.67528474,0.000029442645,0.32446924,0.0000041525063,0.0000071245836,0.00018908406,8.499148e-7,0.000007601799,0.000007764232],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894098,0.00790736,0.0007768646,0.00025808386,0.0013480784,0.00029982234],"domain_scores_gemma":[0.9058805,0.09295272,0.00023424455,0.0006519073,0.0002093207,0.0000713251],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032364007,0.00015661067,0.00051995926,0.00006370126,0.00010981767,0.000012320083,0.0005161812,0.00007924562,0.000008713187],"category_scores_gemma":[0.06968031,0.000054902997,0.000039501687,0.00024285483,0.0015708974,0.000042276704,0.00016268369,0.000552514,2.3376492e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018980056,0.00078309426,0.02241156,0.0010131998,0.00006780739,0.000005805091,0.014355585,0.0013103926,0.0020718959,0.5593496,0.000038234637,0.3966948],"study_design_scores_gemma":[0.0005410898,0.0043616975,0.0034575702,0.0005499005,0.00002042718,0.0000013475361,0.00080512936,0.33898777,0.014179145,0.63702965,0.0000028252878,0.00006343971],"about_ca_topic_score_codex":0.0003791909,"about_ca_topic_score_gemma":0.00017959418,"teacher_disagreement_score":0.39663136,"about_ca_system_score_codex":0.0002633104,"about_ca_system_score_gemma":0.00026282368,"threshold_uncertainty_score":0.99638486},"labels":[],"label_agreement":null},{"id":"W2035409154","doi":"10.1177/0962280210372454","title":"A comparison of classification algorithms for the identification of smoke plumes from satellite images","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Energy and Environment Impacts","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University; Western University","funders":"","keywords":"Smoke; Satellite; Satellite imagery; Remote sensing; Computer science; Identification (biology); Environmental science; Air quality index; Data mining; Meteorology; Geography","score_opus":0.2288055250202884,"score_gpt":0.5778930655071207,"score_spread":0.3490875404868323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035409154","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087650456,0.0001539095,0.90892214,0.0014446466,0.00018979721,0.00036899993,0.00010051884,0.0000066671155,0.001162876],"genre_scores_gemma":[0.7150806,0.00014203758,0.2845659,0.000017147813,0.000032823722,0.000060893104,0.000025088428,0.000007842338,0.000067647445],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996515,0.0009342983,0.0006685957,0.00028526585,0.0012874932,0.0003093658],"domain_scores_gemma":[0.981684,0.01761994,0.00012220754,0.0003801939,0.000027249822,0.0001663532],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010846034,0.00008129001,0.00022841815,0.000055298686,0.000091258524,0.000015074799,0.0005184804,0.00016437302,0.003205224],"category_scores_gemma":[0.020258749,0.000055629185,0.000034922137,0.00029316355,0.0021389257,0.00006315807,0.00016660844,0.0006707226,0.000017904315],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006093043,0.00022312363,0.01775191,0.000019128847,0.000009746737,8.241715e-7,0.00028575,0.00006148134,0.14511794,0.0062621543,0.00032409737,0.8298829],"study_design_scores_gemma":[0.00027072564,0.00009019508,0.82131857,0.000018050718,0.000012191518,3.4598742e-7,0.00034953328,0.059055086,0.07221863,0.042867042,0.0037300158,0.000069647496],"about_ca_topic_score_codex":0.0008805455,"about_ca_topic_score_gemma":0.00017107376,"teacher_disagreement_score":0.82981324,"about_ca_system_score_codex":0.000045223893,"about_ca_system_score_gemma":0.000035713678,"threshold_uncertainty_score":0.997706},"labels":[],"label_agreement":null},{"id":"W2036536239","doi":"10.1177/0962280213480576","title":"An adaptive clinical trials procedure for a sensitive subgroup examined in the multiple sclerosis context","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"University of British Columbia","keywords":"Context (archaeology); Multiple sclerosis; Biomarker; Medicine; Clinical trial; Subgroup analysis; Oncology; Statistical power; Internal medicine; Outcome (game theory); Statistics; Meta-analysis; Immunology; Mathematics","score_opus":0.9252194452879065,"score_gpt":0.7518419097395197,"score_spread":0.17337753554838675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036536239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008650542,0.000071491995,0.9765431,0.0040533547,0.00054972083,0.008905694,0.00041809637,0.00006749361,0.0007404562],"genre_scores_gemma":[0.18661493,0.00008825471,0.8074244,0.0011787058,0.0007870584,0.0037659241,0.000013870081,0.00008278321,0.000044040135],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76078594,0.22284827,0.0072129425,0.002126001,0.004573914,0.0024529323],"domain_scores_gemma":[0.051490314,0.94392973,0.000519397,0.001284971,0.0013600253,0.0014155791],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42447096,0.0005199531,0.0032758552,0.00046102956,0.00026132842,0.00023269224,0.0017697742,0.0012768201,0.002269217],"category_scores_gemma":[0.9691238,0.00032813952,0.00037965257,0.001548517,0.0034197366,0.0001964018,0.00035419487,0.0049077827,0.000081475206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00215964,0.0017350498,0.00047875728,0.00018250756,0.00007218963,0.00009366578,0.0006428978,3.1134377e-7,0.00019526327,0.3287201,0.005873401,0.6598462],"study_design_scores_gemma":[0.005922207,0.002685414,0.021611953,0.0005262938,0.000064169246,0.0000090773365,0.0045400606,0.053698406,0.00022452594,0.9100258,0.0003070672,0.0003850455],"about_ca_topic_score_codex":0.0005719239,"about_ca_topic_score_gemma":0.00054378016,"teacher_disagreement_score":0.72108144,"about_ca_system_score_codex":0.00023380945,"about_ca_system_score_gemma":0.00089113065,"threshold_uncertainty_score":0.9999171},"labels":[],"label_agreement":null},{"id":"W2043640852","doi":"10.1177/0962280213476771","title":"Adjusted inference procedures for the interobserver agreement in twin studies","year":2013,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Statistics; Confidence interval; Statistic; Statistical inference; Computer science; Interval estimation; Statistical hypothesis testing; Multiple comparisons problem; Sample size determination; Cohen's kappa; Kappa; Test statistic; Mathematics; Econometrics; Artificial intelligence","score_opus":0.7237431735697322,"score_gpt":0.680536609079811,"score_spread":0.04320656448992122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043640852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026959958,0.0020380772,0.91454524,0.049598075,0.0007740607,0.0044193463,0.000021690917,0.000018991695,0.0016245357],"genre_scores_gemma":[0.5705475,0.000859089,0.4213044,0.0015061229,0.00020029815,0.004205858,0.000003671205,0.000020061125,0.0013529769],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9807243,0.008307147,0.0017207309,0.00090811605,0.007288438,0.0010512819],"domain_scores_gemma":[0.50127786,0.49087238,0.0002603459,0.0020758954,0.0045612785,0.000952243],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11421105,0.00019007131,0.0005605791,0.00039698128,0.00020797232,0.0002391555,0.0020414994,0.0001649981,0.0074444185],"category_scores_gemma":[0.6344833,0.00009572729,0.0000748693,0.0016241755,0.0015630176,0.00016783048,0.00085662625,0.0012807924,0.00024061234],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114913724,0.00032995417,0.01147687,0.00014969136,0.000032768196,0.0000137489815,0.0012881386,0.000044688524,0.0001409662,0.028953765,0.032792144,0.92466235],"study_design_scores_gemma":[0.0010022672,0.00043636098,0.16511637,0.0004097923,0.0000064201377,9.625664e-7,0.009585211,0.037000734,0.00017070943,0.7768029,0.009294668,0.00017358357],"about_ca_topic_score_codex":0.000516375,"about_ca_topic_score_gemma":0.0021128883,"teacher_disagreement_score":0.9244888,"about_ca_system_score_codex":0.00026456517,"about_ca_system_score_gemma":0.0005156538,"threshold_uncertainty_score":0.9934629},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3339326463437911,"score_gpt":0.6084049746751412,"score_spread":0.2744723283313501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047330460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057675125,0.0009652539,0.9938105,0.0017294683,0.0001767211,0.0005098383,0.00035062208,0.000055675486,0.001825168],"genre_scores_gemma":[0.041751135,0.00048500666,0.95707226,0.00018947957,0.00025533116,0.00009764597,0.000044612825,0.000042785974,0.00006174795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.986936,0.0072485944,0.00088352466,0.00085489586,0.00257838,0.0014986248],"domain_scores_gemma":[0.8534924,0.14141966,0.00012638212,0.0013442549,0.0004636583,0.0031536657],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028489921,0.00028405632,0.0006493485,0.00026893662,0.00021260466,0.00012049162,0.0012252426,0.0002666891,0.0036083763],"category_scores_gemma":[0.6194571,0.0002177205,0.000019690093,0.0011163902,0.0021613482,0.00030018808,0.0015141179,0.0016821602,0.00004215434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013728328,0.00031822562,0.0058085076,0.0010140275,0.000013677462,0.00027454022,0.0001693043,1.0801058e-8,0.000024205128,0.49729496,0.001353319,0.49359193],"study_design_scores_gemma":[0.00046653085,0.00012338388,0.020483812,0.00076462893,0.000034606066,0.000029269891,0.000099992685,0.0069601275,0.000053838005,0.969192,0.001493776,0.00029803207],"about_ca_topic_score_codex":0.00024498126,"about_ca_topic_score_gemma":0.00019195158,"teacher_disagreement_score":0.59096724,"about_ca_system_score_codex":0.00008595233,"about_ca_system_score_gemma":0.0013905702,"threshold_uncertainty_score":0.9973025},"labels":[],"label_agreement":null},{"id":"W2047721006","doi":"10.1177/09622802070160030704","title":"Book review: Kraemer HC, Kraemer-Lowe K, Kupfer DJ 2005: To your health: How to understand what research tells us about risk. New York: Oxford University Press. xviii + 270 pp. Tables and figures. US$49.95 Hardcover. ISBN 0 19 517870 X (#149)","year":2007,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Historical and modern epidemiology studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Sociology; Gerontology; Medicine","score_opus":0.3301029359075657,"score_gpt":0.5567726553447272,"score_spread":0.22666971943716152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047721006","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007640114,0.46077722,0.3644473,0.1565617,0.0006340443,0.002462399,0.00024357438,0.000067742054,0.014729619],"genre_scores_gemma":[0.000049310114,0.79272026,0.12469323,0.019519962,0.0006762914,0.000036507176,0.000020340582,0.0000494967,0.062234633],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9673463,0.020628475,0.0010931949,0.0017028417,0.0051071495,0.0041220435],"domain_scores_gemma":[0.95172197,0.040211342,0.00016810712,0.0007396378,0.00078282383,0.006376138],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.09029324,0.00041838913,0.0014358249,0.00047816298,0.0025018784,0.00018384856,0.0013713065,0.00066832005,0.0025223196],"category_scores_gemma":[0.15087904,0.00036251903,0.00013268177,0.0020408395,0.0042986413,0.00037486394,0.0012115823,0.003741727,0.00006497294],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035631508,0.00012953297,0.00052778405,0.00032192608,0.00005517446,0.00016390443,0.0032342535,0.0000029102648,0.0000045923393,0.0094552655,0.82155967,0.16418868],"study_design_scores_gemma":[0.00059789664,0.00047430472,0.0016073004,0.001133348,0.000028247914,0.0000023988302,0.0055648056,0.000072169234,0.0000071728346,0.0043781423,0.9857692,0.00036501724],"about_ca_topic_score_codex":0.03886785,"about_ca_topic_score_gemma":0.017250912,"teacher_disagreement_score":0.331943,"about_ca_system_score_codex":0.0022331765,"about_ca_system_score_gemma":0.0026231273,"threshold_uncertainty_score":0.9998827},"labels":[],"label_agreement":null},{"id":"W2048205624","doi":"10.1191/0962280203sm323ra","title":"Latent mixed Markov modelling of smoking transitions using Monte Carlo bootstrapping","year":2003,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Health Information; Western University","funders":"","keywords":"Bootstrapping (finance); Markov chain; Markov chain Monte Carlo; Statistics; Goodness of fit; Econometrics; Markov model; Mathematics; Computer science; Bayesian probability; Psychology","score_opus":0.3686365064289348,"score_gpt":0.5523188855137922,"score_spread":0.18368237908485735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048205624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.261545,0.0001106722,0.73660636,0.00020079716,0.00013333355,0.0002553396,0.000013621655,0.00001468789,0.0011201885],"genre_scores_gemma":[0.69008803,0.00005573814,0.3097286,0.000026564743,0.000032168966,0.000021009368,0.0000056874096,0.00001953762,0.000022651835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99351907,0.002607271,0.000696702,0.00038586042,0.0021556474,0.000635469],"domain_scores_gemma":[0.9955948,0.0033116671,0.00004819843,0.00027240295,0.00032481388,0.00044811887],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012271376,0.00013721963,0.00046336808,0.00044796537,0.00010959437,0.000018028892,0.0001269622,0.00028607738,0.0011575005],"category_scores_gemma":[0.00851748,0.00012406324,0.00007877183,0.0008393988,0.00051583024,0.000049036873,0.000034196975,0.0015029239,6.6593043e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009789558,0.0024434912,0.102708094,0.0021845673,0.00031013865,0.0024014795,0.003739888,0.00943557,0.020616192,0.09003579,0.0002567459,0.76488906],"study_design_scores_gemma":[0.0043104705,0.00055127597,0.05839062,0.0027672348,0.0002846837,0.00020965119,0.0024432887,0.89510685,0.010279303,0.024799919,0.0004010538,0.0004556564],"about_ca_topic_score_codex":0.00038287512,"about_ca_topic_score_gemma":0.000010425573,"teacher_disagreement_score":0.88567126,"about_ca_system_score_codex":0.00022778031,"about_ca_system_score_gemma":0.0005571992,"threshold_uncertainty_score":0.9998342},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2466960887406669,"score_gpt":0.6088668988222045,"score_spread":0.36217081008153756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049288534","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031280045,0.0001645742,0.99117154,0.002506514,0.0004636322,0.0012225958,0.0003599458,0.00008299766,0.0009001914],"genre_scores_gemma":[0.013467278,0.00018408347,0.98395663,0.0003565757,0.0007458958,0.0010197314,0.00010036092,0.00009784684,0.00007157979],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96013814,0.030714633,0.0016034434,0.0018274247,0.0039569945,0.0017593738],"domain_scores_gemma":[0.6431692,0.35200801,0.00018291578,0.0025033085,0.0005735903,0.0015629423],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10573425,0.00040482983,0.0016350446,0.0006210344,0.00015952035,0.00006113995,0.0015350234,0.00052662357,0.0017034339],"category_scores_gemma":[0.59481585,0.0002813079,0.00007217339,0.0016683068,0.0010845512,0.00011511461,0.0014531136,0.002321317,0.000104009705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008911373,0.00057343056,0.020381436,0.0007023775,0.00004956122,0.00020930052,0.00019312608,7.256307e-7,0.000023624532,0.2013495,0.041693214,0.73393255],"study_design_scores_gemma":[0.00067300274,0.00066133257,0.029563887,0.00035681663,0.00012087821,0.0000129586615,0.00014838725,0.029788094,0.00005092171,0.9197101,0.018222341,0.00069127127],"about_ca_topic_score_codex":0.00018456741,"about_ca_topic_score_gemma":0.000046214776,"teacher_disagreement_score":0.7332413,"about_ca_system_score_codex":0.00025796035,"about_ca_system_score_gemma":0.00060349575,"threshold_uncertainty_score":0.9999804},"labels":[],"label_agreement":null},{"id":"W2052404934","doi":"10.1177/0962280214553330","title":"On the analysis of composite measures of quality in medical research","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Health Canada; Partenariat Canadien Contre Le Cancer; Heart and Stroke Foundation of Canada","keywords":"Binomial regression; Statistics; Logistic regression; Generalized linear model; Mathematics; Generalized estimating equation; Poisson regression; Marginal model; Regression analysis; Negative binomial distribution; Overdispersion; Quasi-likelihood; Linear regression; Gee; Econometrics; Poisson distribution; Medicine; Population","score_opus":0.89062208648722,"score_gpt":0.7857866714285195,"score_spread":0.10483541505870042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052404934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027486425,0.000069582304,0.95076215,0.0074082823,0.00022724114,0.0009815294,0.00019239206,0.000022165279,0.012850252],"genre_scores_gemma":[0.24993728,0.00012338352,0.7493024,0.00026812768,0.000116491334,0.00015686522,0.0000044213384,0.00004080367,0.00005020802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7226506,0.24497475,0.0061843847,0.0014826737,0.022604099,0.002103493],"domain_scores_gemma":[0.106773086,0.8885837,0.00034527932,0.0017336005,0.0015106633,0.0010536611],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.50820994,0.00030946673,0.0029188546,0.0020578597,0.00015374339,0.00003690338,0.002580996,0.0009275924,0.0104591735],"category_scores_gemma":[0.964639,0.00019902387,0.0003130263,0.00818005,0.007796699,0.000033930195,0.0010466818,0.0066502416,0.00002372492],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006335776,0.0009938073,0.001312478,0.0002795913,0.00021583503,0.000047225705,0.00020176082,0.0000042237016,0.00020722978,0.70625705,0.00081075315,0.28903648],"study_design_scores_gemma":[0.0011646968,0.00048723796,0.027862562,0.0006502027,0.00008730845,0.0000011289513,0.00022550105,0.02209767,0.00087631587,0.94610924,0.00025894077,0.00017921855],"about_ca_topic_score_codex":0.0012833021,"about_ca_topic_score_gemma":0.0008060411,"teacher_disagreement_score":0.643609,"about_ca_system_score_codex":0.00023219924,"about_ca_system_score_gemma":0.00085135346,"threshold_uncertainty_score":0.99564147},"labels":[],"label_agreement":null},{"id":"W2052567778","doi":"10.1177/0962280212448973","title":"Comparing variational Bayes with Markov chain Monte Carlo for Bayesian computation in neuroimaging","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; Western University; University of Victoria","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Monte Carlo method; Bayesian probability; Context (archaeology); Computation; Artificial intelligence; Approximate Bayesian computation; Bayesian inference; Inverse problem; Algorithm; Machine learning; Mathematics; Statistics; Inference","score_opus":0.13727059447463075,"score_gpt":0.5244023664070628,"score_spread":0.3871317719324321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052567778","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007828873,0.000056057124,0.9932759,0.003574588,0.00010098716,0.00056286505,0.000005238656,0.000076390046,0.0015651071],"genre_scores_gemma":[0.34368163,0.000005065951,0.65584886,0.0002262147,0.000053893866,0.00015339965,0.0000053244476,0.000011991887,0.000013609654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99230295,0.0043115993,0.00051696895,0.00047096587,0.0015764509,0.00082105387],"domain_scores_gemma":[0.98271364,0.01635696,0.00005791108,0.0002511218,0.00022370224,0.0003966551],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024262227,0.00014032915,0.0003204583,0.00057468895,0.00011711415,0.00014227284,0.00062784896,0.000120027136,0.000053573054],"category_scores_gemma":[0.0113852965,0.00012272819,0.000024445426,0.0010377166,0.0002589197,0.00039394936,0.00029880775,0.0010437183,0.0000030414133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094577015,0.00027037147,0.013943617,0.000079073405,0.000008898494,0.00003504852,0.0017146018,0.00041326668,0.00004945686,0.5451467,0.00051507435,0.43772933],"study_design_scores_gemma":[0.0006055072,0.00011809395,0.050151534,0.00008279681,0.0000014504978,0.000010563158,0.00006903249,0.9023379,0.000068843314,0.04600294,0.00042102276,0.00013030818],"about_ca_topic_score_codex":0.00020289798,"about_ca_topic_score_gemma":0.00011196957,"teacher_disagreement_score":0.90192467,"about_ca_system_score_codex":0.00017019236,"about_ca_system_score_gemma":0.00034711778,"threshold_uncertainty_score":0.9969422},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8657958110574773,"score_gpt":0.6909467344486384,"score_spread":0.17484907660883886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057830194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025856705,0.0006585826,0.9611034,0.005559365,0.00014922024,0.0011288803,0.00041647692,0.000021907192,0.00510549],"genre_scores_gemma":[0.11932376,0.00017845204,0.87898654,0.0010068857,0.00015012677,0.00015694252,0.00008647029,0.000040488656,0.00007034424],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9801155,0.013534556,0.003227109,0.0012608673,0.0007522085,0.0011097887],"domain_scores_gemma":[0.94838136,0.049314447,0.00042637577,0.0011197878,0.00012623623,0.0006318151],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.17380299,0.0001848765,0.0014560858,0.0017062194,0.00016307386,0.000087776985,0.0008925429,0.00027567442,0.0060531106],"category_scores_gemma":[0.16945189,0.00019352419,0.00004618592,0.0030675144,0.00060837844,0.0003199579,0.00038273117,0.0013368179,0.00027084965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000189316,0.00082534924,0.48806524,0.0011441319,0.00047493755,0.00035221348,0.0018599622,0.0015634313,0.000009191648,0.4517593,0.0026686618,0.05108823],"study_design_scores_gemma":[0.0011842039,0.000068952264,0.04847097,0.00021490177,0.000016029104,0.000005002364,0.00061722985,0.9212367,0.0000028923243,0.023724454,0.004215135,0.00024356734],"about_ca_topic_score_codex":0.005053329,"about_ca_topic_score_gemma":0.0018654774,"teacher_disagreement_score":0.9196732,"about_ca_system_score_codex":0.0010511628,"about_ca_system_score_gemma":0.00026402288,"threshold_uncertainty_score":0.99485546},"labels":[],"label_agreement":null},{"id":"W2059439741","doi":"10.1177/0962280209344926","title":"Outlier detection for a hierarchical Bayes model in a study of hospital variation in surgical procedures","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Carleton University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Southern California","keywords":"Outlier; Bayes' theorem; Variation (astronomy); Computer science; Multilevel model; Statistics; Anomaly detection; Random effects model; Bayesian hierarchical modeling; Data mining; Bayesian probability; Artificial intelligence; Medicine; Machine learning; Mathematics","score_opus":0.056961056414367765,"score_gpt":0.4984115217864363,"score_spread":0.4414504653720685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059439741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06535888,0.000017990385,0.9320059,0.0007271104,0.00023701241,0.0013047996,0.0000071565078,0.000019419196,0.000321741],"genre_scores_gemma":[0.4542117,0.000006877548,0.5453468,0.000014151646,0.000045398123,0.0003541908,6.99978e-7,0.000009898068,0.0000102832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912995,0.0042944285,0.00096159894,0.0008969075,0.0017198197,0.000827757],"domain_scores_gemma":[0.98369414,0.015100935,0.0000681225,0.00048865005,0.00026254423,0.00038563067],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02813781,0.00017644005,0.0005510312,0.0008177569,0.0000666281,0.0000613482,0.00096394,0.0004060784,0.00004329629],"category_scores_gemma":[0.048269715,0.00014641507,0.000048417533,0.0014421107,0.00034223823,0.00017357545,0.00041228347,0.0025613823,0.0000010178425],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023055126,0.002172618,0.0005428439,0.00009882604,0.000006759746,0.00011870692,0.0032864828,0.000031573873,0.0010373092,0.27423373,0.000012750979,0.71822786],"study_design_scores_gemma":[0.0014809744,0.0007479488,0.009437502,0.0000402645,0.0000017993235,0.000004207198,0.00005216481,0.5717137,0.0001387152,0.41625372,0.000022223572,0.00010681552],"about_ca_topic_score_codex":0.00030267477,"about_ca_topic_score_gemma":0.0018846742,"teacher_disagreement_score":0.71812105,"about_ca_system_score_codex":0.000087668406,"about_ca_system_score_gemma":0.0007276428,"threshold_uncertainty_score":0.99973977},"labels":[],"label_agreement":null},{"id":"W2063974614","doi":"10.1191/0962280205sm0391oa","title":"On group sequential procedures under variance heterogeneity","year":2005,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variance (accounting); Group (periodic table); Statistics; Econometrics; Computer science; Mathematics; Economics","score_opus":0.7225271869331464,"score_gpt":0.7272749290543858,"score_spread":0.004747742121239407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063974614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022374673,0.00008034224,0.9820144,0.0044765635,0.00059959706,0.0009621779,0.00011018962,0.00012562862,0.009393622],"genre_scores_gemma":[0.034033705,0.00010505913,0.9627651,0.0014405723,0.0009977554,0.0003233798,0.0000050134554,0.00009193564,0.0002374541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9629804,0.026176767,0.00219012,0.0015061134,0.005217883,0.0019287525],"domain_scores_gemma":[0.6050908,0.392111,0.00015361268,0.0009689937,0.00033222625,0.0013433344],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071765244,0.0004259197,0.0012464799,0.00041650803,0.00025122572,0.00011756535,0.0012963124,0.000820916,0.012496996],"category_scores_gemma":[0.75534326,0.00034266774,0.00016216128,0.0011561692,0.002169226,0.00009805984,0.00062914396,0.0040892432,0.00034917652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041500686,0.00084582646,0.000040287243,0.00018462942,0.0000397303,0.00014942093,0.000035704117,0.0000057521643,0.00019920275,0.7040132,0.004419881,0.2896513],"study_design_scores_gemma":[0.0017048,0.0005139346,0.0011460958,0.00036796342,0.000023492554,0.00002091103,0.000038002683,0.005522822,0.0007655932,0.9871373,0.002409252,0.0003498385],"about_ca_topic_score_codex":0.000047058427,"about_ca_topic_score_gemma":0.00019461286,"teacher_disagreement_score":0.683578,"about_ca_system_score_codex":0.00047982627,"about_ca_system_score_gemma":0.0006879122,"threshold_uncertainty_score":0.99990255},"labels":[],"label_agreement":null},{"id":"W2064839688","doi":"10.1177/0962280211406470","title":"A multi-state model for the analysis of changes in cognitive scores over a fixed time interval","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Capital District Health Authority; Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Statistics; Poisson distribution; Multivariate statistics; Cognition; Mathematics; Econometrics; Survival function; Poisson regression; Survival analysis; Psychology; Medicine; Population; Psychiatry","score_opus":0.3759594243516181,"score_gpt":0.6005438283901415,"score_spread":0.22458440403852342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064839688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024407065,0.00014752193,0.97090846,0.00061529706,0.0000883586,0.0013516479,0.00030836725,0.000016457887,0.0021568045],"genre_scores_gemma":[0.63096255,0.00045261905,0.36727843,0.00018467088,0.000038267946,0.00059268874,0.000012634545,0.000017890156,0.00046024442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99109477,0.0051307823,0.0005381677,0.000450562,0.0019559432,0.00082975195],"domain_scores_gemma":[0.97742045,0.021630026,0.00008063034,0.00024069933,0.00037684577,0.00025132837],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036348313,0.00012754994,0.00051843293,0.0009528446,0.00017741964,0.000032369844,0.0007358146,0.0001450514,0.0020934003],"category_scores_gemma":[0.046066992,0.00009244583,0.0001258836,0.0026261613,0.0031420437,0.00005928925,0.00028981303,0.00068058464,0.0000050686945],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011811815,0.0012366356,0.06672574,0.00017109425,0.0010485771,0.000108094195,0.057695437,0.000047738857,0.00005638821,0.05377448,0.0005670823,0.8173876],"study_design_scores_gemma":[0.0006811614,0.00009706192,0.27976257,0.00010155723,0.00013371992,4.8385797e-8,0.0022555173,0.6830042,0.00002802613,0.03373642,0.00008620836,0.00011349406],"about_ca_topic_score_codex":0.0102328025,"about_ca_topic_score_gemma":0.063635156,"teacher_disagreement_score":0.81727403,"about_ca_system_score_codex":0.00009667399,"about_ca_system_score_gemma":0.0002825438,"threshold_uncertainty_score":0.99957085},"labels":[],"label_agreement":null},{"id":"W2069283580","doi":"10.1177/0962280212469682","title":"A cure rate survival model under a hybrid latent activation scheme","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Unobservable; Poisson distribution; Carcinogenesis; Survival analysis; Statistics; Mathematics; Biology; Econometrics; Cancer; Genetics","score_opus":0.853355063546163,"score_gpt":0.7394206970475853,"score_spread":0.11393436649857769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069283580","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003848191,0.00006179825,0.9852623,0.0036903657,0.0007407828,0.0009091844,0.00011139978,0.000110235276,0.0052657966],"genre_scores_gemma":[0.033220775,0.00010256311,0.9646643,0.00049148424,0.0007081718,0.00029676806,0.000010525016,0.00010575761,0.00039966565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95748496,0.031830564,0.0022502944,0.0010468819,0.004766077,0.0026212283],"domain_scores_gemma":[0.5229411,0.47319135,0.00020596688,0.0009826466,0.00059250905,0.002086401],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12751694,0.0004211615,0.0013445569,0.00042801673,0.00022262294,0.00008673055,0.0009244824,0.0006373098,0.0063979886],"category_scores_gemma":[0.75748354,0.00034072745,0.0001573301,0.0011708377,0.0015495435,0.0002146618,0.0007980264,0.0043164887,0.00016232443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038171213,0.0009649861,0.00038496093,0.0002427557,0.00006308455,0.00004999048,0.00011426516,0.0000089756295,0.0010393701,0.8769533,0.0046525695,0.115144044],"study_design_scores_gemma":[0.0013445136,0.00013693185,0.0019635707,0.00024410854,0.00002634858,0.0000073142833,0.000101776175,0.08675495,0.0012156388,0.90722686,0.0006352507,0.00034270843],"about_ca_topic_score_codex":0.00006281424,"about_ca_topic_score_gemma":0.000007755167,"teacher_disagreement_score":0.62996656,"about_ca_system_score_codex":0.00044252953,"about_ca_system_score_gemma":0.0007093268,"threshold_uncertainty_score":0.99990445},"labels":[],"label_agreement":null},{"id":"W2071158082","doi":"10.1177/0962280207081606","title":"Stratified and randomized play-the-winner rule","year":2008,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Randomized controlled trial; Confounding; Computer science; Selection (genetic algorithm); Selection bias; Medicine; Statistics; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.7300653694511776,"score_gpt":0.7097057590069843,"score_spread":0.02035961044419332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071158082","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030141878,0.00026029587,0.9729402,0.0048171887,0.00047923514,0.0016360796,0.00006074785,0.000072147894,0.01671991],"genre_scores_gemma":[0.00982452,0.0006520205,0.98739195,0.00045637647,0.00038315446,0.0004665792,0.0000025992947,0.000058008358,0.0007647695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9275453,0.06223586,0.0028137218,0.0011526902,0.0046396377,0.0016128024],"domain_scores_gemma":[0.29652825,0.7011834,0.00014993371,0.0007806313,0.00035224165,0.0010055517],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1393079,0.00033800566,0.0019778681,0.0002810246,0.00045885053,0.000076432705,0.000925139,0.00058818166,0.007055494],"category_scores_gemma":[0.8714675,0.00020449646,0.00015452472,0.0007828408,0.010040703,0.00006411024,0.00063058635,0.0037828228,0.00006939682],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005650241,0.00025923608,0.00008516525,0.00012172448,0.00006565465,0.00055294944,0.0004213907,1.457807e-7,0.000051259743,0.76037246,0.0057917093,0.22662807],"study_design_scores_gemma":[0.026454093,0.00013871354,0.00095868384,0.00012967046,0.000036552196,0.00007916672,0.00012742387,0.0040077474,0.00016918627,0.9667336,0.0009348115,0.00023039206],"about_ca_topic_score_codex":0.00012952981,"about_ca_topic_score_gemma":0.00002091834,"teacher_disagreement_score":0.73215955,"about_ca_system_score_codex":0.00009324988,"about_ca_system_score_gemma":0.00050542434,"threshold_uncertainty_score":0.9985155},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.9591079010063465,"score_gpt":0.7651604513098256,"score_spread":0.1939474496965209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071412894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024195572,0.00015809297,0.9770606,0.00075421913,0.0024218038,0.0021002067,0.00033148617,0.00010679445,0.014647195],"genre_scores_gemma":[0.0093945945,0.00042477084,0.9882727,0.00026112335,0.0011461711,0.00025370656,0.000018986953,0.00009325169,0.00013469401],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8460084,0.13009137,0.009853249,0.003544012,0.007201209,0.0033017641],"domain_scores_gemma":[0.17811501,0.81459594,0.00056161184,0.0038441082,0.0007308595,0.0021524925],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4092959,0.0004675223,0.0027588734,0.0006180527,0.00013553373,0.0000877326,0.0039345697,0.0011314946,0.011180243],"category_scores_gemma":[0.9459789,0.00038007653,0.00016788153,0.0017964777,0.0030876067,0.00018076594,0.0026407347,0.006641019,0.00015532176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018828643,0.0026807596,0.0024006956,0.00021260513,0.00007291404,0.0015490688,0.00014568504,6.433889e-8,0.000010987402,0.2713148,0.0029421425,0.6998416],"study_design_scores_gemma":[0.029964518,0.0011266021,0.00554166,0.0005145044,0.000047070364,0.0000122731135,0.00017659913,0.011682262,0.000049029222,0.9488743,0.0015954248,0.00041577828],"about_ca_topic_score_codex":0.0005986322,"about_ca_topic_score_gemma":0.00036986376,"teacher_disagreement_score":0.6994259,"about_ca_system_score_codex":0.00018521091,"about_ca_system_score_gemma":0.0012816591,"threshold_uncertainty_score":0.9998651},"labels":[],"label_agreement":null},{"id":"W2075432660","doi":"10.1177/0962280214544251","title":"Statistical methods for incomplete data: Some results on model misspecification","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Estimator; Inverse probability weighting; Inverse probability; Imputation (statistics); Weighting; Mathematics; Covariate; Estimating equations; Applied mathematics; Statistics; Inverse; Asymptotic distribution; Empirical likelihood; Delta method; Econometrics; Computer science; Missing data; Posterior probability; Bayesian probability","score_opus":0.7813321794790806,"score_gpt":0.7350020607206029,"score_spread":0.0463301187584777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075432660","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001936389,0.000033706943,0.98823833,0.0030470132,0.00014492935,0.0011994992,0.0010298792,0.00019161272,0.006095658],"genre_scores_gemma":[0.0018100708,0.00010028814,0.99616784,0.0003672961,0.00032224134,0.0005079048,0.0003937867,0.00009272733,0.0002378357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98039716,0.012319811,0.0017327188,0.0016178079,0.0024738228,0.0014586691],"domain_scores_gemma":[0.7480708,0.24806792,0.00017972107,0.002165597,0.0005705045,0.0009455169],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.081970245,0.0003565433,0.0009394543,0.00048219386,0.00023963534,0.00009038029,0.001937323,0.00050075335,0.00039670407],"category_scores_gemma":[0.5519355,0.00030026204,0.0000516333,0.00058259396,0.0014019196,0.00021896148,0.00088405324,0.0024384232,0.00003780865],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033469795,0.00018921965,7.8882175e-7,0.00012316153,0.0000089967525,0.0000076006418,0.000048068156,0.0000063317543,0.00050242123,0.55711895,0.0100202635,0.4316395],"study_design_scores_gemma":[0.00064283214,0.0003818708,0.00003451569,0.00011732486,0.000010066623,0.0000023840016,0.000028985723,0.39908612,0.00084023667,0.5865196,0.012149302,0.00018673677],"about_ca_topic_score_codex":0.000036632962,"about_ca_topic_score_gemma":0.000018864968,"teacher_disagreement_score":0.46996525,"about_ca_system_score_codex":0.00033340193,"about_ca_system_score_gemma":0.00046515823,"threshold_uncertainty_score":0.9999449},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06775448943020891,"score_gpt":0.4855262341241343,"score_spread":0.4177717446939254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082197682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020352664,0.0001277931,0.9937761,0.00035167387,0.000070634786,0.0012842189,0.000045392226,0.00032242225,0.0038182621],"genre_scores_gemma":[0.03403563,0.00015611632,0.96263015,0.000096320735,0.0000443094,0.0028729804,0.000052924217,0.000059516984,0.000052017895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963962,0.0008747172,0.00047652918,0.00040218415,0.001047013,0.00080338836],"domain_scores_gemma":[0.98822606,0.010538485,0.000030354156,0.00032903583,0.0004697655,0.00040629672],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036143735,0.00020470597,0.0003246964,0.00044389282,0.00009651009,0.00007262595,0.00039851852,0.0002077525,0.0014053135],"category_scores_gemma":[0.0069522667,0.0001695469,0.000030402512,0.0008966268,0.00044191707,0.00021789463,0.000060062066,0.0008123331,0.000011218479],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021162986,0.0002710963,0.00073260505,0.00077370135,0.00006269818,0.000029017008,0.00028673047,0.01590714,0.001213727,0.096551016,0.006044538,0.8779161],"study_design_scores_gemma":[0.000522824,0.00022257524,0.00033507886,0.00016986005,0.0000048234006,6.125061e-7,0.000081707716,0.7064664,0.0047256513,0.28648055,0.0008168314,0.00017312418],"about_ca_topic_score_codex":0.00005649881,"about_ca_topic_score_gemma":0.000013987255,"teacher_disagreement_score":0.877743,"about_ca_system_score_codex":0.00011897593,"about_ca_system_score_gemma":0.00023965118,"threshold_uncertainty_score":0.99950755},"labels":[],"label_agreement":null},{"id":"W2084416125","doi":"10.1177/0962280208096046","title":"Efficient sampling approaches to address confounding in database studies","year":2008,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Primary Care and Health Outcomes","field":"Health Professions","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Confounding; Pharmacoepidemiology; Medical prescription; Computer science; Sampling (signal processing); Medicine; Data mining; Statistics; Mathematics; Pharmacology","score_opus":0.9154363551370552,"score_gpt":0.7780213316583924,"score_spread":0.13741502347866286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084416125","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020873035,0.91026247,0.07526864,0.0018150165,0.0012425056,0.0042998893,0.00034072783,0.000046170626,0.006722469],"genre_scores_gemma":[5.333877e-7,0.7309792,0.26457474,0.0009878395,0.0004698469,0.002534096,0.00012207711,0.000073390125,0.00025825243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94828886,0.040060148,0.0034749976,0.0014882644,0.0035399047,0.0031478517],"domain_scores_gemma":[0.78283596,0.2141049,0.00023090336,0.00093993713,0.0002963095,0.0015920174],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.058859326,0.000571475,0.004462663,0.0021228383,0.00083467213,0.000019656412,0.001321362,0.0011622371,0.0017985563],"category_scores_gemma":[0.23118564,0.00042224553,0.00016633514,0.0028642225,0.0010168833,0.00003384045,0.0027442048,0.012730152,0.00050449563],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000051415904,0.00013468527,0.000031306303,0.046601687,0.000047737463,0.0006615124,0.0012937672,0.0000013529644,4.7675737e-8,0.026737947,0.009414161,0.9150244],"study_design_scores_gemma":[0.00053201226,0.00009564779,0.00005948258,0.0369735,0.000033232853,0.0000146947,0.0016745902,0.0002179123,4.2571802e-8,0.0019133836,0.9581074,0.0003780759],"about_ca_topic_score_codex":0.00064225687,"about_ca_topic_score_gemma":0.0006102582,"teacher_disagreement_score":0.9486933,"about_ca_system_score_codex":0.004463305,"about_ca_system_score_gemma":0.013966466,"threshold_uncertainty_score":0.9998229},"labels":[],"label_agreement":null},{"id":"W2086701312","doi":"10.1177/0962280211399562","title":"Bayesian sample size calculation for estimation of the difference between two binomial proportions","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; University of Tehran","keywords":"Dirichlet distribution; Sample size determination; Statistics; Mathematics; Bayesian probability; Binomial (polynomial); Beta-binomial distribution; Binomial distribution; Negative binomial distribution; Econometrics; Prior probability; Computer science; Poisson distribution","score_opus":0.7821547142411684,"score_gpt":0.7131122956078051,"score_spread":0.06904241863336336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086701312","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015516534,0.0000043953582,0.99355537,0.00050676736,0.00031421537,0.0017881624,0.001346207,0.00003314305,0.0009000646],"genre_scores_gemma":[0.07066869,0.0000043005584,0.9284818,0.000037183367,0.00020839821,0.00047591366,0.000011350693,0.000039108305,0.000073258736],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98257476,0.011573321,0.0021330223,0.0006389759,0.00225688,0.00082302303],"domain_scores_gemma":[0.27656975,0.7210425,0.00036748618,0.00086504733,0.00058928004,0.00056591415],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037365764,0.00022015175,0.00091631693,0.00018374628,0.00021699024,0.000024952098,0.00089595624,0.00039157714,0.0062600053],"category_scores_gemma":[0.91480875,0.00014790634,0.00016205013,0.0010141303,0.002085638,0.00004655328,0.00038846495,0.0013839926,0.0000053873787],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018499784,0.00030229273,0.0024155139,0.00028272308,0.00003328347,0.0000040992886,0.00019897436,0.0000010343425,0.00009586909,0.3775213,0.0005761691,0.6183837],"study_design_scores_gemma":[0.0010240162,0.00026370925,0.04774433,0.00024491682,0.00005679792,0.0000013010559,0.00003613592,0.022684978,0.0018191651,0.92591536,0.00006321132,0.00014605369],"about_ca_topic_score_codex":0.00038258234,"about_ca_topic_score_gemma":0.000079474776,"teacher_disagreement_score":0.87744296,"about_ca_system_score_codex":0.00015134765,"about_ca_system_score_gemma":0.0006474956,"threshold_uncertainty_score":0.9946484},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.738749131992883,"score_gpt":0.6926737143409845,"score_spread":0.04607541765189849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093541024","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.29747e-7,0.4339816,0.5621131,0.00022855568,0.000044680346,0.0032347718,0.00019560136,0.000020406264,0.00018112834],"genre_scores_gemma":[2.0836067e-7,0.4780119,0.5209906,0.000053660762,0.00007339095,0.0007500855,0.000031227628,0.00006406453,0.000024817647],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9285965,0.06086383,0.0030372427,0.002249393,0.004080705,0.0011723542],"domain_scores_gemma":[0.6671864,0.3263926,0.0005959125,0.0031040972,0.0013828509,0.0013381671],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13047242,0.0007764693,0.005417142,0.00076094,0.00017646307,0.000106636006,0.002386424,0.00053250795,0.0012299377],"category_scores_gemma":[0.5777086,0.00050413987,0.000093037415,0.0036292265,0.0009758025,0.000083455496,0.0015325504,0.0032555945,0.000021329248],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094633215,0.00059354666,0.000010063713,0.14055802,0.00015013786,0.00012286355,0.00003660742,3.2572952e-8,9.822122e-8,0.05905841,0.0016668506,0.79770875],"study_design_scores_gemma":[0.0010805945,0.007044042,0.00022670972,0.400109,0.0018740298,0.00012888639,0.000092257826,0.0011181141,0.0000033878266,0.32062545,0.26645625,0.0012412823],"about_ca_topic_score_codex":0.00010309026,"about_ca_topic_score_gemma":0.000043943055,"teacher_disagreement_score":0.7964675,"about_ca_system_score_codex":0.00021092834,"about_ca_system_score_gemma":0.0027408046,"threshold_uncertainty_score":0.999741},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.9107676203454614,"score_gpt":0.7895228873335225,"score_spread":0.12124473301193894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096206421","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007578008,0.00020519763,0.98474,0.0020526035,0.0007756311,0.002492466,0.0000313148,0.000057980804,0.0020667901],"genre_scores_gemma":[0.041361913,0.00041124914,0.9565368,0.0002760998,0.0003178461,0.0007832706,5.983648e-7,0.00006583877,0.00024635054],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7452556,0.23940074,0.0052893804,0.0019790104,0.004492835,0.0035824473],"domain_scores_gemma":[0.19702874,0.8006013,0.00016435393,0.0009501172,0.00034921625,0.00090627105],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27730417,0.0003685841,0.0015722369,0.00039033042,0.0006623239,0.000055774915,0.0014168667,0.00057463825,0.0033292116],"category_scores_gemma":[0.9292687,0.00023832863,0.00010929834,0.0018960898,0.004822175,0.00006528135,0.0008757352,0.005873616,0.0000988882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017035316,0.00227804,0.0036248816,0.00008416734,0.000087372486,0.065169364,0.0007901061,0.0000055735836,0.000027723234,0.3232525,0.016690446,0.5862863],"study_design_scores_gemma":[0.0035016902,0.0007441092,0.0038808451,0.00006740793,0.000019345423,0.0007532061,0.0007650864,0.012934333,0.000049077746,0.9759517,0.0010758194,0.00025740408],"about_ca_topic_score_codex":0.00056093157,"about_ca_topic_score_gemma":0.00032863987,"teacher_disagreement_score":0.6526992,"about_ca_system_score_codex":0.00034400297,"about_ca_system_score_gemma":0.0008148605,"threshold_uncertainty_score":0.9978861},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.9834534062452185,"score_gpt":0.7951079030339979,"score_spread":0.18834550321122057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096814695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008672418,0.007456789,0.96306723,0.012046651,0.00021236199,0.0026972801,0.0001784833,0.000007115926,0.013466841],"genre_scores_gemma":[0.010582632,0.0017084386,0.9759682,0.0018655624,0.00012686409,0.001128489,0.000004679291,0.000035704536,0.008579441],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8289838,0.13508217,0.014519197,0.002796852,0.017287627,0.0013303738],"domain_scores_gemma":[0.62098926,0.36863783,0.0020996714,0.0035520531,0.0033019544,0.0014192135],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6035617,0.00042326798,0.006921274,0.0012616282,0.0005143928,0.0018769247,0.0019881614,0.0003858016,0.13554327],"category_scores_gemma":[0.621998,0.00018831308,0.0017547648,0.0027474489,0.0008410545,0.0003647358,0.00041260305,0.0012375647,0.00055467966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019645906,0.00028317454,0.00019880201,0.00019910077,0.0028094628,0.000031849784,0.0072263023,8.711416e-7,0.00014723586,0.17969674,0.03469609,0.7745139],"study_design_scores_gemma":[0.0005606615,0.00063621026,0.0011182259,0.00018742181,0.001836807,0.000005285885,0.0048520486,0.0064308774,0.00028851576,0.9349602,0.048862938,0.00026082495],"about_ca_topic_score_codex":0.00031717122,"about_ca_topic_score_gemma":0.00019102203,"teacher_disagreement_score":0.7742531,"about_ca_system_score_codex":0.000076134,"about_ca_system_score_gemma":0.00038709017,"threshold_uncertainty_score":0.9991592},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.12325957161327475,"score_gpt":0.5478868605346664,"score_spread":0.4246272889213917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098775098","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012463845,0.00003527765,0.97789174,0.004208371,0.0003487558,0.00049798883,0.000059827606,0.00004588971,0.015665745],"genre_scores_gemma":[0.053140707,0.00005576058,0.9458799,0.00037892017,0.0001991514,0.00014118051,0.000004937903,0.00003809613,0.0001613588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98987526,0.0054951413,0.00077470124,0.0007841011,0.0020031251,0.001067696],"domain_scores_gemma":[0.8763109,0.12105164,0.000056820834,0.00061008806,0.00015102525,0.0018195393],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021916136,0.0002714344,0.0006526818,0.00041102056,0.00023755674,0.00012349586,0.0005264054,0.0004026912,0.010815248],"category_scores_gemma":[0.33684352,0.00020717568,0.000058177113,0.00061886176,0.0015242494,0.000054439915,0.00032196371,0.003967457,0.00002779794],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021012276,0.000124549,0.00021838961,0.00015305825,0.0000075878916,0.00036003676,0.00007652908,1.1542578e-8,0.000055121065,0.54652447,0.001159168,0.45111093],"study_design_scores_gemma":[0.00124708,0.00015572888,0.007943009,0.00028176117,0.000011285205,0.000013649746,0.000074624506,0.01675708,0.00003945466,0.97206366,0.0011751008,0.00023757784],"about_ca_topic_score_codex":0.00006485998,"about_ca_topic_score_gemma":0.00007351935,"teacher_disagreement_score":0.45087335,"about_ca_system_score_codex":0.00004533359,"about_ca_system_score_gemma":0.0003556439,"threshold_uncertainty_score":0.9983304},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interchangeability; Agreement; Metric (unit); Limits of agreement; Computer science; Units of measurement; Physics; Engineering","score_opus":0.8455312682296875,"score_gpt":0.6788734831139276,"score_spread":0.1666577851157599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099077995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011491402,0.00032868056,0.96496737,0.0049651666,0.00069213734,0.0018865867,0.00003972745,0.000012590646,0.015616356],"genre_scores_gemma":[0.6608213,0.000015546693,0.33805937,0.00018720844,0.00046641406,0.00031499847,0.000007411359,0.000017214292,0.00011051873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.90176743,0.04603641,0.0034198512,0.001767464,0.045421597,0.0015872299],"domain_scores_gemma":[0.96619326,0.024394171,0.00033659494,0.0018917132,0.005061493,0.0021227675],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3749643,0.00030738555,0.0009721339,0.0006872685,0.00027325907,0.000609609,0.0035681117,0.00017360438,0.0006258779],"category_scores_gemma":[0.2304376,0.00017501293,0.00009620861,0.0024496578,0.0009993035,0.00031551314,0.0009649156,0.001505947,0.00017208036],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016506291,0.001129789,0.0073038535,0.00009439813,0.00009324845,0.00003767438,0.003018375,0.002225057,0.0002898197,0.035049196,0.0075629684,0.94303054],"study_design_scores_gemma":[0.00698043,0.006074854,0.089565635,0.0018063405,0.00013658123,0.000015175086,0.081105605,0.23762509,0.0033789997,0.49072278,0.081134416,0.0014540886],"about_ca_topic_score_codex":0.001354066,"about_ca_topic_score_gemma":0.0002028967,"teacher_disagreement_score":0.9415765,"about_ca_system_score_codex":0.0010024825,"about_ca_system_score_gemma":0.0013651608,"threshold_uncertainty_score":0.7760447},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.39344469527150544,"score_gpt":0.579674810655022,"score_spread":0.18623011538351658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100697007","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031924318,0.00003326925,0.9945339,0.0002634128,0.00013959,0.0006872028,0.00011673707,0.0000060947373,0.001027356],"genre_scores_gemma":[0.22631381,0.000033734443,0.7734734,0.000010043263,0.000036446574,0.00010684032,0.0000029838914,0.0000131559555,0.0000095683745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98780173,0.0088264,0.0010886348,0.00033760752,0.0014658555,0.00047978424],"domain_scores_gemma":[0.7031545,0.2955875,0.00026117553,0.00041106244,0.00043969922,0.00014605564],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032903746,0.00017743201,0.00084811874,0.00009037222,0.00017265533,0.00001930212,0.0005253757,0.00017675404,0.0002047556],"category_scores_gemma":[0.23965181,0.00008294976,0.000060061382,0.00023949608,0.0029941527,0.000073457675,0.00032857314,0.00089750905,2.8853017e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003435344,0.00011976326,0.00019460407,0.0011478201,0.000022726857,3.4948425e-7,0.0006867333,0.000013955494,0.00006043642,0.8486877,0.000031725853,0.14869064],"study_design_scores_gemma":[0.00055075437,0.00028310664,0.00034526887,0.00046194045,0.000028670482,5.841314e-7,0.00016522325,0.42189258,0.00014624187,0.57607096,0.0000048280644,0.000049831655],"about_ca_topic_score_codex":0.000118697135,"about_ca_topic_score_gemma":0.000009171365,"teacher_disagreement_score":0.42187864,"about_ca_system_score_codex":0.000032209904,"about_ca_system_score_gemma":0.00024095713,"threshold_uncertainty_score":0.99971914},"labels":[],"label_agreement":null},{"id":"W2103521794","doi":"10.1177/0962280215591236","title":"Global tests for novelty","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Jenny ja Antti Wihurin Rahasto; Natural Sciences and Engineering Research Council of Canada; Turun Yliopistosäätiö; Magnus Ehrnroothin Säätiö","keywords":"Novelty; Novelty detection; Computer science; Outlier; Permutation (music); Set (abstract data type); Relation (database); Range (aeronautics); Data mining; Null hypothesis; Resampling; Machine learning; Artificial intelligence; Statistical hypothesis testing; Data set; Statistics; Mathematics","score_opus":0.35127345044304936,"score_gpt":0.6502540705804974,"score_spread":0.2989806201374481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103521794","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004496147,0.000049135015,0.98640335,0.004389458,0.00010859654,0.0003675337,0.000022622591,0.000099876466,0.008514485],"genre_scores_gemma":[0.014367106,0.000010061606,0.98475033,0.00025579,0.000082363134,0.0003970107,0.0000027542676,0.0000056753393,0.00012892587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966846,0.00086863374,0.00031005865,0.00043502008,0.0011794842,0.00052220834],"domain_scores_gemma":[0.9926899,0.0057567363,0.000023237119,0.00042998916,0.0003855427,0.0007146089],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012790143,0.000079772995,0.00017399686,0.000109703346,0.000093511204,0.00007557866,0.0010447949,0.00015130625,0.000092398106],"category_scores_gemma":[0.03190062,0.00006721531,0.000028180482,0.0012346744,0.00034134777,0.00007954263,0.0004504028,0.00041505363,0.00003081181],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006534765,0.000051052866,0.00007929924,0.000005713438,0.0000011273336,0.000007229956,0.000013427612,4.7240317e-7,0.00000986533,0.5099526,0.0073270653,0.48254558],"study_design_scores_gemma":[0.00034083298,0.00024543743,0.0019471254,0.0000144159,8.4328985e-7,0.0000135493865,0.000025867017,0.1061651,0.00016942465,0.81485003,0.07614131,0.00008604013],"about_ca_topic_score_codex":0.0001206346,"about_ca_topic_score_gemma":0.000038756334,"teacher_disagreement_score":0.48245955,"about_ca_system_score_codex":0.00020576364,"about_ca_system_score_gemma":0.0006435743,"threshold_uncertainty_score":0.9762541},"labels":[],"label_agreement":null},{"id":"W2113489980","doi":"10.1177/0962280209340213","title":"Estimation of dose–response functions for longitudinal data using the generalised propensity score","year":2010,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Propensity score matching; Longitudinal data; Statistics; Estimation; Covariate; Econometrics; Mathematics; Computer science; Medicine; Data mining; Economics","score_opus":0.8340373806115695,"score_gpt":0.7034432853645637,"score_spread":0.13059409524700583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113489980","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06551564,0.000009968689,0.9322391,0.0008080852,0.00012423708,0.000970434,0.00019188561,0.00003651566,0.000104148894],"genre_scores_gemma":[0.1128569,0.000004629284,0.8868123,0.000022889624,0.00007743342,0.00012153084,0.000032603526,0.000021794405,0.00004986361],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935046,0.003500683,0.0006330128,0.0004652878,0.0013848048,0.00051162386],"domain_scores_gemma":[0.93043727,0.06731599,0.000112999405,0.001329805,0.0005518391,0.00025211033],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042029724,0.00012846742,0.00035988522,0.00018345764,0.00021347533,0.0000367068,0.0009527778,0.00021177663,0.00058798754],"category_scores_gemma":[0.3488487,0.00008409653,0.00003040474,0.000548292,0.0015841668,0.00014161674,0.00067717733,0.0015618093,0.0000019548681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012630047,0.00032303395,0.00043257282,0.00027103923,0.000026537562,0.000030879753,0.0001347039,0.00002119791,0.03093677,0.3506688,0.001912824,0.6139786],"study_design_scores_gemma":[0.00036227194,0.00018130471,0.0024572401,0.0001036077,0.000022145934,0.000016896356,0.000055279295,0.32121548,0.0042219623,0.67086256,0.00039847073,0.00010276423],"about_ca_topic_score_codex":0.000095576266,"about_ca_topic_score_gemma":0.00018356356,"teacher_disagreement_score":0.61387587,"about_ca_system_score_codex":0.00007175847,"about_ca_system_score_gemma":0.00071754615,"threshold_uncertainty_score":0.986432},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6888032750728122,"score_gpt":0.7167444363492629,"score_spread":0.027941161276450632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115308689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012421281,0.009118079,0.9220251,0.053261295,0.00036483767,0.0019375064,0.0006377089,0.000021335085,0.00021285967],"genre_scores_gemma":[0.05070716,0.0015881163,0.9450152,0.0016342803,0.00028911332,0.00060179806,0.000083217135,0.00003495263,0.00004616408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95629984,0.035760473,0.004853297,0.0013841768,0.0006842504,0.0010179313],"domain_scores_gemma":[0.9403105,0.05745054,0.00041822664,0.0005975872,0.00032455727,0.0008986168],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20616123,0.00020671496,0.0024762293,0.0022074669,0.00014568074,0.00004449554,0.00035646497,0.00022849029,0.0023762337],"category_scores_gemma":[0.2838238,0.00022506584,0.00005461395,0.0025716547,0.0007813663,0.00015833043,0.00020285427,0.00092404766,0.00003880172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016956609,0.00044172126,0.015811116,0.0024060346,0.0003469394,0.000015532678,0.015756033,0.0014027792,0.0000042903353,0.57640046,0.0033230025,0.38392252],"study_design_scores_gemma":[0.002639194,0.002288371,0.2139026,0.0005349517,0.000061759594,0.000005692493,0.034467015,0.51265043,0.000014900678,0.17725603,0.055368386,0.00081066095],"about_ca_topic_score_codex":0.0057170363,"about_ca_topic_score_gemma":0.0020857905,"teacher_disagreement_score":0.51124763,"about_ca_system_score_codex":0.0016731032,"about_ca_system_score_gemma":0.00023890007,"threshold_uncertainty_score":0.99853575},"labels":[],"label_agreement":null},{"id":"W2115420947","doi":"10.1191/0962280205sm411oa","title":"The role of proxy information in missing data analysis","year":2005,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Statistics Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Proxy (statistics); Missing data; Computer science; Data mining; Econometrics; Mathematics; Machine learning","score_opus":0.7108746652615446,"score_gpt":0.7422157901858673,"score_spread":0.031341124924322616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115420947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003526494,0.00022189955,0.98796016,0.003366327,0.00010370748,0.00065540476,0.00017414057,0.000021677808,0.007144039],"genre_scores_gemma":[0.011635098,0.00018478706,0.98782235,0.000079651094,0.00013976004,0.0000755943,0.000016365208,0.000017656128,0.000028718914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9661383,0.02368517,0.0037186008,0.00070581975,0.0044959113,0.0012562191],"domain_scores_gemma":[0.4581985,0.5387499,0.0002837178,0.0018008103,0.0004329561,0.0005341628],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1485063,0.00018524105,0.0010019292,0.00068994536,0.00014418674,0.00009644919,0.0020789453,0.0003707121,0.0015777873],"category_scores_gemma":[0.8501134,0.00012444211,0.0000830714,0.0032395944,0.0016580514,0.00024697674,0.0011558358,0.0022349409,0.000027828599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013582727,0.00016668659,0.000781725,0.00006405112,0.000062376355,0.000008157393,0.00013583682,0.0000036842268,0.000019162148,0.3002184,0.00030683205,0.6980973],"study_design_scores_gemma":[0.0005074963,0.000063121595,0.0022276319,0.00010088891,0.00005571467,0.0000012608901,0.00030891394,0.2208648,0.00019807153,0.7664724,0.0090973405,0.00010233745],"about_ca_topic_score_codex":0.00019735564,"about_ca_topic_score_gemma":0.00025860014,"teacher_disagreement_score":0.7016071,"about_ca_system_score_codex":0.00017616329,"about_ca_system_score_gemma":0.0005825273,"threshold_uncertainty_score":0.99933493},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.35473691480919106,"score_gpt":0.6128973161725231,"score_spread":0.258160401363332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123033778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052668586,0.000040515486,0.93829817,0.005628624,0.00064934476,0.0006895743,0.00009816025,0.000005139726,0.0019218824],"genre_scores_gemma":[0.6721897,0.0000249475,0.3271143,0.00014894128,0.000095799274,0.0001044804,0.0000021368103,0.000006607864,0.00031307407],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9890402,0.003324019,0.0010477146,0.0004582904,0.0056920745,0.00043772138],"domain_scores_gemma":[0.9306525,0.06664287,0.00013728043,0.00066605146,0.0015385784,0.00036273804],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11007071,0.00008988532,0.00031068604,0.00018262716,0.00023344407,0.00009938571,0.0008777013,0.00015703536,0.0028721017],"category_scores_gemma":[0.34850413,0.00004952302,0.000063534746,0.0007182384,0.0017101875,0.00010201585,0.00037061874,0.00111577,0.000010059624],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017618667,0.00007759803,0.0054638404,0.00004866521,0.000008367719,0.0000012322457,0.00040470657,0.0000018255514,0.0020888152,0.12643728,0.002488403,0.8628031],"study_design_scores_gemma":[0.0006617922,0.00041057877,0.066613436,0.00009610029,0.00000979521,0.0000023256164,0.0009008228,0.010950559,0.003013095,0.89752686,0.019725276,0.00008934994],"about_ca_topic_score_codex":0.00011278957,"about_ca_topic_score_gemma":0.0010551981,"teacher_disagreement_score":0.86271375,"about_ca_system_score_codex":0.00004761361,"about_ca_system_score_gemma":0.00048759108,"threshold_uncertainty_score":0.9980394},"labels":[],"label_agreement":null},{"id":"W2123602065","doi":"10.1177/0962280214527386","title":"Bayesian hierarchical modelling of noisy spatial rates on a modestly large and discontinuous irregular lattice","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Health Technology Assessment Programme; Natural Sciences and Engineering Research Council of Canada; National Institute for Health and Care Research","keywords":"Markov chain Monte Carlo; Overdispersion; Bayesian probability; Bayesian inference; Computer science; Statistics; Autoregressive model; Random effects model; Negative binomial distribution; Spatial analysis; Spatial dependence; Bayesian hierarchical modeling; Hierarchical database model; Econometrics; Mathematics; Poisson distribution; Data mining","score_opus":0.1687164579898777,"score_gpt":0.5362347401415055,"score_spread":0.36751828215162785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123602065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027080653,0.000048630638,0.9914983,0.0009553161,0.00010532798,0.000431647,0.000107441345,0.000031967396,0.004113304],"genre_scores_gemma":[0.18836525,0.00004369895,0.81120884,0.0000969852,0.0001340439,0.00005942814,0.000006227714,0.000043779648,0.000041751908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98371273,0.010632048,0.0011480786,0.00085074734,0.0024392183,0.001217153],"domain_scores_gemma":[0.9003151,0.09788633,0.000106140156,0.00055757957,0.00026219533,0.0008726394],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027895646,0.00031319045,0.0010626795,0.00038842674,0.0001768393,0.00007095668,0.00054769113,0.0004014962,0.001033604],"category_scores_gemma":[0.13769114,0.00024337752,0.00007095461,0.00055927737,0.0017073787,0.000059549002,0.00039262636,0.0022579366,0.000009565239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019877314,0.0003205313,0.00015056234,0.00028559667,0.000014787684,0.000060181286,0.0001696819,0.000003775684,0.000066876535,0.6455783,0.00007059161,0.35308033],"study_design_scores_gemma":[0.00061887637,0.00040383587,0.0005522883,0.00030525404,0.000013998206,0.000006271112,0.000054919477,0.4288019,0.00019335694,0.5687446,0.00015756258,0.00014714742],"about_ca_topic_score_codex":0.00022875078,"about_ca_topic_score_gemma":0.000060265025,"teacher_disagreement_score":0.4287981,"about_ca_system_score_codex":0.000061867286,"about_ca_system_score_gemma":0.00023030287,"threshold_uncertainty_score":0.9998796},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8484463315588613,"score_gpt":0.7874845120641984,"score_spread":0.06096181949466284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124200703","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011951552,0.0018917224,0.9812484,0.0018155325,0.00020584637,0.0022934275,0.0003744306,0.000025970661,0.00019312419],"genre_scores_gemma":[0.093135096,0.00026765687,0.90536034,0.00005452193,0.000104888895,0.0002843631,0.0006924045,0.00003733836,0.0000633898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97479826,0.020372119,0.0012715742,0.00087962364,0.0016454046,0.0010330358],"domain_scores_gemma":[0.9087705,0.08910696,0.0002572823,0.0007655952,0.00047430434,0.0006253733],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02994441,0.00018742132,0.00084333675,0.00033734486,0.00035244267,0.000033979424,0.0007122235,0.00020830303,0.0019131199],"category_scores_gemma":[0.052608203,0.00014678534,0.00002555148,0.0006037927,0.0010908688,0.00013183999,0.00056449807,0.0015529583,0.000012062769],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072962017,0.0004899923,0.022167757,0.0004170019,0.00009760774,0.000002972297,0.003535705,0.000037766044,0.0010480406,0.0051281727,0.00062646705,0.9657189],"study_design_scores_gemma":[0.0016202317,0.0010177689,0.03238528,0.00024231363,0.000008909223,0.000001254573,0.008283837,0.9455897,0.000091842725,0.0070274947,0.0036081704,0.00012316859],"about_ca_topic_score_codex":0.018874144,"about_ca_topic_score_gemma":0.0010571879,"teacher_disagreement_score":0.9655957,"about_ca_system_score_codex":0.00045843353,"about_ca_system_score_gemma":0.00053024513,"threshold_uncertainty_score":0.99899924},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6337766155694683,"score_gpt":0.6851863314577871,"score_spread":0.051409715888318774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124612672","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012133463,0.00040320115,0.9828664,0.001471446,0.00037153868,0.0014382722,0.0001924127,0.00003296987,0.0010902729],"genre_scores_gemma":[0.089288056,0.00023612488,0.90944713,0.00008432268,0.0004552401,0.00021955746,0.00000869457,0.000041562762,0.00021932108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97533524,0.01776009,0.0021838506,0.0008307165,0.0024075569,0.0014825271],"domain_scores_gemma":[0.61731297,0.37913826,0.0001935879,0.00071799115,0.0004782811,0.0021588972],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06395736,0.00032571144,0.0014494564,0.0003053347,0.000098220255,0.00004615737,0.00054344407,0.00040307353,0.003274916],"category_scores_gemma":[0.61901015,0.00024408927,0.00008284411,0.001013301,0.00091533875,0.00008585429,0.00038835366,0.0009167476,0.00002608506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019427809,0.001416553,0.0031271167,0.00041815185,0.00007947448,0.000031481868,0.0005654806,0.000008107209,0.0010059123,0.52222127,0.0023375442,0.46684614],"study_design_scores_gemma":[0.007352473,0.003174561,0.012598608,0.00054831064,0.0000990958,0.000014475529,0.00037915824,0.026818996,0.0036902304,0.9432756,0.001602287,0.0004462277],"about_ca_topic_score_codex":0.00051975413,"about_ca_topic_score_gemma":0.00004041615,"teacher_disagreement_score":0.5550528,"about_ca_system_score_codex":0.00026645281,"about_ca_system_score_gemma":0.0007917726,"threshold_uncertainty_score":0.9976362},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.6529093814670139,"score_gpt":0.6393137010129344,"score_spread":0.01359568045407955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130845266","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033598647,0.00011316535,0.9917343,0.0006589983,0.00013238392,0.00093873974,0.00012169509,0.000027580974,0.002913261],"genre_scores_gemma":[0.075252645,0.000067725974,0.92433786,0.00007285537,0.000024350806,0.0000927905,0.0000035751943,0.000033904882,0.00011426938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895895,0.005487652,0.0008293383,0.00088179193,0.0024840427,0.00072769134],"domain_scores_gemma":[0.9634731,0.03325433,0.00013850842,0.0017035921,0.00091185037,0.00051866384],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018044092,0.00024380392,0.0007742554,0.00023387636,0.00018282364,0.00001471166,0.0014113152,0.00024399952,0.00039163115],"category_scores_gemma":[0.23182559,0.00012315117,0.00003222159,0.0014822171,0.0017742758,0.00007994386,0.0019348416,0.0016805376,0.0000064295577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010922828,0.0004988915,0.00033711243,0.00026812757,0.000052123352,0.0001540343,0.0018039148,0.0000030861872,0.0005184634,0.78065616,0.0019821788,0.21263362],"study_design_scores_gemma":[0.00053172966,0.00054021366,0.006427182,0.0013797388,0.00003351434,0.000010329956,0.00060000905,0.13625926,0.00092726195,0.8531279,0.000008963104,0.00015390763],"about_ca_topic_score_codex":0.0001341799,"about_ca_topic_score_gemma":0.000051109804,"teacher_disagreement_score":0.21378149,"about_ca_system_score_codex":0.00012390342,"about_ca_system_score_gemma":0.0004903477,"threshold_uncertainty_score":0.7746451},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8048558980284114,"score_gpt":0.6387257078840167,"score_spread":0.16613019014439467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130892140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028440778,0.000011871445,0.9903134,0.0023896953,0.00012972543,0.0021951252,0.000015942718,0.000212565,0.0018875598],"genre_scores_gemma":[0.015413428,0.000014519701,0.98250854,0.00070073665,0.00018436913,0.00077669154,0.000006102607,0.00006940301,0.00032619567],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.984615,0.009178501,0.0010145501,0.0008633208,0.002881132,0.0014474749],"domain_scores_gemma":[0.9449784,0.052337542,0.00008479368,0.0007590652,0.00048554692,0.0013546408],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04425421,0.0003058909,0.0008699326,0.0006580444,0.00022555598,0.00009867826,0.00090601924,0.0003073219,0.0016157173],"category_scores_gemma":[0.21380223,0.0002234423,0.00004516722,0.0015071362,0.000435686,0.00012546252,0.0011452816,0.001838264,0.00020972759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009454069,0.00022106284,0.000023087026,0.00024752034,0.000013894086,0.00024014419,0.00066271564,0.000014525139,0.0018416028,0.46687075,0.005612906,0.52330637],"study_design_scores_gemma":[0.0006863254,0.0014071774,0.00055583497,0.00081274286,0.0000111908,0.000041423216,0.00010870745,0.0073986133,0.0051571983,0.98020107,0.0032833726,0.00033633658],"about_ca_topic_score_codex":0.00046794792,"about_ca_topic_score_gemma":0.00042691026,"teacher_disagreement_score":0.52297,"about_ca_system_score_codex":0.00048665897,"about_ca_system_score_gemma":0.00049195986,"threshold_uncertainty_score":0.99929696},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.6678900408750544,"score_gpt":0.7118649138188959,"score_spread":0.0439748729438415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135596283","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000061411606,0.0007954914,0.99094075,0.0034926974,0.00022798133,0.0022865133,0.0006149219,0.00003039257,0.0016051059],"genre_scores_gemma":[0.0007468303,0.00033750475,0.9968156,0.0003079526,0.00013831425,0.0013525474,0.000043868647,0.000053573913,0.00020379906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.907059,0.08260415,0.0043302136,0.0011587017,0.0033462062,0.0015017029],"domain_scores_gemma":[0.34693414,0.6503012,0.00037294425,0.0008782746,0.0009457167,0.00056774257],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24947068,0.00040398835,0.004901627,0.0009701997,0.00027899756,0.00011587172,0.0011138226,0.0004902914,0.026452323],"category_scores_gemma":[0.74345386,0.00022403128,0.0010601846,0.0035863451,0.0020054735,0.00007551836,0.00035021122,0.0015418326,0.0000079398815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010211144,0.00020820842,0.00001895735,0.00011572204,0.011022689,0.000015349618,0.00010707098,0.000005562256,0.000039206705,0.5596755,0.001300982,0.42646962],"study_design_scores_gemma":[0.0020933533,0.00020720832,0.00033480703,0.00001841016,0.036232688,0.000005537394,0.00013597337,0.17207973,0.00012772768,0.7849769,0.0035851349,0.00020253891],"about_ca_topic_score_codex":0.00020013888,"about_ca_topic_score_gemma":0.000094667295,"teacher_disagreement_score":0.56769705,"about_ca_system_score_codex":0.00011362512,"about_ca_system_score_gemma":0.0004737924,"threshold_uncertainty_score":0.97443765},"labels":[],"label_agreement":null},{"id":"W2138930389","doi":"10.1177/0962280212448975","title":"Comparison of four shape features for detecting hippocampal shape changes in early Alzheimer's","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Alzheimer Society","keywords":"Spherical harmonics; Pattern recognition (psychology); Mathematics; Shape analysis (program analysis); Orthonormal basis; Artificial intelligence; Binary classification; Diffeomorphism; Mathematical analysis; Support vector machine; Computer science; Physics","score_opus":0.3136085106434523,"score_gpt":0.5916406204490242,"score_spread":0.2780321098055719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138930389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87983,0.051061258,0.050729137,0.0056933523,0.00062216754,0.0070837294,0.00039268826,0.000115476185,0.0044721607],"genre_scores_gemma":[0.7896943,0.00012282915,0.20937234,0.00006338924,0.00025703176,0.0004072539,0.000031599797,0.000041372874,0.00000988355],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99138075,0.0027547241,0.0007170107,0.00052144186,0.0027531392,0.0018729569],"domain_scores_gemma":[0.97698444,0.020452844,0.0000809241,0.00036781168,0.0003668479,0.0017471483],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013011986,0.00024907093,0.0009588871,0.0007223746,0.00012377958,0.000025672089,0.00033686304,0.00037552297,0.0018452123],"category_scores_gemma":[0.04114864,0.00019748569,0.000101479935,0.0009682424,0.0008388306,0.00008693105,0.00026768964,0.0018145045,0.000026378482],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019779752,0.0014983884,0.20186949,0.00035841303,0.00085498806,0.00019811255,0.00066651194,2.030369e-7,0.0002797179,0.0024308953,0.00039936978,0.7894659],"study_design_scores_gemma":[0.007304835,0.0041373232,0.9393203,0.0010681204,0.00037116537,0.000051629257,0.001772608,0.024234587,0.008365917,0.012311087,0.0006469242,0.00041547001],"about_ca_topic_score_codex":0.00032962256,"about_ca_topic_score_gemma":0.00018095964,"teacher_disagreement_score":0.78905046,"about_ca_system_score_codex":0.00017848934,"about_ca_system_score_gemma":0.00059645146,"threshold_uncertainty_score":0.99906725},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.5155792263631098,"score_gpt":0.6760756832121154,"score_spread":0.1604964568490056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140873752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21378352,0.000006116392,0.7838694,0.000046357265,0.00011521123,0.0020377028,0.000004956453,0.000026219283,0.00011053141],"genre_scores_gemma":[0.37643883,0.0000062354734,0.6231458,0.0000051879992,0.000018501836,0.00034114352,0.0000015350347,0.000019658284,0.0000230797],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9869672,0.009475101,0.0009907219,0.00040203112,0.0015880933,0.00057684357],"domain_scores_gemma":[0.7662256,0.23251875,0.00018706256,0.0005034197,0.00040528606,0.00015988252],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.02892184,0.00021214815,0.00090993446,0.00016252749,0.00017921005,0.00001862807,0.00048345924,0.00014145301,0.000022243334],"category_scores_gemma":[0.30922505,0.00011820365,0.000065447486,0.0003132129,0.0006179622,0.000048655016,0.0002742928,0.00073857955,7.1147224e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036104704,0.0012096565,0.005778417,0.0009499553,0.000071017734,0.0000032243288,0.00031530974,0.000049225582,0.00044644234,0.06942978,0.000007484675,0.92137843],"study_design_scores_gemma":[0.0012588846,0.004514739,0.044890888,0.000533442,0.000043629258,2.9733877e-7,0.00007096007,0.5025642,0.0069990708,0.4389927,0.0000073278907,0.0001238892],"about_ca_topic_score_codex":0.000030607884,"about_ca_topic_score_gemma":0.000019281977,"teacher_disagreement_score":0.9212546,"about_ca_system_score_codex":0.00014081076,"about_ca_system_score_gemma":0.00009677532,"threshold_uncertainty_score":0.9999293},"labels":[],"label_agreement":null},{"id":"W2143838957","doi":"10.1177/0962280212447152","title":"On identification in Bayesian disease mapping and ecological–spatial regression models","year":2012,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Canadian Institutes of Health Research; University of British Columbia; Ministry of Health, British Columbia; Indian Council of Agricultural Research","keywords":"Bayesian probability; Prior probability; Bayesian linear regression; Bayesian inference; Poisson distribution; Statistics; Econometrics; Computer science; Random effects model; Univariate; Gaussian; Bayesian multivariate linear regression; Identification (biology); Mathematics; Regression analysis; Multivariate statistics; Ecology; Biology","score_opus":0.28231828112242724,"score_gpt":0.5858811142094335,"score_spread":0.3035628330870062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143838957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042119953,0.0001333247,0.99102414,0.0011589195,0.00020572804,0.00055153464,0.000039703526,0.00003134253,0.0026433347],"genre_scores_gemma":[0.33466852,0.00009209227,0.66481286,0.00010175379,0.00009441368,0.00016859597,0.0000062451095,0.000020867516,0.00003460928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9862612,0.009115712,0.00096135715,0.00064297946,0.0018590494,0.001159722],"domain_scores_gemma":[0.9302728,0.067717046,0.000087984394,0.00043747394,0.0001257553,0.001358927],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.027456744,0.00023667529,0.0005592288,0.000521332,0.0001558732,0.00006907211,0.0003725122,0.00033927453,0.0019532524],"category_scores_gemma":[0.19659393,0.0001750088,0.00003713194,0.00071683235,0.0008164112,0.00014855864,0.0003248929,0.0018256368,0.000021235473],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010700874,0.00041752463,0.0011338632,0.00014199186,0.0000030893764,0.00008670465,0.00019144457,3.441229e-7,0.00005264541,0.5869139,0.00020127276,0.41075024],"study_design_scores_gemma":[0.00044261263,0.000088602006,0.07879955,0.00041089777,0.000005660912,0.000003464572,0.00012398761,0.080539346,0.000033173143,0.8393155,0.00006864756,0.00016859877],"about_ca_topic_score_codex":0.00009251661,"about_ca_topic_score_gemma":0.000027353848,"teacher_disagreement_score":0.41058165,"about_ca_system_score_codex":0.00020411464,"about_ca_system_score_gemma":0.00018636075,"threshold_uncertainty_score":0.9989591},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6796715167424592,"score_gpt":0.626117586072389,"score_spread":0.05355393067007019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146502722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46957535,0.00007009695,0.52806205,0.00077603327,0.000067744324,0.0010582848,0.0003648641,0.0000018742388,0.000023718283],"genre_scores_gemma":[0.9690751,0.000054818214,0.03068065,0.000028302324,0.000033252047,0.00010306569,0.000004800685,0.0000101977785,0.0000098459395],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915701,0.004603124,0.0023042876,0.00033937662,0.0009139205,0.0002692037],"domain_scores_gemma":[0.9278744,0.0699003,0.0011277966,0.00036701432,0.00053938426,0.0001911322],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10452107,0.00011150982,0.00070912746,0.00017105925,0.00013518061,0.000010619617,0.0002293212,0.00012768227,0.000025148805],"category_scores_gemma":[0.32262626,0.00006764787,0.000047960024,0.00022412771,0.0006970976,0.00009948146,0.00018331589,0.00049331255,3.087811e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020572646,0.003339462,0.81720155,0.0015803538,0.00029689635,5.616211e-7,0.015109995,0.05228376,0.00004270096,0.044251923,0.0007615737,0.063073955],"study_design_scores_gemma":[0.0009261368,0.00033844996,0.24616049,0.00011623041,0.0000089003715,2.5174208e-7,0.0020880182,0.7352668,0.000036796937,0.014996446,0.000016579292,0.000044921384],"about_ca_topic_score_codex":0.001166653,"about_ca_topic_score_gemma":0.00017276422,"teacher_disagreement_score":0.68298304,"about_ca_system_score_codex":0.00019433122,"about_ca_system_score_gemma":0.00054522586,"threshold_uncertainty_score":0.922084},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.18016007865582498,"score_gpt":0.53160055665824,"score_spread":0.35144047800241507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147254563","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03250522,0.0001508446,0.96068263,0.0024035536,0.0001333415,0.0032773442,0.00034120673,0.00005716657,0.00044868805],"genre_scores_gemma":[0.0641417,0.0011988573,0.9319421,0.0010700938,0.00055720424,0.00077032694,0.0002107409,0.00007204409,0.000036914527],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99382377,0.0012136613,0.0011170128,0.0009507271,0.0016879413,0.0012069014],"domain_scores_gemma":[0.9813813,0.01538202,0.00009005651,0.00049117487,0.0010596493,0.0015958227],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0091907205,0.00029101656,0.00089253945,0.00044313,0.0002754299,0.000052333813,0.00036070176,0.00040761163,0.0005760578],"category_scores_gemma":[0.032861054,0.00022755748,0.000069053065,0.0007244959,0.000413049,0.00010957106,0.00024018162,0.0013368079,0.000026548536],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006213397,0.0010074876,0.0050800745,0.00088272814,0.00015170184,0.000051063067,0.0052783205,0.000032539127,0.005807086,0.121151924,0.0040282197,0.8559075],"study_design_scores_gemma":[0.0022686187,0.00038610568,0.05346469,0.00060137897,0.000024593424,0.000010529298,0.0011102995,0.45255718,0.0012536779,0.48678643,0.0012408709,0.00029563962],"about_ca_topic_score_codex":0.011035084,"about_ca_topic_score_gemma":0.00032204826,"teacher_disagreement_score":0.85561186,"about_ca_system_score_codex":0.00045002298,"about_ca_system_score_gemma":0.0018963405,"threshold_uncertainty_score":0.9955505},"labels":[],"label_agreement":null},{"id":"W2155839122","doi":"10.1177/0962280214568110","title":"Bayesian regression models for the estimation of net cost of disease using aggregate data","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":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Toronto General Hospital; Public Health Ontario; University of Toronto","funders":"","keywords":"Heteroscedasticity; Aggregate (composite); Econometrics; Computer science; Bayesian probability; Skewness; Linear regression; Bayesian linear regression; Linear model; Estimation; Regression; Statistics; Bayesian inference; Data mining; Mathematics; Machine learning; Artificial intelligence; Economics","score_opus":0.8612777946749054,"score_gpt":0.7029062873227251,"score_spread":0.1583715073521803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155839122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006460895,0.001767575,0.9830902,0.011593344,0.00022548511,0.0010755913,0.0013160259,0.0000055808323,0.0002800851],"genre_scores_gemma":[0.09559126,0.00017974473,0.9034148,0.00037905175,0.000128127,0.000118616794,0.00012585233,0.000024119614,0.000038457158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918088,0.0035674593,0.0030239497,0.0004993387,0.00064138556,0.00045910006],"domain_scores_gemma":[0.9479891,0.04882473,0.0009077761,0.0012042171,0.0003071821,0.00076700357],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15379947,0.00010635326,0.0007386873,0.00030603647,0.00010087048,0.000026456526,0.00087559194,0.00014197273,0.0002693243],"category_scores_gemma":[0.29581395,0.0000895683,0.000038063547,0.00039375408,0.00066143967,0.00025521166,0.00034877038,0.00041051573,0.000011898457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004906472,0.00027713424,0.0013455438,0.0015458545,0.00005169659,0.0000052480555,0.0009802827,0.01636476,0.000002785485,0.8117885,0.01520964,0.15193793],"study_design_scores_gemma":[0.0004612796,0.000044452856,0.00030770793,0.00022352004,0.0000043923947,4.8536833e-7,0.00026212228,0.64953893,0.00000433987,0.34802538,0.0010741523,0.000053253665],"about_ca_topic_score_codex":0.0012341902,"about_ca_topic_score_gemma":0.000048240992,"teacher_disagreement_score":0.6331742,"about_ca_system_score_codex":0.00026321996,"about_ca_system_score_gemma":0.0011501302,"threshold_uncertainty_score":0.8713415},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.2276033325385271,"score_gpt":0.5725945814759557,"score_spread":0.34499124893742855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157235443","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00072125875,0.00003499243,0.9940387,0.0013898927,0.00006699164,0.00040532794,0.0003252042,0.000022496792,0.0029951348],"genre_scores_gemma":[0.17179947,0.00002314458,0.827825,0.00007907413,0.000071829425,0.00010057118,0.00005609067,0.000021772916,0.000023064855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9880795,0.0076314816,0.0010455702,0.0004722243,0.0021640968,0.00060712587],"domain_scores_gemma":[0.8324588,0.16606681,0.00017264391,0.00040973528,0.0006027401,0.00028929615],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02596157,0.00017968085,0.00050606416,0.00015394994,0.00021845024,0.00005549985,0.00065832323,0.00021812166,0.0015269292],"category_scores_gemma":[0.23581852,0.00012424443,0.000050639293,0.0006987746,0.0015557003,0.0000741524,0.0002030862,0.0012913207,0.000014176641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006642779,0.00015499977,0.00020557233,0.00008632043,0.000013306226,0.0000034688446,0.00020958761,0.000006489765,0.0011124291,0.77630347,0.0020015042,0.21983644],"study_design_scores_gemma":[0.00036296842,0.000080121055,0.0011675959,0.00006291507,0.000007657975,0.0000020653385,0.00014355937,0.35835126,0.0008803408,0.638704,0.00015032156,0.00008720977],"about_ca_topic_score_codex":0.000083563486,"about_ca_topic_score_gemma":0.000019580562,"teacher_disagreement_score":0.35834476,"about_ca_system_score_codex":0.00008742861,"about_ca_system_score_gemma":0.00028436646,"threshold_uncertainty_score":0.99938583},"labels":[],"label_agreement":null},{"id":"W2164186633","doi":"10.1177/0962280211414620","title":"A likelihood-based two-part marginal model for longitudinal semicontinuous data","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Medical Research Council","keywords":"Marginal model; Marginal structural model; Marginal distribution; Marginal likelihood; Covariate; Random effects model; Mixed model; Robustness (evolution); Statistics; Computer science; Statistical model; Population; Econometrics; Mathematics; Maximum likelihood; Regression analysis; Random variable; Medicine; Observational study","score_opus":0.6006715937666185,"score_gpt":0.6232256022617889,"score_spread":0.02255400849517042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164186633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014132108,0.00006575188,0.9909917,0.0005314763,0.0002402678,0.00092200725,0.0010113501,0.0000713946,0.0060247383],"genre_scores_gemma":[0.0042550024,0.000023296985,0.99460065,0.00019797136,0.00024183745,0.00040297874,0.000072128896,0.00007423523,0.0001318666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885012,0.004575496,0.0012667998,0.0014063568,0.0023639346,0.0018862403],"domain_scores_gemma":[0.92892534,0.06758534,0.000120034914,0.0015984752,0.0005739052,0.0011969242],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041858207,0.00035677006,0.00094382965,0.00037483405,0.00021663806,0.00008059617,0.0020944816,0.00037035687,0.0053463215],"category_scores_gemma":[0.21800078,0.00029522876,0.00008433013,0.000709978,0.0014843452,0.00012491102,0.0008449003,0.001992439,0.000036130066],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044163447,0.000520235,0.00034707988,0.00031549705,0.000024562107,0.00019892438,0.00011306067,4.154192e-7,0.00004446068,0.5832958,0.0068806917,0.40781763],"study_design_scores_gemma":[0.00095261354,0.00021059155,0.00022960843,0.00019656445,0.00002865387,0.000009316109,0.000041241277,0.43688813,0.000108195985,0.560648,0.00048750505,0.00019955798],"about_ca_topic_score_codex":0.00021171929,"about_ca_topic_score_gemma":0.00022000869,"teacher_disagreement_score":0.4368877,"about_ca_system_score_codex":0.00014250688,"about_ca_system_score_gemma":0.0014584208,"threshold_uncertainty_score":0.99995},"labels":[],"label_agreement":null},{"id":"W2164288176","doi":"10.1177/0962280215601458","title":"An improved procedure for estimation of malignant breast cancer prevalence using partially rank ordered set samples with multiple concomitants","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Fields Institute for Research in Mathematical Sciences; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Ranking (information retrieval); Rank (graph theory); Estimator; Sampling (signal processing); Statistics; Mathematics; Logistic regression; Set (abstract data type); Population; Breast cancer; Computer science; Data mining; Artificial intelligence; Cancer; Medicine; Combinatorics","score_opus":0.38167056655703446,"score_gpt":0.6098130584075224,"score_spread":0.22814249185048796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164288176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00947998,0.000026268379,0.98408437,0.00075181754,0.00003594307,0.0013923307,0.0041610277,0.000035669877,0.000032595155],"genre_scores_gemma":[0.3565217,0.000008990124,0.64281875,0.000025955791,0.00002907595,0.00048193967,0.00008487372,0.000020216683,0.000008504287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954418,0.0014368183,0.00078068423,0.0004691648,0.0013109737,0.0005605775],"domain_scores_gemma":[0.9823068,0.015246239,0.00015311649,0.00033458948,0.0012710803,0.0006881739],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007420761,0.00017374314,0.00045703477,0.00012330309,0.00012802031,0.00004262265,0.00035628682,0.00017969412,0.0005627571],"category_scores_gemma":[0.07352161,0.00013255191,0.000027215869,0.0006033826,0.00085852895,0.00011358662,0.000065316264,0.00041257436,0.0000020340767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022781137,0.0013636526,0.0034632885,0.0029120885,0.00007512349,0.000017258506,0.00084597437,0.0007563535,0.003748661,0.7125862,0.0013561117,0.27059713],"study_design_scores_gemma":[0.0017811573,0.00023882782,0.0073024286,0.0003427707,0.0000371963,0.000014120786,0.00032763826,0.8021558,0.0007575265,0.18686745,0.000029387056,0.00014569679],"about_ca_topic_score_codex":0.00025164243,"about_ca_topic_score_gemma":0.00020520229,"teacher_disagreement_score":0.80139947,"about_ca_system_score_codex":0.00019240062,"about_ca_system_score_gemma":0.0015802385,"threshold_uncertainty_score":0.93428254},"labels":[],"label_agreement":null},{"id":"W2170857766","doi":"10.1177/0962280210395739","title":"A generalized <i>p</i> -value approach for assessing noninferiority in a three-arm trial","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Confidence interval; Type I and type II errors; Statistics; Monte Carlo method; Sample size determination; Fraction (chemistry); Placebo; Mathematics; Value (mathematics); Medicine","score_opus":0.85810859778597,"score_gpt":0.7266962355247384,"score_spread":0.13141236226123165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170857766","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030692127,0.000065694556,0.9756126,0.00029113112,0.00079547166,0.0039990875,0.00010691018,0.00008285063,0.01597704],"genre_scores_gemma":[0.0041046403,0.000046705733,0.99257654,0.0002103201,0.0006380266,0.0022426655,0.000008907381,0.00011203723,0.00006015121],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.956814,0.031489577,0.003663327,0.0017587319,0.0038363305,0.002438041],"domain_scores_gemma":[0.61616546,0.38074696,0.00026792657,0.0010782718,0.00050041167,0.0012409522],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15566811,0.00047269097,0.0022960962,0.0006436325,0.00020482414,0.00013198033,0.0014274833,0.0011194664,0.0032242676],"category_scores_gemma":[0.7848223,0.00039136902,0.00025670032,0.0017380989,0.0021151954,0.00014243557,0.000700425,0.0039635366,0.000014155977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012349926,0.0025407374,0.0002790508,0.00044349424,0.000039239814,0.0001770148,0.00022785539,5.333892e-7,0.00005164461,0.7446031,0.00038985047,0.23889756],"study_design_scores_gemma":[0.03287898,0.00093542563,0.00088167994,0.00023170792,0.00004226842,0.000008192671,0.00014406606,0.039137978,0.00020505193,0.92490035,0.00023791935,0.0003963588],"about_ca_topic_score_codex":0.00053882593,"about_ca_topic_score_gemma":0.00010840852,"teacher_disagreement_score":0.62915415,"about_ca_system_score_codex":0.00038505375,"about_ca_system_score_gemma":0.0013233179,"threshold_uncertainty_score":0.99985385},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4464294343882807,"score_gpt":0.573171685688689,"score_spread":0.12674225130040834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171446894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028640343,0.000076403536,0.9685049,0.001337623,0.00011121628,0.00079336937,0.0000383242,0.0000111476475,0.00048664748],"genre_scores_gemma":[0.43475822,0.000041524574,0.564775,0.0000694605,0.000055853954,0.00018715645,0.000015816395,0.000010212228,0.00008675085],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9967114,0.00082995626,0.00042409785,0.000252482,0.0013954022,0.00038668883],"domain_scores_gemma":[0.98187757,0.017087588,0.000051059764,0.00030967774,0.00040143094,0.00027265883],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009546593,0.00010011473,0.00028781293,0.00013156504,0.00010125575,0.000012132748,0.0002778321,0.00011445265,0.0006562506],"category_scores_gemma":[0.023250954,0.00005744169,0.00003378151,0.00027993615,0.0007654647,0.00003376994,0.000061424216,0.0006817441,0.00000502328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015033173,0.0005956877,0.025530374,0.00034242397,0.00016124207,0.000041062176,0.0033924493,0.000007507574,0.00058208086,0.088548705,0.0003282924,0.87896687],"study_design_scores_gemma":[0.0051113036,0.0038232668,0.6180181,0.00117222,0.00011335598,0.000032064876,0.0020196503,0.31066397,0.0052837073,0.051935863,0.0016213426,0.00020515616],"about_ca_topic_score_codex":0.0004661519,"about_ca_topic_score_gemma":0.00010243739,"teacher_disagreement_score":0.8787617,"about_ca_system_score_codex":0.000061675775,"about_ca_system_score_gemma":0.00041273527,"threshold_uncertainty_score":0.9849766},"labels":[],"label_agreement":null},{"id":"W2332566401","doi":"10.1177/0962280214552291","title":"Confidence intervals for a difference between lognormal means in cluster randomization trials","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Confidence interval; Statistics; Randomization; Coverage probability; Sample size determination; Variance (accounting); Inference; Cluster randomised controlled trial; Mathematics; Cluster (spacecraft); Causal inference; Randomized controlled trial; Econometrics; Computer science; Medicine; Artificial intelligence","score_opus":0.41840400507326886,"score_gpt":0.6391732705030557,"score_spread":0.22076926542978687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2332566401","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035913012,0.000031521664,0.9938891,0.0016523462,0.00021444552,0.0017270094,0.00012990042,0.00003281603,0.001963722],"genre_scores_gemma":[0.03828313,0.000041160347,0.9603411,0.00020780406,0.00029627304,0.0006896429,0.000019043267,0.000038852962,0.00008299809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9482192,0.044257212,0.0028885263,0.00093915756,0.0022603555,0.0014355963],"domain_scores_gemma":[0.44946036,0.548568,0.00023247353,0.00052843516,0.00048870547,0.0007220346],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15371072,0.0002955289,0.0020032178,0.00053386256,0.000117805466,0.00011353399,0.0008190731,0.00048914715,0.0017101011],"category_scores_gemma":[0.7791874,0.00022071811,0.00012950356,0.0007735752,0.0010146657,0.00008013601,0.0003108038,0.0016661164,0.00001256683],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050980336,0.000095001735,0.00048579584,0.00026613794,0.000012724624,0.000009416864,0.00015760245,3.5629614e-7,0.000042544696,0.5468896,0.00029968773,0.45123133],"study_design_scores_gemma":[0.0054970724,0.00038334102,0.003605409,0.000636457,0.00002970444,0.0000031081117,0.00007080459,0.07363477,0.00027150344,0.91527194,0.00036651694,0.00022935835],"about_ca_topic_score_codex":0.00013757213,"about_ca_topic_score_gemma":0.0001471226,"teacher_disagreement_score":0.62547666,"about_ca_system_score_codex":0.00015531793,"about_ca_system_score_gemma":0.00034365262,"threshold_uncertainty_score":0.9992025},"labels":[],"label_agreement":null},{"id":"W2339513403","doi":"10.1177/0962280215613378","title":"Bayesian analysis of multi-type recurrent events and dependent termination with nonparametric covariate functions","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; University of Texas at Austin","keywords":"Covariate; Nonparametric statistics; Event (particle physics); Statistics; Multivariate statistics; Bayesian probability; Econometrics; Computer science; Mathematics","score_opus":0.4006036106045842,"score_gpt":0.6092943891545313,"score_spread":0.20869077854994705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339513403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057738307,0.00009389248,0.9924701,0.00014539703,0.00013152153,0.00035614544,0.00008942833,0.000015386579,0.000924311],"genre_scores_gemma":[0.15847711,0.000039623515,0.84126943,0.000015819238,0.000018956118,0.000050662045,0.000014871961,0.000015872978,0.00009763602],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9903225,0.0055392203,0.00078610465,0.0005179287,0.0023030762,0.0005312252],"domain_scores_gemma":[0.961686,0.036142416,0.0001190016,0.0003606149,0.0008903647,0.00080160174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01926312,0.00017177641,0.00071777025,0.0011939512,0.000064975975,0.000028580198,0.00027572212,0.00020306812,0.00086083956],"category_scores_gemma":[0.21540634,0.00012500581,0.00003592282,0.004078051,0.0006212497,0.00004921687,0.00021382532,0.00092469616,0.0000057269986],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042291233,0.0010532761,0.0072649783,0.000172435,0.00027505064,0.00007989818,0.0003382055,0.000009164591,0.00007450356,0.14740527,0.00014916123,0.84275514],"study_design_scores_gemma":[0.0020855805,0.0022773542,0.06844581,0.00024066659,0.00055302476,0.000014852552,0.0006415984,0.3785972,0.0001556431,0.54650724,0.00016490709,0.00031608742],"about_ca_topic_score_codex":0.00022803449,"about_ca_topic_score_gemma":0.00022097312,"teacher_disagreement_score":0.84243906,"about_ca_system_score_codex":0.00016620875,"about_ca_system_score_gemma":0.0003738988,"threshold_uncertainty_score":0.94255894},"labels":[],"label_agreement":null},{"id":"W2373287088","doi":"10.1177/0962280215590432","title":"Accounting for dropout reason in longitudinal studies with nonignorable dropout","year":2015,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Infectious Diseases Centre; McGill University","funders":"National Institute of Allergy and Infectious Diseases; National Institute on Drug Abuse","keywords":"Dropout (neural networks); Longitudinal data; Econometrics; Psychology; Medicine; Statistics; Computer science; Economics; Mathematics; Data mining; Machine learning","score_opus":0.7294024134950148,"score_gpt":0.7194349984114543,"score_spread":0.009967415083560471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2373287088","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036634528,0.00059632823,0.98969465,0.0009250204,0.00008024889,0.0009483477,0.000017061257,0.00009936646,0.0039755055],"genre_scores_gemma":[0.054727376,0.00017923214,0.9439917,0.000046079924,0.00011012505,0.00067806925,0.000005739036,0.00005418491,0.00020746783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99243677,0.0024576196,0.00080420246,0.000679977,0.0023800659,0.0012413929],"domain_scores_gemma":[0.94030887,0.0573384,0.00010454127,0.0004942241,0.0011798332,0.000574156],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03785107,0.00024779254,0.0008218834,0.00043872898,0.000109256725,0.000056824898,0.00054108864,0.00026812538,0.00019699654],"category_scores_gemma":[0.3055673,0.0001828117,0.00003238345,0.0010161331,0.001332413,0.00021611075,0.00038305635,0.0017357488,0.00001079641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006404841,0.00041682235,0.012553327,0.00075334817,0.00004105015,0.0005728963,0.00096958963,0.0000028743482,0.00006331759,0.69050276,0.0041313544,0.28935218],"study_design_scores_gemma":[0.0011223943,0.000728756,0.00019191473,0.0008241953,0.00001157759,0.000018481393,0.0025598654,0.010879626,0.0006112544,0.9809935,0.0018241543,0.00023428719],"about_ca_topic_score_codex":0.000170954,"about_ca_topic_score_gemma":0.00072282687,"teacher_disagreement_score":0.29049075,"about_ca_system_score_codex":0.0006894039,"about_ca_system_score_gemma":0.00081893534,"threshold_uncertainty_score":0.9907348},"labels":[],"label_agreement":null},{"id":"W2401418077","doi":"10.1177/0962280212451883","title":"Letter to the editor","year":2012,"lang":"en","type":"letter","venue":"Statistical Methods in Medical Research","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University","funders":"","keywords":"Computer science; Data science","score_opus":0.21606490369746106,"score_gpt":0.5879729825449449,"score_spread":0.37190807884748384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401418077","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022528906,0.000087186636,0.1482326,0.84111863,0.0060170763,0.00083829765,0.00005696183,0.000030892134,0.0035958579],"genre_scores_gemma":[0.00018266145,0.00003610397,0.089341335,0.7623577,0.14385013,0.00055904535,0.0002383166,0.0000911429,0.0033435267],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98427135,0.0062889974,0.000637564,0.0006502571,0.006645902,0.001505946],"domain_scores_gemma":[0.977005,0.020980403,0.000043685726,0.00088882615,0.00035507238,0.00072701776],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.023957772,0.00027136403,0.00063732144,0.00051945477,0.00014578419,0.0000648765,0.00069221715,0.001835393,0.014436773],"category_scores_gemma":[0.053952876,0.00016425615,0.000093965435,0.0008763814,0.0007885701,0.00003128512,0.000371565,0.016516145,0.0003891961],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044652,0.00006171862,0.00046590244,0.00015440516,0.000015749969,0.0008530313,0.000116056144,1.7633331e-8,0.000009953962,0.00022257256,0.78588384,0.21217208],"study_design_scores_gemma":[0.00034797715,0.00018828428,0.009641873,0.0003561454,0.00005807687,0.000039301718,0.000024674984,0.00003460897,0.000040056017,0.0013673628,0.98773295,0.00016867321],"about_ca_topic_score_codex":0.00019187828,"about_ca_topic_score_gemma":0.000008331152,"teacher_disagreement_score":0.2120034,"about_ca_system_score_codex":0.00041181679,"about_ca_system_score_gemma":0.0006377413,"threshold_uncertainty_score":0.99946046},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.7553058634596144,"score_gpt":0.6754228526511649,"score_spread":0.0798830108084495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2484604119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017214797,0.00002032209,0.97755045,0.001633163,0.000040703853,0.0004047685,0.000021710966,0.00009795216,0.0030161273],"genre_scores_gemma":[0.1537364,0.00009587079,0.8458018,0.00006209577,0.000043582626,0.000063111955,0.0000019007639,0.000025905274,0.00016935825],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.984878,0.011620697,0.00054473354,0.0005137769,0.0016477286,0.0007950766],"domain_scores_gemma":[0.93476176,0.06406335,0.000043197695,0.00037175964,0.00024964657,0.0005102865],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04732967,0.00015264848,0.00046832,0.0001913246,0.00011364587,0.000035169334,0.0003910556,0.00020291746,0.0026037623],"category_scores_gemma":[0.15967041,0.00009138939,0.000019275747,0.00034903098,0.0016426947,0.00010125407,0.0006510787,0.0010415172,0.000021542819],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019056504,0.000053281015,0.0013738788,0.00007912275,0.0000041385506,0.00010979929,0.000049773553,4.306601e-9,0.002658465,0.4401305,0.00056153315,0.5549604],"study_design_scores_gemma":[0.0003006932,0.00013051946,0.034871917,0.00034069532,0.000002297766,0.000017538132,0.000034543675,0.000110709254,0.0008863888,0.9627134,0.00046167072,0.00012960804],"about_ca_topic_score_codex":0.00013502204,"about_ca_topic_score_gemma":0.0001419505,"teacher_disagreement_score":0.55483085,"about_ca_system_score_codex":0.00013698624,"about_ca_system_score_gemma":0.0001890827,"threshold_uncertainty_score":0.998308},"labels":[],"label_agreement":null},{"id":"W2510561985","doi":"10.1177/0962280216660127","title":"A two-stage model in a Bayesian framework to estimate a survival endpoint in the presence of confounding by indication","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut National Du Cancer","keywords":"Prostate-specific antigen; Prostate cancer; Medicine; Oncology; Biomarker; Prostate; Hormonal therapy; Clinical endpoint; Hormone therapy; Internal medicine; Randomized controlled trial; Cancer; Biology","score_opus":0.6285155508790987,"score_gpt":0.7340032660082315,"score_spread":0.1054877151291328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510561985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061325002,0.000025535946,0.9844503,0.005488424,0.00018008245,0.0015260645,0.0002699098,0.000022861776,0.0019043394],"genre_scores_gemma":[0.11863387,0.000048511465,0.88041776,0.00018219402,0.00006837233,0.0005386165,0.00000197535,0.000043151354,0.0000655421],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95115995,0.037366074,0.0032614553,0.0012366382,0.0051949346,0.0017809583],"domain_scores_gemma":[0.38697532,0.61080647,0.00023201463,0.0010412339,0.00023976096,0.0007052086],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13694763,0.00030257695,0.0012637693,0.00065530237,0.00007457783,0.000057021465,0.001742415,0.0005118166,0.0012962656],"category_scores_gemma":[0.8684334,0.00018532659,0.00007804556,0.0021799284,0.0016996918,0.00008889746,0.0006278428,0.0026666948,0.000022318809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005149454,0.0005212306,0.0011635892,0.00022247154,0.000011313074,0.00012938416,0.0009209224,0.00001303884,0.0009882941,0.8261719,0.00030779326,0.16903515],"study_design_scores_gemma":[0.0014491022,0.00024617914,0.0017429815,0.0012757757,0.000008512661,0.0000021473338,0.000369549,0.04510296,0.00043486478,0.94907385,0.00008467452,0.00020940616],"about_ca_topic_score_codex":0.00023536671,"about_ca_topic_score_gemma":0.0003062088,"teacher_disagreement_score":0.7314858,"about_ca_system_score_codex":0.00033853075,"about_ca_system_score_gemma":0.0006311197,"threshold_uncertainty_score":0.9996342},"labels":[],"label_agreement":null},{"id":"W2514759531","doi":"10.1177/0962280216662494","title":"Mortality and morbidity peaks modeling: An extreme value theory approach","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre hospitalier universitaire de Québec; Institut National de Santé Publique du Québec; Université Laval; Institut National de la Recherche Scientifique","funders":"","keywords":"Extreme value theory; Public health; Metropolitan area; Health care; Value (mathematics); Actuarial science; Medicine; Computer science; Operations research; Statistics; Econometrics; Business; Mathematics; Economics; Nursing","score_opus":0.30642057569356257,"score_gpt":0.5375606796132323,"score_spread":0.23114010391966971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514759531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1279967,0.00004494041,0.85374105,0.000550968,0.000030418965,0.00012564314,0.000011459486,0.000018251769,0.017480575],"genre_scores_gemma":[0.6971126,0.00009821487,0.30233836,0.00012894734,0.00005692262,0.000039101815,0.0000042497563,0.000011261965,0.00021030259],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863833,0.010138331,0.00038635184,0.00076186005,0.0016092083,0.0007209042],"domain_scores_gemma":[0.99175197,0.0069414303,0.000022091082,0.00047107722,0.000022184704,0.0007912299],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03691945,0.00013748572,0.0003148104,0.00009510414,0.00017605032,0.000020401441,0.00049458037,0.00028802364,0.013266633],"category_scores_gemma":[0.024558777,0.000084502375,0.000033552762,0.0004148583,0.002823654,0.00014664822,0.0005660844,0.0008521818,0.000088621025],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017842761,0.00055080256,0.039547045,0.000027713199,0.000039188122,0.00018712692,0.00040030014,0.00021695603,0.0014083997,0.19777004,0.00029594658,0.7593781],"study_design_scores_gemma":[0.0002874779,0.00009109393,0.02323633,0.000009843975,0.000013020696,0.0000064304536,0.00007724538,0.4630478,0.000036188205,0.51289564,0.00018680772,0.00011211427],"about_ca_topic_score_codex":0.0012674738,"about_ca_topic_score_gemma":0.0002319048,"teacher_disagreement_score":0.75926596,"about_ca_system_score_codex":0.00012216304,"about_ca_system_score_gemma":0.00006850817,"threshold_uncertainty_score":0.9998901},"labels":[],"label_agreement":null},{"id":"W2515545921","doi":"10.1177/0962280216660419","title":"Linear models of coregionalization for multivariate lattice data: Order-dependent and order-free cMCARs","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Univariate; Autoregressive model; Computer science; Multivariate analysis; Context (archaeology); Covariance; Linear model; Generalized linear mixed model; Econometrics; Statistics; Mathematics; Machine learning","score_opus":0.44791645230417537,"score_gpt":0.6086216280736643,"score_spread":0.1607051757694889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515545921","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008999982,0.000092954404,0.9950272,0.0023142346,0.00012599838,0.000715235,0.000978095,0.000024795945,0.0006314997],"genre_scores_gemma":[0.0016847559,0.00024943455,0.9976038,0.00006419481,0.00010448824,0.000115125746,0.000022784407,0.000042437117,0.00011298521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991493,0.004062902,0.0010044158,0.0008073159,0.0018972391,0.0007351326],"domain_scores_gemma":[0.8490635,0.14801064,0.00013726283,0.0010798032,0.0011756007,0.00053320033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022816699,0.00020916926,0.00067769096,0.0002379036,0.00010952152,0.000028412183,0.0010533634,0.00031038673,0.0006696902],"category_scores_gemma":[0.43528578,0.00013682153,0.00002576568,0.0006244666,0.0013716411,0.0001585378,0.0010457883,0.00055759563,0.0000033658955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018335979,0.00014998773,0.00004453079,0.00037242807,0.000022323398,0.000018146466,0.000065837325,3.434671e-7,0.00021002254,0.6493979,0.00067987357,0.34885526],"study_design_scores_gemma":[0.0016925142,0.00022401026,0.00020739155,0.0004317772,0.00002615802,0.0000071943396,0.00006152284,0.16207466,0.00017251642,0.8345676,0.0003858242,0.00014884623],"about_ca_topic_score_codex":0.00017488637,"about_ca_topic_score_gemma":0.00007887546,"teacher_disagreement_score":0.4124691,"about_ca_system_score_codex":0.00006828626,"about_ca_system_score_gemma":0.00054940506,"threshold_uncertainty_score":0.7907858},"labels":[],"label_agreement":null},{"id":"W2516304337","doi":"10.1177/0962280216660407","title":"A Gaussian random field model for similarity-based smoothing in Bayesian disease mapping","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Fogarty International Center; National Institute on Drug Abuse; National Institute of Mental Health","keywords":"Smoothing; Similarity (geometry); Mathematics; Spatial analysis; Bayesian probability; Gaussian random field; Gaussian; Random field; Computer science; Statistics; Artificial intelligence; Pattern recognition (psychology); Gaussian process","score_opus":0.2324085936925764,"score_gpt":0.48457481351439907,"score_spread":0.25216621982182263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516304337","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027366812,0.00020503126,0.9788523,0.018371386,0.00008174361,0.000360173,0.000601611,0.000012377857,0.0012417381],"genre_scores_gemma":[0.33630472,0.00016540701,0.6614242,0.0013380909,0.000113584036,0.00034706012,0.000047741167,0.000028320917,0.00023086887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99663043,0.00071947655,0.0009055514,0.00065713166,0.00031168794,0.00077574863],"domain_scores_gemma":[0.97912055,0.019768879,0.00007056587,0.0003843971,0.00005352664,0.0006020794],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016790874,0.00014085842,0.0005834724,0.0007708172,0.00010467524,0.000056100227,0.00049200136,0.0002768933,0.0028333366],"category_scores_gemma":[0.08691062,0.0001124857,0.00010271382,0.00064713345,0.00025594284,0.000099771416,0.00013003247,0.00080700923,0.000033838216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001107701,0.00032020296,0.03116037,0.0003227288,0.000035344918,0.00017762433,0.00028008028,0.00014158276,0.00003195893,0.4120033,0.0013848111,0.5530343],"study_design_scores_gemma":[0.0016287836,0.000034767418,0.002462874,0.00013039833,0.0000024747205,1.301978e-7,0.000015735637,0.59582055,0.000009190314,0.3974901,0.0022894542,0.000115553084],"about_ca_topic_score_codex":0.00074938947,"about_ca_topic_score_gemma":0.0004139173,"teacher_disagreement_score":0.5956789,"about_ca_system_score_codex":0.00015123538,"about_ca_system_score_gemma":0.00024434805,"threshold_uncertainty_score":0.9980782},"labels":[],"label_agreement":null},{"id":"W2521300970","doi":"10.1177/0962280216668554","title":"Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of British Columbia; McGill University; Jewish General Hospital","funders":"IC Design Education Center; Canadian Institutes of Health Research; Biogen; EMD Serono; Pfizer","keywords":"Covariate; Confounding; Marginal structural model; Proportional hazards model; Econometrics; Statistics; Event (particle physics); Marginal model; Estimation; Computer science; Medicine; Regression analysis; Mathematics","score_opus":0.6270859484776903,"score_gpt":0.6922224989551746,"score_spread":0.06513655047748435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521300970","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014698675,0.000157327,0.9824223,0.0002183809,0.000036819776,0.00072635507,0.000035577967,0.000059415597,0.0016451743],"genre_scores_gemma":[0.4335834,0.000048122456,0.5661186,0.0000040154628,0.000017049038,0.00016752697,0.0000017507863,0.000027630533,0.000031921612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863187,0.00851573,0.0011377563,0.00064789795,0.0024645838,0.0009153061],"domain_scores_gemma":[0.8220934,0.17682351,0.00011897565,0.00034989227,0.00031492685,0.0002992506],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03316026,0.0002472036,0.0012391855,0.000442409,0.00007244287,0.000017854398,0.00046082475,0.00019374026,0.0005852656],"category_scores_gemma":[0.14120343,0.0001498566,0.00002674864,0.00051794626,0.002481595,0.00009706332,0.0003905842,0.0012639329,0.0000122268575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042967524,0.00033395147,0.004270694,0.0006838685,0.000045668927,0.00016533428,0.00050912256,0.000003144282,0.001784439,0.7605519,0.000058063528,0.23116413],"study_design_scores_gemma":[0.0011121073,0.000499964,0.0014232668,0.0025606595,0.000016407232,0.000008530859,0.0013139626,0.002643872,0.020121286,0.9700329,0.000032949414,0.00023413087],"about_ca_topic_score_codex":0.00008720709,"about_ca_topic_score_gemma":0.0001707017,"teacher_disagreement_score":0.41888472,"about_ca_system_score_codex":0.0004656682,"about_ca_system_score_gemma":0.00028019535,"threshold_uncertainty_score":0.995565},"labels":[],"label_agreement":null},{"id":"W2559863382","doi":"10.1177/0962280216680834","title":"A graphical perspective of marginal structural models: An application for the estimation of the effect of physical activity on blood pressure","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Hôpital du Sacré-Cœur de Montréal; McGill University Health Centre; Université Laval; The Quebec Population Health Research Network; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Marginal structural model; Counterfactual thinking; Causal inference; Causal model; Computer science; Marginal model; Graphical model; Econometrics; Causal structure; Graph; Inference; Context (archaeology); Data mining; Mathematics; Machine learning; Statistics; Artificial intelligence; Regression analysis; Theoretical computer science; Psychology","score_opus":0.20943349816461482,"score_gpt":0.6226692917242447,"score_spread":0.41323579355962986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559863382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061858326,0.000018494426,0.93589705,0.00057961803,0.00001579965,0.001375038,0.0001191335,0.000015203323,0.00012133543],"genre_scores_gemma":[0.7655255,0.0000055332935,0.23411952,0.0000022257282,0.000026446769,0.0003025407,6.973933e-7,0.000012867056,0.000004623655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99389106,0.003637662,0.00033605075,0.00031826893,0.0015113618,0.00030561685],"domain_scores_gemma":[0.9195434,0.07928397,0.00015415298,0.0005446517,0.00037527972,0.00009855813],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007996588,0.00013553078,0.0004578422,0.000108028464,0.00006759419,0.000004355002,0.00058686454,0.00016369938,0.00003369402],"category_scores_gemma":[0.067778036,0.00005822845,0.00009064751,0.0003978384,0.0019544656,0.00008599677,0.0001578111,0.0006717913,1.2027664e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060560275,0.00017716462,0.000035463945,0.00022537864,0.00003883398,3.6443328e-7,0.00016190349,0.000033882923,0.01129502,0.7096121,0.000007455769,0.27780688],"study_design_scores_gemma":[0.0004419732,0.0015230573,0.0009499881,0.00015941072,0.00006795244,0.0000010140094,0.00003725161,0.20394605,0.09278261,0.7000447,0.0000013864669,0.00004463231],"about_ca_topic_score_codex":0.00008722618,"about_ca_topic_score_gemma":0.000013019956,"teacher_disagreement_score":0.7036672,"about_ca_system_score_codex":0.000047028836,"about_ca_system_score_gemma":0.00013750888,"threshold_uncertainty_score":0.94007444},"labels":[],"label_agreement":null},{"id":"W2560836925","doi":"10.1177/0962280216681599","title":"Interval estimation for a proportion using a double-sampling scheme with two fallible classifiers","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Confidence interval; Statistics; Credible interval; Robust confidence intervals; Percentile; Coverage probability; Mathematics; Tolerance interval; Binomial proportion confidence interval; Sample size determination; Classifier (UML); Confidence distribution; Computer science; Artificial intelligence; Negative binomial distribution; Poisson distribution","score_opus":0.7224746746721421,"score_gpt":0.731382168623437,"score_spread":0.008907493951294865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560836925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004192549,0.00003222238,0.99275213,0.0013421666,0.00024611352,0.0007926053,0.00004035094,0.000042562107,0.000559322],"genre_scores_gemma":[0.13273118,0.000005115608,0.86663955,0.00003066594,0.0001549762,0.00023932823,0.0000036712477,0.000034332512,0.0001611552],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885982,0.0018587665,0.0013339065,0.0011331742,0.0059009027,0.0011750131],"domain_scores_gemma":[0.9244221,0.07254213,0.0002011169,0.00052899355,0.0014792241,0.0008264656],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036550634,0.0002201013,0.00057244446,0.00064145,0.0003060784,0.00021572327,0.0008638664,0.00019618019,0.0006727817],"category_scores_gemma":[0.26199728,0.00012314804,0.000052084048,0.0016502205,0.001564012,0.0004799658,0.0003317578,0.0009040622,0.000036887708],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011604888,0.000081046455,0.0008784959,0.000058453465,0.000010515702,0.00004726081,0.000077546596,0.00013846163,0.0022201452,0.13543585,0.000057475205,0.85983425],"study_design_scores_gemma":[0.00247752,0.00034113755,0.0004490081,0.00047009304,0.0000069247235,0.000016386746,0.00028587756,0.35099778,0.0012578239,0.64266115,0.0008417054,0.00019457494],"about_ca_topic_score_codex":0.000068068264,"about_ca_topic_score_gemma":0.000053295913,"teacher_disagreement_score":0.8596397,"about_ca_system_score_codex":0.00048408084,"about_ca_system_score_gemma":0.0008811625,"threshold_uncertainty_score":0.9920739},"labels":[],"label_agreement":null},{"id":"W2569952854","doi":"10.1177/0962280216684671","title":"Detecting and correcting for publication bias in meta-analysis – A truncated normal distribution approach","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Publication bias; Funnel plot; Estimator; Statistics; Selection bias; Meta-analysis; Random effects model; Parametric statistics; Truncation (statistics); Econometrics; Computer science; Mathematics; Confidence interval; Medicine","score_opus":0.5688831534431038,"score_gpt":0.6084837730401228,"score_spread":0.03960061959701899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569952854","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057347276,0.000068304,0.9961601,0.0014936668,0.000044070137,0.00068535376,0.00028490095,0.00003431741,0.0006557989],"genre_scores_gemma":[0.07226749,0.000015904574,0.9268004,0.0000378479,0.000043555974,0.00071304594,0.000036130434,0.000022018434,0.00006361528],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9872894,0.008272415,0.001240865,0.0008373129,0.0013752882,0.0009846878],"domain_scores_gemma":[0.8395129,0.15894546,0.00015353883,0.0003655694,0.0005511113,0.00047144576],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05582694,0.00022333654,0.001190056,0.0006300342,0.00016758952,0.00010725339,0.00034742884,0.00031713815,0.0011670203],"category_scores_gemma":[0.52011645,0.00013752705,0.00017759672,0.002503353,0.00064353517,0.000121714926,0.0002175422,0.000898772,0.0000031273726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009514686,0.00014361326,0.0007512229,0.00013007986,0.0008545187,0.000009391878,0.000092220755,1.2415478e-7,0.00007502324,0.36912,0.00010336399,0.6286253],"study_design_scores_gemma":[0.00088629936,0.00015907864,0.0049430626,0.000040705945,0.0024610325,0.000012259279,0.00024125926,0.06189983,0.0004104572,0.9285584,0.00014420519,0.00024342211],"about_ca_topic_score_codex":0.00021632304,"about_ca_topic_score_gemma":0.00013286073,"teacher_disagreement_score":0.6283819,"about_ca_system_score_codex":0.00020181027,"about_ca_system_score_gemma":0.00021165214,"threshold_uncertainty_score":0.999746},"labels":[],"label_agreement":null},{"id":"W2573716001","doi":"10.1177/0962280216688031","title":"An efficient test based on the inferential model for the non-inferiority of odds ratio in matched-pairs design","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Odds ratio; Test (biology); Sample size determination; Odds; Statistics; Score test; Computer science; Type I and type II errors; Inference; Function (biology); Mathematics; Medicine; Statistical hypothesis testing; Logistic regression; Artificial intelligence","score_opus":0.7979925770576195,"score_gpt":0.7224137239264271,"score_spread":0.07557885313119239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573716001","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00080053083,0.0000071121203,0.9907001,0.004425477,0.00032735252,0.002825813,0.00024070713,0.000020161755,0.00065274263],"genre_scores_gemma":[0.29915044,0.000013719072,0.6997835,0.00014438923,0.00014641686,0.0006992128,0.0000015957665,0.000040365052,0.000020356742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9761662,0.016300183,0.002039092,0.00086061255,0.0034455683,0.0011883483],"domain_scores_gemma":[0.31463915,0.6818939,0.00031419058,0.0021210206,0.00054427754,0.00048746984],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1514196,0.00031947318,0.0011471843,0.00023212213,0.00061160355,0.0002006244,0.0027104614,0.000517504,0.0010847627],"category_scores_gemma":[0.8827624,0.00017957753,0.00015227815,0.00042371693,0.0037644529,0.000051470102,0.00045120815,0.002677925,0.000008396378],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019723277,0.0025740182,0.0004355001,0.00040999064,0.000036849375,0.000044699576,0.00041137432,0.0035949918,0.000463554,0.7936212,0.00087446946,0.19556107],"study_design_scores_gemma":[0.0011011678,0.0004394764,0.0033602302,0.00018146996,0.00002000003,3.0949036e-7,0.00007042371,0.5429936,0.00057634467,0.4511445,0.0000061583287,0.00010636691],"about_ca_topic_score_codex":0.00015390155,"about_ca_topic_score_gemma":0.00010547021,"teacher_disagreement_score":0.73134273,"about_ca_system_score_codex":0.00017525027,"about_ca_system_score_gemma":0.0012982002,"threshold_uncertainty_score":0.9998284},"labels":[],"label_agreement":null},{"id":"W2609604109","doi":"10.1177/0962280217708662","title":"Prediction and tolerance intervals for dynamic treatment regimes","year":2017,"lang":"en","type":"preprint","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Tolerance interval; Interval (graph theory); Computer science; Confidence interval; Estimation; Econometrics; Prediction interval; Data mining; Statistics; Machine learning; Mathematics; Engineering","score_opus":0.5751032498731449,"score_gpt":0.6926307709134367,"score_spread":0.11752752104029185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609604109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070027757,0.00060173083,0.9915056,0.0015774714,0.00030823168,0.002098647,0.0005565966,0.00013386951,0.0025175363],"genre_scores_gemma":[0.0077124205,0.0026434448,0.98572767,0.00002590991,0.00015978249,0.0026713756,0.00006250452,0.0000643132,0.00093256414],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99321896,0.0028096824,0.00086623355,0.001015266,0.0012827531,0.00080713315],"domain_scores_gemma":[0.9595559,0.038362972,0.00019305725,0.001052737,0.00037688203,0.00045840658],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.015469481,0.00035332027,0.0010465055,0.00032143257,0.00019919086,0.0001359872,0.00075333065,0.00086106465,0.00028068203],"category_scores_gemma":[0.14617059,0.00028349663,0.00008881538,0.000091835784,0.0015359987,0.00006986352,0.001136251,0.002260786,0.0000028065056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015495071,0.00018768258,0.000051751987,0.001064477,0.000043270735,0.00006831871,0.00024987262,7.348931e-7,0.00006295555,0.19672188,0.0013151866,0.8000789],"study_design_scores_gemma":[0.0005265368,0.000632217,0.00038184723,0.0016948549,0.000028939688,0.000009039726,0.000054654185,0.04473418,0.0003985571,0.9487905,0.0025466892,0.0002020166],"about_ca_topic_score_codex":0.0001272457,"about_ca_topic_score_gemma":0.00011426574,"teacher_disagreement_score":0.79987687,"about_ca_system_score_codex":0.00066327327,"about_ca_system_score_gemma":0.0006172194,"threshold_uncertainty_score":0.99996173},"labels":[],"label_agreement":null},{"id":"W2612495025","doi":"10.1177/0962280217708665","title":"Model validation and selection for personalized medicine using dynamic-weighted ordinary least squares","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; University of Texas Southwestern Medical Center","keywords":"Ordinary least squares; Robustness (evolution); Computer science; Personalized medicine; Selection (genetic algorithm); Generalized least squares; Econometrics; Data mining; Statistics; Mathematics; Machine learning; Bioinformatics; Estimator","score_opus":0.6475070671778674,"score_gpt":0.7094544250062448,"score_spread":0.06194735782837735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612495025","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005959292,0.00006267278,0.9908261,0.0015894297,0.000045446595,0.0006981297,0.000029347028,0.000066974724,0.00072266284],"genre_scores_gemma":[0.05312406,0.000113699934,0.9461924,0.000030280631,0.000079102036,0.00016966042,0.000011835559,0.000037239915,0.00024173953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99564195,0.0015346209,0.00051621726,0.0004917188,0.0012325619,0.0005829179],"domain_scores_gemma":[0.98222435,0.016509192,0.00012837451,0.000307738,0.00049640995,0.0003339692],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014388126,0.00017529963,0.0004923989,0.00028806226,0.0005492091,0.00006812351,0.0003865781,0.00028277474,0.0004430329],"category_scores_gemma":[0.13762906,0.00014093102,0.000028140568,0.00018930172,0.00188634,0.00019334398,0.00025240175,0.00091869984,8.510251e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025623332,0.00008372219,0.00009728682,0.0003153916,0.0000152536195,0.000012027842,0.00021429792,0.000002670432,0.0076858765,0.7507244,0.00041740361,0.24017546],"study_design_scores_gemma":[0.00046870386,0.00017582247,0.000077910045,0.00021472317,0.000011960837,0.000009345659,0.0000848237,0.458506,0.00043246747,0.5398525,0.00008568098,0.000080047685],"about_ca_topic_score_codex":0.00015969657,"about_ca_topic_score_gemma":0.00006814354,"teacher_disagreement_score":0.4585033,"about_ca_system_score_codex":0.00025257538,"about_ca_system_score_gemma":0.00026302616,"threshold_uncertainty_score":0.86963505},"labels":[],"label_agreement":null},{"id":"W2613103431","doi":"10.1177/0962280217702540","title":"Comparing heteroscedastic measurement systems with the probability of agreement","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo","funders":"","keywords":"Homoscedasticity; Heteroscedasticity; Metric (unit); Observational error; Computer science; Statistics; Mathematics; Engineering","score_opus":0.7493861067260326,"score_gpt":0.6289003428450651,"score_spread":0.12048576388096743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613103431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039895643,0.00023717505,0.93705666,0.0075632255,0.0004715428,0.0016615908,0.000013377774,0.000009726415,0.013091033],"genre_scores_gemma":[0.9373242,0.000016281381,0.062255096,0.00003607123,0.00007110191,0.00019582015,5.419494e-7,0.00000866726,0.00009219721],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9526764,0.016344182,0.00191822,0.0011231829,0.026860977,0.0010770345],"domain_scores_gemma":[0.96345603,0.029645495,0.00044608655,0.0030822563,0.0027716586,0.00059844257],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.24910049,0.00019637149,0.0007489277,0.00019305073,0.0007492167,0.0005378898,0.0037057395,0.0001293468,0.0009842395],"category_scores_gemma":[0.26424545,0.000093811104,0.000072582276,0.00048932,0.0038596678,0.00012938419,0.0009970277,0.0013143372,0.00005060629],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010675256,0.0018211257,0.18604782,0.00069313135,0.00014259764,0.00011460665,0.0010290885,0.0009232444,0.0013548638,0.12632635,0.0065151094,0.67396456],"study_design_scores_gemma":[0.002358788,0.0014621908,0.6582694,0.0012801354,0.000033464425,0.000008780909,0.0023369289,0.080041446,0.0007546898,0.24301313,0.01004713,0.00039391764],"about_ca_topic_score_codex":0.00081028964,"about_ca_topic_score_gemma":0.0008219313,"teacher_disagreement_score":0.8974286,"about_ca_system_score_codex":0.00034370046,"about_ca_system_score_gemma":0.0006091844,"threshold_uncertainty_score":0.999929},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3791836015499943,"score_gpt":0.623165077965462,"score_spread":0.24398147641546775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613408792","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035302895,0.000036106005,0.9651938,0.024123322,0.000056497338,0.00034971072,0.00018554696,0.000018433599,0.0065063094],"genre_scores_gemma":[0.26287854,0.000019862353,0.73604655,0.000055749708,0.0002286394,0.00008843834,0.00009066907,0.000003919041,0.0005876122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921122,0.0033230921,0.00022798519,0.0010997643,0.0023513776,0.0008855515],"domain_scores_gemma":[0.96524525,0.03185216,0.000047064637,0.0018814697,0.0004251078,0.00054896454],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032565013,0.0001252237,0.00041935773,0.00030396198,0.001001383,0.00043196985,0.0040861024,0.00016967607,0.0004053116],"category_scores_gemma":[0.056824155,0.00010748356,0.00004594064,0.0006568397,0.0020511404,0.00030778444,0.006361615,0.0015250638,0.000023181168],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015957061,0.0005533941,0.00113155,0.00012773456,0.00019602104,0.0002695168,0.00014331717,0.000010333621,0.002140614,0.14742748,0.0056195613,0.8422209],"study_design_scores_gemma":[0.00036423895,0.00013684414,0.02884987,0.000029168279,0.000016938253,0.000007684821,0.0000131886345,0.7599959,0.0005219453,0.20619464,0.0037623958,0.000107207496],"about_ca_topic_score_codex":0.00027608467,"about_ca_topic_score_gemma":0.000050461655,"teacher_disagreement_score":0.8421137,"about_ca_system_score_codex":0.000059402806,"about_ca_system_score_gemma":0.00027798122,"threshold_uncertainty_score":0.9961779},"labels":[],"label_agreement":null},{"id":"W2615126006","doi":"10.1177/0962280217708683","title":"Proportional hazards under Conway–Maxwell-Poisson cure rate model and associated inference","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Inference; Poisson distribution; Poisson regression; Overdispersion; Applied mathematics; Mathematics; Statistics; Proportional hazards model; Econometrics; Medicine; Computer science; Count data; Artificial intelligence; Environmental health","score_opus":0.1357556402941482,"score_gpt":0.5222345565827372,"score_spread":0.386478916288589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615126006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004270325,0.0000949247,0.9890923,0.0012811269,0.000104776234,0.0001754039,0.00003644387,0.000054658365,0.0048900507],"genre_scores_gemma":[0.75995505,0.0005980251,0.23889023,0.00005385854,0.000047817975,0.00005664553,0.000041547737,0.000027112615,0.00032969564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974244,0.0005166531,0.0003186462,0.00029245717,0.00095529406,0.00049250416],"domain_scores_gemma":[0.99665195,0.002530292,0.000037208818,0.00024460835,0.000178755,0.00035717463],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067229983,0.00012983105,0.00025242893,0.00011886776,0.0002704121,0.00017325261,0.00033283472,0.00026339275,0.0007504096],"category_scores_gemma":[0.026645863,0.00011123931,0.00001562948,0.00009878082,0.0006279363,0.000119109594,0.0001902833,0.0011422071,0.000005498132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008804941,0.00017337507,0.0019227071,0.00066239486,0.000072922456,0.00013857229,0.00034456924,0.082751215,0.00028333734,0.20888737,0.0024347233,0.70224077],"study_design_scores_gemma":[0.00033375574,0.000028296072,0.01952144,0.000097419834,0.000003886845,8.128683e-7,0.000014035125,0.8299009,0.00021497799,0.1495187,0.0002550485,0.00011069267],"about_ca_topic_score_codex":0.00006277807,"about_ca_topic_score_gemma":0.000064195105,"teacher_disagreement_score":0.75568473,"about_ca_system_score_codex":0.00009464364,"about_ca_system_score_gemma":0.00025547753,"threshold_uncertainty_score":0.98155314},"labels":[],"label_agreement":null},{"id":"W2616441786","doi":"10.1177/0962280217708673","title":"Prediction accuracy for the cure probabilities in mixture cure models","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Censoring (clinical trials); Estimator; Cure rate; Statistics; Identifiability; Inverse probability; Computer science; Mathematics; Bayesian probability; Medicine; Posterior probability; Surgery","score_opus":0.18013863621807136,"score_gpt":0.545927531221922,"score_spread":0.3657888950038506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616441786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057667904,0.0020003628,0.97534305,0.012686959,0.00047313352,0.001232664,0.00049176865,0.0000057195393,0.0019995412],"genre_scores_gemma":[0.49618825,0.014980864,0.48301473,0.00072238134,0.001984367,0.0020700577,0.00022845247,0.000079799596,0.0007310919],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975102,0.00063638925,0.00032805649,0.0004345234,0.00056927855,0.0005215335],"domain_scores_gemma":[0.9920189,0.006860088,0.00004886537,0.00066950446,0.0002106784,0.00019200635],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073464927,0.00011771573,0.00019320252,0.000058755642,0.00029530402,0.00010666222,0.0007561958,0.0003228278,0.0000993211],"category_scores_gemma":[0.06846974,0.00008355961,0.00004816505,0.000079757316,0.0008643432,0.000007822721,0.00042632045,0.00074669806,0.0000015250808],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000849397,0.00030338144,0.0024514801,0.00029846563,0.000049027294,0.000037294914,0.00039437535,0.0003818812,0.0038053098,0.16331634,0.04512766,0.7829854],"study_design_scores_gemma":[0.0024641813,0.00080812717,0.011510514,0.00021855232,0.000019725909,0.000011258328,0.00054690376,0.12078606,0.003104823,0.61100245,0.24921356,0.00031385059],"about_ca_topic_score_codex":0.00026491453,"about_ca_topic_score_gemma":0.0007789762,"teacher_disagreement_score":0.7826715,"about_ca_system_score_codex":0.000059371498,"about_ca_system_score_gemma":0.0005738388,"threshold_uncertainty_score":0.93937695},"labels":[],"label_agreement":null},{"id":"W2646223782","doi":"10.1177/0962280217712088","title":"Functional principal component analysis of glomerular filtration rate curves after kidney transplant","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Functional principal component analysis; Renal function; Principal component analysis; Functional data analysis; Filtration (mathematics); Kidney transplant; Kidney transplantation; Function (biology); Kidney; Urology; Medicine; Internal medicine; Mathematics; Biology; Statistics","score_opus":0.11661366098704007,"score_gpt":0.494865302077494,"score_spread":0.37825164109045395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2646223782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065423985,0.00027530084,0.9920177,0.0051200488,0.00024929247,0.00022881507,0.000098771074,0.000015988624,0.001339886],"genre_scores_gemma":[0.08078938,0.00041546364,0.9180234,0.0004792407,0.000058587608,0.00008889962,0.000033551925,0.00000859421,0.00010284513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9898252,0.0060743648,0.0006855,0.0006595016,0.0021544087,0.00060106255],"domain_scores_gemma":[0.9916241,0.0061497013,0.00011384129,0.001053274,0.00029690852,0.000762172],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02684355,0.00015994576,0.0006110585,0.00052142097,0.00021887664,0.0001212154,0.001366159,0.00018998208,0.001552734],"category_scores_gemma":[0.01971471,0.00012691507,0.00013301248,0.0008217989,0.00088518724,0.00021588341,0.0003801362,0.0009575878,0.000008727785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022537482,0.0003517053,0.0025505784,0.00039526436,0.0003203244,0.0004270367,0.00029384278,0.000008623108,0.0016701156,0.49723294,0.0011106706,0.4954135],"study_design_scores_gemma":[0.00079132925,0.0001840287,0.3904789,0.000548959,0.0001522636,0.000008778088,0.000006380311,0.45690313,0.0015752849,0.14752534,0.0015446618,0.00028094798],"about_ca_topic_score_codex":0.00018525493,"about_ca_topic_score_gemma":0.00005653537,"teacher_disagreement_score":0.49513257,"about_ca_system_score_codex":0.00005959673,"about_ca_system_score_gemma":0.000542489,"threshold_uncertainty_score":0.99935997},"labels":[],"label_agreement":null},{"id":"W2724536226","doi":"10.1177/0962280217708686","title":"Likelihood inference for COM-Poisson cure rate model with interval-censored data and Weibull lifetimes","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Minnesota","keywords":"Poisson distribution; Statistics; Weibull distribution; Overdispersion; Mathematics; Interval (graph theory); Applied mathematics; Inference; Count data; Expectation–maximization algorithm; Computer science; Maximum likelihood; Artificial intelligence","score_opus":0.41110056473687834,"score_gpt":0.6454746309299403,"score_spread":0.23437406619306195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724536226","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023369055,0.000028622024,0.97955674,0.015622831,0.000032490723,0.000747509,0.0023603623,0.00003797713,0.0013797536],"genre_scores_gemma":[0.065304436,0.00009488927,0.9335948,0.00013762664,0.000045950448,0.00031380547,0.00023468302,0.000028694065,0.00024509866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959377,0.0011161848,0.00057570636,0.00069724815,0.0009988173,0.0006743505],"domain_scores_gemma":[0.9642443,0.03309378,0.00012840595,0.0013183538,0.00049619755,0.0007189759],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010925795,0.0001917729,0.00046916978,0.0001041554,0.0005451878,0.00024643025,0.0012625895,0.0002046803,0.00071272755],"category_scores_gemma":[0.20173039,0.00014534628,0.000020682226,0.00016033862,0.0017366391,0.00015145281,0.00084255805,0.000936196,0.000017788758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000143239,0.00020667462,0.000104411345,0.00020753879,0.000018707606,0.000013302548,0.00006851671,0.0000013318806,0.000035209672,0.8113853,0.011800238,0.17601557],"study_design_scores_gemma":[0.0007109591,0.000090906535,0.0012676623,0.00015445233,0.000016550848,0.000002706675,0.000056468496,0.49733698,0.000038004633,0.49850535,0.0017130282,0.00010692493],"about_ca_topic_score_codex":0.000051775092,"about_ca_topic_score_gemma":0.00008085148,"teacher_disagreement_score":0.49733564,"about_ca_system_score_codex":0.00005846541,"about_ca_system_score_gemma":0.00045009697,"threshold_uncertainty_score":0.80499375},"labels":[],"label_agreement":null},{"id":"W2728427291","doi":"10.1177/0962280217708671","title":"Bayesian cure rate models induced by frailty in survival analysis","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Markov chain Monte Carlo; Bayesian probability; Computer science; Bayesian inference; Poisson distribution; Inference; Markov chain; Econometrics; Statistics; Survival analysis; Mathematics; Artificial intelligence; Machine learning","score_opus":0.28525290172911694,"score_gpt":0.6164067651596781,"score_spread":0.33115386343056114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2728427291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013445036,0.00013111914,0.80683154,0.0088765705,0.00050639233,0.00080976286,0.00010797871,0.0000437013,0.16924793],"genre_scores_gemma":[0.90658486,0.00080322666,0.09138875,0.00015819413,0.00017363827,0.00015236631,0.00002139139,0.00002536053,0.000692221],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9729417,0.019277181,0.0007896897,0.00090865983,0.004491165,0.0015916028],"domain_scores_gemma":[0.9882241,0.009467587,0.00012541095,0.0009780719,0.0002934136,0.00091144047],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08047827,0.00021013296,0.0007542762,0.0008956993,0.0010445314,0.00039096564,0.0021317138,0.00047835312,0.0029526385],"category_scores_gemma":[0.05627755,0.00019541489,0.00013182558,0.0023690287,0.0029951793,0.00030148818,0.0005965769,0.0023103189,0.000028798679],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000967402,0.00040453006,0.0691125,0.000054827597,0.00018738296,0.00034551145,0.0016540647,0.000023550634,0.0000367061,0.41514623,0.0022333593,0.5107046],"study_design_scores_gemma":[0.0010621872,0.00009248781,0.38719255,0.00008589617,0.00006893896,1.1810639e-7,0.0022719768,0.06455665,0.000020471074,0.53336096,0.010850256,0.00043753718],"about_ca_topic_score_codex":0.034542352,"about_ca_topic_score_gemma":0.052971616,"teacher_disagreement_score":0.89313984,"about_ca_system_score_codex":0.00028146748,"about_ca_system_score_gemma":0.0005912736,"threshold_uncertainty_score":0.9999914},"labels":[],"label_agreement":null},{"id":"W2730038733","doi":"10.1177/0962280217713347","title":"Causality on longitudinal data: Stable specification search in constrained structural equation modeling","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; IXICO; H. Lundbeck A/S; Eisai; Servier; University of California, San Diego; University of Glasgow; Radboud Universiteit; University of Aberdeen; Newcastle University; Northern California Institute for Research and Education; Genentech; University of Dundee; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Meso Scale Diagnostics; Leids Universitair Medisch Centrum; Universiteit Leiden; Alzheimer's Disease Neuroimaging Initiative; Alzheimer's Association","keywords":"Computer science; Causal model; Causality (physics); Stability (learning theory); Structural equation modeling; Set (abstract data type); Machine learning; Artificial intelligence; Data mining; Mathematics; Statistics","score_opus":0.8721763018702403,"score_gpt":0.725111040097272,"score_spread":0.1470652617729683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2730038733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018674813,0.00001755422,0.9750437,0.0012612417,0.00009598472,0.0006444088,0.00011142308,0.00005671728,0.004094162],"genre_scores_gemma":[0.5017137,0.00004125215,0.4980161,0.00001165537,0.000078509765,0.00004686346,0.000043316388,0.000018379837,0.000030244822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99039394,0.0039410754,0.00093045284,0.000935383,0.002804046,0.0009951225],"domain_scores_gemma":[0.9763174,0.02078458,0.00011085899,0.0019989565,0.0003966534,0.00039157062],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037069913,0.00020480281,0.0005155106,0.00037053507,0.00035576217,0.00019449479,0.0016851322,0.00030596356,0.0011748847],"category_scores_gemma":[0.19838606,0.00017858909,0.000022075463,0.0003345067,0.0013188955,0.00042559206,0.0009396499,0.0026486574,0.00001654134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020995513,0.00014214613,0.0035234366,0.0001382576,0.000008603961,0.00016659027,0.00013795702,0.00007767105,0.00023791708,0.7769892,0.00012396555,0.2182443],"study_design_scores_gemma":[0.00032378876,0.000073440744,0.004868237,0.00016753342,0.0000021396004,0.0000029554378,0.00014552969,0.4574317,0.0002364794,0.53662664,0.000015897731,0.00010565585],"about_ca_topic_score_codex":0.0013518448,"about_ca_topic_score_gemma":0.0007942077,"teacher_disagreement_score":0.48303887,"about_ca_system_score_codex":0.00048671963,"about_ca_system_score_gemma":0.00057713117,"threshold_uncertainty_score":0.99973816},"labels":[],"label_agreement":null},{"id":"W2732108610","doi":"10.1177/096228020401300507","title":"Book Review: Analyzing medical data using S-PLUS","year":2004,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Data science","score_opus":0.7380944379549161,"score_gpt":0.7792716709767741,"score_spread":0.04117723302185794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2732108610","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010493999,0.09547354,0.8297169,0.06902933,0.00079969503,0.001683662,0.000088693894,0.00008060805,0.0030226174],"genre_scores_gemma":[0.0007138408,0.09738587,0.8132525,0.085468784,0.0018972231,0.00037796918,0.00020797364,0.00013326929,0.00056256744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9628647,0.02391773,0.0027041985,0.0013183766,0.006609056,0.0025859375],"domain_scores_gemma":[0.920786,0.07189865,0.00022750143,0.002500485,0.0011171218,0.0034702097],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.09176061,0.0002596697,0.0010003276,0.00041567994,0.0009845245,0.000018241297,0.002672341,0.000945659,0.07334567],"category_scores_gemma":[0.42075935,0.00021446818,0.00005291288,0.0018865546,0.0017474792,0.00021570387,0.0026282757,0.009618367,0.0009025075],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020386162,0.00029630028,0.002187629,0.00779157,0.000043731623,0.0032426238,0.0010502541,0.0000143911075,0.00004315607,0.05307409,0.31578007,0.61627233],"study_design_scores_gemma":[0.0011632585,0.00024854759,0.00042558162,0.036661603,0.000044919514,0.0000691757,0.0018847163,0.16608082,0.000058114078,0.09099461,0.70176643,0.0006022083],"about_ca_topic_score_codex":0.008296027,"about_ca_topic_score_gemma":0.0016374032,"teacher_disagreement_score":0.6156701,"about_ca_system_score_codex":0.0014816982,"about_ca_system_score_gemma":0.013245353,"threshold_uncertainty_score":0.9998754},"labels":[],"label_agreement":null},{"id":"W2736383080","doi":"10.1177/0962280217715487","title":"A model averaging approach for estimating propensity scores by optimizing balance","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Propensity score matching; Covariate; Estimator; Statistics; Statistic; Nonparametric statistics; Inverse probability weighting; Causal inference; Weighting; Mathematics; Parametric statistics; Econometrics; Parametric model; Computer science; Medicine","score_opus":0.6341758442076512,"score_gpt":0.6615234680562492,"score_spread":0.027347623848598013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736383080","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035327458,0.000033610737,0.9924604,0.00049997336,0.000050894192,0.0010778897,0.000052417312,0.000111248366,0.0053602606],"genre_scores_gemma":[0.017504288,0.00002407518,0.9814073,0.000065579676,0.00008474324,0.00066689996,0.00001334929,0.00005256352,0.00018119643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946545,0.0013163198,0.00063937856,0.00071343506,0.0015928472,0.0010835212],"domain_scores_gemma":[0.9793472,0.018786494,0.00016044654,0.00087774376,0.00037438778,0.00045369443],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023979614,0.0002216665,0.00064659293,0.0001378345,0.0007130911,0.00022090442,0.0012538871,0.00026138133,0.00009934621],"category_scores_gemma":[0.275305,0.00018487421,0.00004872867,0.00014051785,0.0013248691,0.00023888619,0.0008317298,0.0017680168,0.0000020042005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015264173,0.00031987473,0.00027198705,0.0009404214,0.000021031794,0.00005272885,0.0003109914,0.00018647654,0.002425297,0.49550655,0.0067507713,0.49306124],"study_design_scores_gemma":[0.00024979052,0.000049685703,0.000014255468,0.00019022085,0.0000036723163,0.0000032342236,0.000026746055,0.53251565,0.0010523597,0.46575817,0.000023002216,0.000113213835],"about_ca_topic_score_codex":0.00007520004,"about_ca_topic_score_gemma":0.000007006952,"teacher_disagreement_score":0.5323292,"about_ca_system_score_codex":0.00020228105,"about_ca_system_score_gemma":0.00033303222,"threshold_uncertainty_score":0.83109033},"labels":[],"label_agreement":null},{"id":"W2745473302","doi":"10.1177/0962280217726800","title":"Adjustment for time-dependent unmeasured confounders in marginal structural Cox models using validation sample data","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Marginal structural model; Confounding; Proportional hazards model; Econometrics; Statistics; Computer science; Sample (material); Sample size determination; Marginal model; Mathematics; Regression analysis; Chemistry","score_opus":0.7887223164067655,"score_gpt":0.7025856314109221,"score_spread":0.08613668499584337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745473302","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013341077,0.000034942834,0.9958562,0.00048060936,0.000121770514,0.001195082,0.00043495104,0.00004370285,0.0004986366],"genre_scores_gemma":[0.041396085,0.00003835414,0.95810723,0.000030734114,0.00009234984,0.00013623717,0.00011585908,0.00003966997,0.000043473403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992838,0.0025542376,0.00076915027,0.00072124915,0.0022133817,0.0009039678],"domain_scores_gemma":[0.9665323,0.031121159,0.00016318019,0.0014608549,0.00035100576,0.00037149747],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023965633,0.00020663781,0.00055256067,0.00025356954,0.00029107984,0.00014342742,0.0016207737,0.00028557447,0.00087968993],"category_scores_gemma":[0.18204321,0.00018392285,0.000029202141,0.00015184625,0.000986216,0.000421568,0.0010042031,0.0011657034,0.0000033551519],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043802,0.00016207034,0.00018648934,0.00032299297,0.000033372384,0.00007213123,0.00018797394,0.00008392632,0.0013603524,0.6514244,0.0006450306,0.3450832],"study_design_scores_gemma":[0.0005929835,0.00007861937,0.00015401724,0.00013948957,0.000008984491,0.0000042980914,0.00008315883,0.39833486,0.00046233792,0.5999788,0.00004546412,0.000116996554],"about_ca_topic_score_codex":0.00091668445,"about_ca_topic_score_gemma":0.00032029717,"teacher_disagreement_score":0.39825094,"about_ca_system_score_codex":0.00060135295,"about_ca_system_score_gemma":0.0006588727,"threshold_uncertainty_score":0.9631988},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6773318042169131,"score_gpt":0.6953959658900677,"score_spread":0.01806416167315461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749556736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081217947,0.000031795324,0.98703885,0.0013809869,0.00032461187,0.0007351151,0.0003529374,0.000030561463,0.009292979],"genre_scores_gemma":[0.017974984,0.00003795197,0.9811468,0.00003389324,0.00026384005,0.00019941747,0.000021303002,0.000053018037,0.000268759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.990856,0.0033144208,0.0007236952,0.0010153555,0.002776684,0.0013138585],"domain_scores_gemma":[0.88131344,0.11465413,0.00013689455,0.0025594728,0.0004782385,0.0008577947],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042711075,0.00023439276,0.00070380134,0.00015768685,0.00061992655,0.0002675056,0.0029069092,0.00025915937,0.0013470066],"category_scores_gemma":[0.5166262,0.00016642742,0.00003126006,0.00017099838,0.0016333354,0.00014227044,0.0015866763,0.0015189259,0.000015348987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020295537,0.000117312615,0.0018671671,0.00019313417,0.000019765475,0.00015478306,0.000029372704,9.407604e-8,0.000018972669,0.5327839,0.0006892779,0.46392322],"study_design_scores_gemma":[0.0014007523,0.00037984195,0.016095845,0.00031806054,0.000022680775,0.000012499691,0.000108689215,0.04231053,0.0001549956,0.9365232,0.0024285591,0.00024435448],"about_ca_topic_score_codex":0.0003557405,"about_ca_topic_score_gemma":0.0011797815,"teacher_disagreement_score":0.47391507,"about_ca_system_score_codex":0.00009803521,"about_ca_system_score_gemma":0.000542514,"threshold_uncertainty_score":0.9995659},"labels":[],"label_agreement":null},{"id":"W2751885691","doi":"10.1177/0962280217729844","title":"Bayesian sensitivity analysis for unmeasured confounding in causal mediation analysis","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confounding; Bayesian probability; Causal inference; Sensitivity (control systems); Mediation; Econometrics; Causal analysis; Statistics; Causal model; Computer science; Psychology; Mathematics; Sociology","score_opus":0.4857710251652698,"score_gpt":0.6844394513291232,"score_spread":0.19866842616385338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751885691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028861796,0.000013073719,0.9939336,0.0009981956,0.000068208865,0.00062311586,0.000084383755,0.000054603715,0.0013385986],"genre_scores_gemma":[0.4575465,0.000021637516,0.54212123,0.000019773768,0.000052971507,0.00015974518,0.000026711876,0.00001586332,0.000035561006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98895186,0.00606006,0.0009507234,0.00073735736,0.0023060278,0.0009939641],"domain_scores_gemma":[0.9283943,0.06939448,0.00021365347,0.0009854826,0.0005175331,0.0004945111],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06243595,0.0002149856,0.00116923,0.0018092614,0.0003342737,0.00015524488,0.00058474473,0.00041935753,0.00071111595],"category_scores_gemma":[0.42260322,0.00019567115,0.00017569488,0.0021980554,0.0010515873,0.00018664855,0.000303789,0.0014409029,0.000003142023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025901993,0.00036832463,0.07658045,0.00022252633,0.0010244477,0.00047657036,0.00048829016,0.000062905245,0.00095672766,0.662792,0.00018955179,0.25657916],"study_design_scores_gemma":[0.0004400375,0.00007803623,0.057550233,0.000049584534,0.0002591357,0.0000011396585,0.00013613765,0.2538816,0.0005286319,0.6868278,0.000060466635,0.0001872441],"about_ca_topic_score_codex":0.00086580974,"about_ca_topic_score_gemma":0.011641164,"teacher_disagreement_score":0.45466033,"about_ca_system_score_codex":0.0005003654,"about_ca_system_score_gemma":0.0003551605,"threshold_uncertainty_score":0.9654195},"labels":[],"label_agreement":null},{"id":"W2752464292","doi":"10.1177/0962280217720947","title":"Competing risks modeling of cumulative effects of time-varying drug exposures","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Hazard; Computer science; Statistics; Econometrics; Risk analysis (engineering); Medicine; Mathematics","score_opus":0.7693399576326204,"score_gpt":0.7370097003486988,"score_spread":0.03233025728392158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752464292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025094936,0.00012848097,0.9649021,0.00028424038,0.00039396196,0.00092256046,0.00007337731,0.000031641706,0.00816868],"genre_scores_gemma":[0.2577915,0.00008241385,0.74183017,0.000016711609,0.000151111,0.000040253602,0.000001185927,0.000047923942,0.000038729973],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96474546,0.025665559,0.0031539965,0.00090584287,0.004333894,0.0011952689],"domain_scores_gemma":[0.4376161,0.5591952,0.0006047667,0.0012374625,0.00075537123,0.00059109053],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.087793246,0.00031252857,0.0020566215,0.00037470364,0.00034692924,0.00006260649,0.0017970235,0.00045933053,0.0014083947],"category_scores_gemma":[0.91993684,0.00025885552,0.00018487657,0.0003969546,0.0033269392,0.00010474653,0.001381592,0.002552289,0.000014894545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009583378,0.0011407795,0.0022298037,0.0045626718,0.00022401674,0.00038634875,0.0013654429,0.00013404229,0.0020673897,0.34327474,0.00042400716,0.6432324],"study_design_scores_gemma":[0.0013244897,0.00022267403,0.0007955291,0.002070523,0.000042352687,0.0000019242614,0.000107278094,0.24750398,0.004067642,0.7436844,0.0000050475946,0.00017412326],"about_ca_topic_score_codex":0.0005612015,"about_ca_topic_score_gemma":0.000011039991,"teacher_disagreement_score":0.8321436,"about_ca_system_score_codex":0.00010032963,"about_ca_system_score_gemma":0.0004092146,"threshold_uncertainty_score":0.99998635},"labels":[],"label_agreement":null},{"id":"W2756553568","doi":"10.1177/0962280217729573","title":"Joint modeling of longitudinal and survival data with a covariate subject to a limit of detection","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Estimator; Confidence interval; Mathematics; Weibull distribution; Missing data; Econometrics; Computer science","score_opus":0.5664562877201138,"score_gpt":0.6143606527333666,"score_spread":0.04790436501325279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756553568","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074623753,0.000022726626,0.99026114,0.00038815377,0.00007716027,0.00035498635,0.00015786449,0.000008812928,0.0012667615],"genre_scores_gemma":[0.3115102,0.000030392155,0.68837714,0.000005330949,0.000033722532,0.000020319027,0.0000019047111,0.0000157399,0.0000052640426],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930701,0.0030489373,0.00081841415,0.00064011774,0.0018601146,0.00056227675],"domain_scores_gemma":[0.9712778,0.026283674,0.00015260068,0.0012910477,0.00048515465,0.0005097418],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029257674,0.00016174222,0.0007982705,0.0002532384,0.00017576426,0.0000653819,0.00089616346,0.00016804291,0.00029382712],"category_scores_gemma":[0.2825097,0.00011829081,0.000021456914,0.00030724466,0.0012064306,0.00009372463,0.0011823995,0.0009277006,0.0000016200132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059410185,0.00017186117,0.00096354773,0.0005870875,0.000040672596,0.00009831345,0.00014831031,0.0000014287544,0.0008258386,0.41213754,0.000016906983,0.5844144],"study_design_scores_gemma":[0.0006753402,0.00069903524,0.012755966,0.0006140952,0.000032072945,0.000014358322,0.00013022842,0.25320518,0.00083912397,0.7308849,0.000011333024,0.0001383753],"about_ca_topic_score_codex":0.0013462484,"about_ca_topic_score_gemma":0.0006802782,"teacher_disagreement_score":0.584276,"about_ca_system_score_codex":0.000039602193,"about_ca_system_score_gemma":0.0003406228,"threshold_uncertainty_score":0.9995835},"labels":[],"label_agreement":null},{"id":"W2762807097","doi":"10.1177/0962280217732597","title":"A hierarchical modeling approach for assessing the safety of exposure to complex antiretroviral drug regimens during pregnancy","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Public Health Agency of Canada; National Institutes of Health; Tulane University","keywords":"Antiretroviral drug; Pregnancy; Confounding; Medicine; Drug; Human immunodeficiency virus (HIV); Drug class; Intensive care medicine; ANTIRETROVIRAL AGENTS; Antiretroviral therapy; Obstetrics; Pharmacology; Viral load; Immunology; Internal medicine; Biology","score_opus":0.22655852030302848,"score_gpt":0.5795414981409522,"score_spread":0.35298297783792376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762807097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01820211,0.00019461155,0.96171194,0.0055939634,0.00004221926,0.0016340916,0.00013321624,0.000018486517,0.012469377],"genre_scores_gemma":[0.48657548,0.000059840753,0.5114596,0.000026256248,0.00013418443,0.00023973793,0.000028228274,0.000027470098,0.0014491807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916874,0.0030867395,0.00091002457,0.0006220411,0.002519218,0.0011745574],"domain_scores_gemma":[0.9904883,0.006702845,0.00008531327,0.0011038347,0.00061354216,0.0010061609],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0141044995,0.00018263022,0.00068769476,0.0003742489,0.0009779216,0.00015580651,0.0010574685,0.00018400623,0.0006162554],"category_scores_gemma":[0.12027737,0.00012207986,0.00018887993,0.00038480107,0.0016522065,0.0001253998,0.000804371,0.0021881484,0.0000052478304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019303736,0.0011909367,0.0052978816,0.0028089855,0.00014531585,0.00029553348,0.001197934,0.000058573347,0.00868468,0.055304416,0.00379302,0.91929233],"study_design_scores_gemma":[0.0046670204,0.003343745,0.03691372,0.0042881286,0.000046517547,0.00006612431,0.0016866308,0.93001115,0.00075615366,0.017251961,0.0006931482,0.00027569584],"about_ca_topic_score_codex":0.00027059802,"about_ca_topic_score_gemma":0.000025574349,"teacher_disagreement_score":0.92995256,"about_ca_system_score_codex":0.00016096867,"about_ca_system_score_gemma":0.00062851043,"threshold_uncertainty_score":0.95065373},"labels":[],"label_agreement":null},{"id":"W2762940523","doi":"10.1177/0962280217734969","title":"Cure rate modelling","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Manufacturing Process and Optimization","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Statistics; Mathematics","score_opus":0.183779304838902,"score_gpt":0.5401490284692693,"score_spread":0.35636972363036723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762940523","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005503501,0.0001296975,0.9790878,0.00052686094,0.00022068502,0.00010227141,0.0000064318365,0.000051716077,0.019324156],"genre_scores_gemma":[0.17006026,0.0008616381,0.8285921,0.000026031976,0.0001397226,0.000042657088,0.000005526636,0.000029996987,0.00024205806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977969,0.00050195673,0.00024834162,0.00022538021,0.00072759535,0.0004998173],"domain_scores_gemma":[0.99669755,0.0025437018,0.000014962272,0.00035988406,0.00007763027,0.0003062722],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0075508635,0.00009388453,0.00019058635,0.00012386989,0.00023482608,0.00014541876,0.00052991556,0.00017121427,0.0017016205],"category_scores_gemma":[0.0101137655,0.00008094904,0.000016262347,0.000093566494,0.00030866952,0.00008867207,0.00014379926,0.0011306858,0.000036888658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024020588,0.000030495608,0.00011633492,0.0003349829,0.000011176128,0.00015068112,0.0001411348,0.07552016,0.000036518937,0.045134883,0.0011897716,0.87730986],"study_design_scores_gemma":[0.00019260873,0.000015409867,0.00083977776,0.00008284467,0.0000014885139,8.457984e-7,0.000014070894,0.9205546,0.0005374863,0.07206517,0.005608529,0.000087212255],"about_ca_topic_score_codex":0.000076368524,"about_ca_topic_score_gemma":0.000014621399,"teacher_disagreement_score":0.87722266,"about_ca_system_score_codex":0.000050827388,"about_ca_system_score_gemma":0.00006705469,"threshold_uncertainty_score":0.99921095},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.5151171744634669,"score_gpt":0.6288287204909679,"score_spread":0.113711546027501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770711354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016521399,0.000050785944,0.99146265,0.0015937063,0.00037678698,0.0015594829,0.0006962534,0.00005626072,0.004038847],"genre_scores_gemma":[0.013556318,0.000044854005,0.9853024,0.000042857253,0.00029159102,0.0003934043,0.000069537105,0.000078016186,0.00022104612],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9856184,0.007046818,0.0012752436,0.0015115264,0.0028309687,0.0017170445],"domain_scores_gemma":[0.8881384,0.106839046,0.00019205695,0.003123953,0.00045077933,0.001255748],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.060506452,0.00040039918,0.0013487642,0.000279968,0.00074753666,0.00036979397,0.0029823282,0.0004961239,0.0028686917],"category_scores_gemma":[0.48381826,0.00030403046,0.00011251603,0.00023375913,0.002193979,0.0002649884,0.0022174604,0.0019636536,0.00007902505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024170394,0.00024485012,0.0003202807,0.00045457637,0.000054162174,0.00021783868,0.00003365071,4.6222115e-7,0.00012133931,0.4142254,0.005189246,0.57889646],"study_design_scores_gemma":[0.0009497844,0.00033601344,0.002704668,0.00028977304,0.000040052488,0.000011966002,0.000008418804,0.4096709,0.00020252625,0.58534133,0.00023067041,0.00021391173],"about_ca_topic_score_codex":0.00024781268,"about_ca_topic_score_gemma":0.00007286959,"teacher_disagreement_score":0.57868254,"about_ca_system_score_codex":0.00017138672,"about_ca_system_score_gemma":0.00047487102,"threshold_uncertainty_score":0.9999412},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.738761936625469,"score_gpt":0.7244365658423263,"score_spread":0.014325370783142666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772202324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041908356,0.000033086922,0.9923211,0.0012334622,0.00003273234,0.00054178823,0.000012795879,0.000056156325,0.0015780808],"genre_scores_gemma":[0.1815319,0.000045166045,0.8180809,0.00003682825,0.0000115949615,0.00023464521,0.0000032018368,0.000022819439,0.00003292802],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9873966,0.0070550577,0.0009058359,0.0007208243,0.0030688446,0.00085285696],"domain_scores_gemma":[0.9535067,0.044036295,0.00021161723,0.0011235991,0.00056142133,0.00056037604],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057110183,0.0002661473,0.0009997903,0.000911619,0.00024156258,0.00016862762,0.0007505812,0.00029418495,0.00056839385],"category_scores_gemma":[0.42858076,0.00018881277,0.000044256136,0.00093131757,0.0016647476,0.00023013307,0.00054780475,0.0018328062,0.0000040731557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009716386,0.00022295461,0.042652145,0.0001831349,0.000121276804,0.00020774012,0.00032795157,0.00000704873,0.0001528375,0.23466107,0.00003646065,0.7213302],"study_design_scores_gemma":[0.00056447426,0.00023930965,0.157762,0.00030087674,0.0000759594,0.0000036379047,0.00015344055,0.05635436,0.00070061185,0.7835747,0.000045621167,0.0002250059],"about_ca_topic_score_codex":0.0011259973,"about_ca_topic_score_gemma":0.003859657,"teacher_disagreement_score":0.7211052,"about_ca_system_score_codex":0.00036783566,"about_ca_system_score_gemma":0.00046705056,"threshold_uncertainty_score":0.9709035},"labels":[],"label_agreement":null},{"id":"W2790635366","doi":"10.1177/0962280218759693","title":"MethodCompare: An R package to assess bias and precision in method comparison studies","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Data Analysis with R","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"R package; Statistics; Computer science; Econometrics; Mathematics","score_opus":0.6339406249091168,"score_gpt":0.7103905885533488,"score_spread":0.07644996364423196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790635366","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024855002,0.0002520028,0.99345225,0.0020470775,0.0002579976,0.00040677591,0.00001624611,0.00006351718,0.0010186365],"genre_scores_gemma":[0.026427299,0.000058861828,0.97293353,0.0002947076,0.00012680085,0.00010204426,0.000006379281,0.000019249272,0.000031140553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95779604,0.034547023,0.0012204518,0.001624818,0.0035496582,0.0012620284],"domain_scores_gemma":[0.91487664,0.0809546,0.00010064157,0.0016651326,0.0008012134,0.001601794],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10690925,0.0002612404,0.0010958649,0.0013309444,0.00020907652,0.0002937022,0.0024335475,0.00022200114,0.0002004412],"category_scores_gemma":[0.15065375,0.00020424544,0.00003442837,0.004157698,0.0010593918,0.00042959806,0.0030314112,0.0016304331,0.000071012706],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007033278,0.0001919693,0.0019971523,0.00005069814,0.000023043278,0.00018273715,0.0017784993,0.000004067343,0.00032276986,0.14047898,0.0016766079,0.85322315],"study_design_scores_gemma":[0.0009697363,0.0013376981,0.041671462,0.00038957354,0.000015837391,0.00002442021,0.0028758778,0.78679156,0.0032450561,0.15507211,0.0071498957,0.00045678962],"about_ca_topic_score_codex":0.00044976946,"about_ca_topic_score_gemma":0.0011362993,"teacher_disagreement_score":0.85276634,"about_ca_system_score_codex":0.0002892134,"about_ca_system_score_gemma":0.0003439522,"threshold_uncertainty_score":0.91962487},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.7850233477568593,"score_gpt":0.6838532647255835,"score_spread":0.10117008303127584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792390571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045869797,0.000044284265,0.9510462,0.00062719657,0.000079044796,0.0008735818,0.0000137432025,0.00009631469,0.0013497893],"genre_scores_gemma":[0.044231758,0.000024635528,0.95511323,0.0002011067,0.00013362247,0.00011906843,0.0000027932638,0.000047225356,0.00012657771],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98669344,0.008907622,0.000686778,0.00059969834,0.0021610386,0.00095140265],"domain_scores_gemma":[0.95751595,0.04011943,0.00016988232,0.0006620935,0.0011774623,0.00035516938],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023325764,0.00024406968,0.0007010302,0.00016748857,0.00040078888,0.00021655952,0.0007234432,0.00022132957,0.0016030701],"category_scores_gemma":[0.13289842,0.00012531278,0.000028813449,0.000777058,0.0040533924,0.00024263108,0.00044692622,0.0017020339,0.000007986716],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014349945,0.00026600627,0.0021354528,0.00021412023,0.00007240154,0.0006319301,0.001790146,0.0000012282826,0.006442675,0.8662613,0.0014494115,0.11930033],"study_design_scores_gemma":[0.0007966979,0.0010565997,0.0017278196,0.00084149296,0.000024411642,0.000053877786,0.0008253125,0.020210242,0.005693028,0.9680012,0.00050417456,0.00026514294],"about_ca_topic_score_codex":0.00036525793,"about_ca_topic_score_gemma":0.00039976873,"teacher_disagreement_score":0.119035184,"about_ca_system_score_codex":0.0001986211,"about_ca_system_score_gemma":0.0009573112,"threshold_uncertainty_score":0.9993096},"labels":[],"label_agreement":null},{"id":"W2793641334","doi":"10.1177/0962280218757560","title":"Efficient robust doubly adaptive regularized regression with applications","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Robustness (evolution); Estimator; Computer science; Oracle; Mathematical optimization; Robust regression; Linear regression; Algorithm; Regression; Monte Carlo method; Mathematics; Statistics; Artificial intelligence; Machine learning","score_opus":0.34605395600941213,"score_gpt":0.6137930848336274,"score_spread":0.26773912882421524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793641334","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018696355,0.00005906825,0.98620975,0.0007694643,0.00008489955,0.0011738979,0.00005799825,0.000078892896,0.011379091],"genre_scores_gemma":[0.0062176175,0.000020941894,0.9921371,0.000098004144,0.0002798905,0.0007065583,0.0000074062204,0.00006406785,0.0004684275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98835295,0.0056168083,0.0008184458,0.0010100632,0.002966977,0.00123474],"domain_scores_gemma":[0.9525774,0.044571098,0.000111397276,0.00082207663,0.0008916595,0.0010263623],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018330943,0.00029645173,0.0007130574,0.00034088982,0.00040152972,0.000046755882,0.0006377642,0.00034341618,0.0022273392],"category_scores_gemma":[0.050650924,0.00019460576,0.000048888447,0.0013910922,0.0034694667,0.00003815385,0.00039979917,0.0019039558,0.000041092346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055297505,0.00029910475,0.0000053618796,0.00006741428,0.000015319756,0.00009293806,0.00013603226,0.000018724013,0.00016060205,0.6487223,0.0004728558,0.3494564],"study_design_scores_gemma":[0.0011512147,0.00064027694,0.000074865326,0.0003471481,0.000017791785,0.000020842377,0.00023361333,0.20926885,0.00035319847,0.78556764,0.0020960611,0.00022852077],"about_ca_topic_score_codex":0.000046016747,"about_ca_topic_score_gemma":0.00005439201,"teacher_disagreement_score":0.34922788,"about_ca_system_score_codex":0.00022518422,"about_ca_system_score_gemma":0.0005173771,"threshold_uncertainty_score":0.99924254},"labels":[],"label_agreement":null},{"id":"W2795636674","doi":"10.1177/0962280218766964","title":"Decoding and modelling of time series count data using Poisson hidden Markov model and Markov ordinal logistic regression models","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Vibrio bacteria research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Markov chain; Statistics; Mathematics; Markov model; Poisson distribution; Hidden Markov model; Variable-order Markov model; Markov property; Overdispersion; Markov chain Monte Carlo; Stochastic matrix; Ordinal regression; Poisson regression; Count data; Computer science; Bayesian probability; Artificial intelligence; Population; Medicine","score_opus":0.28185465909972757,"score_gpt":0.5365581696180117,"score_spread":0.25470351051828416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795636674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10448204,0.0009488341,0.8932505,0.00033417658,0.00003486788,0.00024168384,0.00021116852,0.0000057050124,0.000490966],"genre_scores_gemma":[0.1938078,0.0023337796,0.803498,0.000021766,0.00012767226,0.000011918961,0.00006310966,0.00002547267,0.00011048173],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99532944,0.001665195,0.0004641348,0.0007849623,0.001067742,0.00068851805],"domain_scores_gemma":[0.99699473,0.0015980942,0.000061052226,0.00057542976,0.00038510573,0.00038560023],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009997493,0.00019021843,0.00042506625,0.0001681529,0.00021479772,0.000053908472,0.00051487336,0.00026141334,0.00010318518],"category_scores_gemma":[0.01596706,0.00015305191,0.000017210767,0.0002154692,0.0026501217,0.000029253017,0.0027018436,0.000528595,9.803598e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004748383,0.0002629352,0.0010519747,0.0011720946,0.0002156364,0.00018532026,0.00044827288,0.00041524234,0.35588893,0.0056229094,0.0027407173,0.6272476],"study_design_scores_gemma":[0.000458703,0.00036000702,0.00014613138,0.00027015645,0.0000142533945,0.00002658918,0.000108637374,0.97415406,0.0022373453,0.021979857,0.00008930615,0.00015498025],"about_ca_topic_score_codex":0.0002024747,"about_ca_topic_score_gemma":0.000049526006,"teacher_disagreement_score":0.9737388,"about_ca_system_score_codex":0.000048233782,"about_ca_system_score_gemma":0.0004284609,"threshold_uncertainty_score":0.99232185},"labels":[],"label_agreement":null},{"id":"W2800160739","doi":"10.1177/0962280218772065","title":"Understanding and diagnosing the potential for bias when using machine learning methods with doubly robust causal estimators","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital du Sacré-Cœur de Montréal; Université de Montréal","funders":"Canadian Institutes of Health Research; Université de Montréal; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Propensity score matching; Resampling; Estimator; Causal inference; Average treatment effect; Computer science; Parametric statistics; Statistics; Econometrics; Mathematics","score_opus":0.7613136427473822,"score_gpt":0.6566960719608058,"score_spread":0.10461757078657641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800160739","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013868983,0.000091119146,0.9962102,0.0009316527,0.00009928077,0.00081364514,0.000015995654,0.000104674706,0.00034649167],"genre_scores_gemma":[0.024498826,0.000041214575,0.9749656,0.00006868248,0.0001849407,0.00012471166,0.00000475955,0.00007457764,0.000036732526],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9897584,0.006555946,0.0006215433,0.00060401374,0.0014327727,0.0010273654],"domain_scores_gemma":[0.91164154,0.08707067,0.00012957884,0.0003526115,0.00036248038,0.00044310198],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034768716,0.00026314083,0.00055109244,0.00031936722,0.0007436246,0.00016886408,0.00041906553,0.00026999996,0.00043790622],"category_scores_gemma":[0.13698238,0.00016710728,0.00003734106,0.00058514526,0.0027549688,0.00014657377,0.00045846746,0.0020166943,0.0000010258643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005015178,0.00012333601,0.0009048196,0.00033138972,0.00007600611,0.00015738524,0.0011618345,0.000065620115,0.0010793321,0.7937569,0.0004130883,0.20142879],"study_design_scores_gemma":[0.00046101422,0.0004929823,0.000045839657,0.0003022092,0.000032809814,0.00005305753,0.0005602171,0.34942973,0.0012512748,0.6469744,0.00023573393,0.0001607622],"about_ca_topic_score_codex":0.00027847776,"about_ca_topic_score_gemma":0.00019773084,"teacher_disagreement_score":0.3493641,"about_ca_system_score_codex":0.0003794815,"about_ca_system_score_gemma":0.00034351478,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W2805193208","doi":"10.1177/0962280218776690","title":"Assessing the performance of the generalized propensity score for estimating the effect of quantitative or continuous exposures on survival or 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":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Global Positioning System; Medicine; Inverse probability weighting; Observational study; Weighting; Mathematics; Computer science","score_opus":0.5441098280577505,"score_gpt":0.667460193097909,"score_spread":0.1233503650401585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805193208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33466697,0.0000058088485,0.66224414,0.00076881796,0.00010786051,0.001940268,0.000021876105,0.000020607971,0.0002236349],"genre_scores_gemma":[0.17643909,0.0000025603051,0.8228173,0.000073218485,0.0000580186,0.00035374137,0.0000010697179,0.00002783488,0.00022713422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871896,0.009243456,0.00083141844,0.00032707822,0.0018624954,0.00054595637],"domain_scores_gemma":[0.8429137,0.15556358,0.00022582525,0.00060380425,0.00057421747,0.000118915945],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038352944,0.00019850771,0.00079001783,0.00009145134,0.00032698037,0.000045021494,0.0009827438,0.00012591165,0.00043294442],"category_scores_gemma":[0.36424434,0.000067812085,0.00007687285,0.0006016751,0.0023629267,0.00006323414,0.0004973072,0.0008819289,0.0000048251754],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006368501,0.00042683413,0.0106894225,0.0019370647,0.00019850768,0.000025628593,0.0022271727,0.000051611205,0.00809509,0.1373919,0.002504097,0.83008415],"study_design_scores_gemma":[0.0037945146,0.028358817,0.041752953,0.0060007316,0.00017611559,0.000019949082,0.0009894085,0.34514013,0.2783183,0.2944035,0.00038453378,0.0006610806],"about_ca_topic_score_codex":0.000047691883,"about_ca_topic_score_gemma":0.000054249304,"teacher_disagreement_score":0.82942307,"about_ca_system_score_codex":0.000085344516,"about_ca_system_score_gemma":0.00036498162,"threshold_uncertainty_score":0.990218},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10006292289328535,"score_gpt":0.5157611724700032,"score_spread":0.41569824957671786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808600279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3570075,0.00001816056,0.64182353,0.00005357444,0.00005176611,0.00059660146,0.0001384298,0.0000055980704,0.00030487202],"genre_scores_gemma":[0.563062,0.000048473743,0.43670776,0.000005257397,0.000039378894,0.000034022207,0.00007012586,0.000006411415,0.00002657496],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951286,0.0017835209,0.00073157076,0.00046857347,0.0014369681,0.0004508145],"domain_scores_gemma":[0.98490816,0.014149241,0.00014563966,0.00015680752,0.00038646435,0.00025368182],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013829933,0.00014907667,0.0007545039,0.00062267546,0.000238816,0.00002507234,0.00017449523,0.00015650228,0.00011195497],"category_scores_gemma":[0.009605398,0.0001308639,0.000044587076,0.0011345922,0.0026215082,0.00009271249,0.00017751943,0.00042891438,1.8019209e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003285219,0.0011903406,0.4754702,0.003258426,0.0010855418,0.000029120334,0.010440898,0.012081135,0.000924356,0.07227068,0.00013105822,0.41983306],"study_design_scores_gemma":[0.0011822205,0.0001959705,0.19702291,0.00006138372,0.00008913994,3.961281e-7,0.00029605703,0.7953933,0.000026571972,0.005620405,0.000017662953,0.00009398118],"about_ca_topic_score_codex":0.0022726667,"about_ca_topic_score_gemma":0.0014791824,"teacher_disagreement_score":0.78331214,"about_ca_system_score_codex":0.000054245163,"about_ca_system_score_gemma":0.00020412968,"threshold_uncertainty_score":0.9987371},"labels":[],"label_agreement":null},{"id":"W2884046250","doi":"10.1177/0962280218786525","title":"Analysis of conversion of Alzheimer’s disease using a multi-state Markov model","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; Michigan State University","keywords":"Disease; Apolipoprotein E; Neuroimaging; Medicine; Alzheimer's disease; Alzheimer's Disease Neuroimaging Initiative; Population; Risk factor; Apolipoprotein B; Internal medicine; Psychology; Neuroscience; Cholesterol; Environmental health","score_opus":0.252798915671842,"score_gpt":0.6051278958011224,"score_spread":0.3523289801292804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884046250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20083286,0.00019275706,0.79712653,0.00025026285,0.00003164135,0.00047311344,0.0001237215,0.0000072928565,0.00096183096],"genre_scores_gemma":[0.58398235,0.00010085766,0.41565922,0.000063775326,0.000019340754,0.000017083295,0.000024024519,0.000013099875,0.00012022768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922001,0.0026923593,0.00075083313,0.00046773232,0.003186581,0.00070241804],"domain_scores_gemma":[0.9932171,0.003902598,0.00007908735,0.0003928583,0.0013200736,0.0010883013],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013583695,0.00013529796,0.00072802574,0.0014582165,0.000068454814,0.000009358573,0.00024837782,0.00011751504,0.0052990336],"category_scores_gemma":[0.02450325,0.00010856379,0.00014665254,0.0025262916,0.0028125243,0.000046638143,0.00037651113,0.00071031344,0.000009328693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0072333766,0.0038531448,0.3519245,0.0014611164,0.0026357544,0.0009085514,0.0007349226,0.00003517607,0.021354388,0.001794117,0.00032820195,0.6077367],"study_design_scores_gemma":[0.0014711306,0.00044736394,0.21882756,0.00019962664,0.0006708144,0.0000013058891,0.00012659228,0.7715789,0.0052759675,0.0012932799,0.00003123952,0.00007619477],"about_ca_topic_score_codex":0.00032937806,"about_ca_topic_score_gemma":0.000014683548,"teacher_disagreement_score":0.77154374,"about_ca_system_score_codex":0.00008797508,"about_ca_system_score_gemma":0.0012351964,"threshold_uncertainty_score":0.99990124},"labels":[],"label_agreement":null},{"id":"W2884668939","doi":"10.1177/0962280218786980","title":"Joint modelling for organ transplantation outcomes for patients with diabetes and the end-stage renal disease","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Renal Transplantation Outcomes and Treatments","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Renal function; Proportional hazards model; Kidney transplantation; End stage renal disease; Transplantation; Internal medicine; Disease; Intensive care medicine","score_opus":0.14855449154126799,"score_gpt":0.4956272917796851,"score_spread":0.34707280023841713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884668939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05217159,0.00004076599,0.94281334,0.0023553034,0.00005542263,0.001933176,0.00049159536,0.00001275709,0.00012604748],"genre_scores_gemma":[0.39925304,0.000113804155,0.5991088,0.0003487969,0.00007484578,0.0005629031,0.00029669667,0.00002966926,0.00021141747],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969957,0.0006893928,0.00039050783,0.0003556615,0.0010399692,0.00052878406],"domain_scores_gemma":[0.9844061,0.014565337,0.000038136994,0.0001673558,0.0003400677,0.0004830051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045487373,0.00014529486,0.0004070803,0.00014022857,0.00022893814,0.00003323622,0.00009380794,0.000077827426,0.00025995745],"category_scores_gemma":[0.0048038294,0.00007317515,0.00005655807,0.00018340572,0.0011856513,0.000044267606,0.000019517589,0.00029989137,0.0000021353096],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.042842276,0.0016462746,0.38059756,0.005861808,0.00076350104,0.00017911216,0.002458188,0.000032654138,0.00007553341,0.25311607,0.0001286183,0.31229842],"study_design_scores_gemma":[0.07026022,0.0043110154,0.60160965,0.001846748,0.0007003454,0.0000043459295,0.00021463844,0.21992691,0.00078537985,0.09889823,0.0010226293,0.0004199024],"about_ca_topic_score_codex":0.000027006969,"about_ca_topic_score_gemma":0.000016502523,"teacher_disagreement_score":0.34708145,"about_ca_system_score_codex":0.000045217403,"about_ca_system_score_gemma":0.00019486315,"threshold_uncertainty_score":0.5750979},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8985570285078743,"score_gpt":0.7640029906638991,"score_spread":0.13455403784397524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888226965","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020928404,0.00035314896,0.97986263,0.0011691077,0.0017653868,0.0007323119,0.000020159545,0.00006865517,0.013935788],"genre_scores_gemma":[0.016873172,0.000021535663,0.9816599,0.00042004586,0.00042369694,0.00021467308,0.0000035403139,0.000036928603,0.00034654545],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94885397,0.036030002,0.0034519536,0.0018003222,0.007858512,0.0020052395],"domain_scores_gemma":[0.14406781,0.84874594,0.0004109763,0.0016308691,0.003645804,0.0014985864],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32825193,0.00028602633,0.001169978,0.0019171911,0.00053358544,0.00030291808,0.0021462305,0.0004716288,0.0049690767],"category_scores_gemma":[0.96920043,0.00019259013,0.00018062095,0.0066023236,0.0023593027,0.00014178432,0.00095781806,0.0018387709,0.00006134739],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001910056,0.00009392485,0.013021754,0.000015291651,0.000025751819,0.000065267675,0.00020132777,7.63793e-7,0.0004984044,0.015123013,0.003951239,0.96681225],"study_design_scores_gemma":[0.0008773163,0.0010505043,0.026300084,0.00006933623,0.000015545022,0.00004393475,0.0012549591,0.06631203,0.0011010166,0.7799944,0.122650385,0.00033048607],"about_ca_topic_score_codex":0.00015250932,"about_ca_topic_score_gemma":0.000031408283,"teacher_disagreement_score":0.96648175,"about_ca_system_score_codex":0.00015644051,"about_ca_system_score_gemma":0.0005487871,"threshold_uncertainty_score":0.9959405},"labels":[],"label_agreement":null},{"id":"W2890155095","doi":"10.1177/0962280218797145","title":"Eliminating systematic bias from case-crossover designs","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Government of Alberta; Alberta Health Services","funders":"Health Research Board","keywords":"Crossover; Statistics; Confounding; Calibration; Crossover study; Computer science; Econometrics; Confidence interval; Meta-analysis; Publication bias; Medicine; Mathematics","score_opus":0.7550744409644745,"score_gpt":0.7229459907852953,"score_spread":0.0321284501791792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890155095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008436683,0.00041198402,0.97363675,0.00047123808,0.0007372853,0.0008995623,0.00006567203,0.000048812137,0.01529202],"genre_scores_gemma":[0.16646382,0.000009323682,0.8321209,0.0002874515,0.00034411182,0.00016070138,0.0000030549681,0.000041093106,0.00056953897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9206273,0.06157307,0.0027594515,0.0016682474,0.011723217,0.0016487059],"domain_scores_gemma":[0.62481576,0.3704985,0.0002550768,0.0015137399,0.0014661757,0.0014507273],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.19606236,0.00032665124,0.0012660925,0.0009191419,0.00053759286,0.0006885874,0.002219333,0.0004846388,0.02719697],"category_scores_gemma":[0.72692835,0.00022623158,0.00012478503,0.003496544,0.0038160635,0.00027344722,0.0012592258,0.0019897828,0.0019376832],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049600267,0.0005061928,0.0007454312,0.0006701403,0.00006680835,0.014514359,0.0040727607,0.0000027218932,0.008685268,0.08475431,0.0068907244,0.8785953],"study_design_scores_gemma":[0.001633283,0.0012723422,0.0016419713,0.002499367,0.00003041674,0.0007567715,0.01073465,0.24139817,0.013873408,0.72443175,0.0010760506,0.00065178605],"about_ca_topic_score_codex":0.0010942464,"about_ca_topic_score_gemma":0.0001475893,"teacher_disagreement_score":0.8779435,"about_ca_system_score_codex":0.00035942261,"about_ca_system_score_gemma":0.00060386705,"threshold_uncertainty_score":0.998895},"labels":[],"label_agreement":null},{"id":"W2891506233","doi":"10.1177/0962280218799540","title":"A review and empirical comparison of causal inference methods for clustered observational data with application to the evaluation of the effectiveness of medical devices","year":2018,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Observational study; Causal inference; Propensity score matching; Confounding; Matching (statistics); Cluster analysis; Metric (unit); Variance (accounting); Computer science; Statistics; Econometrics; Inference; Cluster (spacecraft); Data mining; Medicine; Mathematics; Artificial intelligence; Engineering; Operations management","score_opus":0.885421416171426,"score_gpt":0.8016456215590271,"score_spread":0.08377579461239892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891506233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020532282,0.34037727,0.65415967,0.00040820253,0.000027977641,0.0047738883,0.00021125171,0.000007176955,0.000032489803],"genre_scores_gemma":[0.00004169108,0.2906206,0.707092,0.000051249313,0.000039323077,0.0020206755,0.00010347081,0.000029730312,0.0000012984175],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.931025,0.05828843,0.0028957578,0.0010394359,0.0062065725,0.00054475776],"domain_scores_gemma":[0.6632987,0.33007997,0.0010150395,0.0022110855,0.003055612,0.0003395433],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19764741,0.00031053487,0.0026848451,0.00020116224,0.00008622992,0.000014279586,0.0028348344,0.00055063365,0.00014117043],"category_scores_gemma":[0.48234946,0.00015444818,0.00008946415,0.0016358588,0.0021560856,0.00006810754,0.0019176847,0.0014920288,5.868196e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006646064,0.00016812743,0.000052297768,0.073627174,0.00008485366,1.8373612e-7,0.000052326697,2.519608e-7,0.0000017577593,0.04547108,0.0005554103,0.87992007],"study_design_scores_gemma":[0.0009388491,0.001299932,0.0009468764,0.21256244,0.0030347402,0.000020055966,0.00009957981,0.05065166,0.00012820763,0.56621045,0.16359504,0.00051218556],"about_ca_topic_score_codex":0.00007506337,"about_ca_topic_score_gemma":0.0002312227,"teacher_disagreement_score":0.8794079,"about_ca_system_score_codex":0.00017614898,"about_ca_system_score_gemma":0.0036729018,"threshold_uncertainty_score":0.8261908},"labels":[],"label_agreement":null},{"id":"W2896073293","doi":"10.1177/0962280218804275","title":"Benefits of combining prevalent and incident cohorts: An application to myotonic dystrophy","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Genetic Neurodegenerative Diseases","field":"Neuroscience","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Cohort; Myotonic dystrophy; Medicine; Cohort study; Disease; Demography; Sample size determination; Pediatrics; Internal medicine; Statistics","score_opus":0.14378130381616575,"score_gpt":0.5384049972434336,"score_spread":0.3946236934272679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896073293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70319706,0.000045193512,0.29517844,0.00037344746,0.00007329624,0.0006462771,0.000048873128,0.000013563771,0.000423855],"genre_scores_gemma":[0.8392765,0.00007300967,0.16005519,0.0002945591,0.000068369896,0.00019662987,0.0000026173266,0.000017620403,0.000015539405],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99157566,0.0046122978,0.0004920671,0.0007992187,0.0019777208,0.0005430226],"domain_scores_gemma":[0.9913328,0.0070229624,0.00005052282,0.0004407321,0.0002846378,0.000868291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005407569,0.0001281877,0.00029638605,0.00026985983,0.00013334968,0.000037021073,0.00050180644,0.000086686734,0.00045152794],"category_scores_gemma":[0.05710501,0.00011343595,0.000016272848,0.0007394425,0.0015250995,0.000049809485,0.00049215916,0.00046094225,0.000024844281],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024993962,0.00048612244,0.0038725748,0.000126688,0.0000035516362,0.000021457827,0.0005359106,0.000029578323,0.27443892,0.11289229,0.00011839506,0.6072246],"study_design_scores_gemma":[0.00072704465,0.0027561907,0.27062887,0.00015685445,0.00001128352,0.000012264985,0.00014543612,0.019917628,0.67100644,0.034023553,0.00038584578,0.00022859694],"about_ca_topic_score_codex":0.000068431924,"about_ca_topic_score_gemma":0.00003557445,"teacher_disagreement_score":0.60699594,"about_ca_system_score_codex":0.00006012538,"about_ca_system_score_gemma":0.00022629219,"threshold_uncertainty_score":0.9508374},"labels":[],"label_agreement":null},{"id":"W2896304424","doi":"10.1177/0962280218804569","title":"Identifying treatment responders using counterfactual modeling and potential outcomes","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Covariate; Observational study; Counterfactual thinking; Multinomial distribution; Computer science; Statistics; Outcome (game theory); Econometrics; Medicine; Selection bias; Machine learning; Mathematics; Psychology","score_opus":0.5780682473959962,"score_gpt":0.6666451500665824,"score_spread":0.08857690267058627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896304424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090131566,0.000060175003,0.90786886,0.0003314739,0.00026620863,0.0003263923,0.000038432972,0.000032997847,0.00094391813],"genre_scores_gemma":[0.21410072,0.00005973283,0.7854883,0.000068565554,0.00014401691,0.00002733131,0.0000015794078,0.000032455686,0.00007726016],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9901416,0.0052755964,0.00084513024,0.00070999423,0.001978014,0.0010497026],"domain_scores_gemma":[0.9661188,0.03233733,0.00005817183,0.00040460855,0.0003643335,0.00071672513],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01590601,0.00026365893,0.0007134129,0.00039819858,0.00033245859,0.00013932402,0.00034001507,0.00028450607,0.0028516843],"category_scores_gemma":[0.100320764,0.00019661406,0.000051674342,0.0004601323,0.001697878,0.00008112234,0.00036673716,0.0009286863,0.000020589494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003006461,0.00025010193,0.0004488522,0.00012759304,0.00006437508,0.00030367437,0.0011622801,0.0000033997908,0.0012688603,0.37997434,0.000081506,0.61601436],"study_design_scores_gemma":[0.00064092985,0.00034467722,0.0006473117,0.00012330757,0.000021772656,0.000021670689,0.0004488425,0.39211494,0.00019353238,0.6052312,0.000060178732,0.0001515826],"about_ca_topic_score_codex":0.00047867547,"about_ca_topic_score_gemma":0.000054100616,"teacher_disagreement_score":0.6158628,"about_ca_system_score_codex":0.00029603764,"about_ca_system_score_gemma":0.0004257739,"threshold_uncertainty_score":0.99805987},"labels":[],"label_agreement":null},{"id":"W2898839296","doi":"10.1177/0962280218808817","title":"Causal inference with multiple concurrent medications: A comparison of methods and an application in multidrug-resistant tuberculosis","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Université de Montréal; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Causal inference; Propensity score matching; Marginal structural model; Inverse probability weighting; Estimation; Statistics; Econometrics; Outcome (game theory); Inference; Tuberculosis; Weighting; Medicine; Counterfactual thinking; Parametric statistics; Computer science; Intensive care medicine; Mathematics; Artificial intelligence; Psychology","score_opus":0.3771174340888153,"score_gpt":0.6903954447855432,"score_spread":0.31327801069672784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898839296","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018092023,0.00013534275,0.9800333,0.00030056725,0.000029715753,0.0008981311,0.000038145947,0.0000596842,0.0004131322],"genre_scores_gemma":[0.41593435,0.000073146795,0.5835443,0.000014497447,0.000028341407,0.00037269216,0.000011181647,0.000018605226,0.0000028737695],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894316,0.0065463483,0.0011904965,0.000700864,0.0014673166,0.00066334236],"domain_scores_gemma":[0.9419184,0.05596073,0.0001893574,0.0006573624,0.0007005227,0.0005736407],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.019298658,0.00022601185,0.0007739183,0.000497671,0.00010077168,0.000024792787,0.0005200611,0.00029978386,0.00026097958],"category_scores_gemma":[0.095859975,0.00017676252,0.000019015977,0.0011381223,0.0034203692,0.0001418358,0.00031069736,0.0014377756,0.0000029406738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016571152,0.0006955365,0.008433528,0.00024126227,0.00001709067,0.000008940163,0.001326842,6.415226e-7,0.006163781,0.30734468,0.000049241782,0.6755527],"study_design_scores_gemma":[0.0014004301,0.0017934787,0.01995386,0.00082209276,0.000031654323,0.000006580486,0.0019136023,0.27457604,0.020779165,0.67784786,0.0005048695,0.00037035774],"about_ca_topic_score_codex":0.00097600045,"about_ca_topic_score_gemma":0.0033903243,"teacher_disagreement_score":0.6751824,"about_ca_system_score_codex":0.00019333453,"about_ca_system_score_gemma":0.00040401903,"threshold_uncertainty_score":0.9992918},"labels":[],"label_agreement":null},{"id":"W2904833574","doi":"10.1177/0962280218815301","title":"Shape invariant mixture model for clustering non-linear longitudinal growth trajectories","year":2018,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Markov chain Monte Carlo; Mixture model; Computer science; Invariant (physics); Bayesian probability; Bayesian inference; Linear model; Longitudinal data; Inference; Mathematics; Econometrics; Applied mathematics; Data mining; Artificial intelligence; Machine learning","score_opus":0.16600573259292056,"score_gpt":0.5160146234251991,"score_spread":0.35000889083227854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904833574","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000914116,0.00007499463,0.9937416,0.0029344885,0.0005040841,0.0005757827,0.000031570642,0.00006149254,0.0019845907],"genre_scores_gemma":[0.019625023,0.00004633745,0.978763,0.00046540983,0.00065308565,0.00019737915,0.0000052877285,0.000034845456,0.00020962425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923981,0.0024796664,0.00070268445,0.0011329758,0.0018769868,0.0014095927],"domain_scores_gemma":[0.9855357,0.01198398,0.000059860013,0.00071210053,0.00080979633,0.0008986081],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024472091,0.0002762807,0.00059196155,0.00037466036,0.00035881315,0.00015710822,0.0019572866,0.0004338096,0.0002825099],"category_scores_gemma":[0.031338636,0.00022153999,0.00008913905,0.0011528579,0.0011308646,0.00025302116,0.0009989974,0.0015553777,0.000018023367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012574407,0.00011195347,0.000036834917,0.00014879183,0.000017260792,0.00010240684,0.0008188067,0.0000058216633,0.0004634211,0.50663,0.0015145615,0.4900244],"study_design_scores_gemma":[0.00044678044,0.00027982309,0.0002430728,0.000081925326,0.0000040708596,0.000016296339,0.000010422044,0.63454485,0.0005109409,0.36345488,0.000244641,0.00016229953],"about_ca_topic_score_codex":0.00009056311,"about_ca_topic_score_gemma":0.00011180765,"teacher_disagreement_score":0.634539,"about_ca_system_score_codex":0.00012912246,"about_ca_system_score_gemma":0.0009147487,"threshold_uncertainty_score":0.9768208},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.7075499601632524,"score_gpt":0.6697690744611742,"score_spread":0.03778088570207827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906515425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029392002,0.000010970766,0.96650577,0.001169612,0.000134154,0.0010072764,0.000038878043,0.00015880291,0.0015825104],"genre_scores_gemma":[0.16266116,0.000008812897,0.8365687,0.00015631676,0.00014119214,0.00011926339,0.000014721438,0.000057760833,0.00027203275],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98529184,0.007923195,0.0013950929,0.00089884875,0.0029721218,0.0015188771],"domain_scores_gemma":[0.96774524,0.029935952,0.00012045395,0.00072318467,0.0007033687,0.00077178085],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.028308034,0.00033351744,0.0012395919,0.00078976137,0.0001587607,0.000084837884,0.0009422849,0.00040688823,0.0066339667],"category_scores_gemma":[0.21545951,0.0002609257,0.00008072814,0.0018430379,0.0011677145,0.000101184174,0.0011776596,0.002066738,0.00024391178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011830956,0.001794988,0.01169642,0.0006811857,0.00020949221,0.0021652563,0.0018756444,0.000023723565,0.026806053,0.3731161,0.0036177053,0.5768303],"study_design_scores_gemma":[0.0010724453,0.0007273431,0.06488276,0.000591472,0.000030528052,0.000014520681,0.0004713798,0.0170595,0.004169718,0.9102369,0.0002412386,0.0005021912],"about_ca_topic_score_codex":0.0008109504,"about_ca_topic_score_gemma":0.00043691896,"teacher_disagreement_score":0.57632816,"about_ca_system_score_codex":0.00042022663,"about_ca_system_score_gemma":0.00056332257,"threshold_uncertainty_score":0.9999843},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11733146660538908,"score_gpt":0.5295953286551724,"score_spread":0.4122638620497834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916199673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001231846,0.000046302383,0.98581463,0.0023269777,0.00024311041,0.0003206654,0.000008275831,0.00006817348,0.009940035],"genre_scores_gemma":[0.15616171,0.0000335232,0.8430324,0.00012817269,0.000089064306,0.00008072532,0.000025280142,0.000011844397,0.00043723756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920716,0.004554745,0.00035988208,0.00057681487,0.0019242212,0.0005127052],"domain_scores_gemma":[0.9864148,0.012258116,0.000039114322,0.00066225027,0.0002665578,0.00035915413],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018758154,0.00010112385,0.0002478553,0.00027722036,0.00007220577,0.0001182646,0.0009863201,0.00013110305,0.001038131],"category_scores_gemma":[0.035101596,0.00006973299,0.000019987503,0.0008507797,0.00027034958,0.0001991362,0.0003670312,0.0013564732,0.00022892043],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012921236,0.00007905403,0.015597556,0.000055187775,0.0000069803573,0.00003724471,0.00011204915,0.000012673885,0.000056381698,0.1994792,0.0014164041,0.78301805],"study_design_scores_gemma":[0.0023340744,0.000737239,0.19260347,0.00023949429,0.0000026395144,0.000019077066,0.00006376723,0.7150648,0.000102071994,0.062127825,0.026554542,0.00015097606],"about_ca_topic_score_codex":0.00010622664,"about_ca_topic_score_gemma":0.00005631314,"teacher_disagreement_score":0.7828671,"about_ca_system_score_codex":0.00007493543,"about_ca_system_score_gemma":0.00029339903,"threshold_uncertainty_score":0.99987507},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.5909202286661872,"score_gpt":0.6355710282862124,"score_spread":0.04465079962002516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923957350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007927972,0.00063878996,0.9887173,0.006295281,0.00015411487,0.0010065953,0.0020497737,0.000050686493,0.00029462748],"genre_scores_gemma":[0.02280295,0.00008277015,0.97616804,0.00019299948,0.00013194726,0.0003892481,0.00017326785,0.000054271022,0.0000044814788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9629133,0.027326958,0.0027868117,0.0016968988,0.004264077,0.0010119674],"domain_scores_gemma":[0.6833035,0.31346932,0.0005192623,0.0013690706,0.00053169264,0.0008072051],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05253502,0.0005217831,0.0035783353,0.0006114612,0.00022124144,0.000340528,0.0011311877,0.00073376775,0.0044851275],"category_scores_gemma":[0.48795423,0.00034024208,0.0003784739,0.0019631558,0.0014963866,0.00005116817,0.002122386,0.0064056343,0.0000046104387],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021846704,0.0001807485,0.0012515386,0.0006975657,0.012968427,0.0006602444,0.0015742896,0.000029653898,0.000011722046,0.6804383,0.00047482518,0.30149427],"study_design_scores_gemma":[0.0002262395,0.00006915385,0.0030856142,0.00011183805,0.009219206,0.000002142423,0.00018776936,0.25850573,0.000015414766,0.7282733,0.000062135514,0.00024149263],"about_ca_topic_score_codex":0.0077053523,"about_ca_topic_score_gemma":0.004483876,"teacher_disagreement_score":0.4354192,"about_ca_system_score_codex":0.00020679717,"about_ca_system_score_gemma":0.0008653528,"threshold_uncertainty_score":0.99990493},"labels":[],"label_agreement":null},{"id":"W2933605766","doi":"10.1177/0962280219837656","title":"Handling ties in continuous outcomes for confounder adjustment with rank-ordered logit and its application to ordinal outcomes","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut universitaire en santé mentale de Montréal","funders":"National Medical Research Council; Cancerfonden","keywords":"Econometrics; Odds; Statistics; Ordered logit; Ordinal data; Logit; Confounding; Ordinal regression; Mathematics; Scaling; Equivalence (formal languages); Computer science; Logistic regression; Discrete mathematics","score_opus":0.2995074587587282,"score_gpt":0.6181559167719965,"score_spread":0.31864845801326835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2933605766","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016190138,0.00006325102,0.9780878,0.0017159584,0.000046771787,0.0028058365,0.000027760425,0.00005981183,0.0010026618],"genre_scores_gemma":[0.17370676,0.000033021417,0.82435054,0.00024905943,0.000018902263,0.0012177915,0.0000070779233,0.000032654836,0.00038418436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99601996,0.00095922034,0.0006152746,0.0005381955,0.0011537975,0.0007135247],"domain_scores_gemma":[0.9630773,0.035903174,0.00006351663,0.00030648467,0.00032670403,0.00032280173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00873206,0.0002107726,0.0007956723,0.00032392578,0.00005674301,0.000037725724,0.00030750167,0.00021382907,0.00031517944],"category_scores_gemma":[0.04639553,0.00014788154,0.00002645658,0.00036247823,0.00029531974,0.00008002629,0.00021983807,0.000806017,0.0000130705475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037922992,0.00018134798,0.015575844,0.00040134258,0.000030035455,0.000018916724,0.00031159708,0.0000030263952,0.00035070698,0.767261,0.00012256144,0.21536435],"study_design_scores_gemma":[0.0025704557,0.00095485477,0.025694635,0.0003364142,0.000015711772,0.000005232063,0.0010262344,0.007046174,0.0007082962,0.9603736,0.0009496799,0.00031876087],"about_ca_topic_score_codex":0.00008903631,"about_ca_topic_score_gemma":0.00019377793,"teacher_disagreement_score":0.21504559,"about_ca_system_score_codex":0.00019171438,"about_ca_system_score_gemma":0.00020098368,"threshold_uncertainty_score":0.9616371},"labels":[],"label_agreement":null},{"id":"W2937710358","doi":"10.1177/0962280219842362","title":"Comparing the high-dimensional propensity score for use with administrative data with propensity scores derived from high-quality clinical data","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Confounding; Medicine; Hazard ratio; Proxy (statistics); Statistics; Internal medicine; Mathematics; Confidence interval","score_opus":0.899460556396185,"score_gpt":0.6935688475760646,"score_spread":0.20589170882012042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937710358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38152108,0.000011641111,0.6139935,0.0008005414,0.000066676206,0.0024037806,0.0010851423,0.000067265864,0.00005034843],"genre_scores_gemma":[0.36166748,0.000012805113,0.6372101,0.00013415446,0.00008965786,0.000107632564,0.0007092954,0.000039517556,0.00002936414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98196155,0.010424266,0.0013298874,0.0019530255,0.003326157,0.0010051115],"domain_scores_gemma":[0.8151516,0.17669326,0.0004031317,0.005647349,0.0013116667,0.00079301826],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03964532,0.0003710367,0.0014045301,0.000091522685,0.00028578023,0.00018865851,0.0032520266,0.00031800682,0.0005183053],"category_scores_gemma":[0.14560233,0.00019599238,0.000029485596,0.00047992618,0.0037116937,0.0005795095,0.0043801423,0.0031899214,0.000016250862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018366497,0.0025351641,0.26990962,0.00077493244,0.00063745596,0.00070286734,0.000261898,0.000006819799,0.00096969114,0.5637118,0.0063580372,0.13576518],"study_design_scores_gemma":[0.003678158,0.0023694788,0.44559878,0.001441422,0.00012305638,0.000023456425,0.00020253005,0.027066197,0.001806473,0.51670766,0.0003101867,0.0006726303],"about_ca_topic_score_codex":0.0023852761,"about_ca_topic_score_gemma":0.0048521403,"teacher_disagreement_score":0.17568916,"about_ca_system_score_codex":0.00012835998,"about_ca_system_score_gemma":0.0018296414,"threshold_uncertainty_score":0.99910975},"labels":[],"label_agreement":null},{"id":"W29415624","doi":"10.1177/0962280218756159","title":"Variasi Bentuk Penguatan pada Pembelajaran Bahasa Jawa Kelas VII di SMP Se-Kecamatan Winong Kabupaten Pati","year":2012,"lang":"en","type":"dissertation","venue":"Statistical Methods in Medical Research","topic":"Educational Research and Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Humanities; Psychology; Physics; Art","score_opus":0.2623628753972758,"score_gpt":0.6661840673525657,"score_spread":0.4038211919552899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W29415624","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007194709,0.003096461,0.05882279,0.0032160787,0.004247632,0.0024717804,0.00044043732,0.00012745295,0.9203827],"genre_scores_gemma":[0.73470277,0.0055275136,0.2161361,0.00020674277,0.0045048143,0.0016498254,0.003247015,0.00030532866,0.033719912],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9501559,0.031506393,0.0016319917,0.0015382961,0.011291944,0.0038754866],"domain_scores_gemma":[0.9371414,0.0556746,0.00025689497,0.0009546102,0.0016978236,0.0042746314],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.05983713,0.00064175867,0.0013220841,0.0012078198,0.0015060488,0.00041433435,0.0026305479,0.0019362246,0.39222556],"category_scores_gemma":[0.14054903,0.0005918736,0.00023385158,0.002679423,0.002520141,0.00037859994,0.0004251015,0.0077417823,0.0005152226],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036096302,0.00069295324,0.0018545692,0.00050242944,0.000098612785,0.00024873752,0.011725497,3.3214857e-7,0.00017767829,0.09628704,0.0050542466,0.8829969],"study_design_scores_gemma":[0.0011841248,0.00040682155,0.7350805,0.001093834,0.0000916445,0.000008159691,0.03163544,0.0004739213,0.00022324604,0.1142721,0.11446073,0.0010694644],"about_ca_topic_score_codex":0.01882613,"about_ca_topic_score_gemma":0.006475712,"teacher_disagreement_score":0.8866627,"about_ca_system_score_codex":0.0014380014,"about_ca_system_score_gemma":0.012045621,"threshold_uncertainty_score":0.9997938},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["insufficient_payload"],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2948592660","doi":"10.1177/0962280219852721","title":"Investigating protein patterns in human leukemia cell line experiments: A Bayesian approach for extremely small sample sizes","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; University of Texas MD Anderson Cancer Center; National Institutes of Health; Cancer Prevention and Research Institute of Texas","keywords":"Myeloid leukemia; Bayesian probability; Computational biology; Sample size determination; Leukemia; Computer science; Cancer cell lines; Mass cytometry; Sample (material); Bioinformatics; Biology; Cancer; Statistics; Chemistry; Mathematics; Cancer research; Cancer cell; Phenotype; Chromatography; Artificial intelligence; Genetics; Gene","score_opus":0.16581169265453438,"score_gpt":0.5168562717667535,"score_spread":0.35104457911221915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948592660","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051079214,0.000051856965,0.9426124,0.00016898823,0.000009043272,0.0014540207,0.0001438777,0.00005655749,0.004424043],"genre_scores_gemma":[0.15708484,0.000011687357,0.83847547,0.00005749587,0.00008154042,0.0037764853,0.00016256655,0.000051952513,0.00029795596],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960213,0.00062700245,0.000787496,0.0008229281,0.00083512615,0.00090620515],"domain_scores_gemma":[0.992768,0.0060333493,0.0000904909,0.0005464037,0.0001236395,0.0004381263],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054286,0.00022117079,0.00044972196,0.00017520513,0.00012953798,0.000050602543,0.0007063315,0.00036773822,0.0021568476],"category_scores_gemma":[0.011639912,0.00020933704,0.000052057138,0.00039403533,0.00036555392,0.000048829555,0.0003692304,0.0018105444,0.0000035407493],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009399361,0.0006170704,0.003528198,0.0019672771,0.000011150846,0.000015785587,0.00040424743,0.000039314487,0.726548,0.072984405,0.00006869133,0.19372183],"study_design_scores_gemma":[0.0021827763,0.00025078695,0.00016268858,0.0006405378,0.000004696587,0.0000020612497,0.0009779701,0.15077399,0.5340854,0.30934945,0.0011005705,0.00046906323],"about_ca_topic_score_codex":0.00073073636,"about_ca_topic_score_gemma":0.00004743534,"teacher_disagreement_score":0.23636505,"about_ca_system_score_codex":0.0004487427,"about_ca_system_score_gemma":0.0003571773,"threshold_uncertainty_score":0.99875534},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8933866589386059,"score_gpt":0.704013528761424,"score_spread":0.18937313017718194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951322845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003366892,0.00024285229,0.98974866,0.0033317106,0.00011217294,0.0009439769,0.00022757518,0.000059291488,0.0019668855],"genre_scores_gemma":[0.33643562,0.00002990411,0.6628709,0.0002469768,0.00019768186,0.00013721814,0.000010069138,0.000030697334,0.000040926385],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97966427,0.012632916,0.0020786847,0.0013497483,0.002687089,0.0015872786],"domain_scores_gemma":[0.75569725,0.24099597,0.0002233479,0.0015915759,0.00047997906,0.001011888],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08411132,0.0003143999,0.0017256918,0.00033795397,0.00026626565,0.000027858292,0.0019841883,0.0003920318,0.0009063702],"category_scores_gemma":[0.62746066,0.00023923666,0.000072316834,0.001240448,0.0017596026,0.00008179315,0.0039817905,0.0018879871,0.00002653739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036563267,0.00057735376,0.001270791,0.00086723187,0.00009822574,0.00005915512,0.001693986,0.000048207836,0.00015135216,0.4550656,0.029531026,0.51027143],"study_design_scores_gemma":[0.00022850139,0.00032189264,0.0002686677,0.0001579314,0.000016096223,9.877278e-7,0.0008657824,0.4937134,0.000080072,0.50346494,0.00074153586,0.00014017145],"about_ca_topic_score_codex":0.0015102902,"about_ca_topic_score_gemma":0.001134643,"teacher_disagreement_score":0.5433493,"about_ca_system_score_codex":0.0002871963,"about_ca_system_score_gemma":0.00033565215,"threshold_uncertainty_score":0.9924118},"labels":[],"label_agreement":null},{"id":"W2952368191","doi":"10.1177/0962280219852747","title":"Statistical methods for detecting outlying and influential studies in meta-analysis of diagnostic test accuracy studies","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Forest ecology and management","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bivariate analysis; Computer science; Meta-analysis; Statistics; Sensitivity (control systems); Data mining; Random effects model; Statistical hypothesis testing; Econometrics; Machine learning; Mathematics; Medicine","score_opus":0.35820890604690775,"score_gpt":0.6359007442394153,"score_spread":0.2776918381925076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952368191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02206045,0.0029493028,0.9718686,0.00079907855,0.00021288368,0.0015497683,0.00007041213,0.00001552974,0.00047402762],"genre_scores_gemma":[0.21773574,0.0007328949,0.7807197,0.00014592615,0.000013616017,0.0005449996,0.0000054721886,0.00001553821,0.00008609546],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9905952,0.00566067,0.0010666627,0.0008037142,0.0010363258,0.00083742343],"domain_scores_gemma":[0.58781683,0.41144446,0.00011320638,0.0003098321,0.0000905312,0.00022511746],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040500063,0.0002185794,0.001611541,0.0005117352,0.00013924332,0.000021164384,0.00039797436,0.00016978673,0.0037122145],"category_scores_gemma":[0.596032,0.00016325818,0.00013969441,0.0014549315,0.0025988156,0.000111921516,0.0013835245,0.0008436626,0.000021019756],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003042471,0.00071920693,0.06989185,0.0013147519,0.024081873,0.00023047441,0.003557917,0.0009341371,0.0005289501,0.07953302,0.0007420134,0.81816155],"study_design_scores_gemma":[0.0027498004,0.0017615808,0.2520593,0.00014419443,0.02184849,0.0000066352472,0.008728519,0.1161316,0.00060752366,0.59230864,0.0029037248,0.00074995833],"about_ca_topic_score_codex":0.00037715226,"about_ca_topic_score_gemma":0.0012834403,"teacher_disagreement_score":0.8174116,"about_ca_system_score_codex":0.00022736637,"about_ca_system_score_gemma":0.000052376472,"threshold_uncertainty_score":0.9971985},"labels":[],"label_agreement":null},{"id":"W2953345044","doi":"10.1177/0962280216660128","title":"Principal component of explained variance: An efficient and optimal data dimension reduction framework for association studies","year":2016,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Douglas Mental Health University Institute; McGill University; Jewish General Hospital","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Dimensionality reduction; Principal component analysis; Covariate; Dimension (graph theory); Context (archaeology); Computer science; Variance (accounting); Component (thermodynamics); Variance reduction; Data mining; Mathematics; Machine learning; Artificial intelligence","score_opus":0.23584234104567728,"score_gpt":0.5864195385407014,"score_spread":0.35057719749502414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953345044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08691949,0.0004120489,0.9102462,0.0018341182,0.00020914462,0.0002858471,0.000071224065,0.0000040472046,0.000017887305],"genre_scores_gemma":[0.34889138,0.0007354751,0.64993864,0.000025337029,0.00017089256,0.00009183105,0.00006905233,0.000010066767,0.000067299785],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9967052,0.001519566,0.0003263395,0.00049422757,0.00068191055,0.00027277277],"domain_scores_gemma":[0.9961002,0.0029195023,0.00008029213,0.00041539542,0.0003086864,0.00017591384],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009462968,0.00007676134,0.00018489956,0.000074366406,0.00007612958,0.000008983756,0.00023858587,0.00021440293,0.00004146093],"category_scores_gemma":[0.048907302,0.00005222413,0.000013493869,0.00012873905,0.00030807825,0.000005184299,0.00034544495,0.00018706839,5.9498313e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008154031,0.00026436785,0.00023511804,0.00009979492,0.000044669865,0.0000017126182,0.00020037305,0.000015583542,0.6361878,0.027959773,0.0019571881,0.3322182],"study_design_scores_gemma":[0.010874248,0.0063655875,0.043589648,0.002346767,0.00011940368,0.000026453641,0.0068477397,0.10342468,0.6479529,0.12389928,0.053406052,0.0011472268],"about_ca_topic_score_codex":0.0000054764237,"about_ca_topic_score_gemma":0.0000026173602,"teacher_disagreement_score":0.331071,"about_ca_system_score_codex":0.000072923314,"about_ca_system_score_gemma":0.00015866649,"threshold_uncertainty_score":0.9591042},"labels":[],"label_agreement":null},{"id":"W2954051196","doi":"10.1177/0962280219859037","title":"A novel model for the X-chromosome inactivation association on survival data","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Skewness; Population; Chromosome; Locus (genetics); Mathematics; Genetics; Biological data; Biology; Computer science; Statistics; Computational biology; Gene; Medicine","score_opus":0.19955920848409536,"score_gpt":0.5290297773718313,"score_spread":0.32947056888773596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954051196","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053218226,0.000062073865,0.99004525,0.0016712284,0.00030368555,0.0005850397,0.00024244469,0.0000043780333,0.0017640538],"genre_scores_gemma":[0.15473405,0.000052340125,0.8422445,0.0003548902,0.00036773027,0.00012882547,0.00029313893,0.00002626849,0.0017982783],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969344,0.0008118521,0.0002635662,0.0005047056,0.0010465977,0.00043888253],"domain_scores_gemma":[0.99013424,0.008853936,0.000044156015,0.0006644249,0.00016973207,0.00013350687],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011164847,0.000100417295,0.00016448782,0.000047951056,0.00009196355,0.00002551313,0.0007633962,0.00027115838,0.00019979734],"category_scores_gemma":[0.036487266,0.00007159723,0.000025120149,0.00016237187,0.0001556605,0.0000038654644,0.00036223032,0.00058339554,0.000015773096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010649253,0.0006712185,0.0011611967,0.00013303642,0.00014010005,9.153724e-7,0.00018031246,0.0025294523,0.054649904,0.44702235,0.012997833,0.47944877],"study_design_scores_gemma":[0.0030799392,0.0014664212,0.042455405,0.00008356583,0.000025354904,0.0000027888814,0.00028078683,0.8044912,0.002844302,0.116590396,0.028319238,0.00036059733],"about_ca_topic_score_codex":0.000034159675,"about_ca_topic_score_gemma":0.000039147126,"teacher_disagreement_score":0.8019618,"about_ca_system_score_codex":0.00006830461,"about_ca_system_score_gemma":0.00040745572,"threshold_uncertainty_score":0.9716288},"labels":[],"label_agreement":null},{"id":"W2964567104","doi":"10.1177/0962280219863076","title":"Joint nested frailty models for clustered recurrent and terminal events: An application to colonoscopy screening visits and colorectal cancer risks in Lynch Syndrome families","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Genetic factors in colorectal cancer","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; University of Toronto; Memorial University of Newfoundland; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Family history; Colonoscopy; Colorectal cancer; Lynch syndrome; Medicine; Covariate; Disease; Cancer; Event (particle physics); Computer science; Internal medicine; Machine learning","score_opus":0.21744779482678706,"score_gpt":0.5662762707348751,"score_spread":0.348828475908088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964567104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6373059,0.00024200947,0.3591525,0.0006901159,0.0001072582,0.0023516964,0.00008104942,0.000012753395,0.000056695142],"genre_scores_gemma":[0.65999174,0.00016912172,0.33845448,0.00013844552,0.000040271712,0.0011363174,0.000026006317,0.0000266846,0.000016950436],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99507755,0.0013880578,0.0006322709,0.0008870259,0.0012531505,0.00076197216],"domain_scores_gemma":[0.9938525,0.0047063436,0.00005495824,0.00026353102,0.00026706516,0.00085560157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065034856,0.00022060407,0.00070164324,0.00047378973,0.00008061126,0.000031361906,0.00020033153,0.00033112988,0.00022468367],"category_scores_gemma":[0.007897969,0.00019441731,0.000027204016,0.0006104491,0.00033656272,0.00008227885,0.00032185568,0.0010697648,0.000002851589],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005174355,0.00028898966,0.034585644,0.000767678,0.000031249223,0.000065812514,0.0009478177,0.00014033595,0.0061444617,0.0007215582,0.000064234475,0.95106786],"study_design_scores_gemma":[0.00320827,0.0054188445,0.50143063,0.0009259706,0.000025245981,0.000070476286,0.0005586404,0.47820324,0.0009450256,0.008810201,0.00015353909,0.00024987862],"about_ca_topic_score_codex":0.0013466586,"about_ca_topic_score_gemma":0.0009662533,"teacher_disagreement_score":0.950818,"about_ca_system_score_codex":0.00036913477,"about_ca_system_score_gemma":0.00048161487,"threshold_uncertainty_score":0.9455177},"labels":[],"label_agreement":null},{"id":"W2979956400","doi":"10.1177/0962280219881032","title":"Time-stratified case-crossover design applied with conditional logistic regression is not free from overlap bias","year":2019,"lang":"en","type":"letter","venue":"Statistical Methods in Medical Research","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services","funders":"","keywords":"Logistic regression; Crossover; Statistics; Crossover study; Econometrics; Mathematics; Computer science; Medicine; Artificial intelligence","score_opus":0.6160523859351099,"score_gpt":0.6265387992108831,"score_spread":0.010486413275773154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979956400","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000043674063,0.00013488084,0.9069193,0.07574439,0.0005809629,0.0019053301,0.003839249,0.000062549894,0.010769662],"genre_scores_gemma":[0.0003572729,0.000018578316,0.8894079,0.101768136,0.0013392336,0.00037837317,0.00051399536,0.00016445912,0.006052091],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92868316,0.038372297,0.0028869633,0.0038618955,0.02381375,0.0023819522],"domain_scores_gemma":[0.6528362,0.34205654,0.0005170947,0.0027880336,0.0009662966,0.0008358356],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.07022276,0.0010439579,0.002636788,0.0013907749,0.00046347087,0.0010135083,0.0046148747,0.0033163044,0.078732006],"category_scores_gemma":[0.25353375,0.00067885517,0.00023477079,0.0023477364,0.0069348733,0.0002468314,0.001803815,0.013241078,0.0036343231],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019014094,0.00017619514,0.000014945158,0.00006895838,0.000101601916,0.029746618,0.00022490759,0.000023664867,0.0015159053,0.0051061804,0.89659166,0.06452795],"study_design_scores_gemma":[0.0046371766,0.0013703275,0.0002238591,0.0007094414,0.00008380569,0.0006881342,0.00054689357,0.053243496,0.00464159,0.80112404,0.13117811,0.0015531544],"about_ca_topic_score_codex":0.00046527444,"about_ca_topic_score_gemma":0.000011879671,"teacher_disagreement_score":0.7960178,"about_ca_system_score_codex":0.00069640315,"about_ca_system_score_gemma":0.0029865177,"threshold_uncertainty_score":0.99956626},"labels":[],"label_agreement":null},{"id":"W2980191247","doi":"10.1177/0962280219880571","title":"Causal variance decompositions for institutional comparisons in healthcare","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Public Health Ontario; University of Toronto","funders":"","keywords":"Variance (accounting); Pairwise comparison; Health care; Estimator; Variation (astronomy); Contrast (vision); Causal inference; Quality (philosophy)","score_opus":0.5111091620525015,"score_gpt":0.6978161455830484,"score_spread":0.18670698353054693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980191247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010006529,0.00006424966,0.9885825,0.005687598,0.00015220151,0.0011964071,0.00013776065,0.00006505378,0.0031136128],"genre_scores_gemma":[0.09953522,0.00003513018,0.8994191,0.00020690006,0.000055833163,0.0006004471,0.00003460824,0.000022279652,0.00009044665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99399304,0.0025585613,0.00075197074,0.0005083862,0.0013000796,0.0008879727],"domain_scores_gemma":[0.9535546,0.045323685,0.000049776398,0.00036396805,0.00030661412,0.0004013941],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0128537305,0.00015364749,0.00052162074,0.0003791176,0.00012029353,0.000027245604,0.00046343866,0.00029980936,0.0011424997],"category_scores_gemma":[0.051677633,0.00014208203,0.000038508806,0.0007429766,0.0006560307,0.00009958639,0.0001738676,0.001893608,0.000037787122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094675495,0.000263547,0.0012401124,0.00025543742,0.0000055889573,0.000051181705,0.00005591545,0.000005567163,0.000262486,0.95396703,0.0017309756,0.04206748],"study_design_scores_gemma":[0.0006803994,0.0002687653,0.0032140338,0.00036711383,0.0000024748076,0.000011746516,0.000071154696,0.018082,0.00031508214,0.97294134,0.003896423,0.00014944648],"about_ca_topic_score_codex":0.00032150696,"about_ca_topic_score_gemma":0.00061139074,"teacher_disagreement_score":0.09853457,"about_ca_system_score_codex":0.00048469292,"about_ca_system_score_gemma":0.0009282318,"threshold_uncertainty_score":0.9997706},"labels":[],"label_agreement":null},{"id":"W2981954851","doi":"10.1177/0962280219882968","title":"Estimating the quantile medical cost under time-dependent covariates and right censored time-to-event variable based on a state process","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Covariate; Quantile; Censoring (clinical trials); Estimator; Statistics; Inverse probability weighting; Econometrics; Computer science; Quantile function; Weighting; Quantile regression; Cumulative distribution function; Event (particle physics); Mathematics; Medicine; Probability density function","score_opus":0.09840022808209999,"score_gpt":0.5383808817050073,"score_spread":0.43998065362290734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981954851","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017820973,0.000020427618,0.9852167,0.0044871136,0.00018754648,0.0016519361,0.00019374449,0.00006619868,0.0063942736],"genre_scores_gemma":[0.010335391,0.0000058635633,0.98690355,0.0012482804,0.00010353902,0.00033402987,0.000015738226,0.00007519505,0.0009783875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9812796,0.009524952,0.0011969345,0.0010741863,0.0054569044,0.0014674009],"domain_scores_gemma":[0.86231846,0.13509947,0.00011510032,0.0006937054,0.00043405793,0.0013392062],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.04492265,0.0003824863,0.0009438146,0.0003055771,0.00025078707,0.00018049637,0.0010234304,0.00038319203,0.06406656],"category_scores_gemma":[0.23559484,0.00024183762,0.000049880924,0.0010461904,0.0009781275,0.00005472809,0.0005001592,0.0026679323,0.0009896021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009990599,0.0013352832,0.00018688619,0.0010828933,0.00009689199,0.0003904616,0.00052295905,0.0011313587,0.00041101896,0.62574327,0.0057953447,0.36230457],"study_design_scores_gemma":[0.0007752258,0.00038471536,0.00026801307,0.00058497785,0.000012779096,0.000011082279,0.0000410489,0.5615904,0.00013697484,0.43556982,0.00043093605,0.00019402005],"about_ca_topic_score_codex":0.00011103133,"about_ca_topic_score_gemma":0.000009753468,"teacher_disagreement_score":0.560459,"about_ca_system_score_codex":0.0001952528,"about_ca_system_score_gemma":0.0012264124,"threshold_uncertainty_score":0.9997882},"labels":[],"label_agreement":null},{"id":"W2990322717","doi":"10.1177/0962280219888741","title":"Random forests for homogeneous and non-homogeneous Poisson processes with excess zeros","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fondation HEC","keywords":"Homogeneous; Poisson distribution; Zero-inflated model; Zero (linguistics); Applied mathematics; Mathematics; Compound Poisson process; Statistics; Poisson process; Poisson regression; Statistical physics; Computer science; Mathematical optimization; Combinatorics; Physics","score_opus":0.14256903439322716,"score_gpt":0.5536162434177959,"score_spread":0.41104720902456876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990322717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03587026,0.00025021273,0.9597344,0.0003849081,0.00013053884,0.0019672639,0.00014489275,0.000039233983,0.0014782854],"genre_scores_gemma":[0.13333344,0.0001536285,0.8653494,0.000091058464,0.000110703455,0.0005853941,0.000009932108,0.000068943475,0.000297495],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99269307,0.0023058278,0.00079616514,0.00093326304,0.001992983,0.0012786668],"domain_scores_gemma":[0.85454863,0.14336471,0.00009365755,0.00047872617,0.000711154,0.00080314174],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01430246,0.00033140046,0.0010178913,0.00026748292,0.00017952596,0.00012193318,0.00057286944,0.00035358057,0.0012908909],"category_scores_gemma":[0.19119929,0.0002295976,0.000044024415,0.0007613052,0.0010864248,0.00006299143,0.00028131844,0.0010926086,0.00001980591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002925278,0.0005235047,0.006095695,0.005533251,0.000083587336,0.00045572873,0.0005296539,0.000004125228,0.0004867818,0.19081652,0.00094564824,0.7916002],"study_design_scores_gemma":[0.0051375595,0.0021716694,0.0038867265,0.00092587457,0.000043928496,0.000114346636,0.0002535949,0.021310005,0.0020655335,0.96240634,0.0012136798,0.0004707549],"about_ca_topic_score_codex":0.00009391668,"about_ca_topic_score_gemma":0.00025241773,"teacher_disagreement_score":0.79112947,"about_ca_system_score_codex":0.000084615494,"about_ca_system_score_gemma":0.00093479024,"threshold_uncertainty_score":0.99962205},"labels":[],"label_agreement":null},{"id":"W3003262140","doi":"10.1177/0962280220901728","title":"Variable selection via penalized generalized estimating equations for a marginal survival model","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Covariate; Multivariate statistics; Estimator; Marginal model; Generalized estimating equation; Estimating equations; Model selection; Feature selection; Mathematics; Proportional hazards model; Statistics; Generalized linear model; Selection (genetic algorithm); Applied mathematics; Regression; Econometrics; Regression analysis; Computer science; Artificial intelligence","score_opus":0.5164316858740705,"score_gpt":0.6278889334165795,"score_spread":0.11145724754250896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003262140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051878316,0.000022739561,0.9931142,0.0027664287,0.00018384098,0.00093560014,0.00014839326,0.00008609699,0.0026908708],"genre_scores_gemma":[0.0011506458,0.000005447257,0.9972718,0.00038929272,0.00035691776,0.00060679193,0.000027127693,0.00005962006,0.00013239408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98839754,0.0062803715,0.0011477079,0.00080038473,0.0022044173,0.0011695833],"domain_scores_gemma":[0.88300383,0.114610575,0.000121288846,0.00028838942,0.0008057023,0.0011702002],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02462576,0.00026263343,0.000832861,0.00019427288,0.0003244827,0.00010150777,0.0005422713,0.00031872446,0.0049083172],"category_scores_gemma":[0.454742,0.00022894712,0.00007988728,0.0012115324,0.0004959558,0.000078140074,0.00025953163,0.001573273,0.000020339765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003113984,0.00014282709,0.000013353175,0.0003660894,0.000024359915,0.000012791777,0.00016954339,0.00021370394,0.0012840015,0.8189796,0.0015050552,0.17697728],"study_design_scores_gemma":[0.00082001707,0.0001770831,0.000011124076,0.000053330314,0.000017478353,0.0000020985408,0.00002416974,0.5041007,0.000080298356,0.49434868,0.0002396611,0.00012537405],"about_ca_topic_score_codex":0.00012866934,"about_ca_topic_score_gemma":0.00001749791,"teacher_disagreement_score":0.503887,"about_ca_system_score_codex":0.00016997392,"about_ca_system_score_gemma":0.0009381815,"threshold_uncertainty_score":0.9960013},"labels":[],"label_agreement":null},{"id":"W3004330284","doi":"10.1177/0962280219900362","title":"Estimation of causal effects with repeatedly measured outcomes in a Bayesian framework","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Causal inference; Observational study; Bayesian probability; Markov chain Monte Carlo; Propensity score matching; Computer science; Inverse probability; Marginal structural model; Econometrics; Bayesian inference; Machine learning; Posterior probability; Statistics; Artificial intelligence; Mathematics","score_opus":0.29924381672434486,"score_gpt":0.6201955815925178,"score_spread":0.3209517648681729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004330284","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041329195,0.000027444,0.9923323,0.0018864902,0.000024649771,0.0007361414,0.000011233047,0.000091041285,0.00075780146],"genre_scores_gemma":[0.32028008,0.000011087796,0.679427,0.00009981247,0.000015296819,0.00013217649,0.0000025504296,0.000026665917,0.000005282533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99088913,0.0046690563,0.0008324757,0.00049557124,0.0024592804,0.00065446954],"domain_scores_gemma":[0.9350013,0.06375433,0.00009332762,0.00040127733,0.0002184833,0.00053124805],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.010560865,0.0002000608,0.0008258191,0.0002863966,0.00003641573,0.00001901499,0.00043711893,0.00035550722,0.00040237035],"category_scores_gemma":[0.3882593,0.00014795501,0.00003204816,0.0013274738,0.0007714746,0.00008366436,0.00019373353,0.0023281742,0.0000052686432],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003900548,0.00033139603,0.0055599473,0.0010013158,0.000032072996,0.00070804707,0.001078835,0.000018225734,0.0005039502,0.61700153,0.00017236409,0.37320226],"study_design_scores_gemma":[0.0005848187,0.0010438396,0.0051128054,0.0009381708,0.000010488647,0.000004203544,0.00012576781,0.034688156,0.0039056453,0.95341045,0.000012917747,0.00016272129],"about_ca_topic_score_codex":0.00009551286,"about_ca_topic_score_gemma":0.00006088188,"teacher_disagreement_score":0.37769842,"about_ca_system_score_codex":0.00015313755,"about_ca_system_score_gemma":0.00036735038,"threshold_uncertainty_score":0.9999735},"labels":[],"label_agreement":null},{"id":"W3005076266","doi":"10.1177/0962280220902179","title":"Modeling of cumulative effects of time-varying drug exposures on within-subject changes in a continuous outcome","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Institute of Population and Public Health; Canadian Institutes of Health Research","keywords":"Random effects model; Statistics; Outcome (game theory); Econometrics; Mixed model; Medicine; Regression analysis; Correlation; Mathematics; Computer science; Meta-analysis; Internal medicine","score_opus":0.6354828221668393,"score_gpt":0.6687579758259045,"score_spread":0.03327515365906519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005076266","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045620136,0.00011222799,0.9482494,0.001879692,0.00028622866,0.0017264532,0.00010314666,0.000050102295,0.001972592],"genre_scores_gemma":[0.23061162,0.000044349046,0.76882774,0.00022664317,0.00012658094,0.00007857206,0.0000018211138,0.000056714438,0.000025960164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.963566,0.027029414,0.0033565287,0.0010039345,0.003980282,0.0010638224],"domain_scores_gemma":[0.5245866,0.4735356,0.00029754027,0.0004978898,0.0003916358,0.00069074775],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0520197,0.00035280033,0.002524083,0.0005181199,0.000053507778,0.000020318379,0.0008869296,0.00045179308,0.00084782095],"category_scores_gemma":[0.8565768,0.00028366462,0.00013650855,0.0014787865,0.0012632454,0.000043963275,0.0005627278,0.0029570288,0.00001536766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071812966,0.0030651747,0.0049073733,0.012625349,0.00033400833,0.0019681724,0.011472153,0.0011319652,0.007287607,0.5840921,0.00076523056,0.3651696],"study_design_scores_gemma":[0.0025299627,0.0013099803,0.00026366083,0.0015989162,0.0000346505,0.0000014570419,0.00026339933,0.28658205,0.009184215,0.6979885,0.0000059093645,0.00023727045],"about_ca_topic_score_codex":0.00020884235,"about_ca_topic_score_gemma":0.000034197517,"teacher_disagreement_score":0.8045571,"about_ca_system_score_codex":0.00012287412,"about_ca_system_score_gemma":0.0003205657,"threshold_uncertainty_score":0.99996156},"labels":[],"label_agreement":null},{"id":"W3009413281","doi":"10.1177/0962280220907113","title":"Expanding attributable fraction applications to outcomes wholly attributable to a risk factor","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Alcohol Consumption and Health Effects","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Attributable risk; Fraction (chemistry); Econometrics; Disease; Risk factor; Statistics; Estimation; Epidemiology; Mathematics; Medicine; Economics; Chemistry; Pathology","score_opus":0.48967691462226376,"score_gpt":0.6623582638765955,"score_spread":0.1726813492543317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009413281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009340485,0.00019966987,0.9487825,0.03824228,0.00010306341,0.002432713,0.00026471872,0.00009498441,0.0005395984],"genre_scores_gemma":[0.12611374,0.00028131125,0.84906834,0.021681914,0.00049714977,0.0017635701,0.00005988949,0.00006708322,0.0004669637],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99269575,0.0023871611,0.00071644085,0.00077204197,0.0022831964,0.0011454084],"domain_scores_gemma":[0.9796889,0.015548189,0.00005314266,0.00038777624,0.00036932493,0.0039526764],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008225619,0.00019403636,0.0008710013,0.00045643645,0.00027676634,0.00006155628,0.00029897224,0.0002837713,0.008661527],"category_scores_gemma":[0.11724062,0.0001681494,0.00006571826,0.0020877696,0.00017941142,0.00006972459,0.0003233612,0.0023586592,0.0015462058],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008623246,0.00033416972,0.07229952,0.0005286622,0.00005054711,0.00021268998,0.00060094893,0.000007886552,0.0022709244,0.0034521082,0.02165313,0.8977271],"study_design_scores_gemma":[0.002768301,0.0015543121,0.59031224,0.00032328392,0.000043586104,0.000014915499,0.00041413013,0.004403183,0.00090445747,0.0028896902,0.39600968,0.0003622016],"about_ca_topic_score_codex":0.00025503925,"about_ca_topic_score_gemma":0.000026290578,"teacher_disagreement_score":0.8973649,"about_ca_system_score_codex":0.0005039884,"about_ca_system_score_gemma":0.00077093637,"threshold_uncertainty_score":0.99994296},"labels":[],"label_agreement":null},{"id":"W3010790150","doi":"10.1177/0962280220907625","title":"A study of alternative approaches to non-normal latent trait distributions in item response theory models used for health outcome measurement","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Polytomous Rasch model; Item response theory; Skewness; Normality; Statistics; Econometrics; Outcome (game theory); Mathematics; Psychology; Psychometrics","score_opus":0.957603297598445,"score_gpt":0.7042964429288336,"score_spread":0.25330685466961134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010790150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068435,0.000051434185,0.9172918,0.011764688,0.00011541341,0.0019577371,0.00022323162,0.000012211078,0.00014845286],"genre_scores_gemma":[0.5834897,0.0000027074195,0.41599372,0.00016373272,0.000031261196,0.00029650042,0.0000019446386,0.000010239793,0.000010198729],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9282534,0.052906547,0.0038516475,0.0016938945,0.01164318,0.0016513104],"domain_scores_gemma":[0.47987115,0.5169968,0.00027313776,0.0006529298,0.00074367126,0.00146229],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.31745926,0.00019089157,0.0010829605,0.0010575486,0.00015248558,0.00007389828,0.0015402328,0.00012940614,0.00019891468],"category_scores_gemma":[0.86797816,0.00013398346,0.00008963202,0.0050521223,0.0003889065,0.000089207235,0.0006560164,0.001197323,0.0000039921597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0071817287,0.0020450258,0.014538727,0.00012334008,0.000059160076,0.00013234283,0.016235009,0.0017607966,0.000117890035,0.061393183,0.00081341824,0.89559937],"study_design_scores_gemma":[0.004151815,0.0060408683,0.20518817,0.00014116883,0.000008672263,0.0000025933919,0.017131863,0.2947284,0.00013434156,0.47200325,0.00020644692,0.0002624025],"about_ca_topic_score_codex":0.0002193422,"about_ca_topic_score_gemma":0.00011625922,"teacher_disagreement_score":0.895337,"about_ca_system_score_codex":0.00034744036,"about_ca_system_score_gemma":0.00077525794,"threshold_uncertainty_score":0.70281935},"labels":[],"label_agreement":null},{"id":"W3011337113","doi":"10.1177/0962280221995963","title":"Causal simulation experiments: Lessons from bias amplification","year":2021,"lang":"en","type":"preprint","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Causal inference; Estimator; Context (archaeology); Computer science; Confounding; Econometrics; Inference; Parametric statistics; Set (abstract data type); Class (philosophy); Selection bias; Sensitivity (control systems); Artificial intelligence; Statistics; Mathematics; Engineering","score_opus":0.8123613022187561,"score_gpt":0.7422349751842946,"score_spread":0.07012632703446153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011337113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029547361,0.0003056078,0.9918408,0.0012529723,0.00037109014,0.00094606343,0.00023238389,0.00021869334,0.0018776777],"genre_scores_gemma":[0.10906555,0.00032937716,0.88883156,0.0000889828,0.00026599414,0.00076623267,0.00047668128,0.00008739687,0.00008823204],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9794481,0.012526098,0.0015415656,0.0014947386,0.0039758985,0.0010136048],"domain_scores_gemma":[0.8997803,0.09695418,0.00024051838,0.0014630441,0.0008998074,0.0006621814],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.018317737,0.00042702898,0.0010846982,0.0004845276,0.00013930746,0.0002215564,0.0010695931,0.0014066208,0.007159589],"category_scores_gemma":[0.29191494,0.0004062664,0.00010380298,0.00067189796,0.0009794442,0.00011367769,0.002334539,0.0061293556,0.0000291089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009841956,0.00078741385,0.00011689103,0.00044168255,0.00008432206,0.0004222152,0.0012937558,0.00009285409,0.0019187981,0.43208793,0.001167846,0.56148785],"study_design_scores_gemma":[0.00026168348,0.000067712586,0.00060626166,0.0010988123,0.00002142964,0.0000014956463,0.00064220367,0.059235994,0.0043001575,0.9327475,0.000666709,0.00035006276],"about_ca_topic_score_codex":0.0008868171,"about_ca_topic_score_gemma":0.00017442454,"teacher_disagreement_score":0.5611378,"about_ca_system_score_codex":0.0008553529,"about_ca_system_score_gemma":0.00136164,"threshold_uncertainty_score":0.9998898},"labels":[],"label_agreement":null},{"id":"W3012516591","doi":"10.1177/0962280220912772","title":"A threshold linear mixed model for identification of treatment-sensitive subsets in a clinical trial based on longitudinal outcomes and a continuous covariate","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Smoothing; Mixed model; Clinical trial; Statistics; Randomized controlled trial; Mathematics; Medicine; Computer science; Internal medicine","score_opus":0.6259681310711347,"score_gpt":0.6463079348273147,"score_spread":0.020339803756180053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012516591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03828101,0.000010285549,0.95763445,0.0017083685,0.000112404705,0.0017194004,0.00038579814,0.000017705159,0.00013059114],"genre_scores_gemma":[0.37742215,0.000020773774,0.6220876,0.00012927009,0.00005767893,0.00023433188,0.000010845733,0.000022341072,0.000014997366],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99002045,0.005295018,0.0020275812,0.0008290085,0.0011891264,0.0006387863],"domain_scores_gemma":[0.87408024,0.12441985,0.00019779075,0.0003399933,0.00035834283,0.0006037684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023636827,0.0002467993,0.0013344388,0.00024505178,0.000063697305,0.00003434925,0.00027372118,0.0003526402,0.00010808152],"category_scores_gemma":[0.34048894,0.00018623647,0.00012448952,0.0004946106,0.0009814224,0.000033149638,0.00011671257,0.0009824551,0.0000034117425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.04722837,0.0023661864,0.0072047273,0.00050208584,0.00009153755,0.00018846437,0.00063152116,0.00009165631,0.00014109857,0.6007813,0.00020961066,0.34056345],"study_design_scores_gemma":[0.017883444,0.002379817,0.008505833,0.000094939016,0.000028401506,6.35414e-7,0.00007246211,0.7048146,0.000097457436,0.2659953,0.000007388559,0.0001197002],"about_ca_topic_score_codex":0.000072835806,"about_ca_topic_score_gemma":0.00006566261,"teacher_disagreement_score":0.704723,"about_ca_system_score_codex":0.000114578244,"about_ca_system_score_gemma":0.0006544702,"threshold_uncertainty_score":0.81921},"labels":[],"label_agreement":null},{"id":"W3012656410","doi":"10.1177/0962280220902794","title":"Comparing two counterfactual-outcome approaches in causal mediation analysis of a multicategorical exposure: An application for the estimation of the effect of maternal intake of inhaled corticosteroids doses on birthweight","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Counterfactual thinking; Categorical variable; Mediation; Marginal structural model; Econometrics; Robustness (evolution); Causal inference; Regression; Medicine; Regression analysis; Outcome (game theory); Statistics; Psychology; Mathematics; Social psychology","score_opus":0.435067383054229,"score_gpt":0.5923306492432306,"score_spread":0.15726326618900166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012656410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39169574,0.000009818398,0.607298,0.00012082699,0.000012878311,0.00080268143,0.000037735434,0.000008004155,0.000014299351],"genre_scores_gemma":[0.78780454,0.0000063408447,0.21188645,0.00000763278,0.000012332362,0.00025438156,0.000015049905,0.000012843036,4.16161e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99342686,0.0030110837,0.001477538,0.0003003091,0.0015203134,0.00026390533],"domain_scores_gemma":[0.9535081,0.045357384,0.00040625807,0.0004088341,0.00020294337,0.00011653129],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0100527145,0.00014896443,0.00090628676,0.00032453905,0.00003268305,0.000008088727,0.00057084113,0.00014193325,0.000045808803],"category_scores_gemma":[0.054870296,0.00008667091,0.00008574387,0.0013668918,0.0008483601,0.00006203104,0.00016741677,0.0006362115,2.2524509e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032444333,0.00088388036,0.21106438,0.0028697427,0.00040337097,0.0000058399523,0.0035083373,0.00493326,0.019158654,0.30019155,0.000007858724,0.45372868],"study_design_scores_gemma":[0.0009503688,0.001043441,0.065800086,0.00009407912,0.00014111098,6.9484327e-7,0.00017301434,0.80794585,0.07848212,0.045298275,6.9965193e-7,0.000070253875],"about_ca_topic_score_codex":0.0001744291,"about_ca_topic_score_gemma":0.00014586459,"teacher_disagreement_score":0.8030126,"about_ca_system_score_codex":0.00010355884,"about_ca_system_score_gemma":0.00009049686,"threshold_uncertainty_score":0.9530909},"labels":[],"label_agreement":null},{"id":"W3030652012","doi":"10.1177/09622802221146313","title":"A generalization of moderated statistics to data adaptive semiparametric estimation in high-dimensional biology","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; Natural Sciences and Engineering Research Council of Canada; National Institute of Allergy and Infectious Diseases; National Science Foundation; National Cancer Institute; Fogarty International Center","keywords":"Estimator; Semiparametric regression; Computer science; Nonparametric statistics; Variance (accounting); Generalization; Semiparametric model; Parametric statistics; Econometrics; Curse of dimensionality; Statistics; Mathematics; Machine learning","score_opus":0.439192402014067,"score_gpt":0.6232240612529034,"score_spread":0.1840316592388364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030652012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045865886,0.00006193237,0.99104345,0.00043157622,0.0001834373,0.0006728504,0.0027334015,0.000018282224,0.00026849698],"genre_scores_gemma":[0.0855788,0.000018626579,0.91360617,0.00013771726,0.000024477147,0.00021617346,0.0003633714,0.000029460922,0.00002518119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9794617,0.014988076,0.0014070056,0.0008878742,0.0024292115,0.0008261317],"domain_scores_gemma":[0.9318447,0.0663247,0.00014125954,0.000760689,0.00047055812,0.00045808833],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02800124,0.00019792834,0.00074486044,0.0011509351,0.00014874389,0.000020478088,0.0009902716,0.00018126713,0.0049639135],"category_scores_gemma":[0.26511124,0.0001845022,0.000017594182,0.003501311,0.0005220545,0.000053788815,0.0017266746,0.0015993073,0.000008886387],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023847939,0.0003837792,0.00016100112,0.000064426036,0.000013099566,0.000054211738,0.000112583715,0.0008663679,0.0001925125,0.6416617,0.002209986,0.35404184],"study_design_scores_gemma":[0.00033346104,0.00039146395,0.0011727776,0.000037750186,0.0000060851125,0.000002928234,0.000050747152,0.4993646,0.00006316388,0.49841622,0.00006114703,0.0000996433],"about_ca_topic_score_codex":0.0012605113,"about_ca_topic_score_gemma":0.000119862045,"teacher_disagreement_score":0.49849826,"about_ca_system_score_codex":0.00033524784,"about_ca_system_score_gemma":0.00084789796,"threshold_uncertainty_score":0.9959457},"labels":[],"label_agreement":null},{"id":"W3031396609","doi":"10.1177/0962280220925840","title":"Robust bivariate random-effects model for accommodating outlying and influential studies in meta-analysis of diagnostic test accuracy studies","year":2020,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bivariate analysis; Random effects model; Statistics; Weighting; Point estimation; Inference; Mathematics; Confidence interval; Econometrics; Meta-analysis; Computer science; Artificial intelligence; Medicine","score_opus":0.8395150209186724,"score_gpt":0.7124022221931562,"score_spread":0.12711279872551617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3031396609","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.3220783e-7,0.4639501,0.53357863,0.00011705201,0.0000651107,0.0017772192,0.0004779125,0.000014195503,0.000019446677],"genre_scores_gemma":[0.000007973088,0.47895625,0.51907504,0.000025417185,0.00004635462,0.0018181239,0.000015719263,0.0000487832,0.0000063603425],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97230774,0.018470136,0.0041017802,0.0015217692,0.002315948,0.0012826547],"domain_scores_gemma":[0.14469956,0.85260946,0.0007049141,0.0006480127,0.00077621336,0.0005618542],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045649316,0.0008271702,0.013988162,0.0016254267,0.00019734491,0.00009249573,0.0009653121,0.000633198,0.00015049182],"category_scores_gemma":[0.9511696,0.0005514589,0.0010062382,0.0034975593,0.0020811283,0.00010624718,0.0015587939,0.0029717535,0.0000019683384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057689496,0.00021819634,0.000004241003,0.05760411,0.028930223,0.00021722498,0.00074465654,0.00000989477,4.871026e-7,0.10966393,0.00011894831,0.8024304],"study_design_scores_gemma":[0.0012825058,0.00024721993,0.0000048510315,0.007860773,0.107084766,0.0000055193136,0.0003333152,0.16162065,0.0000018284941,0.7195122,0.0015050661,0.00054126745],"about_ca_topic_score_codex":0.000060543498,"about_ca_topic_score_gemma":0.00010996867,"teacher_disagreement_score":0.9055203,"about_ca_system_score_codex":0.00026498345,"about_ca_system_score_gemma":0.0008331826,"threshold_uncertainty_score":0.9996937},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.9463831388066777,"score_gpt":0.7778418496968618,"score_spread":0.16854128910981592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041396397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1470226e-8,0.45876813,0.52903146,0.00021834402,0.00031860324,0.011048316,0.000546974,0.000023155177,0.000044997014],"genre_scores_gemma":[9.028888e-8,0.49116793,0.50475293,0.00006965491,0.00020227411,0.0036788674,0.000021273063,0.000088459696,0.000018521947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.51096505,0.47086933,0.009951133,0.0020889873,0.004582991,0.0015425098],"domain_scores_gemma":[0.04442916,0.9503744,0.0015041998,0.0015421334,0.0007138472,0.0014362484],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.5551415,0.0009410062,0.026074596,0.0012272828,0.00021299873,0.000166126,0.0022114436,0.0017680826,0.0010115993],"category_scores_gemma":[0.97361684,0.0005055639,0.0024298835,0.004074937,0.0041842386,0.00008597986,0.0010936299,0.0042431825,0.0000061557325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065810704,0.00019482462,2.5796567e-8,0.018890265,0.0032660994,0.000037228216,0.00005871476,0.0000027073675,8.033118e-8,0.38208544,0.0006756268,0.5882079],"study_design_scores_gemma":[0.019673198,0.0003341664,3.2607466e-7,0.00525555,0.020156538,0.0000033610645,0.00002529548,0.25444874,0.0000011147898,0.68005204,0.01971435,0.00033529862],"about_ca_topic_score_codex":0.00004566109,"about_ca_topic_score_gemma":0.000011289847,"teacher_disagreement_score":0.5878726,"about_ca_system_score_codex":0.00020598486,"about_ca_system_score_gemma":0.0014988476,"threshold_uncertainty_score":0.9999016},"labels":[],"label_agreement":null},{"id":"W3042988590","doi":"10.1177/0962280220938418","title":"Random effects models for complex designs","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Grains Research and Development Corporation","keywords":"Variety (cybernetics); Variance (accounting); Computer science; Set (abstract data type); Row; Table (database); Block (permutation group theory); Algorithm; Data mining; Statistics; Mathematics; Artificial intelligence","score_opus":0.7962302970634183,"score_gpt":0.7196117283011839,"score_spread":0.07661856876223438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042988590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007240582,0.00027707743,0.9819587,0.00624357,0.00022960152,0.0016497193,0.00005498449,0.00004611663,0.00946786],"genre_scores_gemma":[0.02037993,0.000026164746,0.9768267,0.0018881103,0.00021910213,0.000462135,0.000008225555,0.00004221276,0.00014739003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95328236,0.034249496,0.0015453921,0.0014513076,0.008071691,0.0013997675],"domain_scores_gemma":[0.6692301,0.3274498,0.00009053029,0.000584029,0.0006589679,0.001986556],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.108294636,0.00026070216,0.0011048993,0.00042644853,0.00024511127,0.0002660539,0.002188633,0.00032520294,0.0053314534],"category_scores_gemma":[0.55894893,0.00018935604,0.00016300775,0.0023453338,0.0015006056,0.00020311665,0.0007380665,0.0014444203,0.00023008547],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017415897,0.00016374499,0.000027355454,0.00008123762,0.00001691581,0.00017866847,0.0006469994,0.00014673578,0.015476811,0.17036843,0.02028323,0.7908683],"study_design_scores_gemma":[0.0021869962,0.000628507,0.00015298654,0.00002733665,0.0000040626414,0.000003062366,0.00024149925,0.5326016,0.002900265,0.45605767,0.005057306,0.00013870293],"about_ca_topic_score_codex":0.000039081653,"about_ca_topic_score_gemma":0.0000035775076,"teacher_disagreement_score":0.7907296,"about_ca_system_score_codex":0.00013237193,"about_ca_system_score_gemma":0.00055846333,"threshold_uncertainty_score":0.9955778},"labels":[],"label_agreement":null},{"id":"W3045459365","doi":"10.1177/0962280220941874","title":"Relative efficiencies of alternative preference-based designs for randomised trials","year":2020,"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":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preference; Selection (genetic algorithm); Clinical trial; Medicine; Treatment effect; Randomized controlled trial; Computer science; Statistics; Mathematics; Machine learning; Surgery; Internal medicine","score_opus":0.9296075659363878,"score_gpt":0.6965327909158466,"score_spread":0.2330747750205412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045459365","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012812535,0.0005124808,0.95574206,0.03672354,0.00018067606,0.00268015,0.0006604883,0.000015598733,0.0022037334],"genre_scores_gemma":[0.08223274,0.00008324645,0.91324055,0.0030521676,0.00027812645,0.0009814766,0.00003332777,0.00003129807,0.000067035646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97078145,0.019984063,0.00687445,0.00082982116,0.000757579,0.0007726598],"domain_scores_gemma":[0.59246063,0.4040659,0.0016384699,0.0004050081,0.00046664767,0.00096331746],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2742923,0.00016809713,0.0022232179,0.00043320443,0.000121001496,0.000037060716,0.00060136814,0.0002573636,0.0030276915],"category_scores_gemma":[0.79485714,0.00016365752,0.00016551645,0.0006176572,0.00081975095,0.00012038362,0.00009379201,0.0007636689,0.00011586632],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022684701,0.00019877237,0.00057495915,0.00083919504,0.0000837487,0.0000046261403,0.0027930033,0.00017650663,0.00003387137,0.97691697,0.004719494,0.011390396],"study_design_scores_gemma":[0.016640132,0.0009469269,0.0009115694,0.00026325491,0.0000113833585,3.658966e-7,0.0010473743,0.2995286,0.00048017575,0.67261153,0.0073009315,0.00025778293],"about_ca_topic_score_codex":0.00025334957,"about_ca_topic_score_gemma":0.000014782803,"teacher_disagreement_score":0.52056485,"about_ca_system_score_codex":0.0003163318,"about_ca_system_score_gemma":0.0011176531,"threshold_uncertainty_score":0.9978837},"labels":[],"label_agreement":null},{"id":"W3067784497","doi":"10.1177/0962280220948159","title":"Model-robust designs for nonlinear quantile regression","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quantile regression; Quantile; Statistics; Computer science; Nonlinear regression; Nonlinear system; Econometrics; Regression; Regression analysis; Mathematics","score_opus":0.7951379235756372,"score_gpt":0.7090320201533811,"score_spread":0.0861059034222561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3067784497","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028691744,0.00025896134,0.98637986,0.007417027,0.00021884932,0.0009185795,0.00014674914,0.000048758626,0.0043242867],"genre_scores_gemma":[0.0052181,0.00005335909,0.99265134,0.0011308487,0.0002549156,0.00022195515,0.000014145004,0.00005143934,0.0004038882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9719606,0.014924723,0.0017212112,0.0016390933,0.008360325,0.0013940642],"domain_scores_gemma":[0.88145715,0.11417745,0.00014888597,0.0008597267,0.0010108984,0.0023458672],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.084480844,0.0002800814,0.0009080352,0.0004637276,0.00028603678,0.00024882978,0.0022912773,0.0004431602,0.0057902667],"category_scores_gemma":[0.5042462,0.00019268191,0.00015260662,0.0024860867,0.0013575219,0.00020611913,0.00089887343,0.001857771,0.00027093448],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012057677,0.00027378043,0.00008651612,0.000059193586,0.000011133593,0.00016315164,0.0006796515,0.00063424936,0.014709645,0.07574068,0.03393458,0.8725017],"study_design_scores_gemma":[0.00074609247,0.0005838146,0.000049967417,0.00006396831,0.0000037540183,0.0000034849052,0.00058337464,0.8053923,0.004387172,0.17893496,0.0090683885,0.00018266535],"about_ca_topic_score_codex":0.000025376079,"about_ca_topic_score_gemma":0.0000061660658,"teacher_disagreement_score":0.872319,"about_ca_system_score_codex":0.00013945009,"about_ca_system_score_gemma":0.0009605286,"threshold_uncertainty_score":0.99511856},"labels":[],"label_agreement":null},{"id":"W3088077156","doi":"10.1177/0962280220951834","title":"Pattern discovery of health curves using an ordered probit model with Bayesian smoothing and functional principal component analysis","year":2020,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; Actua; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Principal component analysis; Bayesian probability; Functional principal component analysis; Econometrics; Smoothing; Component (thermodynamics); Probit model; Functional data analysis; Statistics; Mathematics; Ordered probit; Computer science; Physics","score_opus":0.45791737199466426,"score_gpt":0.5783035747154114,"score_spread":0.12038620272074713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088077156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009568703,0.00013288003,0.98706007,0.0024988635,0.000018073757,0.00043948984,0.00015175933,0.000019324983,0.000110847395],"genre_scores_gemma":[0.17842901,0.000061600986,0.8210116,0.00038957372,0.00002988531,0.000028605325,0.00001998326,0.00002401304,0.0000057630537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9885824,0.006743801,0.001053736,0.0006859082,0.0022638,0.00067040394],"domain_scores_gemma":[0.9826916,0.015760513,0.00016499308,0.00030587695,0.00027110594,0.0008059289],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014783781,0.00021014387,0.0010318017,0.00025893538,0.00014510805,0.000057095793,0.000271216,0.00012805915,0.00051729335],"category_scores_gemma":[0.035985198,0.0001548786,0.000047648922,0.0011687451,0.0009714767,0.00012164433,0.00029186308,0.001188179,4.2177777e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005859582,0.0012781692,0.009159707,0.0060458314,0.0004736564,0.00013579492,0.0020727953,0.0007840727,0.00069062185,0.458226,0.00014769082,0.5203997],"study_design_scores_gemma":[0.0004736847,0.00048384006,0.005964611,0.00047586096,0.00007677382,0.0000044786475,0.00027355787,0.8470465,0.00004720301,0.14499152,0.0000054820243,0.00015651266],"about_ca_topic_score_codex":0.00050045433,"about_ca_topic_score_gemma":0.0001139538,"teacher_disagreement_score":0.8462624,"about_ca_system_score_codex":0.00009077212,"about_ca_system_score_gemma":0.00082477904,"threshold_uncertainty_score":0.9721351},"labels":[],"label_agreement":null},{"id":"W3109789378","doi":"10.1177/09622802211032713","title":"General regression methods for respondent-driven sampling data","year":2021,"lang":"en","type":"preprint","venue":"Statistical Methods in Medical Research","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de Santé Publique du Québec; Public Health Ontario; University of Toronto; Toronto Metropolitan University; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Homophily; Multivariate statistics; Respondent; Sampling (signal processing); Covariate; Regression; Psychology; Sample (material); Econometrics; Statistics; Computer science; Social psychology; Mathematics; Political science","score_opus":0.6374063881264357,"score_gpt":0.7194754488290467,"score_spread":0.082069060702611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109789378","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001516068,0.002790012,0.9828051,0.0055528157,0.0015928638,0.0026319316,0.0009603783,0.00010637972,0.0020444957],"genre_scores_gemma":[0.00034710835,0.0019541536,0.98842186,0.0004895453,0.0016835224,0.00074030785,0.0043827314,0.00021753226,0.0017632658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9577826,0.028123276,0.0023540116,0.003704597,0.0055948435,0.0024406547],"domain_scores_gemma":[0.8643458,0.12321013,0.0003468697,0.006517854,0.0020630355,0.0035163031],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.08707008,0.0007106565,0.002566408,0.0012275352,0.00029606328,0.00025488719,0.0031717161,0.0022688687,0.0043087215],"category_scores_gemma":[0.4814865,0.0005817213,0.00023152672,0.0013176671,0.0016260821,0.00011443286,0.012513649,0.01207388,0.00003259376],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014898073,0.0005693283,0.00021723015,0.0025651467,0.00020548608,0.001248026,0.0011042231,0.0000144143805,0.005409533,0.0043244804,0.009154952,0.97369736],"study_design_scores_gemma":[0.006210757,0.0012724191,0.0038953999,0.011498689,0.0005140863,0.00023120966,0.0080503505,0.72132134,0.0031943377,0.13013539,0.112173945,0.0015020486],"about_ca_topic_score_codex":0.00043584596,"about_ca_topic_score_gemma":0.0001163561,"teacher_disagreement_score":0.9721953,"about_ca_system_score_codex":0.0008316285,"about_ca_system_score_gemma":0.0069206473,"threshold_uncertainty_score":0.9996634},"labels":[],"label_agreement":null},{"id":"W3120262376","doi":"10.1177/09622802211046383","title":"Modeling treatment effect modification in multidrug-resistant tuberculosis in an individual patientdata meta-analysis","year":2021,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Université de Montréal; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Observational study; Meta-analysis; Covariate; Confounding; Random effects model; Context (archaeology); Marginal structural model; Estimator; Econometrics; Computer science; Medicine; Treatment effect; Statistics; Mathematics; Internal medicine; Biology","score_opus":0.7887158097793469,"score_gpt":0.6989781964767243,"score_spread":0.08973761330262253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120262376","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000049933296,0.46416554,0.53227776,0.000061270744,0.0000663295,0.0018738816,0.0013500918,0.000023362292,0.00013181956],"genre_scores_gemma":[0.00006318186,0.431241,0.56563056,0.000011508209,0.000040106643,0.0022307243,0.0006947286,0.0000738708,0.000014321911],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9131184,0.07446869,0.0040280917,0.0024109366,0.0042448305,0.0017290364],"domain_scores_gemma":[0.8562232,0.14034097,0.0002528275,0.0018259508,0.00035127896,0.0010057165],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057299525,0.0010217581,0.009985981,0.0030696231,0.00012652688,0.00022584386,0.0015040996,0.0012802621,0.0035765094],"category_scores_gemma":[0.15603952,0.00068045146,0.0011879936,0.0063085975,0.00057263474,0.00012534282,0.00057898037,0.004053512,0.000019121275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045548146,0.0013170602,0.000015832842,0.004039193,0.0069011105,0.0006748373,0.00029939736,0.000034461493,4.1280705e-7,0.04574104,0.000011633105,0.94091946],"study_design_scores_gemma":[0.0022097642,0.0019816118,0.00011859031,0.006252567,0.121673495,0.000016877528,0.00044066954,0.651945,0.000007576581,0.2058755,0.007384717,0.0020936376],"about_ca_topic_score_codex":0.0023221767,"about_ca_topic_score_gemma":0.0029406955,"teacher_disagreement_score":0.93882585,"about_ca_system_score_codex":0.0012993074,"about_ca_system_score_gemma":0.0012610325,"threshold_uncertainty_score":0.99956465},"labels":[],"label_agreement":null},{"id":"W3123045227","doi":"10.1177/0962280220986193","title":"Clustered longitudinal data subject to irregular observation","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Cluster analysis; Econometrics; Random effects model; Computer science; Outcome (game theory); Statistics; Parametric statistics; Mathematics; Medicine","score_opus":0.5085080922538269,"score_gpt":0.6444488331804581,"score_spread":0.13594074092663122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123045227","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04070299,0.0003037187,0.9276694,0.019676473,0.00046959412,0.00044630462,0.00012285961,0.000044419885,0.010564257],"genre_scores_gemma":[0.18619211,0.00009826728,0.8114044,0.00043678377,0.00048098151,0.000042843658,0.00020491179,0.000016927057,0.0011227712],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9868555,0.007569274,0.00051649136,0.00086686783,0.0032903587,0.00090148044],"domain_scores_gemma":[0.98554754,0.012114097,0.000025777636,0.00086588087,0.00050718564,0.00093953195],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03869969,0.00010195205,0.00030856678,0.00013794006,0.00036594033,0.00013743577,0.0013294822,0.000233623,0.009338697],"category_scores_gemma":[0.1322972,0.000094582865,0.000028253513,0.0020320693,0.0010289962,0.0002180762,0.0005799722,0.0010440989,0.00005974565],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011485646,0.0003126396,0.16796614,0.00009039384,0.0000153931,0.00084691704,0.0011676876,6.629619e-7,0.00013918633,0.053414464,0.0058136135,0.77011806],"study_design_scores_gemma":[0.00047447393,0.000066693865,0.8149201,0.00014285823,0.000011290306,0.0000012293062,0.0013327575,0.0024834352,0.00018638241,0.10494811,0.075217515,0.00021511957],"about_ca_topic_score_codex":0.0034373805,"about_ca_topic_score_gemma":0.016919695,"teacher_disagreement_score":0.76990294,"about_ca_system_score_codex":0.00018956841,"about_ca_system_score_gemma":0.0021389492,"threshold_uncertainty_score":0.9915669},"labels":[],"label_agreement":null},{"id":"W3132771408","doi":"10.1177/0962280220983587","title":"Marginal analysis of bivariate mixed responses with measurement error and misclassification","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; Western University; University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Bivariate analysis; Computer science; Estimator; Binary number; Observational error; Statistics; Component (thermodynamics); Binary data; Econometrics; Data mining; Mathematics","score_opus":0.16133991538509762,"score_gpt":0.498852410879384,"score_spread":0.33751249549428636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132771408","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11236438,0.0007662076,0.8848641,0.0007304597,0.000038768787,0.00011815448,0.000042763422,0.0000024797646,0.0010726822],"genre_scores_gemma":[0.39994752,0.00007418007,0.5997249,0.00003149653,0.000024291117,0.000023570303,0.000031408174,0.000007342319,0.00013532865],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947074,0.0031257337,0.0003127784,0.00043173044,0.0011266695,0.00029569058],"domain_scores_gemma":[0.9976812,0.0012649855,0.000038167127,0.00031156192,0.00046645768,0.00023760684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0066072647,0.00009358454,0.00026534902,0.0001784396,0.00005016662,0.000013750946,0.0001624891,0.0001514384,0.00038188387],"category_scores_gemma":[0.014848389,0.00007424886,0.000030341083,0.00072743546,0.0006701163,0.0000014117202,0.00013323907,0.00029945374,8.6595315e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029928638,0.0008483508,0.018335398,0.0002909604,0.0014127821,0.0000797921,0.0003308236,0.00011255993,0.23417914,0.16969688,0.0008233182,0.5708971],"study_design_scores_gemma":[0.0008199591,0.00070697156,0.96041995,0.000067549874,0.00017878042,0.000011904681,0.00039973698,0.0015043442,0.021574184,0.011089107,0.0030733128,0.00015419362],"about_ca_topic_score_codex":0.000038979008,"about_ca_topic_score_gemma":0.0001833592,"teacher_disagreement_score":0.94208455,"about_ca_system_score_codex":0.00002078376,"about_ca_system_score_gemma":0.00064478855,"threshold_uncertainty_score":0.99345},"labels":[],"label_agreement":null},{"id":"W3137061630","doi":"10.1177/0962280221997505","title":"Variable selection for causal mediation analysis using LASSO-based methods","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Propensity score matching; Estimator; Lasso (programming language); Inverse probability weighting; Causal inference; Weighting; Econometrics; Computer science; Statistics; Regularization (linguistics); Marginal structural model; Mediation; Mathematics; Artificial intelligence; Medicine","score_opus":0.5215065702757662,"score_gpt":0.7100065237874281,"score_spread":0.18849995351166193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137061630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019355651,0.00004328631,0.99779636,0.00040502223,0.00012104001,0.00048011853,0.000058161142,0.00011392987,0.0007885368],"genre_scores_gemma":[0.0012366974,0.000014097847,0.9979378,0.00011941076,0.00013636843,0.00032396664,0.00007088388,0.00004442879,0.00011634696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98435867,0.011241771,0.0009072859,0.00072414964,0.0018216654,0.000946461],"domain_scores_gemma":[0.8953174,0.102392346,0.00011456134,0.00041432946,0.0013205303,0.00044085152],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041286454,0.00020476372,0.0007861965,0.0007713691,0.00019864681,0.000071794384,0.00031447757,0.000482109,0.0035353529],"category_scores_gemma":[0.3507045,0.00019208113,0.000109384106,0.0045487126,0.00038521344,0.00010783855,0.0001754806,0.0014101624,0.0000024794736],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008303755,0.0002763541,0.0005156622,0.0002494671,0.00015091288,0.00003501273,0.00006247034,0.000111034686,0.012632136,0.8384326,0.00045869386,0.1469926],"study_design_scores_gemma":[0.0002782105,0.000088296096,0.000086425636,0.000043244305,0.00009275021,0.0000031815628,0.000060081424,0.39253995,0.015958836,0.5901157,0.0006111438,0.00012215698],"about_ca_topic_score_codex":0.00013045737,"about_ca_topic_score_gemma":0.0002460665,"teacher_disagreement_score":0.3924289,"about_ca_system_score_codex":0.0006267337,"about_ca_system_score_gemma":0.0016252755,"threshold_uncertainty_score":0.99737555},"labels":[],"label_agreement":null},{"id":"W3154875751","doi":"10.1177/09622802211002861","title":"A method for systematically ranking therapeutic drug candidates using multiple uncertain screening criteria","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Alberta Prion Research Institute; Canadian Institutes of Health Research","keywords":"Ranking (information retrieval); Computer science; Robustness (evolution); Data mining; Machine learning; Artificial intelligence","score_opus":0.23236172444489472,"score_gpt":0.5975037064072967,"score_spread":0.36514198196240194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154875751","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026913738,0.0006398978,0.99460757,0.0029186145,0.00037258078,0.00075795595,0.00004287373,0.00006736043,0.0003240327],"genre_scores_gemma":[0.012467497,0.00001557577,0.98647714,0.00052792364,0.00016088696,0.00022968238,0.00002045687,0.000040465235,0.00006035118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.967431,0.02591637,0.0011791425,0.0012169955,0.0029450913,0.0013113639],"domain_scores_gemma":[0.83208364,0.16536377,0.00011032957,0.00076834345,0.0010116567,0.0006622728],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05767273,0.00028791782,0.00085151824,0.00048394248,0.00038312704,0.00051074725,0.0015202388,0.00021043143,0.00038263388],"category_scores_gemma":[0.09407316,0.0002566712,0.00014129408,0.002074772,0.00036659857,0.00029001274,0.0011794374,0.0012295716,0.0000073923256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112984526,0.00014973978,0.000113630806,0.00068499474,0.000064490916,0.00038905107,0.0006398821,0.0013949518,0.0019623109,0.32262325,0.00016943226,0.6716953],"study_design_scores_gemma":[0.00076488976,0.00004289553,0.00027719513,0.00051000726,0.000011597109,0.000081913066,0.00021134238,0.72824544,0.0011880716,0.26788536,0.00057715137,0.0002041173],"about_ca_topic_score_codex":0.0003403022,"about_ca_topic_score_gemma":0.00008639785,"teacher_disagreement_score":0.7268505,"about_ca_system_score_codex":0.0003056547,"about_ca_system_score_gemma":0.00203967,"threshold_uncertainty_score":0.99998856},"labels":[],"label_agreement":null},{"id":"W3154888856","doi":"10.1177/09622802211003620","title":"Calibration of surgical tools using multilevel modeling with LINEX loss function: Theory and experiment","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Aga Khan Foundation","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exponential function; Bayesian probability; Computer science; Calibration; Function (biology); Mean squared error; Likelihood function; Linear model; Multilevel model; Statistics; Mathematics; Algorithm; Artificial intelligence; Machine learning; Estimation theory","score_opus":0.34924827873567577,"score_gpt":0.5901490617878591,"score_spread":0.24090078305218332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154888856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08856938,0.00035561709,0.90891284,0.0004149827,0.000047357782,0.00018651118,0.000008347581,0.000013705729,0.0014912403],"genre_scores_gemma":[0.6673646,0.000069352136,0.33230126,0.00008515781,0.00008929749,0.000014399565,0.000018505996,0.000014312649,0.00004312359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942781,0.0029140997,0.00051654037,0.00038883433,0.0015359404,0.0003664929],"domain_scores_gemma":[0.9834494,0.01546834,0.000029195207,0.0001810072,0.0003744055,0.00049764384],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008616571,0.00011350804,0.00042048428,0.00014001424,0.00007890482,0.000028351928,0.000055402277,0.00018653652,0.0038780188],"category_scores_gemma":[0.014378054,0.00008223785,0.00003262971,0.0004429034,0.0005691193,0.00006611498,0.00011146043,0.00080918794,9.937127e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004135782,0.00044981047,0.0012432524,0.00023217707,0.00007249648,0.0019323479,0.00043108172,0.00081578206,0.0016229264,0.29910794,0.0000042197025,0.6899522],"study_design_scores_gemma":[0.0044601085,0.0003512517,0.000597256,0.00041751424,0.000026097478,0.00011981024,0.0008846613,0.9730963,0.0017930232,0.01775992,0.00038797891,0.00010605413],"about_ca_topic_score_codex":0.000025482503,"about_ca_topic_score_gemma":0.0000031176144,"teacher_disagreement_score":0.97228056,"about_ca_system_score_codex":0.000061086874,"about_ca_system_score_gemma":0.000560103,"threshold_uncertainty_score":0.9970326},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.25922347666239887,"score_gpt":0.6037200504579326,"score_spread":0.3444965737955338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156127058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045256697,0.0005145753,0.9528596,0.00061816757,0.000057023477,0.00028176262,0.00014191635,0.000016950635,0.00025334678],"genre_scores_gemma":[0.28845432,0.00017882734,0.7111826,0.000055372508,0.000052179108,0.000026089348,0.00003208412,0.000012251394,0.000006274106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9592489,0.035278704,0.0011455385,0.0009992928,0.0023821439,0.00094544544],"domain_scores_gemma":[0.8993601,0.09861114,0.00019967783,0.000868896,0.0006125816,0.0003476097],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.068066925,0.00020616443,0.0006111187,0.0002901477,0.00021022433,0.00008883937,0.0016766789,0.00017571523,0.0002010857],"category_scores_gemma":[0.25429446,0.00014197883,0.00002963809,0.0015473091,0.0005495522,0.00018986447,0.0017218956,0.003882219,0.000001009939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014561582,0.0003091747,0.10246094,0.0013944777,0.000019611178,0.00027743608,0.0022418208,0.00059658044,0.0003110035,0.01890256,0.000031116597,0.8733097],"study_design_scores_gemma":[0.0004521105,0.0011231919,0.09781223,0.00057918543,0.0000055033865,0.000049244045,0.0002797451,0.8923295,0.0003424877,0.00685678,0.000056176847,0.00011380251],"about_ca_topic_score_codex":0.00072474027,"about_ca_topic_score_gemma":0.00014437834,"teacher_disagreement_score":0.891733,"about_ca_system_score_codex":0.00010951741,"about_ca_system_score_gemma":0.0017909552,"threshold_uncertainty_score":0.9984159},"labels":[],"label_agreement":null},{"id":"W3160907971","doi":"10.1177/09622802211009265","title":"Functional joint models for chronic kidney disease in kidney transplant recipients","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Kidney disease; Renal function; Kidney transplantation; Medicine; Kidney; Transplantation; Intensive care medicine; Internal medicine","score_opus":0.3647057370632163,"score_gpt":0.5578741015699356,"score_spread":0.19316836450671926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160907971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029777325,0.00017232745,0.9899998,0.004733354,0.0005244487,0.00068914256,0.0011927892,0.000030807652,0.0023595646],"genre_scores_gemma":[0.009686043,0.0002478474,0.9877138,0.0007036189,0.00025706078,0.00070847035,0.00017002836,0.00005426748,0.0004588331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.987587,0.0062497575,0.0012289673,0.0010006637,0.0025488532,0.0013847831],"domain_scores_gemma":[0.94364446,0.05180615,0.00006639858,0.00060854206,0.00059800013,0.003276469],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019351363,0.00027864994,0.00077637105,0.00036028933,0.00015008479,0.00006671039,0.00040863542,0.00032124665,0.010062935],"category_scores_gemma":[0.36492974,0.00024075391,0.000119632474,0.0009707271,0.0007385578,0.00008494898,0.00024551075,0.001887278,0.000026414013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041729587,0.00063951436,0.00029573566,0.0008708735,0.000023455705,0.0006011257,0.00012602657,0.000011532292,0.00028407277,0.817877,0.009623797,0.1692296],"study_design_scores_gemma":[0.0017371328,0.0001554923,0.0032775837,0.0012343882,0.000019394061,0.000007718532,0.000030095956,0.19045368,0.00029225543,0.8009631,0.0016077013,0.00022148158],"about_ca_topic_score_codex":0.000075248834,"about_ca_topic_score_gemma":0.000048545662,"teacher_disagreement_score":0.34557837,"about_ca_system_score_codex":0.0005149524,"about_ca_system_score_gemma":0.0047832304,"threshold_uncertainty_score":0.990842},"labels":[],"label_agreement":null},{"id":"W3178431826","doi":"10.1177/09622802211008945","title":"A competing risks model with binary time varying covariates for estimation of breast cancer risks in <i>BRCA1</i> families","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"BRCA gene mutations in cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; Western University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Center for Advancing Translational Sciences; Canadian Cancer Society","keywords":"Covariate; Breast cancer; Medicine; Estimator; Ovarian cancer; Prophylactic Surgery; Oncology; Statistics; Cancer; Econometrics; Internal medicine; Mathematics","score_opus":0.11853154554642018,"score_gpt":0.528629270064907,"score_spread":0.4100977245184868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3178431826","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06869139,0.00061959354,0.928318,0.0010236327,0.000049552782,0.00034973587,0.0004037814,0.0000059957024,0.0005382937],"genre_scores_gemma":[0.3215249,0.00028102714,0.6776303,0.00007944208,0.000049004346,0.00026360445,0.00011700763,0.00002281373,0.00003193483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655235,0.001330102,0.00046138148,0.00049784046,0.00069544895,0.00046286988],"domain_scores_gemma":[0.99602336,0.0030437831,0.00006211402,0.0002642031,0.0004600582,0.00014648355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050871246,0.00013139728,0.00031487946,0.00015685619,0.000078528545,0.000019710385,0.0002347839,0.00022372641,0.00023319773],"category_scores_gemma":[0.009787415,0.00011780106,0.000033070508,0.00056268525,0.0005469888,0.0000065329386,0.00022463848,0.0005042624,0.0000014828353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017277149,0.0005537933,0.004128196,0.00076522905,0.00014295301,0.000092999755,0.0007190092,0.16304535,0.17630629,0.004547334,0.00065181236,0.6473193],"study_design_scores_gemma":[0.0015300905,0.00018856401,0.0058416263,0.00034828013,0.000017521203,0.000019129,0.00032993316,0.9557281,0.02634043,0.009383134,0.00009940964,0.00017373869],"about_ca_topic_score_codex":0.00052250805,"about_ca_topic_score_gemma":0.00016920481,"teacher_disagreement_score":0.79268277,"about_ca_system_score_codex":0.00015016133,"about_ca_system_score_gemma":0.002035576,"threshold_uncertainty_score":0.9985536},"labels":[],"label_agreement":null},{"id":"W3182035769","doi":"10.1177/09622802211025989","title":"Estimation of ordinal population with multi-observer ranked set samples using ties information","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Categorical variable; Ordinal data; Ranking (information retrieval); Estimator; Statistics; Data mining; Ordinal regression; Computer science; Simple random sample; Data set; Sampling (signal processing); Population; Mathematics; Artificial intelligence","score_opus":0.5037992234895545,"score_gpt":0.6368357119655043,"score_spread":0.13303648847594973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182035769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013850411,0.000017646098,0.9846031,0.00040491068,0.000038176386,0.00033811977,0.00037039147,0.000032393626,0.00034484244],"genre_scores_gemma":[0.23115256,0.0000090885405,0.7682366,0.000035370285,0.000013985872,0.00005654676,0.00046437082,0.0000109957655,0.000020504356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946416,0.0021166892,0.00092085317,0.00025994726,0.0016688334,0.00039207644],"domain_scores_gemma":[0.9860641,0.012381294,0.00014197062,0.00030075907,0.0008351345,0.00027675487],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054951673,0.00014158258,0.00039147193,0.00021910951,0.00015722598,0.0000578558,0.00018344351,0.00018425174,0.0026083328],"category_scores_gemma":[0.07659307,0.00011971439,0.000034951576,0.0011343615,0.0004894719,0.00023987588,0.00011124284,0.00059780444,0.000015191922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007310159,0.00021998824,0.0009190613,0.0005039882,0.000024571,0.000011807876,0.00022859825,0.000257065,0.00010908933,0.8508901,0.00027340083,0.14648922],"study_design_scores_gemma":[0.0012927342,0.00006353914,0.05908398,0.00031525272,0.000032450967,0.000025509407,0.00053575484,0.6429391,0.0009494482,0.29441065,0.00017727358,0.00017434484],"about_ca_topic_score_codex":0.00030602355,"about_ca_topic_score_gemma":0.00008114307,"teacher_disagreement_score":0.642682,"about_ca_system_score_codex":0.00017535948,"about_ca_system_score_gemma":0.00044695704,"threshold_uncertainty_score":0.9983034},"labels":[],"label_agreement":null},{"id":"W3187850904","doi":"10.1177/09622802211034219","title":"The change in estimate method for selecting confounders: A simulation study","year":2021,"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; The Quebec Population Health Research Network","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Confounding; Statistics; Confidence interval; Estimator; Standard error; Computer science; Econometrics; Medicine; Mathematics","score_opus":0.7422332657896927,"score_gpt":0.7739657669283295,"score_spread":0.03173250113863679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187850904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063290726,0.00008118444,0.99552083,0.0011836162,0.00007646153,0.0016915457,0.000008464115,0.000065411565,0.00073960674],"genre_scores_gemma":[0.04629285,0.000028449831,0.9520183,0.000087726316,0.00008300593,0.0013947804,0.000004344451,0.000034690347,0.000055817825],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863074,0.009826011,0.000821649,0.0005492646,0.0015523364,0.00094335777],"domain_scores_gemma":[0.7643433,0.23438004,0.00006509401,0.0003751093,0.00062852463,0.00020790045],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05094796,0.00015745021,0.0004554585,0.00019815358,0.00024147563,0.00010273138,0.0003795447,0.00019748378,0.00026126826],"category_scores_gemma":[0.44169468,0.00011712031,0.00003508757,0.0011298069,0.00031199434,0.00010040574,0.0003140678,0.0015660628,0.000002923347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008729544,0.0003988812,0.00034723623,0.00010453152,0.000013276713,0.00011727054,0.0009702571,0.000012328342,0.00009860739,0.37082416,0.000048281327,0.62697786],"study_design_scores_gemma":[0.0005722842,0.0002308354,0.00058702467,0.00011393518,0.000006145511,0.0000040217524,0.0013675393,0.28923053,0.00028485057,0.70702195,0.00048695988,0.000093935574],"about_ca_topic_score_codex":0.0001906053,"about_ca_topic_score_gemma":0.0015176302,"teacher_disagreement_score":0.6268839,"about_ca_system_score_codex":0.0003028641,"about_ca_system_score_gemma":0.00042052753,"threshold_uncertainty_score":0.9772488},"labels":[],"label_agreement":null},{"id":"W3196511958","doi":"10.1177/09622802211037070","title":"A unified Bayesian framework for exact inference of area under the receiver operating characteristic curve","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; Simon Fraser University","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; Cancer Prevention and Research Institute of Texas","keywords":"Receiver operating characteristic; Inference; Frequentist inference; Computer science; Bayesian probability; Gibbs sampling; Computation; Mathematics; Bayesian inference; Algorithm; Statistics; Mathematical optimization; Artificial intelligence","score_opus":0.3778272087755035,"score_gpt":0.6123346236579378,"score_spread":0.23450741488243426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196511958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001670658,0.000090843496,0.9923384,0.0025474622,0.00024954212,0.0006051072,0.00019721656,0.000021795764,0.002278982],"genre_scores_gemma":[0.07990664,0.0001068472,0.9191376,0.0002994515,0.00012659501,0.00024415276,0.000016210415,0.000038849117,0.00012363816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9852623,0.009872924,0.0012491187,0.00069570326,0.0019125625,0.0010073946],"domain_scores_gemma":[0.6579202,0.33941108,0.00015376329,0.0008101603,0.0011785992,0.00052619213],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023845896,0.00025519144,0.0008579921,0.00015260643,0.00025030237,0.00010438244,0.0007655855,0.00041737562,0.007038642],"category_scores_gemma":[0.59726965,0.00017321474,0.00009374137,0.0011283922,0.001393494,0.000050799394,0.00042787043,0.0023780314,0.0000076265082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006614699,0.0001978401,0.0001738298,0.00030079615,0.000031040345,0.00006311695,0.0002822956,9.429383e-7,0.00048109298,0.7898254,0.00024873138,0.20832878],"study_design_scores_gemma":[0.00041949097,0.00022797992,0.0051189563,0.0007496235,0.000025363022,0.000010061372,0.0009839492,0.03197926,0.0013082363,0.95865065,0.00033300178,0.00019344725],"about_ca_topic_score_codex":0.00007778921,"about_ca_topic_score_gemma":0.0000425974,"teacher_disagreement_score":0.57342374,"about_ca_system_score_codex":0.000114232585,"about_ca_system_score_gemma":0.0011698599,"threshold_uncertainty_score":0.9999235},"labels":[],"label_agreement":null},{"id":"W3200290661","doi":"10.1177/09622802211041759","title":"Flexible extension of the accelerated failure time model to account for nonlinear and time-dependent effects of covariates on the hazard","year":2021,"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":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Proportional hazards model; Accelerated failure time model; Hazard ratio; Hazard; Nonlinear system; Econometrics; Parametric statistics; Statistics; Survival analysis; Computer science; Mathematics; Confidence interval","score_opus":0.47478398657457216,"score_gpt":0.5943613382920601,"score_spread":0.1195773517174879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200290661","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049943913,0.0005564245,0.8416584,0.103330635,0.00023494077,0.0025284812,0.00084494665,0.000014187768,0.00088803103],"genre_scores_gemma":[0.062385753,0.00013837869,0.92813003,0.007303695,0.00017784681,0.00044807378,0.000032933174,0.000057931324,0.0013253541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993367,0.0033217196,0.0018550882,0.0005018007,0.00052433385,0.00043001692],"domain_scores_gemma":[0.94253075,0.05600876,0.0003012624,0.00054328016,0.0003697599,0.0002462088],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.061265983,0.00011917557,0.0007924514,0.0001848962,0.00014061971,0.000039438513,0.00041105223,0.00019630938,0.00083726406],"category_scores_gemma":[0.24118736,0.00008776765,0.000056697732,0.0004508292,0.0003153905,0.000049547805,0.0002971981,0.0005429,0.000108910666],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000356903,0.00065005606,0.00050623936,0.0022095959,0.0001307818,0.0000093804665,0.0014389101,0.0012372913,0.0036258497,0.934119,0.039039113,0.016676899],"study_design_scores_gemma":[0.0010059556,0.00028964135,0.0022494171,0.00053598464,0.000007986479,0.0000024102426,0.00022251523,0.72626126,0.0054672323,0.2613273,0.002477655,0.00015265409],"about_ca_topic_score_codex":0.00011067517,"about_ca_topic_score_gemma":0.000025916263,"teacher_disagreement_score":0.7250239,"about_ca_system_score_codex":0.00016675486,"about_ca_system_score_gemma":0.0006376977,"threshold_uncertainty_score":0.9666242},"labels":[],"label_agreement":null},{"id":"W3201651551","doi":"10.1177/09622802241293776","title":"A Bayesian hierarchical model for disease mapping that accounts for scaling and heavy-tailed latent effects","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"Institut de Valorisation des Données","keywords":"Bayesian probability; Hierarchical database model; Bayesian hierarchical modeling; Scaling; Econometrics; Statistics; Multilevel model; Bayesian inference; Computer science; Mathematics; Data mining","score_opus":0.2650383660648522,"score_gpt":0.5778734444830911,"score_spread":0.3128350784182389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201651551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002866192,0.0005507054,0.9930163,0.002931693,0.00030173172,0.0021637937,0.00048091752,0.00009704537,0.00017121072],"genre_scores_gemma":[0.040123064,0.00011436816,0.95742667,0.0002050582,0.00023214796,0.0016783015,0.000021674572,0.00008693075,0.000111795795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99222386,0.0027117613,0.0008176086,0.0011141496,0.0016947633,0.0014378859],"domain_scores_gemma":[0.8378426,0.16018634,0.000038506947,0.00035254238,0.00020631816,0.0013737273],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.021382397,0.00033955587,0.00082491164,0.00047713713,0.00028686385,0.0003022691,0.0004415793,0.0003570331,0.00022795475],"category_scores_gemma":[0.1350835,0.00026420498,0.00013547779,0.00054102746,0.0009812105,0.00010464488,0.00033440316,0.001531547,0.000004581027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032135923,0.00010558368,0.00008352853,0.0037912382,0.000030098385,0.000109514105,0.0002163227,8.9513185e-7,0.000038103462,0.5185557,0.0007277503,0.47601992],"study_design_scores_gemma":[0.000496791,0.00009670924,0.0002408475,0.0009507031,0.00002867685,0.000003906557,0.00002627069,0.48945644,0.000035081288,0.508286,0.000220653,0.00015792115],"about_ca_topic_score_codex":0.000013587699,"about_ca_topic_score_gemma":0.000008505326,"teacher_disagreement_score":0.48945555,"about_ca_system_score_codex":0.00018116992,"about_ca_system_score_gemma":0.0007325786,"threshold_uncertainty_score":0.999981},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8608263610088677,"score_gpt":0.7112668188145757,"score_spread":0.14955954219429202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202627776","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027746804,0.78792185,0.081031285,0.12451503,0.0008255036,0.004760219,0.00038684663,0.00007853316,0.00045300758],"genre_scores_gemma":[0.000004392932,0.9416707,0.049082246,0.007616272,0.0004301069,0.0007908564,0.000012314384,0.00005359166,0.00033947703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9131244,0.079451844,0.002001151,0.0011628623,0.0032886125,0.0009711604],"domain_scores_gemma":[0.47718894,0.5197455,0.0003790523,0.0021173414,0.0002098997,0.00035924636],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07663086,0.0004390717,0.0023014732,0.00010120436,0.00074841484,0.000056323137,0.0018773928,0.00057314517,0.0030832666],"category_scores_gemma":[0.8132775,0.00016738178,0.00047951887,0.0017670065,0.004007096,0.000028162016,0.0029370508,0.0071232305,0.000023621536],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037788217,0.00023665061,0.0003893369,0.009456234,0.00020811723,0.00008391228,0.00015079866,0.0000016515329,3.6276268e-7,0.07566547,0.20929672,0.70447296],"study_design_scores_gemma":[0.00014239861,0.00003487349,0.00007089466,0.0038654427,0.00012792382,0.000049343984,0.000088910536,0.000040910683,8.696306e-7,0.11378775,0.88163525,0.0001554232],"about_ca_topic_score_codex":0.0007029774,"about_ca_topic_score_gemma":0.00015498642,"teacher_disagreement_score":0.7366466,"about_ca_system_score_codex":0.0011630781,"about_ca_system_score_gemma":0.00097256835,"threshold_uncertainty_score":0.9987034},"labels":[],"label_agreement":null},{"id":"W3215501451","doi":"10.1177/09622802211055856","title":"Impact of minimal sufficient balance, minimization, and stratified permuted blocks on bias and power in the estimation of treatment effect in sequential clinical trials with a binary endpoint","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences","keywords":"Covariate; Statistics; Restricted randomization; Randomization; Econometrics; Predictability; Mathematics; Selection bias; Minification; Clinical trial; Medicine; Mathematical optimization","score_opus":0.686350801538035,"score_gpt":0.717561028463486,"score_spread":0.031210226925451057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215501451","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79450786,0.000097308955,0.20255795,0.0005207043,0.000097801814,0.001620686,0.000256292,0.000007878632,0.00033350123],"genre_scores_gemma":[0.47264802,0.0001374428,0.52702206,0.00002104905,0.00003193752,0.00010546392,0.000010546113,0.000016981327,0.0000064553205],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89229393,0.09926508,0.0044318,0.000999809,0.0022582961,0.0007510997],"domain_scores_gemma":[0.40963176,0.5887896,0.0004020772,0.0005282532,0.00029138592,0.00035693593],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.121122964,0.0003039556,0.0022885394,0.00043822557,0.000047508474,0.000045050212,0.0002649986,0.00043810657,0.0008034641],"category_scores_gemma":[0.7212409,0.00016438031,0.00014956587,0.0012916963,0.0018580745,0.000036707308,0.00015655189,0.0013108809,6.596541e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028312596,0.012760579,0.07703592,0.0015145233,0.0005888199,0.0027213783,0.0039113215,0.0003391545,0.0012000247,0.19387706,0.0006069522,0.67713165],"study_design_scores_gemma":[0.019087182,0.030266978,0.387677,0.0019851937,0.0002200435,0.000049785256,0.0010767311,0.14143158,0.001416653,0.4163388,0.000012921858,0.00043711378],"about_ca_topic_score_codex":0.00013997122,"about_ca_topic_score_gemma":0.00006862518,"teacher_disagreement_score":0.6766946,"about_ca_system_score_codex":0.00018927807,"about_ca_system_score_gemma":0.0011910324,"threshold_uncertainty_score":0.9049888},"labels":[],"label_agreement":null},{"id":"W3215656175","doi":"10.1177/09622802211052972","title":"A functional proportional hazard cure rate model for interval-censored data","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute on Aging; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Covariate; Nonparametric statistics; Proportional hazards model; Functional data analysis; Functional principal component analysis; Computer science; Statistics; Poisson distribution; Econometrics; Mathematics","score_opus":0.632474033616922,"score_gpt":0.6491351215039572,"score_spread":0.016661087887035242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215656175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014662414,0.00009864654,0.98978716,0.005832729,0.0003177833,0.00055887084,0.0013907948,0.00004228484,0.0018251186],"genre_scores_gemma":[0.0011957412,0.00007589321,0.9957307,0.00039184967,0.00027458137,0.00032832133,0.00034968997,0.00004945924,0.0016037801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98788196,0.0061668917,0.0011822375,0.0012005555,0.002480622,0.0010877644],"domain_scores_gemma":[0.9109738,0.08564256,0.00009423629,0.0011056587,0.0013722017,0.00081155],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034604948,0.0002462692,0.0007102648,0.00019027507,0.00020768413,0.00010062833,0.000882804,0.00035361567,0.009022083],"category_scores_gemma":[0.466164,0.00020153137,0.00008005803,0.00068400486,0.0010300215,0.00010457775,0.0011271413,0.0018354113,0.000035752186],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022447431,0.0003869617,0.000042170937,0.00030398834,0.00003609005,0.00015721848,0.000055981065,0.000005116918,0.00028490773,0.7244127,0.042005826,0.23208457],"study_design_scores_gemma":[0.0005886784,0.000070531765,0.00038974744,0.00012582731,0.000015194379,0.000016352562,0.00006972371,0.45104668,0.00014016089,0.54523224,0.0021765376,0.00012835396],"about_ca_topic_score_codex":0.000013068069,"about_ca_topic_score_gemma":0.00006702579,"teacher_disagreement_score":0.45104155,"about_ca_system_score_codex":0.00014775958,"about_ca_system_score_gemma":0.0023634797,"threshold_uncertainty_score":0.9940774},"labels":[],"label_agreement":null},{"id":"W37750213","doi":"10.1177/09622802231198795","title":"Iconography : Localisation primitive « anale et œsophagienne » d'un lymphome non hodgkinien du Malt","year":2008,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Lymphoma Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"MALT lymphoma; Medicine; Lymphoma; Pathology","score_opus":0.12630805879344958,"score_gpt":0.5251216464006785,"score_spread":0.3988135876072289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37750213","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4691425,0.0009653597,0.48422936,0.0125946,0.00034985648,0.0018897296,0.0001199423,0.00010223151,0.030606426],"genre_scores_gemma":[0.7010495,0.0018653314,0.29540053,0.0010429615,0.0001536251,0.00029921057,0.0000878419,0.000029944926,0.00007108379],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9920312,0.003214582,0.0006983575,0.00073993276,0.0023627228,0.0009532073],"domain_scores_gemma":[0.9857221,0.012220453,0.000061783205,0.0004465085,0.00038984828,0.001159283],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009358867,0.00024699306,0.0006928742,0.0006479734,0.00021259257,0.000028977227,0.0002536036,0.00031132318,0.0029812537],"category_scores_gemma":[0.020796059,0.0001901513,0.0001239387,0.0013138958,0.0015163491,0.00009225604,0.00022231693,0.00085392233,0.00011697242],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007173383,0.0026572095,0.14777808,0.00013676725,0.00016058297,0.0077594346,0.0011507684,0.0000014129283,0.00018876314,0.035126574,0.0029427153,0.80138034],"study_design_scores_gemma":[0.005940293,0.0013411694,0.9708596,0.00025156408,0.00004577316,0.00037101778,0.00030821268,0.0038239136,0.0022015227,0.010930045,0.0037202667,0.00020666177],"about_ca_topic_score_codex":0.0005833874,"about_ca_topic_score_gemma":0.000029362944,"teacher_disagreement_score":0.8230815,"about_ca_system_score_codex":0.00049353275,"about_ca_system_score_gemma":0.0010815682,"threshold_uncertainty_score":0.99793017},"labels":[],"label_agreement":null},{"id":"W4200003768","doi":"10.1177/09622802211061634","title":"Functional response regression model on correlated longitudinal microbiome sequencing data","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Functional data analysis; Regression; Regression analysis; Microbiome; Estimator; Computer science; Functional principal component analysis; Functional response; Statistics; Machine learning; Mathematics; Biology; Bioinformatics; Ecology","score_opus":0.3527100488831351,"score_gpt":0.5862111740909964,"score_spread":0.23350112520786132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200003768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.103302315,0.00070752634,0.8881899,0.005586271,0.00040408585,0.00031620555,0.0004288189,0.000016356078,0.0010485363],"genre_scores_gemma":[0.20571524,0.0006266891,0.78526,0.0014590542,0.0003932391,0.00004651855,0.0027213076,0.00006558547,0.0037123172],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99165463,0.005236796,0.00047855914,0.0009857602,0.0009291581,0.0007150743],"domain_scores_gemma":[0.99534476,0.002850925,0.00004136592,0.00096951355,0.00032328826,0.00047016164],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016099522,0.00016097963,0.00027019333,0.00016964448,0.00019096352,0.000035170127,0.0005136104,0.00045547893,0.001166135],"category_scores_gemma":[0.04446611,0.0001352603,0.000034978144,0.00048336832,0.00050048844,0.000005338429,0.0010154118,0.001388813,0.000056967543],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002718569,0.00020557576,0.00019072356,0.00007069191,0.000025358537,0.0007105486,0.000030397478,0.00006657227,0.90876794,0.002052027,0.045037437,0.040124144],"study_design_scores_gemma":[0.011822742,0.0039994824,0.07372351,0.0032295024,0.00007894428,0.0022159074,0.0011493749,0.45809835,0.3152989,0.031019555,0.09712071,0.0022430443],"about_ca_topic_score_codex":0.00003284318,"about_ca_topic_score_gemma":0.00004781799,"teacher_disagreement_score":0.5934691,"about_ca_system_score_codex":0.00016374116,"about_ca_system_score_gemma":0.003454805,"threshold_uncertainty_score":0.9997469},"labels":[],"label_agreement":null},{"id":"W4200043579","doi":"10.1177/09622802211032705","title":"Repeated measures discriminant analysis using multivariate generalized estimation equations","year":2021,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Calgary","funders":"","keywords":"Multivariate statistics; Generalized estimating equation; Statistics; Mathematics; Estimator; Multivariate analysis; Linear discriminant analysis; Covariance; Repeated measures design; Multivariate normal distribution","score_opus":0.47383637507703746,"score_gpt":0.6449874666862396,"score_spread":0.17115109160920217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200043579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00089012587,0.00008206273,0.9964253,0.00070904306,0.00015892675,0.0003078018,0.00011253307,0.000050513165,0.0012637166],"genre_scores_gemma":[0.023921343,0.00004293945,0.9756123,0.00006901084,0.00007170885,0.00008766526,0.00005816338,0.000035129346,0.0001017635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9764341,0.017496267,0.0013190499,0.00087107683,0.0028822902,0.0009972209],"domain_scores_gemma":[0.9209943,0.076259494,0.00013274714,0.0007789002,0.0010659503,0.0007686329],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.024228998,0.00025697696,0.0009832314,0.00068499125,0.00031380178,0.00015061286,0.00041538794,0.0003375774,0.005927509],"category_scores_gemma":[0.45447072,0.00021019946,0.00014821175,0.0040568276,0.0007297537,0.00008999914,0.0003483718,0.0014017045,0.000016273454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004284291,0.00024244316,0.00010621304,0.00008252479,0.00014175374,0.00040575492,0.00021722782,0.000026550748,0.0016338095,0.59174335,0.00007086768,0.40528664],"study_design_scores_gemma":[0.00035928414,0.000029963117,0.0015474758,0.00009573651,0.00018479953,0.000007842844,0.00012915373,0.4689341,0.0006386021,0.5278881,0.000042205218,0.00014274186],"about_ca_topic_score_codex":0.0007589388,"about_ca_topic_score_gemma":0.0002662366,"teacher_disagreement_score":0.46890754,"about_ca_system_score_codex":0.0002784519,"about_ca_system_score_gemma":0.000936309,"threshold_uncertainty_score":0.9949812},"labels":[],"label_agreement":null},{"id":"W4205908064","doi":"10.1177/09622802211065158","title":"A potential outcomes approach to defining and estimating gestational age-specific exposure effects during pregnancy","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Pregnancy and Medication Impact","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Hôpital du Sacré-Cœur de Montréal; Université de Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Inverse probability weighting; Marginal structural model; Pregnancy; Confounding; Observational study; Causal inference; Weighting; Pharmacoepidemiology; Medicine; Inverse probability; Statistics; Estimator; Econometrics; Computer science; Internal medicine; Posterior probability; Bayesian probability; Mathematics","score_opus":0.10330201926296295,"score_gpt":0.5091531585592045,"score_spread":0.40585113929624156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205908064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047454398,0.0017274261,0.9434052,0.002598754,0.00033294564,0.0012533987,0.00004641177,0.00006586769,0.0031155923],"genre_scores_gemma":[0.306454,0.000060885643,0.6921628,0.00021060967,0.00006902467,0.00075399777,0.000048187605,0.000028650611,0.00021182491],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99160147,0.0031653729,0.00060018775,0.00067151693,0.003106993,0.0008544743],"domain_scores_gemma":[0.9893429,0.008981119,0.000054510096,0.00034164943,0.00011035905,0.001169424],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006532954,0.00018740668,0.0005385727,0.0005490737,0.0004708694,0.00004197899,0.000276881,0.00012748477,0.0009151382],"category_scores_gemma":[0.045051374,0.00016271173,0.000050202296,0.00083280244,0.0004457786,0.000058546564,0.0005870008,0.0021984933,0.000012434184],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041149286,0.00096530886,0.007709882,0.0013415139,0.000061393104,0.0026829483,0.002797731,0.00006507422,0.0014003622,0.03535638,0.00052745617,0.9466805],"study_design_scores_gemma":[0.0075683114,0.0017722095,0.9255622,0.0027249123,0.000054272237,0.0009951718,0.0012639504,0.03001567,0.00022981939,0.028374435,0.00095611135,0.00048295243],"about_ca_topic_score_codex":0.00002837204,"about_ca_topic_score_gemma":9.1987283e-7,"teacher_disagreement_score":0.9461975,"about_ca_system_score_codex":0.00024500437,"about_ca_system_score_gemma":0.0004977291,"threshold_uncertainty_score":0.99999815},"labels":[],"label_agreement":null},{"id":"W4234725231","doi":"10.1177/0962280212448971","title":"Editorial","year":2013,"lang":"en","type":"editorial","venue":"Statistical Methods in Medical Research","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Victoria","funders":"","keywords":"Computer science","score_opus":0.12314646047684008,"score_gpt":0.6309105247237368,"score_spread":0.5077640642468967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234725231","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.0435385e-7,0.0003811067,0.05158905,0.00030969732,0.92472166,0.0012322761,0.0010224805,0.0003702679,0.020373138],"genre_scores_gemma":[2.582567e-7,0.0002606733,0.2994572,0.000017325656,0.696035,0.00094331853,0.0004889424,0.0008912212,0.0019060399],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.89850456,0.04873512,0.0027282692,0.002967982,0.04219596,0.004868086],"domain_scores_gemma":[0.4886836,0.49690813,0.00034488263,0.0027829611,0.0059106913,0.0053697308],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.1278155,0.00090883864,0.0023243115,0.001910617,0.00022515267,0.00044555432,0.004140794,0.009153047,0.09372528],"category_scores_gemma":[0.82422966,0.0007808745,0.00019295342,0.0028189134,0.005328795,0.0001841854,0.0022320754,0.037313845,0.064015254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035783916,0.0003659862,0.000002032718,0.0003725253,0.0000584775,0.00034248977,0.000059457496,1.5420781e-7,0.000035071953,0.00650293,0.87551856,0.11638446],"study_design_scores_gemma":[0.001608217,0.0004244571,0.000009018705,0.0006432523,0.000025305766,0.0000017324708,0.000051418705,0.0008541072,0.000012440244,0.082880214,0.91283405,0.00065577327],"about_ca_topic_score_codex":0.0031401725,"about_ca_topic_score_gemma":0.00020508024,"teacher_disagreement_score":0.6964142,"about_ca_system_score_codex":0.002115145,"about_ca_system_score_gemma":0.009020982,"threshold_uncertainty_score":0.9994642},"labels":[],"label_agreement":null},{"id":"W4235408669","doi":"10.1177/0962280216660410","title":"Editorial","year":2016,"lang":"en","type":"editorial","venue":"Statistical Methods in Medical Research","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Medicine; Computer science","score_opus":0.11590070309343611,"score_gpt":0.6424679445791774,"score_spread":0.5265672414857413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235408669","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.407535e-8,0.00029556584,0.110788986,0.00046677524,0.86337787,0.0007574601,0.0023512118,0.00033831762,0.021623733],"genre_scores_gemma":[2.5774452e-7,0.0003788298,0.20872875,0.000015049583,0.78671783,0.00054698164,0.00026203346,0.0009715547,0.002378692],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8904084,0.053594828,0.002770179,0.0032529016,0.044756982,0.0052167275],"domain_scores_gemma":[0.5064891,0.4833357,0.00027085037,0.0022120033,0.003789736,0.0039026064],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","research_integrity","insufficient_payload"],"category_scores_codex":[0.15433422,0.0008599812,0.0021848944,0.0018820924,0.0002153585,0.00024088356,0.004028746,0.0084792385,0.059290856],"category_scores_gemma":[0.84520924,0.0006272154,0.00020867452,0.002179862,0.0060190014,0.00014807875,0.0021514173,0.025178557,0.037551895],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008086851,0.00025681424,0.0000022123536,0.00026124276,0.000054459888,0.0005260516,0.000035460696,2.3421594e-8,0.000066641674,0.00877008,0.81702656,0.17219177],"study_design_scores_gemma":[0.0021742429,0.0004023641,0.0000050010876,0.0011754689,0.000022147411,0.0000017896432,0.000019668323,0.00009165015,0.00002289878,0.11646329,0.87901336,0.000608117],"about_ca_topic_score_codex":0.00061289093,"about_ca_topic_score_gemma":0.00017005378,"teacher_disagreement_score":0.690875,"about_ca_system_score_codex":0.002506319,"about_ca_system_score_gemma":0.010221902,"threshold_uncertainty_score":0.99961793},"labels":[],"label_agreement":null},{"id":"W4239067159","doi":"10.1177/0962280218811186","title":"Authors' reply: Letter to the Editor: Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies (SMMR, Vol 27, Issue 6, 2018)","year":2018,"lang":"en","type":"letter","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Centre for Advancing Health Outcomes; University of British Columbia; Jewish General Hospital; Providence Health Care","funders":"","keywords":"Confounding; Computer science; Econometrics; Statistics; Mathematics","score_opus":0.4172799159375314,"score_gpt":0.6239339484163909,"score_spread":0.20665403247885955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239067159","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000060012197,0.00020988965,0.9281397,0.06616804,0.0016404197,0.0026594347,0.0002088346,0.00010508738,0.0008086089],"genre_scores_gemma":[0.0005559658,0.000050794388,0.97584057,0.010727403,0.010642821,0.0011723931,0.00007236654,0.0002163438,0.0007213306],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9638038,0.023434147,0.0023784142,0.0017352416,0.0065941513,0.0020542366],"domain_scores_gemma":[0.80947423,0.18736058,0.000368486,0.0013043658,0.0010486377,0.0004436962],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.057654,0.0007435613,0.0026995563,0.00089398434,0.00022471626,0.00010981469,0.0017052783,0.0011466464,0.0011095743],"category_scores_gemma":[0.20643282,0.00048613513,0.00008296271,0.00095892674,0.004147796,0.00010256119,0.0012958924,0.011596335,0.00010454531],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004228609,0.00022307278,0.000118601594,0.0025192774,0.00017894023,0.0006090405,0.0018155671,0.0000067478277,0.000044984987,0.022746434,0.9506978,0.020616679],"study_design_scores_gemma":[0.0010620672,0.0017048996,0.000067702196,0.007466698,0.0001632214,0.000023183055,0.0016106173,0.00490733,0.0027242985,0.56537175,0.41374722,0.0011509942],"about_ca_topic_score_codex":0.00041502647,"about_ca_topic_score_gemma":0.00026596664,"teacher_disagreement_score":0.54262537,"about_ca_system_score_codex":0.0009678941,"about_ca_system_score_gemma":0.0005520964,"threshold_uncertainty_score":0.99980354},"labels":[],"label_agreement":null},{"id":"W4281715747","doi":"10.1177/09622802221102628","title":"A Poisson-multinomial spatial model for simultaneous outbreaks with application to arboviral diseases","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Mosquito-borne diseases and control","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Institut de Valorisation des Données; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Dengue fever; Chikungunya; Outbreak; Poisson distribution; Aedes; Poisson regression; Statistics; Geography; Estimation; Aedes aegypti; Population; Demography; Environmental health; Medicine; Biology; Mathematics; Virology; Ecology","score_opus":0.05066987677574371,"score_gpt":0.5120117923460398,"score_spread":0.4613419155702961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281715747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053928364,0.000120523546,0.985182,0.005310448,0.000072130584,0.0027017337,0.0008599436,0.00004563187,0.00031479282],"genre_scores_gemma":[0.7392056,0.0000057163143,0.2548922,0.0011787581,0.0002998787,0.003879972,0.00016641803,0.000047379483,0.00032405663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939068,0.0012359419,0.0005203866,0.0008198507,0.0025692163,0.0009477982],"domain_scores_gemma":[0.98644346,0.011074035,0.000049677034,0.0005136798,0.00033348246,0.0015856447],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038952017,0.00020126691,0.00056160963,0.0002813348,0.00029331853,0.0000344794,0.0004033092,0.000106153915,0.0010705062],"category_scores_gemma":[0.02901864,0.00016258383,0.00008953301,0.00053293287,0.0003255155,0.000023895494,0.0003511444,0.0010736232,0.0000125213655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016387692,0.0011608212,0.00088984746,0.00018838987,0.000047747846,0.00048018323,0.00022475318,0.003175524,0.00047590025,0.01198261,0.0012455572,0.96374094],"study_design_scores_gemma":[0.0041167024,0.002030768,0.0021522306,0.000042949276,0.00007813802,0.000018316186,0.0002476874,0.9774981,0.000022617356,0.00837404,0.0052292272,0.00018922071],"about_ca_topic_score_codex":0.000529586,"about_ca_topic_score_gemma":0.00011456283,"teacher_disagreement_score":0.97432256,"about_ca_system_score_codex":0.00035696043,"about_ca_system_score_gemma":0.0013477039,"threshold_uncertainty_score":0.99984264},"labels":[],"label_agreement":null},{"id":"W4283576203","doi":"10.1177/09622802221108579","title":"Analysis of survival data with cure fraction and variable selection: A pseudo-observations approach","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Thermo Fisher Scientific (Canada); Jewish General Hospital","funders":"National Center for Advancing Translational Sciences; National Institutes of Health; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Proportional hazards model; Hazard ratio; Fraction (chemistry); Statistics; Estimator; Survival analysis; Bounded function; Hazard; Mathematics; Data set; Accelerated failure time model; Econometrics; Computer science; Confidence interval","score_opus":0.4607902702741043,"score_gpt":0.595003016830086,"score_spread":0.13421274655598175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283576203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011500973,0.000037277303,0.99382365,0.00039724493,0.00005281425,0.00030412475,0.0005670192,0.000020918527,0.0036468687],"genre_scores_gemma":[0.005469956,0.000029780427,0.99399984,0.000044179335,0.000040406714,0.00016689413,0.00013135003,0.0000204503,0.00009717067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.986351,0.0090050055,0.00069551775,0.0007314473,0.0026956282,0.00052140496],"domain_scores_gemma":[0.9415784,0.056917235,0.00011361444,0.00067735714,0.00037040704,0.00034297188],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031178499,0.00014657453,0.0007489475,0.0005795049,0.00032593403,0.00003874914,0.0006623223,0.00012390132,0.005520512],"category_scores_gemma":[0.08004282,0.0001187193,0.000024723342,0.005183113,0.00067035074,0.000083868596,0.00090282364,0.0018904359,5.2536916e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017173852,0.00053363596,0.006799281,0.00017655197,0.0002823549,0.000016919608,0.00013132325,0.000041178326,0.00007928397,0.91692626,0.0007829264,0.07405857],"study_design_scores_gemma":[0.0003699398,0.00029198904,0.014138362,0.00002256729,0.00024322126,0.000010826203,0.0007287194,0.54377466,0.000005680035,0.43893445,0.0013538422,0.00012571468],"about_ca_topic_score_codex":0.0006016825,"about_ca_topic_score_gemma":0.00007616627,"teacher_disagreement_score":0.5437335,"about_ca_system_score_codex":0.00011683215,"about_ca_system_score_gemma":0.00056168163,"threshold_uncertainty_score":0.9976056},"labels":[],"label_agreement":null},{"id":"W4285023678","doi":"10.1177/09622802221111546","title":"Unified approach to optimal estimation of mean and standard deviation from sample summaries","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Standard deviation; Sample mean and sample covariance; Statistics; Sample size determination; Variance (accounting); Sample (material); Mathematics; Standard error; Estimation; Computer science","score_opus":0.2764146378609897,"score_gpt":0.5686667043651459,"score_spread":0.2922520665041562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285023678","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010519903,0.00006528887,0.9856812,0.0004402166,0.000083496016,0.000511191,0.0012594057,0.00002239371,0.0014169147],"genre_scores_gemma":[0.049071305,0.000016659857,0.9504924,0.00006598861,0.000032324937,0.00020728869,0.000073731695,0.00002297481,0.000017376009],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9875601,0.0077216467,0.0008452791,0.00055349997,0.0027638345,0.00055562856],"domain_scores_gemma":[0.907298,0.09152255,0.000085370775,0.00034648125,0.00024844948,0.0004991199],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021976475,0.00015651296,0.000597323,0.00031378123,0.00023671275,0.000046312478,0.00040587978,0.000120208904,0.0027216421],"category_scores_gemma":[0.23072587,0.00014045712,0.000027511323,0.00087833183,0.0006478551,0.00004409723,0.00074114883,0.001173546,0.0000018555546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027591482,0.00014312542,0.000086758824,0.00010542923,0.000014839903,0.000008204891,0.0012198999,0.00007388782,0.000058734277,0.59800595,0.00048375325,0.39952347],"study_design_scores_gemma":[0.0004733484,0.000458717,0.0014052358,0.000048519774,0.000016598875,0.0000022855156,0.0015711734,0.16811837,0.0002466642,0.8268399,0.0006853871,0.000133775],"about_ca_topic_score_codex":0.0006754579,"about_ca_topic_score_gemma":0.00003152619,"teacher_disagreement_score":0.3993897,"about_ca_system_score_codex":0.00016660542,"about_ca_system_score_gemma":0.00038022862,"threshold_uncertainty_score":0.99819},"labels":[],"label_agreement":null},{"id":"W4287773546","doi":"10.1177/09622802221111549","title":"Ensemble methods for survival function estimation with time-varying covariates","year":2022,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Covariate; Statistics; Estimation; Computer science; Econometrics; Mathematics","score_opus":0.5077012381482325,"score_gpt":0.6628222937762495,"score_spread":0.15512105562801692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287773546","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.269371e-8,0.20966195,0.78293854,0.000073018215,0.000466274,0.0023795734,0.00023389989,0.00008241944,0.0041643074],"genre_scores_gemma":[3.251317e-8,0.29944673,0.69701016,0.00002808882,0.00016976279,0.002689265,0.00019794675,0.00015212486,0.00030589162],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94736725,0.043663632,0.002322955,0.0016339368,0.0032573885,0.0017548391],"domain_scores_gemma":[0.6100254,0.38774064,0.0003513319,0.00078532967,0.00038229,0.0007149691],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09020485,0.00074269756,0.0038327395,0.00089105696,0.0005355904,0.00017463716,0.0011264168,0.00088582287,0.017306784],"category_scores_gemma":[0.40172333,0.00054325,0.00028767335,0.0022380606,0.0009284873,0.0000857725,0.0007050919,0.004709578,0.00005597876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015179855,0.00018341813,1.5322769e-7,0.009866084,0.00011580159,0.00004384177,0.000033279386,5.9529276e-7,0.0000012175536,0.32771808,0.00055229175,0.66133344],"study_design_scores_gemma":[0.00046014923,0.00077803235,9.056796e-7,0.002831231,0.00035525518,0.000027848157,0.000030128569,0.033512745,0.000002109413,0.548662,0.41292968,0.00040993883],"about_ca_topic_score_codex":0.00007173107,"about_ca_topic_score_gemma":0.0000066532725,"teacher_disagreement_score":0.6609235,"about_ca_system_score_codex":0.00066903775,"about_ca_system_score_gemma":0.002403912,"threshold_uncertainty_score":0.9997019},"labels":[],"label_agreement":null},{"id":"W4296710640","doi":"10.1177/09622802221125912","title":"A nonparametric test for equality of survival medians using right-censored prevalent cohort survival data","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Statistics; Censoring (clinical trials); Estimator; Statistic; Population; Kaplan–Meier estimator; Survival analysis; Sample size determination; Cohort; Medicine; Survival function; Test statistic; Mathematics; Statistical hypothesis testing","score_opus":0.551658796265615,"score_gpt":0.6396868315058465,"score_spread":0.0880280352402315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296710640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023759198,0.00011299701,0.986057,0.00053267274,0.00071890885,0.0016406209,0.0061379448,0.000035032335,0.0023889176],"genre_scores_gemma":[0.018124796,0.000057235728,0.98093206,0.00004243373,0.00017532184,0.0003585797,0.00012972379,0.00006613077,0.00011372061],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96297306,0.024129404,0.0023795823,0.0015394866,0.0072476473,0.001730797],"domain_scores_gemma":[0.52337873,0.4718368,0.0003588499,0.002288867,0.000978043,0.0011587124],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11736139,0.0003176434,0.0014851117,0.00059292134,0.00039165257,0.00004723646,0.0024455956,0.00025880427,0.009012404],"category_scores_gemma":[0.617029,0.00027667993,0.00010254196,0.002391702,0.0016184982,0.00006873134,0.0026427512,0.0023893237,0.000004235846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003973116,0.0018786512,0.005545814,0.0011688616,0.00010051053,0.00012170219,0.00017038884,0.000003838532,0.0004702164,0.8132704,0.0015456195,0.17532668],"study_design_scores_gemma":[0.001471423,0.00078867015,0.004630171,0.0001224071,0.00009605468,0.0000137235265,0.0004560456,0.22472458,0.00020527371,0.76458,0.0025590959,0.000352571],"about_ca_topic_score_codex":0.0005158261,"about_ca_topic_score_gemma":0.00008829505,"teacher_disagreement_score":0.4996676,"about_ca_system_score_codex":0.0004371507,"about_ca_system_score_gemma":0.001492086,"threshold_uncertainty_score":0.9999685},"labels":[],"label_agreement":null},{"id":"W4307761721","doi":"10.1177/09622802221129040","title":"Revisiting Gaussian Markov random fields and Bayesian disease mapping","year":2022,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoregressive model; Covariance; Bayesian probability; Gaussian; Bayesian inference; Variable-order Bayesian network; Computer science; Random field; Markov chain; Conditional independence; Mathematics; Econometrics; Artificial intelligence; Statistics; Machine learning; Physics","score_opus":0.3179237316478053,"score_gpt":0.6023718682123013,"score_spread":0.28444813656449597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307761721","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.19956e-8,0.42163867,0.5720997,0.00033361488,0.0001744385,0.0008959719,0.00018339345,0.000037195572,0.0046369825],"genre_scores_gemma":[3.402393e-7,0.49489087,0.5040682,0.00005523195,0.00025203542,0.00051819877,0.000033398243,0.00007171438,0.00010998507],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9549589,0.035860058,0.002410927,0.0015920767,0.0034434332,0.0017345691],"domain_scores_gemma":[0.7437891,0.2527975,0.00028441814,0.0009467118,0.00011364979,0.0020686646],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051485576,0.0007058165,0.0036850895,0.00097071705,0.00051525515,0.0002245607,0.0012207676,0.0007313173,0.028683878],"category_scores_gemma":[0.3939377,0.0005540474,0.00030400662,0.0017819407,0.0013294943,0.000066432855,0.0016596614,0.007463168,0.000019576708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044648754,0.00006746417,0.0000041185576,0.02228328,0.00004589721,0.0014692625,0.000056879875,3.0541816e-9,1.9633553e-8,0.27762207,0.0006431411,0.6977632],"study_design_scores_gemma":[0.00041651467,0.000058488273,0.000015395186,0.01104309,0.00014057661,0.000048597987,0.00008108256,0.001302253,2.6193437e-8,0.54137254,0.44512162,0.00039981728],"about_ca_topic_score_codex":0.00006172503,"about_ca_topic_score_gemma":0.0000063777456,"teacher_disagreement_score":0.69736344,"about_ca_system_score_codex":0.00036731586,"about_ca_system_score_gemma":0.0016294505,"threshold_uncertainty_score":0.9996911},"labels":[],"label_agreement":null},{"id":"W4307835686","doi":"10.1177/09622802221134172","title":"Bayesian inference for Cox proportional hazard models with partial likelihoods, nonlinear covariate effects and correlated observations","year":2022,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research; St. Michael's Hospital; University of Waterloo; University of Toronto","funders":"","keywords":"Covariate; Laplace's method; Markov chain Monte Carlo; Bayesian probability; Inference; Parametric statistics; Proportional hazards model; Computer science; Bayesian inference; Mathematics; Econometrics; Applied mathematics; Statistics; Algorithm; Artificial intelligence","score_opus":0.23490634914787176,"score_gpt":0.5408256184953694,"score_spread":0.3059192693474976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307835686","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006749607,0.000052021856,0.99494123,0.0016574676,0.00018246679,0.0015794035,0.0004785304,0.0000580939,0.00037584256],"genre_scores_gemma":[0.013588001,0.000028200855,0.98405397,0.00023895962,0.000091543036,0.0017960478,0.00007964535,0.00005235186,0.00007130436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98889077,0.005914003,0.00091030175,0.00081498997,0.0024593743,0.0010105922],"domain_scores_gemma":[0.91099536,0.08726742,0.00012896257,0.00038321767,0.0004909001,0.0007341215],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01595795,0.00027436842,0.00070873054,0.0002724712,0.00063943176,0.000088834975,0.00046701424,0.00021372295,0.001319659],"category_scores_gemma":[0.09894222,0.00022096386,0.00004634516,0.0010037656,0.0010917225,0.0001043831,0.00049063406,0.0021611964,0.000002432529],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005383936,0.0004296805,0.00054101576,0.00040059933,0.000042062577,0.00018110877,0.0002136442,0.00002223544,0.000057530215,0.8422109,0.0006466666,0.15471618],"study_design_scores_gemma":[0.0010603821,0.00080898486,0.00078856916,0.000109624,0.000028150274,0.000021128595,0.00008371235,0.39940405,0.000033847824,0.5969443,0.0005427527,0.00017450168],"about_ca_topic_score_codex":0.00010442231,"about_ca_topic_score_gemma":0.000043939464,"teacher_disagreement_score":0.39938182,"about_ca_system_score_codex":0.00016525514,"about_ca_system_score_gemma":0.001297338,"threshold_uncertainty_score":0.99959326},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.9687413692421736,"score_gpt":0.8023260236013716,"score_spread":0.16641534564080196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309662782","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005077612,0.0038644907,0.9815664,0.0057260557,0.00014622325,0.0008617869,0.00015846286,0.0000035219548,0.0025954465],"genre_scores_gemma":[0.2277382,0.000048814214,0.7706894,0.00013063033,0.000015001115,0.0005637972,0.00001548928,0.0000131974,0.000785431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.41373494,0.43278834,0.060254656,0.0036682212,0.08781437,0.0017394611],"domain_scores_gemma":[0.20209287,0.7627286,0.017690541,0.0086654965,0.0074429857,0.0013795261],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.82260346,0.00024162004,0.010891266,0.0040589953,0.00022544901,0.00013829707,0.002245609,0.00011304241,0.14533326],"category_scores_gemma":[0.9211674,0.0001289555,0.002041938,0.016984692,0.0007620064,0.000098188844,0.0011545353,0.0016783829,0.000056663856],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017999335,0.0007024795,0.015078801,0.00050846307,0.0801764,0.001002315,0.007956277,0.009951241,0.00006936155,0.10229605,0.011713941,0.7703647],"study_design_scores_gemma":[0.00038169773,0.00025524315,0.011567121,0.00003228249,0.026198158,0.000009048851,0.01423692,0.47458687,0.000041998417,0.46816373,0.0042510843,0.00027585053],"about_ca_topic_score_codex":0.00015219803,"about_ca_topic_score_gemma":0.00059160544,"teacher_disagreement_score":0.77008885,"about_ca_system_score_codex":0.00029224178,"about_ca_system_score_gemma":0.00061002444,"threshold_uncertainty_score":0.855448},"labels":[],"label_agreement":null},{"id":"W4313488348","doi":"10.1177/09622802221146311","title":"Intervention treatment distributions that depend on the observed treatment process and model double robustness in causal survival analysis","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Estimator; Robustness (evolution); Average treatment effect; Computer science; Mathematics; Convergence (economics); Mathematical optimization; Econometrics; Statistics; Economics","score_opus":0.6785915120642826,"score_gpt":0.6541200482433555,"score_spread":0.02447146382092713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313488348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14872934,0.000023191322,0.8485003,0.0013713842,0.000027257833,0.00076103496,0.00014348222,0.000088293156,0.00035567407],"genre_scores_gemma":[0.8043897,0.00033381986,0.19313197,0.000008080876,0.000023542878,0.0016974729,0.00013046975,0.000029231353,0.00025572226],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99388903,0.0029897215,0.0005498924,0.000555405,0.0012922339,0.0007237079],"domain_scores_gemma":[0.9745905,0.0245072,0.000058899954,0.00042903848,0.0001342283,0.00028012466],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010299643,0.00022662374,0.0005904221,0.00050906045,0.00016227963,0.00006300945,0.0003060361,0.0002033571,0.00037610045],"category_scores_gemma":[0.014771036,0.00013853886,0.00008559507,0.0021198103,0.0004682926,0.000073296986,0.00017708771,0.00066685677,0.0000051048673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050545816,0.0016239191,0.003690142,0.00015615784,0.00027653907,0.0003585994,0.0007622165,0.0015382797,0.00006082734,0.79378474,0.00008521498,0.1971579],"study_design_scores_gemma":[0.0009856718,0.0004431416,0.0032626004,0.00012311345,0.000074385745,0.0000014286534,0.0007296856,0.4076372,0.001200865,0.585393,0.000016264737,0.00013262767],"about_ca_topic_score_codex":0.0005933001,"about_ca_topic_score_gemma":0.004831032,"teacher_disagreement_score":0.65566033,"about_ca_system_score_codex":0.00072251575,"about_ca_system_score_gemma":0.00021146354,"threshold_uncertainty_score":0.99352795},"labels":[],"label_agreement":null},{"id":"W4315619190","doi":"10.1177/09622802221146305","title":"Taking a chance: How likely am I to receive my preferred treatment in a clinical trial?","year":2023,"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":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Georgia Clinical and Translational Science Alliance; National Center for Advancing Translational Sciences; Yale University","keywords":"Concordance; Medicine; Randomized controlled trial; Clinical trial; Clinical study design; Research design; Clinical equipoise; Physical therapy; Statistics; Surgery; Internal medicine","score_opus":0.8797528067101806,"score_gpt":0.7306201066902023,"score_spread":0.14913270001997836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315619190","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22856921,0.0012813485,0.37511227,0.3645845,0.0043743714,0.011372097,0.0008068903,0.00024688698,0.013652416],"genre_scores_gemma":[0.2103245,0.0031206282,0.7598869,0.009944324,0.0029157945,0.008379203,0.0001592846,0.00020047503,0.0050688568],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97201234,0.01697395,0.0065261256,0.0016819654,0.0009597558,0.0018458696],"domain_scores_gemma":[0.91448337,0.082346365,0.00074027566,0.000864742,0.00014565037,0.0014196128],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.24268565,0.00025326305,0.0019423277,0.0016370068,0.00015637247,0.00013231451,0.00070566393,0.00053333427,0.002516558],"category_scores_gemma":[0.48951533,0.00026669863,0.00013384117,0.0023092877,0.0004387729,0.00015268577,0.0003129518,0.0014438648,0.0025096298],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044536167,0.0013801933,0.019219898,0.00053132727,0.00011638499,0.00030415098,0.0062159663,0.000031195745,0.0000035710277,0.26540318,0.03737271,0.6649678],"study_design_scores_gemma":[0.043493442,0.0051921825,0.26620847,0.0010799044,0.000009663097,0.0000069974485,0.0046820417,0.078890994,0.000010842073,0.3831311,0.21626496,0.001029407],"about_ca_topic_score_codex":0.0017514143,"about_ca_topic_score_gemma":0.0011432508,"teacher_disagreement_score":0.6639384,"about_ca_system_score_codex":0.0016165887,"about_ca_system_score_gemma":0.0011278191,"threshold_uncertainty_score":0.99997854},"labels":[],"label_agreement":null},{"id":"W4317910164","doi":"10.1177/09622802221146308","title":"Estimation of the average treatment effect with variable selection and measurement error simultaneously addressed for potential confounders","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Estimator; Weighting; Inference; Inverse probability weighting; Statistics; Confounding; Causal inference; Mathematics; Computer science; Inverse probability; Selection (genetic algorithm); Average treatment effect; Econometrics; Machine learning; Artificial intelligence; Posterior probability; Bayesian probability; Medicine","score_opus":0.34778535028016205,"score_gpt":0.5989775910914773,"score_spread":0.25119224081131525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317910164","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042487015,0.000010220092,0.99357665,0.0003139218,0.000039858816,0.0015160576,0.000025816755,0.0000649513,0.0002038332],"genre_scores_gemma":[0.30230492,0.000016141412,0.69714475,0.000009293159,0.000017030716,0.00042598613,0.000006693312,0.000019870513,0.000055333967],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99511003,0.0022360994,0.00035410805,0.00029305829,0.0015781003,0.00042862198],"domain_scores_gemma":[0.971177,0.028094705,0.000065323875,0.00019629006,0.00032108132,0.00014559811],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011872208,0.00013862508,0.00034350733,0.00015003353,0.00014128556,0.000023045948,0.00015436581,0.00014301825,0.00015579927],"category_scores_gemma":[0.06290129,0.000079145124,0.000026044454,0.0006325923,0.0004475422,0.00003837656,0.0000775316,0.00039993922,0.000001075047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012946778,0.0003197602,0.00011475468,0.0013191884,0.00013130375,0.000052217085,0.0004375089,0.0025345334,0.008211584,0.35728344,0.00062585046,0.6276752],"study_design_scores_gemma":[0.0009672397,0.0015116594,0.00013283946,0.000253026,0.000030397821,0.00000850666,0.00005736942,0.46267793,0.009208477,0.524971,0.00010222941,0.00007930864],"about_ca_topic_score_codex":0.00013410594,"about_ca_topic_score_gemma":0.00010099776,"teacher_disagreement_score":0.6275959,"about_ca_system_score_codex":0.00031401732,"about_ca_system_score_gemma":0.0003675614,"threshold_uncertainty_score":0.9449923},"labels":[],"label_agreement":null},{"id":"W4318917969","doi":"10.1177/09622802231151210","title":"Revisiting sample size planning for receiver operating characteristic studies: A confidence interval approach with precision and assurance","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Sample size determination; Calculator; Variance (accounting); Computer science; Confidence interval; Coverage probability; Sample (material); Statistics; Range (aeronautics); Estimator; Central limit theorem; Function (biology); Limit (mathematics); Receiver operating characteristic; Mathematics","score_opus":0.7934405002011646,"score_gpt":0.7264650259137247,"score_spread":0.06697547428743988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318917969","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050296015,0.00018073987,0.99103296,0.0010431103,0.00025251173,0.0016579923,0.00022493994,0.000115783056,0.00046236377],"genre_scores_gemma":[0.008024334,0.00034607697,0.98996633,0.00014779238,0.00044019023,0.0008819553,0.000007666762,0.00007840393,0.00010723955],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9791504,0.013431642,0.0020027538,0.001405719,0.00256931,0.0014401713],"domain_scores_gemma":[0.14649652,0.8513118,0.00022394679,0.00052847795,0.0007926174,0.0006466584],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10077014,0.00034975173,0.0016382152,0.00027234136,0.00039107792,0.0001631809,0.0006334004,0.00035081466,0.0003571777],"category_scores_gemma":[0.96032304,0.00025487348,0.00006930045,0.0013607104,0.001738659,0.00011308977,0.0006804861,0.0020510866,0.000009054152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012605848,0.00017053081,0.0012940349,0.004717961,0.00018423024,0.00035958068,0.0021656377,0.000008107262,0.0003137811,0.18406464,0.0018114981,0.8036494],"study_design_scores_gemma":[0.0018089102,0.0006638144,0.00471697,0.0043142685,0.00004726375,0.000025489962,0.0024842024,0.06323023,0.00007596901,0.92196935,0.000311319,0.00035223545],"about_ca_topic_score_codex":0.00002780053,"about_ca_topic_score_gemma":0.0000039292945,"teacher_disagreement_score":0.85955286,"about_ca_system_score_codex":0.00015417478,"about_ca_system_score_gemma":0.00034004386,"threshold_uncertainty_score":0.99999034},"labels":[],"label_agreement":null},{"id":"W4327584872","doi":"10.1177/09622802231158733","title":"Estimating individualized treatment rules in longitudinal studies with covariate-driven observation times","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University; Université de Montréal","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; University of Toronto; Government of Ontario; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Covariate; Econometrics; Longitudinal data; Statistics; Computer science; Medicine; Mathematics; Data mining","score_opus":0.7436792954420733,"score_gpt":0.6962814676362851,"score_spread":0.04739782780578827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327584872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028999016,0.00012832653,0.9674726,0.0011568075,0.00007012023,0.0008606855,0.000044381457,0.0002805776,0.0009874677],"genre_scores_gemma":[0.011166844,0.00032341178,0.9874908,0.00002243922,0.00005737546,0.00073758175,0.000038638747,0.000039575778,0.00012338895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9923261,0.003571394,0.0007721991,0.0005705115,0.0018739321,0.0008859046],"domain_scores_gemma":[0.9386888,0.06030372,0.00009321064,0.0003614424,0.00030127724,0.00025156344],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013924617,0.00023779907,0.00073559326,0.0006089468,0.00012864519,0.00004319492,0.00034298433,0.00020148176,0.00048634218],"category_scores_gemma":[0.11982978,0.00016645479,0.000028197237,0.0016212084,0.00085206586,0.0001449368,0.00031344427,0.0009490685,0.000038494407],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019218671,0.00032149287,0.011947049,0.00041844533,0.00008484901,0.0010605749,0.0017770459,0.00005436119,0.000091033995,0.5255124,0.0006234452,0.45791712],"study_design_scores_gemma":[0.0009911713,0.0006034806,0.009972358,0.0007684002,0.000015662155,0.0000073069705,0.0006799992,0.052632462,0.00028273097,0.93367213,0.00018941921,0.0001848586],"about_ca_topic_score_codex":0.00015214177,"about_ca_topic_score_gemma":0.0003262347,"teacher_disagreement_score":0.45773226,"about_ca_system_score_codex":0.000539049,"about_ca_system_score_gemma":0.0003688565,"threshold_uncertainty_score":0.88758427},"labels":[],"label_agreement":null},{"id":"W4360600249","doi":"10.1177/09622802231160551","title":"Identifying regions of interest in mammogram images","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Breast cancer; Mammography; Computer science; Bivariate analysis; Lasso (programming language); Artificial intelligence; Breast cancer screening; Noise (video); Boundary (topology); Domain (mathematical analysis); Medicine; Triangulation; Region of interest; Segmentation; Data mining; Pattern recognition (psychology); Cancer; Machine learning; Mathematics; Image (mathematics); Internal medicine","score_opus":0.5030285996736024,"score_gpt":0.6263801075811303,"score_spread":0.12335150790752791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360600249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015858888,0.000079389734,0.99330866,0.0029864558,0.00037855151,0.00018970983,0.0000055874316,0.00007214262,0.0013936103],"genre_scores_gemma":[0.15329978,0.000281884,0.8460659,0.00004101368,0.000055271194,0.00010720881,0.0000023088865,0.000013448696,0.0001331864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99304634,0.0038782316,0.00058570254,0.0005283668,0.0012390334,0.00072229846],"domain_scores_gemma":[0.9824234,0.016584922,0.000042141135,0.00051524746,0.00015055898,0.00028370338],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021356212,0.000092647024,0.00027806518,0.0011056,0.000059949398,0.00006391584,0.0012891163,0.00015823016,0.00023433295],"category_scores_gemma":[0.03914593,0.000085713415,0.000033963104,0.00449525,0.0007515411,0.0001536279,0.0011057463,0.0014781159,0.000061107006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014271106,0.000051341474,0.00042801048,0.0000944384,0.0000037346983,0.0003442916,0.00026376484,0.0000030795338,0.00067121297,0.20658253,0.0019348023,0.78960854],"study_design_scores_gemma":[0.00043875733,0.00018476126,0.02993028,0.00041814923,0.0000012837611,0.000013836659,0.00034267383,0.091228075,0.0029897694,0.87304884,0.0012740706,0.0001294837],"about_ca_topic_score_codex":0.0004991566,"about_ca_topic_score_gemma":0.00041260876,"teacher_disagreement_score":0.789479,"about_ca_system_score_codex":0.00017818245,"about_ca_system_score_gemma":0.0003127251,"threshold_uncertainty_score":0.96894777},"labels":[],"label_agreement":null},{"id":"W4361190400","doi":"10.1177/09622802231164730","title":"Adaptive aggregation for longitudinal quantile regression based on censored history process","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Quantile; Estimator; Quantile regression; Computer science; Econometrics; Random effects model; Smoothing; Weighting; Mathematics; Mathematical optimization; Statistics","score_opus":0.4848764879169074,"score_gpt":0.626966810046468,"score_spread":0.14209032212956063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361190400","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050439645,0.0000412958,0.9916553,0.0008559946,0.00040053227,0.0009586314,0.00014078364,0.0001247741,0.005318316],"genre_scores_gemma":[0.023952555,0.000022279499,0.9744443,0.00013276575,0.00016445118,0.0007713983,0.000038042326,0.000059949965,0.00041423104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98901993,0.0052148458,0.0008197276,0.00088931806,0.00292323,0.0011329775],"domain_scores_gemma":[0.8716857,0.12655789,0.00010530421,0.00045322464,0.0006134238,0.000584498],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0256073,0.00026534288,0.00065282546,0.00065981754,0.00019078878,0.000029666762,0.0005274269,0.00037881944,0.002649663],"category_scores_gemma":[0.34374768,0.00020220046,0.000082165454,0.0011384638,0.0009803048,0.00005050537,0.00012310562,0.0014808043,0.000067827],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007730554,0.00026903598,0.000098498116,0.0004480984,0.000009363753,0.000108975706,0.00019862298,0.000008226909,0.000059793903,0.51040477,0.021376586,0.46624497],"study_design_scores_gemma":[0.0007571987,0.000680441,0.0012945216,0.0006149965,0.000009256417,0.0000014925417,0.00025075083,0.40514645,0.00030132712,0.5894123,0.0013640404,0.00016723762],"about_ca_topic_score_codex":0.000050397848,"about_ca_topic_score_gemma":0.000024941897,"teacher_disagreement_score":0.46607772,"about_ca_system_score_codex":0.00049218786,"about_ca_system_score_gemma":0.000995302,"threshold_uncertainty_score":0.99826205},"labels":[],"label_agreement":null},{"id":"W4366463553","doi":"10.1177/09622802231163332","title":"Design and analysis of factorial clinical trials: The impact of one treatment's effectiveness on the statistical power and required sample size of the other","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Statistics; Statistical power; Factorial; Factorial experiment; Multiplicative function; Mathematics; Odds ratio; Outcome (game theory); Treatment effect; Type I and type II errors; Treatment and control groups; Power (physics); Sample (material); Econometrics; Medicine; Physics","score_opus":0.8881970642432903,"score_gpt":0.7718697113697441,"score_spread":0.11632735287354612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366463553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041610353,0.000055821896,0.9524916,0.00083061267,0.00033065764,0.0024815637,0.0020229856,0.000017927014,0.00015850525],"genre_scores_gemma":[0.26371467,0.00023789344,0.7356285,0.000030588773,0.0001266123,0.00019354188,0.000003138878,0.000049475126,0.000015599764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.77940005,0.21116237,0.0042582927,0.0009101261,0.0033684017,0.0009007379],"domain_scores_gemma":[0.09020383,0.90724814,0.0006342615,0.001094748,0.00040958915,0.00040941397],"candidate_categories":["metaresearch","sts","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.273307,0.00033802478,0.0033079986,0.00032360328,0.00016552207,0.00003938275,0.0008460236,0.0005214373,0.0022678254],"category_scores_gemma":[0.95122373,0.00014124655,0.00052343105,0.0029093034,0.006916928,0.000027336131,0.00050962163,0.0014805964,0.0000023582465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0088712545,0.0018511943,0.008257153,0.0003128464,0.005007685,0.000022898575,0.000768054,0.000022149441,0.001319182,0.6459989,0.00082161947,0.3267471],"study_design_scores_gemma":[0.0021789984,0.0024988374,0.13359167,0.00022870467,0.0008022616,7.045298e-7,0.00014091215,0.011251961,0.0007402705,0.8484177,0.000022036227,0.00012596075],"about_ca_topic_score_codex":0.00080026954,"about_ca_topic_score_gemma":0.000022876,"teacher_disagreement_score":0.6960858,"about_ca_system_score_codex":0.0001250269,"about_ca_system_score_gemma":0.00065052963,"threshold_uncertainty_score":0.99864423},"labels":[],"label_agreement":null},{"id":"W4379509156","doi":"10.1177/09622802231176034","title":"qTPI: A quasi-toxicity probability interval design for phase I trials with multiple-grade toxicities","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Science Foundation of Shanghai","keywords":"Toxicity; Dosing; Confidence interval; Interval (graph theory); Computer science; Common Terminology Criteria for Adverse Events; Clinical study design; Medicine; Clinical trial; Statistics; Mathematics; Internal medicine","score_opus":0.9107704970381562,"score_gpt":0.7548613736585712,"score_spread":0.15590912337958496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379509156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034513804,0.000037289647,0.9846308,0.0032707718,0.00058307935,0.0063640885,0.0010031057,0.0003332169,0.00032622693],"genre_scores_gemma":[0.0067111473,0.00007325126,0.9882736,0.0001834309,0.00059903256,0.0037761016,0.000022817323,0.00013917558,0.0002214086],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8825397,0.101149954,0.0052938764,0.00216584,0.0057947473,0.0030559006],"domain_scores_gemma":[0.14068578,0.8553674,0.0003923842,0.0011609754,0.00086994516,0.0015234771],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.33759516,0.0005944681,0.003563443,0.0007524549,0.0003531394,0.00017340072,0.0014535974,0.00088898325,0.0026265902],"category_scores_gemma":[0.96562254,0.00041416116,0.00035395043,0.0025742573,0.0038883945,0.00011841761,0.0006479181,0.003119671,0.00006261634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008949317,0.0034374513,0.000105028455,0.0015617061,0.00022647285,0.0003951189,0.00052041974,0.0000070497586,0.00078238687,0.375492,0.011115981,0.59740704],"study_design_scores_gemma":[0.008948881,0.004460663,0.000160718,0.0006012379,0.000089411864,0.000011276276,0.00047341865,0.06562958,0.003564207,0.9147259,0.00088893395,0.00044578],"about_ca_topic_score_codex":0.000065506836,"about_ca_topic_score_gemma":0.00007895413,"teacher_disagreement_score":0.7542175,"about_ca_system_score_codex":0.00040371247,"about_ca_system_score_gemma":0.0013038144,"threshold_uncertainty_score":0.999831},"labels":[],"label_agreement":null},{"id":"W4380264232","doi":"10.1177/09622802231172032","title":"Methods for comparative effectiveness based on time to confirmed disability progression with irregular observations in multiple sclerosis","year":2023,"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":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Imputation (statistics); Missing data; Covariate; Computer science; Multilevel model; Longitudinal data; Statistics; Medicine; Data mining; Machine learning; Mathematics","score_opus":0.8312643475469137,"score_gpt":0.6918060476561978,"score_spread":0.1394582998907159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380264232","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033991,0.000055251618,0.9361927,0.024274712,0.00013994411,0.0044611306,0.00045368884,0.000056709523,0.00037488746],"genre_scores_gemma":[0.067415856,0.0000056365607,0.92602503,0.0010797521,0.00007560297,0.0051306663,0.00014108657,0.000041115225,0.00008522636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97565186,0.0189846,0.0025785498,0.0011540626,0.0005983261,0.0010326038],"domain_scores_gemma":[0.80299455,0.195386,0.0002442414,0.00055029686,0.00020453184,0.0006203959],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20644198,0.00022071073,0.001428788,0.000734051,0.00025170392,0.00006718509,0.00047286513,0.000265457,0.0010073313],"category_scores_gemma":[0.25573757,0.00021355585,0.00006618888,0.0021040535,0.0007809298,0.00011755753,0.00013307296,0.0007806602,0.00055346865],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006006435,0.0042226296,0.21708271,0.0051769544,0.00016721584,0.000031181622,0.0043026684,0.0066040303,0.00042754124,0.32112744,0.013250985,0.42160022],"study_design_scores_gemma":[0.0021367369,0.0006557771,0.39506721,0.00075985596,0.0000023169841,2.383337e-7,0.00029635482,0.55851775,0.000096836,0.03646429,0.0057709217,0.00023172803],"about_ca_topic_score_codex":0.0004343102,"about_ca_topic_score_gemma":0.00020346286,"teacher_disagreement_score":0.5519137,"about_ca_system_score_codex":0.0010919498,"about_ca_system_score_gemma":0.00051602983,"threshold_uncertainty_score":0.9999059},"labels":[],"label_agreement":null},{"id":"W4381308498","doi":"10.1177/09622802231181224","title":"Model detection for semiparametric accelerated failure additive model with right-censored data","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Accelerated failure time model; Computer science; Inference; Nonparametric statistics; Covariate; Model selection; Spline (mechanical); Econometrics; Semiparametric model; Consistency (knowledge bases); Data mining; Mathematics; Machine learning; Artificial intelligence","score_opus":0.5371735080338076,"score_gpt":0.6177541225214012,"score_spread":0.08058061448759357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381308498","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00068222714,0.000015227151,0.9932262,0.0008548756,0.000077781035,0.0012043812,0.0022651267,0.00016734276,0.001506855],"genre_scores_gemma":[0.01593571,0.000071671115,0.9823792,0.000088133726,0.000102459846,0.0006777939,0.00024166744,0.00008497686,0.00041836378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99001575,0.003519289,0.0009174121,0.0012887664,0.0027360364,0.0015227263],"domain_scores_gemma":[0.8941088,0.103027254,0.00009925866,0.0010740614,0.00088078354,0.00080986304],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024127888,0.00032994171,0.00081504096,0.0008530455,0.00031110455,0.00011896446,0.0013094583,0.00049669883,0.0008977841],"category_scores_gemma":[0.31628722,0.00024087148,0.000046453148,0.0037422713,0.000989684,0.00015633514,0.0007207319,0.0021220455,0.00004070069],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049514225,0.00023898913,0.0000074909035,0.00030025054,0.000047206122,0.00014254269,0.00013909693,0.000227243,0.0005683934,0.44332787,0.016822496,0.5376833],"study_design_scores_gemma":[0.0006492724,0.00020104976,0.000041204003,0.000094833835,0.000019839183,0.0000054441102,0.000100596655,0.5287785,0.00049642357,0.46915758,0.00028919536,0.00016607602],"about_ca_topic_score_codex":0.00005102061,"about_ca_topic_score_gemma":0.0001787262,"teacher_disagreement_score":0.5375172,"about_ca_system_score_codex":0.00019301457,"about_ca_system_score_gemma":0.00092522043,"threshold_uncertainty_score":0.9830106},"labels":[],"label_agreement":null},{"id":"W4381309562","doi":"10.1177/09622802231181220","title":"Two-stage multivariate Mendelian randomization on multiple outcomes with mixed distributions","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre; Queen's University; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Mendelian randomization; Multivariate statistics; Univariate; Confounding; Causal inference; Instrumental variable; Multivariate analysis; Statistics; Outcome (game theory); Computer science; Econometrics; Randomized controlled trial; Medicine; Mathematics; Genetic variants; Internal medicine; Biology","score_opus":0.7000715705924438,"score_gpt":0.7152868082466625,"score_spread":0.015215237654218616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381309562","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025629313,0.0000063723082,0.9869063,0.0034684278,0.0005976027,0.0016559244,0.00096964167,0.0002962673,0.0035365364],"genre_scores_gemma":[0.028121937,0.000044722565,0.96986175,0.00015499756,0.00018367259,0.00072607404,0.00007336051,0.000099765915,0.0007337004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9633978,0.027149428,0.0020037435,0.0012281645,0.0044489778,0.0017718739],"domain_scores_gemma":[0.4865016,0.51128376,0.0001473543,0.00075455947,0.0003976696,0.00091508543],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07379348,0.00043359393,0.0015823734,0.0007372818,0.0003778396,0.000111007736,0.0008707349,0.00048115835,0.003619515],"category_scores_gemma":[0.8807,0.00029619047,0.00014835907,0.0031144342,0.0016453629,0.00007753533,0.00050506566,0.0028962153,0.0003115191],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022045497,0.00073059206,0.0017809899,0.00018785975,0.00012088695,0.0006161622,0.00010763949,0.00003416848,0.00016152106,0.81842536,0.0026966417,0.17293361],"study_design_scores_gemma":[0.014973892,0.00051460275,0.012005628,0.00034330558,0.00004356121,0.0000036448428,0.00028790176,0.054240763,0.000622378,0.9153537,0.001212612,0.00039798053],"about_ca_topic_score_codex":0.00022715113,"about_ca_topic_score_gemma":0.00018849419,"teacher_disagreement_score":0.8069065,"about_ca_system_score_codex":0.00029865777,"about_ca_system_score_gemma":0.00047543304,"threshold_uncertainty_score":0.99994904},"labels":[],"label_agreement":null},{"id":"W4382343881","doi":"10.1177/09622802231181231","title":"A Bayesian genomic selection approach incorporating prior feature ordering and population structures with application to coronary artery disease","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Coronary artery disease; Disease; Bayesian probability; Population; Selection (genetic algorithm); Computer science; Medicine; Machine learning; Artificial intelligence; Internal medicine","score_opus":0.037237744423225125,"score_gpt":0.4451527032697196,"score_spread":0.4079149588464945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382343881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31672683,0.000051492414,0.68196875,0.00077847537,0.000019392406,0.00036617118,0.000013594347,0.00001260613,0.00006265593],"genre_scores_gemma":[0.5955969,0.000029728935,0.4037792,0.000091559654,0.00008851207,0.00014792716,0.00021418964,0.000013689263,0.000038289076],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99727684,0.0012366244,0.00022865311,0.00049763505,0.0003811048,0.00037915065],"domain_scores_gemma":[0.9987432,0.00061085616,0.000040102826,0.00016370772,0.00008796181,0.0003541938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035966737,0.000107622225,0.00017677547,0.0001375311,0.00016950924,0.000022476672,0.00012205231,0.00019381895,0.000015385183],"category_scores_gemma":[0.0062634107,0.00009017937,0.000013517702,0.00051997544,0.00014119466,0.0000032977991,0.0001760732,0.00038688685,0.0000023818347],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047064037,0.00007104654,0.34872258,0.00014025842,0.000042528485,0.000025695517,0.00010851628,0.0021056859,0.017922614,0.004249118,0.001023034,0.62511826],"study_design_scores_gemma":[0.00027143117,0.00018304565,0.88042164,0.000014070991,0.000005859935,0.000014246652,0.00011450126,0.10614149,0.00003681296,0.012427266,0.00026274077,0.000106890446],"about_ca_topic_score_codex":0.000088139226,"about_ca_topic_score_gemma":0.00015027814,"teacher_disagreement_score":0.6250114,"about_ca_system_score_codex":0.000052190404,"about_ca_system_score_gemma":0.00017851767,"threshold_uncertainty_score":0.749834},"labels":[],"label_agreement":null},{"id":"W4385264158","doi":"10.1177/09622802231188513","title":"A flexible micro-randomized trial design and sample size considerations","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"University of California, San Francisco; Agency for Healthcare Research and Quality; Ministry of Education - Singapore; Ministry of Education, India; Duke-NUS Medical School","keywords":"Randomized controlled trial; Calculator; Sample size determination; Computer science; Psychological intervention; Sample (material); Computerized adaptive testing; Statistic; Research design; Extant taxon; Medicine; Statistics; Mathematics; Clinical psychology; Nursing","score_opus":0.4291837682673149,"score_gpt":0.6933266062721429,"score_spread":0.264142838004828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385264158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007716857,0.00020639946,0.952743,0.027869657,0.0005708976,0.013708304,0.00013282284,0.00020594038,0.0037913052],"genre_scores_gemma":[0.0021232157,0.0022870416,0.9566944,0.0024685862,0.00037415794,0.035105716,0.00002171045,0.000037857662,0.00088731974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95497066,0.03934156,0.0017322397,0.00069607,0.0014370219,0.001822457],"domain_scores_gemma":[0.2169861,0.78002596,0.00012418805,0.0005021701,0.00044357745,0.0019180276],"candidate_categories":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09564195,0.00017275108,0.000921005,0.00046605247,0.0014051641,0.000026940133,0.00023234719,0.00051458087,0.012374673],"category_scores_gemma":[0.6564128,0.00013972982,0.00004746199,0.0014472831,0.0014138918,0.00004188061,0.00032015922,0.0031098698,0.00048111455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.14829588,0.000203884,0.000121273086,0.00072989793,0.000023484767,0.000065588836,0.0008358803,0.0000031606733,0.000094791096,0.5292099,0.09157889,0.22883733],"study_design_scores_gemma":[0.22483785,0.00021205808,0.00041281394,0.00014213215,0.0000096494205,0.0000024465937,0.00035977378,0.008495781,0.000013305793,0.74103236,0.024373133,0.00010867823],"about_ca_topic_score_codex":0.0011958836,"about_ca_topic_score_gemma":0.000114245406,"teacher_disagreement_score":0.7406844,"about_ca_system_score_codex":0.00017882074,"about_ca_system_score_gemma":0.004524885,"threshold_uncertainty_score":0.99989486},"labels":[],"label_agreement":null},{"id":"W4385897997","doi":"10.1177/09622802231194753","title":"Does it decay? Obtaining decaying correlation parameter values from previously analysed cluster randomised trials","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; Medical Research Council","keywords":"Correlation; Intracluster medium; Cluster (spacecraft); Statistics; Confidence interval; Physics; Computer science; Mathematics; Galaxy cluster; Astrophysics","score_opus":0.36825796646254416,"score_gpt":0.6185888883650825,"score_spread":0.25033092190253836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385897997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027826817,0.00006059963,0.99031025,0.002232694,0.0006638731,0.0015146035,0.00013606461,0.00016016744,0.002139092],"genre_scores_gemma":[0.009109815,0.00022056325,0.98906237,0.00027628153,0.00038104012,0.0005492211,0.00007297492,0.00007335289,0.00025441239],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93899435,0.050732005,0.0031927975,0.0012737341,0.004008283,0.0017988067],"domain_scores_gemma":[0.50576556,0.49220398,0.00024778492,0.00060696405,0.00036472428,0.0008110189],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13201328,0.00040376434,0.0020865581,0.0008116698,0.0003247005,0.00025212395,0.00081507396,0.0006302327,0.008937364],"category_scores_gemma":[0.740456,0.0002399189,0.00024661492,0.0020962106,0.0010083215,0.00013335074,0.0004967308,0.0023569178,0.0001734856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021434026,0.00016056042,0.0006611335,0.0002345214,0.00017289048,0.00034267324,0.0016500538,0.0000045086595,0.00026265677,0.14140645,0.0058499877,0.84711117],"study_design_scores_gemma":[0.006127271,0.00012878822,0.0010321866,0.00058786554,0.00011139851,0.0000022454205,0.0007895229,0.16482401,0.000337204,0.82540536,0.000364219,0.0002899171],"about_ca_topic_score_codex":0.00024192524,"about_ca_topic_score_gemma":0.000084495216,"teacher_disagreement_score":0.84682125,"about_ca_system_score_codex":0.00021561739,"about_ca_system_score_gemma":0.0005524205,"threshold_uncertainty_score":0.9999447},"labels":[],"label_agreement":null},{"id":"W4387033470","doi":"10.1177/09622802231202384","title":"Marginal structural models with latent class growth analysis of treatment trajectories: Statins for primary prevention among older adults","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University of Manitoba; Institut National de Santé Publique du Québec; McGill University Health Centre; Université de Sherbrooke; Université Laval; Université de Montréal; McGill University; Centre hospitalier de l'Université Laval","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Université Laval","keywords":"Marginal structural model; Covariate; Confounding; Latent class model; Proportional hazards model; Estimator; Statistics; Econometrics; Confidence interval; Latent variable; Estimating equations; Inverse probability; Computer science; Mathematics; Medicine; Bayesian probability; Posterior probability","score_opus":0.2977127906117732,"score_gpt":0.5958492655166311,"score_spread":0.2981364749048579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387033470","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12505624,0.000012740499,0.87296396,0.00011832963,0.000025423476,0.0011898626,0.00026672403,0.00009661776,0.00027008084],"genre_scores_gemma":[0.20801927,0.00009130495,0.7907301,0.000007335983,0.000023979122,0.0007871184,0.00016926478,0.000034813645,0.00013681478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944528,0.0017773893,0.00079176814,0.0005570224,0.0016565619,0.0007644708],"domain_scores_gemma":[0.9759996,0.022601113,0.00013311885,0.00034965627,0.0005926097,0.0003239312],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059348457,0.00022771345,0.0008525483,0.0008422999,0.00008869601,0.000022668202,0.0003138066,0.00021342024,0.0003686712],"category_scores_gemma":[0.012607528,0.00015786075,0.00011664271,0.002421914,0.00078392366,0.00014256,0.00011939932,0.0005586363,7.981909e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013835822,0.00042866854,0.0056277146,0.0013244231,0.00084548315,0.000111426925,0.002289632,0.00017996386,0.00013461188,0.6856931,0.00023151474,0.3017499],"study_design_scores_gemma":[0.0012029778,0.001597817,0.0307696,0.00035028014,0.00022125484,0.000001235683,0.0005826467,0.1883973,0.00051225844,0.77618366,0.0000074279164,0.00017351244],"about_ca_topic_score_codex":0.0002693092,"about_ca_topic_score_gemma":0.000515142,"teacher_disagreement_score":0.30157638,"about_ca_system_score_codex":0.0005443267,"about_ca_system_score_gemma":0.00047619117,"threshold_uncertainty_score":0.9957097},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.3427619520314442,"score_gpt":0.6290504285419702,"score_spread":0.286288476510526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387033650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00057788176,0.00006206441,0.99387866,0.0016289811,0.00047344106,0.0009854945,0.00023446685,0.00022305956,0.0019359475],"genre_scores_gemma":[0.012518583,0.000114323484,0.98624706,0.00010454757,0.00031384832,0.00042526977,0.000045367844,0.00007739198,0.0001536071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98542523,0.008072033,0.001216689,0.0010128476,0.002503737,0.0017694572],"domain_scores_gemma":[0.7849909,0.2132833,0.00011535663,0.00047546742,0.0004167323,0.00071825314],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04866503,0.00032774758,0.00092661224,0.00064822944,0.00044559853,0.00010950887,0.0008068896,0.00047808856,0.001265004],"category_scores_gemma":[0.3711766,0.0002464591,0.00009998311,0.0018077961,0.0011718731,0.000079338795,0.00075392035,0.0020947116,0.00006444401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033113995,0.00013671143,0.00008317323,0.0005679818,0.00002433638,0.00031920985,0.00049426744,0.0000020311836,0.00041334826,0.6767855,0.0045545744,0.3162877],"study_design_scores_gemma":[0.0007468029,0.00054151454,0.0028353862,0.0008166996,0.000021843498,0.000010619503,0.0006706323,0.14004882,0.00014802981,0.8536108,0.0003176219,0.00023123593],"about_ca_topic_score_codex":0.000116719515,"about_ca_topic_score_gemma":0.00002122374,"teacher_disagreement_score":0.32251158,"about_ca_system_score_codex":0.00022181406,"about_ca_system_score_gemma":0.0005370024,"threshold_uncertainty_score":0.99999875},"labels":[],"label_agreement":null},{"id":"W4387607247","doi":"10.1177/09622802231197977","title":"A novel rare variants association test for binary traits in family-based designs via copulas","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Genetic association; Genome-wide association study; Copula (linguistics); Computer science; Score test; Mathematics; Statistics; Data mining; Statistical hypothesis testing; Genetics; Biology; Econometrics; Genotype","score_opus":0.19509139702643266,"score_gpt":0.5361241933542098,"score_spread":0.34103279632777717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387607247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021305729,0.000070411625,0.9738673,0.0034000792,0.00014876261,0.000587711,0.0002950764,0.000015160792,0.00030978234],"genre_scores_gemma":[0.211119,0.00013612298,0.7860191,0.0006514568,0.0002197615,0.00066240877,0.00057253666,0.000042281637,0.0005773335],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99464506,0.002549012,0.0005843911,0.0005586441,0.00070309057,0.0009598208],"domain_scores_gemma":[0.9818019,0.017415803,0.000071092974,0.00019319428,0.00024752956,0.00027046681],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021758666,0.00013879738,0.0003576125,0.00029168295,0.00010759884,0.000016002252,0.00031523578,0.0006325495,0.00011932193],"category_scores_gemma":[0.167007,0.000120596895,0.0000593039,0.0008855227,0.00017903974,0.0000025816644,0.00014543037,0.0005806239,0.0000219584],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000461188,0.0012034181,0.06821506,0.0002335596,0.00008243572,0.00011950933,0.00013802496,0.00054505805,0.4739072,0.002079933,0.04669203,0.40632257],"study_design_scores_gemma":[0.003086346,0.0010873636,0.78881776,0.000080187805,0.000011549428,0.0000029254531,0.00017854964,0.18009415,0.0010501235,0.017806374,0.0075023794,0.00028230742],"about_ca_topic_score_codex":0.00013169387,"about_ca_topic_score_gemma":0.00018846216,"teacher_disagreement_score":0.7206027,"about_ca_system_score_codex":0.00018428933,"about_ca_system_score_gemma":0.0006918589,"threshold_uncertainty_score":0.8400096},"labels":[],"label_agreement":null},{"id":"W4388498740","doi":"10.1177/09622802231210917","title":"A support vector machine-based cure rate model for interval censored data","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Support vector machine; Interval (graph theory); Interval data; Computer science; Statistics; Data mining; Artificial intelligence; Mathematics; Combinatorics","score_opus":0.5100163218704702,"score_gpt":0.6517688622124422,"score_spread":0.14175254034197204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388498740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000048491864,0.000019161833,0.9886959,0.0050924737,0.00027740136,0.0009744076,0.0038339903,0.00015598495,0.0009021672],"genre_scores_gemma":[0.0022916486,0.000042767766,0.995771,0.0003382865,0.00016551456,0.0004252611,0.00046080563,0.000089563175,0.00041516655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9863176,0.0071866484,0.0012290543,0.001258562,0.0022750779,0.0017330764],"domain_scores_gemma":[0.8644399,0.1327935,0.00008727486,0.0013208893,0.0004078681,0.0009505869],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.053118624,0.0003245218,0.00092226634,0.00051601353,0.00020708109,0.000112026675,0.0019483385,0.00041040799,0.0034926971],"category_scores_gemma":[0.37950754,0.0002596805,0.0000901996,0.0014264449,0.0010783918,0.00009394072,0.0010468218,0.0019529294,0.000103181366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003535993,0.00021542318,0.000045089444,0.0006157421,0.000024666728,0.00025928832,0.000112884714,0.0000033829963,0.00014201195,0.60726887,0.04160435,0.34935468],"study_design_scores_gemma":[0.0006970831,0.00016567616,0.00018091453,0.000116871845,0.0000148738845,0.0000023524726,0.000035920373,0.5078354,0.000062623934,0.48924455,0.0014915306,0.00015220582],"about_ca_topic_score_codex":0.00005956273,"about_ca_topic_score_gemma":0.00009297862,"teacher_disagreement_score":0.507832,"about_ca_system_score_codex":0.00013396959,"about_ca_system_score_gemma":0.0012876899,"threshold_uncertainty_score":0.9999855},"labels":[],"label_agreement":null},{"id":"W4389765971","doi":"10.1177/09622802231215804","title":"Privacy-preserving analysis of time-to-event data under nested case-control sampling","year":2023,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Nested case-control study; Pooling; Computer science; Estimator; Event (particle physics); Data mining; Covariate; Sampling (signal processing); Statistics; Proportional hazards model; Regression analysis; Econometrics; Cohort; Machine learning; Artificial intelligence; Mathematics","score_opus":0.29428541173847383,"score_gpt":0.5638527579653154,"score_spread":0.2695673462268416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389765971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015496303,0.00007841372,0.96424615,0.032299966,0.00013005728,0.00050225307,0.0005312397,0.000370377,0.00029192824],"genre_scores_gemma":[0.020471854,0.000056058405,0.9789391,0.0002029776,0.000042234777,0.00007770612,0.00012111923,0.000028509176,0.0000604096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9855843,0.006204676,0.0012176605,0.0017156636,0.0037108215,0.0015668662],"domain_scores_gemma":[0.883081,0.09316825,0.00015559475,0.02210251,0.000509085,0.0009835664],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.053296007,0.00024793728,0.0009385035,0.002997275,0.0002022865,0.000176311,0.05277106,0.000372653,0.001912626],"category_scores_gemma":[0.7308293,0.00022235628,0.0000826162,0.016840495,0.00069317414,0.00036951544,0.20278728,0.001847233,0.00023026594],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006507836,0.00023126135,0.0009932666,0.00015674683,0.00066852086,0.0038392465,0.00015356034,0.00080844626,0.001076709,0.015165118,0.0789282,0.8979139],"study_design_scores_gemma":[0.00031551236,0.00007581543,0.006466982,0.000096327705,0.000056640692,0.000027775688,0.0000729382,0.8016726,0.00007161652,0.19012249,0.00084823504,0.00017307457],"about_ca_topic_score_codex":0.00059479487,"about_ca_topic_score_gemma":0.000115986,"teacher_disagreement_score":0.8977408,"about_ca_system_score_codex":0.00020664092,"about_ca_system_score_gemma":0.0005737751,"threshold_uncertainty_score":0.9989998},"labels":[],"label_agreement":null},{"id":"W4391635477","doi":"10.1177/09622802241227957","title":"Covariate adjustment in Bayesian adaptive randomized controlled trials","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; Fonds de Recherche du Québec - Santé; Compute Canada","keywords":"Covariate; Frequentist inference; Statistics; Econometrics; Bayesian probability; Early stopping; Propensity score matching; Sample size determination; Bayes' theorem; Statistical power; Computer science; Mathematics; Bayesian inference; Machine learning","score_opus":0.7649940798972175,"score_gpt":0.7342759921159407,"score_spread":0.030718087781276715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391635477","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002816643,0.0022505254,0.9670026,0.0048548253,0.0023528575,0.0069857165,0.00017021762,0.00014740672,0.01620773],"genre_scores_gemma":[0.005347639,0.0012706058,0.98775417,0.0002533924,0.00089013035,0.0037984946,0.0000056303375,0.000111161404,0.0005687728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.554706,0.41536453,0.014720243,0.0026996734,0.009288176,0.0032214096],"domain_scores_gemma":[0.050114468,0.946977,0.0003615649,0.00082053273,0.00044337343,0.0012830548],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6087418,0.00061509066,0.011988528,0.0016223936,0.00010306066,0.00022573635,0.0010461356,0.0010518493,0.022439327],"category_scores_gemma":[0.975462,0.00038219837,0.0010029912,0.0024364346,0.0029617534,0.000102776154,0.00056644593,0.005670205,0.00016262053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.056511637,0.00038355554,0.0000021060723,0.00029503848,0.00034648654,0.0010767775,0.00017549844,0.0000012674892,0.00002343387,0.6258604,0.0018057429,0.31351808],"study_design_scores_gemma":[0.12315683,0.00027350165,0.000040899427,0.0014917002,0.00022279489,0.000009698261,0.00014715563,0.10959825,0.000044611996,0.7643821,0.00034536823,0.00028704604],"about_ca_topic_score_codex":0.0002504678,"about_ca_topic_score_gemma":0.00007278492,"teacher_disagreement_score":0.53161246,"about_ca_system_score_codex":0.0006358026,"about_ca_system_score_gemma":0.0017689648,"threshold_uncertainty_score":0.99986297},"labels":[],"label_agreement":null},{"id":"W4393043332","doi":"10.1177/09622802231225963","title":"A latent class linear mixed model for monotonic continuous processes measured with error","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Western University","funders":"Alliance de recherche numérique du Canada; Innovation, Science and Economic Development Canada; National Institute of Mental Health; University of Toronto; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México","keywords":"Monotonic function; Latent class model; Bayesian probability; Mathematics; Statistics; Class (philosophy); Homogeneous; Computer science; Observational error; Applied mathematics; Econometrics; Artificial intelligence; Mathematical analysis; Combinatorics","score_opus":0.18046242781057098,"score_gpt":0.5227246603787071,"score_spread":0.34226223256813615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393043332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008688994,0.001220643,0.99180263,0.004442863,0.00021052969,0.0009901866,0.00004008091,0.00015979253,0.0010463819],"genre_scores_gemma":[0.022186415,0.00011341349,0.97611034,0.00018209532,0.00011044363,0.00074794545,0.0000053512235,0.000045825174,0.00049816654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99186367,0.0027517553,0.0006047958,0.0011692246,0.0023998267,0.0012107085],"domain_scores_gemma":[0.9807058,0.017103536,0.00003630996,0.0006156569,0.00076118775,0.00077753665],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02009535,0.00026178182,0.00060010003,0.00039541852,0.00014754216,0.00026418205,0.0013326185,0.0003246798,0.00006889178],"category_scores_gemma":[0.02682751,0.00017800996,0.000067602894,0.0016114542,0.0005728533,0.00019730405,0.0003810484,0.0016822779,0.000013463145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013907951,0.00016295821,0.000007470658,0.00075464445,0.000042218267,0.00029673893,0.000511194,0.000053893906,0.00020991908,0.40220448,0.0011810448,0.59443635],"study_design_scores_gemma":[0.0004166367,0.00032733887,0.000022414946,0.00036025367,0.000011015463,0.000019096615,0.000014584404,0.7064794,0.000545822,0.2903193,0.0013157316,0.00016844529],"about_ca_topic_score_codex":0.000025855672,"about_ca_topic_score_gemma":0.000063194486,"teacher_disagreement_score":0.7064255,"about_ca_system_score_codex":0.00015135942,"about_ca_system_score_gemma":0.0029638372,"threshold_uncertainty_score":0.9813699},"labels":[],"label_agreement":null},{"id":"W4394847663","doi":"10.1177/09622802241242313","title":"Estimating dynamic treatment regimes for ordinal outcomes with household interference: Application in household smoking cessation","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Odds; Ordinal regression; Smoking cessation; Covariate; Robustness (evolution); Ordered logit; Context (archaeology); Econometrics; Ordinal data; Propensity score matching; Computer science; Odds ratio; Statistics; Medicine; Mathematics; Logistic regression","score_opus":0.3968361982278458,"score_gpt":0.6277471862914228,"score_spread":0.23091098806357696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394847663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008557661,0.00008892465,0.98830986,0.0009081026,0.00008224567,0.0012243557,0.00006969849,0.0002776111,0.0004815526],"genre_scores_gemma":[0.32561508,0.000034228986,0.67264074,0.000018447708,0.00003601834,0.0015033823,0.000020490203,0.00005041101,0.00008118738],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99553984,0.0011550821,0.00074869173,0.0007031905,0.0011295988,0.0007235918],"domain_scores_gemma":[0.9642601,0.034946665,0.000069160174,0.000395745,0.000117032956,0.00021130523],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009326951,0.00025606915,0.0005515556,0.00061145757,0.00009207642,0.00011446636,0.00036759986,0.00025627192,0.000073518226],"category_scores_gemma":[0.022735726,0.00018031475,0.00004456251,0.0008646984,0.0004665556,0.0001652065,0.00012825483,0.0011474548,0.0000017236689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009842645,0.00018934312,0.0014929496,0.0005040165,0.000028662673,0.000099240955,0.00035758756,0.000043133703,0.00014594187,0.328369,0.00011015702,0.6685616],"study_design_scores_gemma":[0.00051121745,0.0005336543,0.0011341878,0.0010167905,0.000019537538,0.000011142765,0.00022561617,0.23351069,0.000395026,0.76226443,0.00019238309,0.00018529811],"about_ca_topic_score_codex":0.0002508785,"about_ca_topic_score_gemma":0.00037810873,"teacher_disagreement_score":0.66837627,"about_ca_system_score_codex":0.00100089,"about_ca_system_score_gemma":0.00041170238,"threshold_uncertainty_score":0.98549616},"labels":[],"label_agreement":null},{"id":"W4395113354","doi":"10.1177/09622802241247742","title":"The performance of marginal structural models for estimating risk differences and relative risks using weighted univariate generalized linear models","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Mathematics; Estimator; Weighting; Univariate; Generalized linear model; Sample size determination; Econometrics; Multivariate statistics; Medicine","score_opus":0.5319458761194644,"score_gpt":0.6391596200709405,"score_spread":0.10721374395147609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395113354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.094573766,0.00039512338,0.9038923,0.00013946347,0.00009619548,0.0005905765,0.00010373463,0.000059472735,0.00014939396],"genre_scores_gemma":[0.18123996,0.00045656654,0.81808317,0.0000039054285,0.00006459238,0.00009082775,0.0000031909776,0.00002930673,0.000028497594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939912,0.002943514,0.0007792999,0.00044168465,0.0011723683,0.0006719402],"domain_scores_gemma":[0.93850225,0.06057092,0.00011156984,0.0002620087,0.00033709256,0.00021614671],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014630578,0.0002041863,0.0005041769,0.00020899811,0.00035926542,0.00007158538,0.00038710132,0.00022829037,0.000061643455],"category_scores_gemma":[0.026417684,0.00012523824,0.000045823086,0.0004983614,0.0014215416,0.0002793254,0.0003082964,0.0016513915,2.8916517e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015036535,0.000013291955,0.00006081076,0.0003669735,0.000039367038,0.000010164926,0.00041365935,0.0004098766,0.00010934119,0.80527717,0.0000117252075,0.19313723],"study_design_scores_gemma":[0.00014988851,0.00012342096,0.000033492197,0.00031329386,0.00001835036,0.0000040157893,0.00006896334,0.50147694,0.00013743433,0.49760005,0.0000039598467,0.00007020847],"about_ca_topic_score_codex":0.00022604225,"about_ca_topic_score_gemma":0.000012276455,"teacher_disagreement_score":0.50106704,"about_ca_system_score_codex":0.00012985332,"about_ca_system_score_gemma":0.000346978,"threshold_uncertainty_score":0.9817832},"labels":[],"label_agreement":null},{"id":"W4396555757","doi":"10.1177/09622802241247736","title":"Sample size and power calculation for testing treatment effect heterogeneity in cluster randomized crossover designs","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging; National Institutes of Health; Patient-Centered Outcomes Research Institute","keywords":"Crossover; Sample size determination; Crossover study; Covariate; Randomized controlled trial; Statistics; Statistical power; Cluster (spacecraft); Cluster size; Statistical hypothesis testing; Computer science; Mathematics; Medicine; Artificial intelligence","score_opus":0.7061155154350921,"score_gpt":0.7199084202257027,"score_spread":0.013792904790610572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396555757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0092365835,0.00025479106,0.98440444,0.0008401657,0.00045455317,0.004022916,0.00023836369,0.00007419284,0.00047398737],"genre_scores_gemma":[0.029776191,0.00005948413,0.96809477,0.000098298406,0.00019552518,0.0016264247,0.0000042385273,0.00007369091,0.00007139456],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95795697,0.035551004,0.0021591524,0.0012525675,0.0017941622,0.0012861307],"domain_scores_gemma":[0.088939786,0.90976,0.00008064751,0.00040039164,0.00021238644,0.00060680695],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11878254,0.00037883702,0.0019746718,0.00034225642,0.00013588587,0.00021350439,0.00028444824,0.0005646896,0.0008799994],"category_scores_gemma":[0.95009714,0.00025146746,0.00019886604,0.00092015916,0.0016520021,0.00007562396,0.00026234775,0.0012933739,0.000010269474],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029531822,0.00040742592,0.0005260642,0.001315329,0.000161595,0.00031292107,0.0002985268,0.000004552995,0.0003516675,0.2804694,0.0003491713,0.68627155],"study_design_scores_gemma":[0.040587775,0.0008815339,0.0006340821,0.0005493054,0.00007150983,0.000009704519,0.000014505095,0.10896288,0.00039549402,0.84748805,0.00018841565,0.00021675522],"about_ca_topic_score_codex":0.00026881404,"about_ca_topic_score_gemma":0.00006418896,"teacher_disagreement_score":0.874209,"about_ca_system_score_codex":0.00046700504,"about_ca_system_score_gemma":0.00039902164,"threshold_uncertainty_score":0.99999374},"labels":[],"label_agreement":null},{"id":"W4398235233","doi":"10.1177/09622802241254197","title":"Demystifying estimands in cluster-randomised trials","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; Medical Research Council; National Institutes of Health; Patient-Centered Outcomes Research Institute","keywords":"Estimator; Cluster (spacecraft); Cluster randomised controlled trial; Consistency (knowledge bases); Econometrics; Statistics; Odds; Psychology; Computer science; Logistic regression; Mathematics; Artificial intelligence; Intervention (counseling); Psychiatry","score_opus":0.4900046249090602,"score_gpt":0.6860493952461615,"score_spread":0.19604477033710127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398235233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002608678,0.00059728033,0.9853252,0.00310695,0.00056332425,0.0010710224,0.00007090926,0.000096047595,0.008908374],"genre_scores_gemma":[0.008060554,0.00017532644,0.99058914,0.00012199998,0.00027179107,0.000491916,0.000007917314,0.0000598803,0.00022147101],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9574987,0.033951685,0.0027674271,0.0011231946,0.0030514416,0.0016075231],"domain_scores_gemma":[0.52048236,0.4779657,0.00007305967,0.00047293227,0.00017314391,0.0008327762],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1625494,0.0003157272,0.001601468,0.0010247312,0.00010932255,0.00033627596,0.0006704164,0.0005153047,0.006936956],"category_scores_gemma":[0.673504,0.00023076008,0.00013989433,0.0020161758,0.0010023356,0.00014516612,0.00035473396,0.0035587142,0.00007648919],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004815189,0.00010358047,0.000038723778,0.00051420956,0.000017427732,0.0008717029,0.00013748133,2.1357877e-7,0.000071980176,0.5045226,0.0013997231,0.49184078],"study_design_scores_gemma":[0.0033898046,0.00017218929,0.00038090395,0.0014765952,0.000024070596,0.000027560618,0.00010553992,0.09992341,0.000102952,0.8925054,0.0016618116,0.00022976182],"about_ca_topic_score_codex":0.0001534361,"about_ca_topic_score_gemma":0.00008314247,"teacher_disagreement_score":0.5109546,"about_ca_system_score_codex":0.0003016792,"about_ca_system_score_gemma":0.0008827237,"threshold_uncertainty_score":0.99874014},"labels":[],"label_agreement":null},{"id":"W4399131742","doi":"10.1177/09622802241248382","title":"Maintaining the validity of inference from linear mixed models in stepped-wedge cluster randomized trials under misspecified random-effects structures","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; Patient-Centered Outcomes Research Institute; National Institute on Aging; National Institutes of Health; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Estimator; Random effects model; Statistics; Linear model; Mathematics; Mixed model; Robust statistics; Variance (accounting); Cluster (spacecraft); Computer science; Econometrics","score_opus":0.46295632730046754,"score_gpt":0.6140813913553269,"score_spread":0.15112506405485937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399131742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020494082,0.0007003951,0.99055624,0.0015166135,0.00068246905,0.0026484479,0.00019298361,0.000049116206,0.0016043541],"genre_scores_gemma":[0.13380817,0.00034475452,0.864906,0.00011995922,0.00029414232,0.00043131624,0.000014861538,0.000050505038,0.00003027956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8841379,0.10690895,0.003353763,0.0010408583,0.0033281131,0.0012304101],"domain_scores_gemma":[0.2981205,0.7003551,0.00018106577,0.00061489077,0.0002829086,0.00044553832],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1427514,0.00041003575,0.0031242606,0.00052776124,0.00012543684,0.0001629963,0.0009691491,0.0005632795,0.002874984],"category_scores_gemma":[0.64463556,0.00023397015,0.0002953356,0.0011720288,0.0025485414,0.00010556264,0.00052691,0.0034589986,0.000013112809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009730283,0.000115027426,0.000011867698,0.00044675326,0.000096894124,0.00019116657,0.0008463855,0.000019607269,0.00015039426,0.7439931,0.00041378074,0.24398476],"study_design_scores_gemma":[0.025109876,0.00008806986,0.00020188208,0.0010037449,0.000082450235,0.0000029994776,0.0003109555,0.24356452,0.0005603173,0.72884965,0.000045719906,0.00017984153],"about_ca_topic_score_codex":0.0004912598,"about_ca_topic_score_gemma":0.00013029673,"teacher_disagreement_score":0.59344614,"about_ca_system_score_codex":0.00019148165,"about_ca_system_score_gemma":0.0008646654,"threshold_uncertainty_score":0.99884003},"labels":[],"label_agreement":null},{"id":"W4399385251","doi":"10.1177/09622802241254211","title":"Group sequential methods based on supremum logrank statistics under proportional and nonproportional hazards","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ligue Contre le Cancer","keywords":"Infimum and supremum; Log-rank test; Statistics; Proportional hazards model; Interim analysis; Interim; Monte Carlo method; Statistical hypothesis testing; Multiple comparisons problem; Computer science; Mathematics; Clinical trial; Medicine; Internal medicine; Law","score_opus":0.6393074929333418,"score_gpt":0.7234070603281539,"score_spread":0.08409956739481217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399385251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014567062,0.0002205508,0.9887209,0.003912687,0.0016165791,0.0012061163,0.001088522,0.00020104411,0.0028879116],"genre_scores_gemma":[0.003411355,0.00012149773,0.99410856,0.00061367545,0.0007791974,0.00043543061,0.00007809595,0.00014896585,0.00030322006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95507807,0.031524863,0.0029331525,0.0020402716,0.006605081,0.001818586],"domain_scores_gemma":[0.64431125,0.35318568,0.00012529931,0.00064348365,0.00048082627,0.0012534783],"candidate_categories":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1115317,0.0005798167,0.0014375871,0.00097247824,0.00030976182,0.00034282287,0.00075629493,0.0009401193,0.017935514],"category_scores_gemma":[0.49534857,0.0004601462,0.00018629924,0.0016417925,0.0044021476,0.000116541596,0.00054740265,0.0051000747,0.00009193597],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033662136,0.00043833922,0.00005193477,0.00063536555,0.00006436822,0.000689513,0.000027821276,0.0000038577946,0.00018940028,0.5802328,0.004549062,0.41278094],"study_design_scores_gemma":[0.0011067215,0.0007733837,0.0011942562,0.0005989212,0.000076510114,0.000042657797,0.000051176623,0.16621463,0.0001779001,0.82563525,0.0037240912,0.00040450582],"about_ca_topic_score_codex":0.00007708818,"about_ca_topic_score_gemma":0.000034077657,"teacher_disagreement_score":0.41237643,"about_ca_system_score_codex":0.00047851086,"about_ca_system_score_gemma":0.0019843865,"threshold_uncertainty_score":0.999785},"labels":[],"label_agreement":null},{"id":"W4400969513","doi":"10.1177/09622802241262521","title":"Analyzing heterogeneity in biomarker discriminative performance through partial time-dependent receiver operating characteristic curve modeling","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Texas at Austin; Pfizer; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Discriminative model; Receiver operating characteristic; Biomarker; Computer science; Artificial intelligence; Biology; Machine learning","score_opus":0.19317553433438792,"score_gpt":0.5356551573303712,"score_spread":0.3424796229959832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400969513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032659527,0.0003539761,0.9641966,0.00094380864,0.0005854366,0.00032305828,0.00001402637,0.0000846249,0.00083893485],"genre_scores_gemma":[0.60360765,0.0003029555,0.39570796,0.000045305558,0.00012455821,0.00014568502,0.000005790317,0.000022739297,0.00003735701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98974013,0.0053686057,0.0008185493,0.0011337069,0.0019300194,0.0010089865],"domain_scores_gemma":[0.9921864,0.0068578315,0.00003697581,0.00044789442,0.00017776621,0.00029312077],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01951289,0.00022168148,0.00040944695,0.00046424606,0.00020090696,0.00035191394,0.0009561215,0.00022127708,0.00047824648],"category_scores_gemma":[0.011647317,0.00019023991,0.000049629867,0.0017666867,0.0003961135,0.00072851975,0.0008705633,0.0021371462,0.00008118749],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005176137,0.00008913627,0.0005387084,0.00023124929,0.000025655561,0.0004879834,0.0014253939,0.0005912264,0.0014982356,0.0068038353,0.000044234508,0.9882126],"study_design_scores_gemma":[0.00023083463,0.00014211438,0.0020005137,0.0005822065,0.0000046545415,0.000020455785,0.000059854166,0.9843782,0.0015839861,0.01064104,0.00015216092,0.00020393333],"about_ca_topic_score_codex":0.00035568178,"about_ca_topic_score_gemma":0.00006661537,"teacher_disagreement_score":0.9880086,"about_ca_system_score_codex":0.00074833666,"about_ca_system_score_gemma":0.0005702381,"threshold_uncertainty_score":0.996678},"labels":[],"label_agreement":null},{"id":"W4400969532","doi":"10.1177/09622802241262527","title":"Minimizing confounding in comparative observational studies with time-to-event outcomes: An extensive comparison of covariate balancing methods using Monte Carlo simulation","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Covariate; Confounding; Observational study; Monte Carlo method; Econometrics; Computer science; Statistics; Event (particle physics); Mathematics","score_opus":0.8432242746118068,"score_gpt":0.7654410243786494,"score_spread":0.07778325023315746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400969532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048692953,0.00024836842,0.94965017,0.00024513403,0.00008637451,0.000836041,0.000028312938,0.00007419018,0.00013846884],"genre_scores_gemma":[0.254606,0.0000062969007,0.74516416,0.000041552947,0.000028714867,0.00008815196,0.00000467391,0.000030190815,0.000030275272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9878798,0.007413037,0.0014377582,0.000660994,0.0019180553,0.0006903529],"domain_scores_gemma":[0.8763608,0.121876575,0.00014710719,0.0003257093,0.00097627967,0.00031356016],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023455447,0.00027819732,0.0013992959,0.00073614554,0.000105596984,0.000058480437,0.00032270915,0.00019198564,0.00024283677],"category_scores_gemma":[0.0896238,0.00021507515,0.00004527744,0.001435109,0.0006708459,0.0002435648,0.00028160991,0.0014459165,0.000004774496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001277386,0.0011789689,0.008035371,0.002950575,0.00069311564,0.0007482059,0.049026787,0.10112334,0.015191549,0.5037282,0.00032981895,0.31571665],"study_design_scores_gemma":[0.00030555748,0.0003791059,0.0017504436,0.0019466882,0.000028569026,0.0000033064398,0.0042004236,0.8138084,0.00098916,0.176333,0.000057481106,0.00019788765],"about_ca_topic_score_codex":0.00015496959,"about_ca_topic_score_gemma":0.000119693446,"teacher_disagreement_score":0.71268505,"about_ca_system_score_codex":0.00075847073,"about_ca_system_score_gemma":0.00053487584,"threshold_uncertainty_score":0.9180447},"labels":[],"label_agreement":null},{"id":"W4401390114","doi":"10.1177/09622802241267812","title":"Inference for restricted mean survival time as a function of restriction time under length-biased sampling","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Health Canada; Medical Research Council; Pfizer Canada; National Institutes of Health; Medical Research Council Canada; National Natural Science Foundation of China; Pfizer; University of International Business and Economics; Southwestern University of Finance and Economics","keywords":"Estimator; Covariate; Statistics; Survival function; Mathematics; Inference; Sampling (signal processing); Sample size determination; Survival analysis; Function (biology); Econometrics; Computer science; Artificial intelligence; Biology","score_opus":0.39626837284745836,"score_gpt":0.617300448325334,"score_spread":0.22103207547787568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401390114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032899885,0.00011784759,0.9893396,0.0005314328,0.0004277121,0.00078171544,0.00023533804,0.00012506093,0.0051513165],"genre_scores_gemma":[0.018405424,0.000108821565,0.98036295,0.000046706704,0.00023627406,0.00020491779,0.00005151329,0.000066411696,0.00051696616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98825216,0.0061522555,0.0013020447,0.00083559484,0.0025017832,0.0009561374],"domain_scores_gemma":[0.78031814,0.21800718,0.00008511262,0.00042862722,0.00064101693,0.00051994174],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.023110427,0.00027274445,0.00078960106,0.0006906563,0.00015252088,0.000110263936,0.00045948353,0.0004888367,0.008322081],"category_scores_gemma":[0.31893426,0.0002273475,0.000107968146,0.001902177,0.00080171647,0.00009421739,0.00022435,0.0017418078,0.0001440975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032472235,0.0001581358,0.000007903028,0.0004345924,0.000045717345,0.00002682135,0.0000869328,0.0000024450112,0.004271186,0.6646758,0.0010209829,0.3289448],"study_design_scores_gemma":[0.00054127065,0.00091449043,0.001191729,0.0006406919,0.000053772124,0.0000038399526,0.00013267242,0.10047149,0.0003550698,0.8943662,0.001119807,0.00020898606],"about_ca_topic_score_codex":0.0001725851,"about_ca_topic_score_gemma":0.00001162588,"teacher_disagreement_score":0.32873583,"about_ca_system_score_codex":0.00023906754,"about_ca_system_score_gemma":0.0011120589,"threshold_uncertainty_score":0.99258447},"labels":[],"label_agreement":null},{"id":"W4401959276","doi":"10.1177/09622802241259175","title":"Unsupervised Liu-type shrinkage estimators for mixture of regression models","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multicollinearity; Covariate; Estimator; Regression; Expectation–maximization algorithm; Computer science; Statistics; Shrinkage estimator; Regression analysis; Lasso (programming language); Artificial intelligence; Mathematics; Econometrics; Maximum likelihood","score_opus":0.13749339727712664,"score_gpt":0.5495093220074783,"score_spread":0.41201592473035165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401959276","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007070497,0.00223913,0.99112004,0.0023768402,0.0007134517,0.00052246277,0.000028923887,0.000090042624,0.0028383804],"genre_scores_gemma":[0.006810132,0.00028327238,0.9922533,0.0001362569,0.00012153777,0.00009467773,0.0000078928415,0.00003290564,0.00025999756],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99178594,0.0037373023,0.000715398,0.0009170252,0.0019622252,0.00088211923],"domain_scores_gemma":[0.9734642,0.024731081,0.000034952544,0.00072789454,0.00039694586,0.0006449499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02265529,0.0002219286,0.0005714008,0.00055594597,0.00010517677,0.00013505615,0.0015098349,0.00043800735,0.00026618293],"category_scores_gemma":[0.021166723,0.00015663788,0.00010322056,0.0018795414,0.0005437476,0.00024667534,0.00061663514,0.001567041,0.000009014393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032380212,0.000049572394,0.000003558697,0.00032645205,0.000009557574,0.00011048401,0.0002452309,0.0000046902937,0.0004758445,0.49359712,0.001553676,0.5035914],"study_design_scores_gemma":[0.00018633931,0.00016260747,0.00002364367,0.00042111095,0.0000038625626,0.000005530403,0.0000092142545,0.49515936,0.00096358743,0.50105286,0.001920055,0.00009183347],"about_ca_topic_score_codex":0.000045275297,"about_ca_topic_score_gemma":0.0000049631158,"teacher_disagreement_score":0.50349957,"about_ca_system_score_codex":0.00008643335,"about_ca_system_score_gemma":0.0009788347,"threshold_uncertainty_score":0.9870784},"labels":[],"label_agreement":null},{"id":"W4403203326","doi":"10.1177/09622802241268466","title":"Joint modeling of zero-inflated longitudinal measurements and time-to-event outcomes with applications to dynamic prediction","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Generalized linear mixed model; Random effects model; Event (particle physics); Computer science; Count data; Poisson distribution; Statistics; Mixed model; Bayesian probability; Markov chain Monte Carlo; Negative binomial distribution; Marginal model; Linear model; Econometrics; Mathematics; Regression analysis; Medicine","score_opus":0.28591415939095105,"score_gpt":0.5747006451452177,"score_spread":0.28878648575426663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403203326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088056776,0.00006396895,0.99533665,0.0012709746,0.000048868154,0.001076816,0.00014758056,0.000057734378,0.001116826],"genre_scores_gemma":[0.051594272,0.000014339096,0.94776386,0.00003772353,0.000023146584,0.00042370646,0.0000067917554,0.000035869725,0.00010030432],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99392873,0.0017346648,0.0008716609,0.0006724401,0.0021888013,0.0006037172],"domain_scores_gemma":[0.98563576,0.012817209,0.00003265132,0.00034714013,0.00039020396,0.00077704305],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.013822454,0.00020341176,0.00059242715,0.00053682516,0.00009546745,0.00007044366,0.00026254074,0.0001610576,0.0010422139],"category_scores_gemma":[0.034551106,0.00014576499,0.00003558969,0.0011438366,0.0003401259,0.00004773027,0.00025761192,0.00089647505,0.000058018606],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013750767,0.00022877386,0.00048803195,0.0008040134,0.000099315104,0.00006483876,0.00023251603,0.000059074722,0.001151764,0.27217367,0.0003205684,0.7242399],"study_design_scores_gemma":[0.00023740008,0.00040085524,0.0027101042,0.00081249425,0.000035964473,0.000010293575,0.00003600137,0.39717153,0.00009300751,0.59825397,0.00010445927,0.00013391605],"about_ca_topic_score_codex":0.000061514875,"about_ca_topic_score_gemma":0.000017270997,"teacher_disagreement_score":0.724106,"about_ca_system_score_codex":0.0001927275,"about_ca_system_score_gemma":0.00032107136,"threshold_uncertainty_score":0.99987096},"labels":[],"label_agreement":null},{"id":"W4403257741","doi":"10.1177/09622802241275401","title":"Comparison of random forest methods for conditional average treatment effect estimation with a continuous treatment","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Random forest; Proxy (statistics); Estimation; Average treatment effect; Statistics; Confounding; Computer science; Treatment effect; Random effects model; Econometrics; Mathematics; Machine learning; Medicine; Propensity score matching; Meta-analysis","score_opus":0.3691927658630903,"score_gpt":0.707653083796802,"score_spread":0.33846031793371173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403257741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010982178,0.00033196926,0.99487406,0.00027284483,0.0000616393,0.002352044,0.00018337178,0.000117218035,0.0007086646],"genre_scores_gemma":[0.07336972,0.000054611137,0.9236954,0.000006933682,0.000051253894,0.0024935065,0.00014993774,0.000043603097,0.00013503814],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9920453,0.004994484,0.0008241569,0.0005177486,0.0010235782,0.00059471966],"domain_scores_gemma":[0.84317166,0.15599665,0.000072108814,0.00027797752,0.00021232892,0.00026927283],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012334163,0.00028177054,0.0011597881,0.00036417297,0.00009046365,0.000051125742,0.0002026319,0.00023049364,0.00070211897],"category_scores_gemma":[0.044066813,0.00016810544,0.00010877331,0.0004621135,0.0008456806,0.000074935946,0.000057006604,0.00052422914,0.0000049316864],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082759804,0.00041460735,0.00014106093,0.00045929794,0.000107254076,0.0000659097,0.0003057808,0.000028000466,0.0003745799,0.3161157,0.00023186665,0.68092835],"study_design_scores_gemma":[0.0023718334,0.006805771,0.00007369502,0.00039258876,0.00007515572,0.000014551674,0.000060314043,0.29574922,0.01762606,0.6749316,0.0017679674,0.00013124663],"about_ca_topic_score_codex":0.000095266216,"about_ca_topic_score_gemma":0.000075857984,"teacher_disagreement_score":0.6807971,"about_ca_system_score_codex":0.00064168894,"about_ca_system_score_gemma":0.00048643962,"threshold_uncertainty_score":0.96398544},"labels":[],"label_agreement":null},{"id":"W4403609944","doi":"10.1177/09622802241287707","title":"Graphical methods to illustrate the nature of the relation between a continuous variable and the outcome when using restricted cubic splines with a Cox proportional hazards model","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Proportional hazards model; Outcome (game theory); Hazard; Hazard ratio; Statistics; Mathematics; Variable (mathematics); Regression analysis; Relation (database); Econometrics; Computer science; Confidence interval; Mathematical analysis; Data mining; Mathematical economics","score_opus":0.2313114365674053,"score_gpt":0.5948531851561868,"score_spread":0.3635417485887815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403609944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002261679,0.00027880483,0.9880983,0.007022691,0.00012978894,0.00146869,0.00016695699,0.000032518634,0.0005405643],"genre_scores_gemma":[0.03423765,0.000024573548,0.96501845,0.00017572881,0.000120461176,0.00017162676,0.0000045380834,0.000046629404,0.00020035476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9833168,0.011502667,0.0012374696,0.00068064465,0.0025269848,0.0007354564],"domain_scores_gemma":[0.89867747,0.09960702,0.00013399427,0.0006190652,0.0005775801,0.0003848538],"candidate_categories":["metaresearch","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03649083,0.00026982845,0.0008169923,0.00022324815,0.00035854342,0.00011009837,0.00065542985,0.00046092187,0.00010657938],"category_scores_gemma":[0.13891944,0.00011265061,0.00008444612,0.0017224149,0.0031685752,0.00007980577,0.00051998877,0.004240143,6.096512e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036551006,0.00004889185,0.0001823315,0.00027597585,0.00007512085,0.00002619783,0.00038124775,0.00017909237,0.00028136544,0.924331,0.00013316296,0.07372009],"study_design_scores_gemma":[0.00043888803,0.00008008977,0.00090553175,0.00029547856,0.00009207957,0.000020197644,0.000093655486,0.37413266,0.000044222637,0.62361765,0.00018295176,0.00009656599],"about_ca_topic_score_codex":0.00013957919,"about_ca_topic_score_gemma":0.000028496754,"teacher_disagreement_score":0.37395358,"about_ca_system_score_codex":0.00010042161,"about_ca_system_score_gemma":0.0008639074,"threshold_uncertainty_score":0.9995442},"labels":[],"label_agreement":null},{"id":"W4403691889","doi":"10.1177/09622802241282091","title":"Applying survey weights to ordinal regression models for improved inference in outcome-dependent samples with ordinal outcomes","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Institute for Work & Health; Western University; Public Health Ontario; University of Toronto","funders":"Agencia Estatal de Investigación; Natural Sciences and Engineering Research Council of Canada; Ministerio de Ciencia e Innovación; University of Toronto; Instituto de Salud Carlos III; Alliance de recherche numérique du Canada; Generalitat de Catalunya; Innovation, Science and Economic Development Canada","keywords":"Statistics; Ordinal regression; Mathematics; Econometrics; Logistic regression; Ordinal data; Ordered logit; Logit; Outcome (game theory); Regression analysis; Sampling bias; Sample size determination","score_opus":0.4117070033392049,"score_gpt":0.6242060080290859,"score_spread":0.21249900468988098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403691889","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00086471665,0.00007812351,0.9939961,0.0013382128,0.00028066672,0.0022787023,0.0005065463,0.000081369755,0.00057559804],"genre_scores_gemma":[0.03703932,0.00003195646,0.96026874,0.00013316744,0.00008419276,0.0021597922,0.000025564768,0.000079702324,0.00017757832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9868099,0.006338037,0.001527738,0.0013316717,0.002368996,0.0016236724],"domain_scores_gemma":[0.77939725,0.21851523,0.00006948841,0.00057240535,0.00047373294,0.0009718711],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038819976,0.00045775503,0.0013276438,0.00092987745,0.00018352226,0.00027097086,0.00088309776,0.00039752945,0.0008930884],"category_scores_gemma":[0.23925833,0.00028801215,0.00008320626,0.0016531381,0.00059738994,0.00016411464,0.00052052154,0.002401503,0.000017527822],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004796217,0.0001845335,0.0053041144,0.0005521132,0.000025025736,0.00018953001,0.00014117232,0.0000025629502,0.000055402186,0.52448124,0.0001989867,0.46838567],"study_design_scores_gemma":[0.0008366127,0.00058452,0.0090985065,0.0011739697,0.000018433244,0.000008681891,0.00015060099,0.121167146,0.00008236712,0.86614835,0.00036092626,0.00036989187],"about_ca_topic_score_codex":0.0013872187,"about_ca_topic_score_gemma":0.002088596,"teacher_disagreement_score":0.4680158,"about_ca_system_score_codex":0.00038320807,"about_ca_system_score_gemma":0.00093096914,"threshold_uncertainty_score":0.9999572},"labels":[],"label_agreement":null},{"id":"W4404422780","doi":"10.1177/09622802241281035","title":"LASSO-type instrumental variable selection methods with an application to Mendelian randomization","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute on Aging","keywords":"Instrumental variable; Mendelian randomization; Estimator; Lasso (programming language); Heteroscedasticity; Computer science; Jackknife resampling; Econometrics; Statistics; Mathematics","score_opus":0.17063553148990346,"score_gpt":0.6105062295924588,"score_spread":0.43987069810255536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404422780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004422149,0.000048736045,0.9914621,0.0007350913,0.0002888583,0.0010456751,0.000038467933,0.00015761814,0.0057811993],"genre_scores_gemma":[0.0052956296,0.000027662994,0.9935641,0.00016075319,0.00020144608,0.00044937088,0.00003200381,0.0000689689,0.00020001859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9842497,0.011007406,0.0008512535,0.0009908522,0.0019833234,0.00091743283],"domain_scores_gemma":[0.9588153,0.03928544,0.00004552694,0.00040514476,0.00049775233,0.0009508709],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036799688,0.0002659447,0.0006065165,0.0006103154,0.00019414719,0.0002174491,0.0004479573,0.00032800573,0.0037241552],"category_scores_gemma":[0.0837516,0.00019859015,0.000030248057,0.003493822,0.00039895566,0.00016354698,0.00018581431,0.0016252865,0.00006528698],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004408577,0.0001257671,0.000027974802,0.00014758453,0.000021015932,0.000017663026,0.00012558985,0.000006792233,0.0018528341,0.509092,0.0004149324,0.48772702],"study_design_scores_gemma":[0.0007847189,0.00096410554,0.00014875304,0.0002418294,0.00002767084,0.000025837853,0.00014697958,0.28106636,0.0014496224,0.7086414,0.006288851,0.00021385774],"about_ca_topic_score_codex":0.0003025611,"about_ca_topic_score_gemma":0.00009340402,"teacher_disagreement_score":0.48751318,"about_ca_system_score_codex":0.00038839926,"about_ca_system_score_gemma":0.00076992315,"threshold_uncertainty_score":0.9971866},"labels":[],"label_agreement":null},{"id":"W4405260740","doi":"10.1177/09622802241293768","title":"Hierarchical selection of genetic and gene by environment interaction effects in high-dimensional mixed models","year":2024,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"National Institute of Dental and Craniofacial Research; National Institute of Neurological Disorders and Stroke; Fonds de Recherche du Québec - Santé; Compute Canada; University at Buffalo; University of North Carolina at Chapel Hill; National Institutes of Health; National Heart, Lung, and Blood Institute; McGill University; Canada Excellence Research Chairs, Government of Canada; Natural Sciences and Engineering Research Council of Canada; Johns Hopkins University","keywords":"Gene–environment interaction; Selection (genetic algorithm); Random effects model; Computer science; Population; Mixed model; Generalized linear mixed model; Multilevel model; Machine learning; Gene; Genetics; Biology","score_opus":0.062179025335524635,"score_gpt":0.4703002740679868,"score_spread":0.40812124873246214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405260740","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004907326,0.64056593,0.35804433,0.000031632393,0.00018907725,0.00054261374,0.00007799207,0.000003299737,0.000054398475],"genre_scores_gemma":[0.00037441202,0.5689652,0.43009314,0.000011504203,0.000109040826,0.00019152998,0.00014458825,0.000037220536,0.000073385665],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99237967,0.0045249006,0.0008271396,0.0008650046,0.00090117933,0.0005021272],"domain_scores_gemma":[0.99669385,0.002628879,0.00006938,0.00024689824,0.0000373861,0.00032363686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032684503,0.00030018098,0.0009008602,0.00030211324,0.00003488696,0.00001662565,0.00027013675,0.0007709857,0.00015056961],"category_scores_gemma":[0.0024944094,0.00024153444,0.000084062485,0.00029110358,0.00066209876,0.0000026434293,0.00046343802,0.0017342417,0.000008630335],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006232206,0.0001809371,0.000005482834,0.0041736793,0.000067740184,0.000018092549,0.000014417481,0.00004433732,0.00030752478,0.005252014,0.00074912835,0.9891243],"study_design_scores_gemma":[0.0038349957,0.007899457,0.003428427,0.022873996,0.0010242083,0.0005169294,0.000050056642,0.025147768,0.0018211086,0.5029665,0.42805797,0.0023785648],"about_ca_topic_score_codex":0.00007461489,"about_ca_topic_score_gemma":0.000014218813,"teacher_disagreement_score":0.9867458,"about_ca_system_score_codex":0.000096991214,"about_ca_system_score_gemma":0.00044361898,"threshold_uncertainty_score":0.9849488},"labels":[],"label_agreement":null},{"id":"W4405260884","doi":"10.1177/09622802241295335","title":"Marginal semiparametric accelerated failure time cure model for clustered survival data","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Accelerated failure time model; Estimator; Semiparametric regression; Semiparametric model; Estimating equations; Correlation; Proportional hazards model; Computer science; Expectation–maximization algorithm; Mathematics; Mixture model; Statistics; Econometrics; Maximum likelihood","score_opus":0.6123641329876975,"score_gpt":0.6574912683814603,"score_spread":0.045127135393762785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405260884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009375445,0.00031084352,0.9892608,0.0037718317,0.0003561059,0.0010079992,0.0021001126,0.00014453052,0.0029540244],"genre_scores_gemma":[0.0021675434,0.000103861355,0.9951244,0.00010187507,0.00031597842,0.00025071434,0.00022586447,0.00009846279,0.0016112732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9865437,0.006060574,0.0012334023,0.0015120133,0.0030488756,0.0016014256],"domain_scores_gemma":[0.8338742,0.1634691,0.00005298893,0.0011666004,0.00051407027,0.0009229828],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045502316,0.00037061135,0.00097387494,0.0007183449,0.00019102423,0.00034562225,0.0019840852,0.0006132509,0.006652737],"category_scores_gemma":[0.31624117,0.00029037494,0.00008122853,0.002471775,0.0009460865,0.00017534354,0.0012695,0.0030239758,0.00014122584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015509357,0.00017803797,0.0000074290238,0.000842473,0.000050871655,0.00017979804,0.000091438334,0.000004554942,0.00014627627,0.47449493,0.060140703,0.46370837],"study_design_scores_gemma":[0.0003557285,0.00011828542,0.000025449343,0.00024843973,0.00002531127,0.000009502063,0.000039778442,0.52702427,0.00002971923,0.46681422,0.0051310225,0.00017824364],"about_ca_topic_score_codex":0.000045984973,"about_ca_topic_score_gemma":0.000041135478,"teacher_disagreement_score":0.52701974,"about_ca_system_score_codex":0.00023844237,"about_ca_system_score_gemma":0.0016203907,"threshold_uncertainty_score":0.9999548},"labels":[],"label_agreement":null},{"id":"W4405382992","doi":"10.1177/09622802241293750","title":"Approximation to the optimal allocation for response adaptive designs","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Bayesian probability; Statistical power; Mathematical optimization; Markov decision process; Coverage probability; Mathematics; Computer science; Randomization; Posterior probability; Probability distribution; Operator (biology); Statistics; Markov process; Clinical trial; Confidence interval","score_opus":0.8459332953070716,"score_gpt":0.7486349097033211,"score_spread":0.09729838560375048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405382992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020896501,0.0001214367,0.97545373,0.01932429,0.0007958822,0.0029485666,0.00021137483,0.00011486889,0.000820902],"genre_scores_gemma":[0.0042843884,0.000027442458,0.99177647,0.0003461162,0.0006118362,0.0023847437,0.0000056136573,0.00007880811,0.00048455966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9551313,0.037088826,0.001805074,0.001206186,0.0034289202,0.0013397043],"domain_scores_gemma":[0.34106052,0.65702564,0.000056217195,0.00063502725,0.0005298822,0.0006927076],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19591086,0.00026411275,0.0006933758,0.00048766675,0.00025138087,0.0002107012,0.0009854034,0.00044660512,0.0016110266],"category_scores_gemma":[0.8611473,0.00017441183,0.00012920078,0.0018405081,0.00096259284,0.00008150903,0.0003813212,0.0020656546,0.00016596934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019013921,0.00010946123,7.3719815e-7,0.0001699396,0.000031618012,0.00004659898,0.0003846926,0.000009049756,0.00033445776,0.54334486,0.01076749,0.44289973],"study_design_scores_gemma":[0.00045048515,0.0008930748,0.000114848444,0.0003872073,0.000032334923,0.0000081683365,0.00033867243,0.15718366,0.0008446628,0.8270915,0.012474663,0.00018067542],"about_ca_topic_score_codex":0.000024037401,"about_ca_topic_score_gemma":0.000017153256,"teacher_disagreement_score":0.6652364,"about_ca_system_score_codex":0.00040116123,"about_ca_system_score_gemma":0.0010144691,"threshold_uncertainty_score":0.9993016},"labels":[],"label_agreement":null},{"id":"W4405382998","doi":"10.1177/09622802241298704","title":"A Bayesian latent class approach to causal inference with longitudinal data","year":2024,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; University Health Network; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Causal inference; Confounding; Covariate; Bayesian probability; Latent class model; Latent variable; Econometrics; Computer science; Bayesian inference; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.6368623295240852,"score_gpt":0.6762469425986279,"score_spread":0.039384613074542774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405382998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013858317,0.00010258731,0.9845422,0.0016449039,0.000082212784,0.0007470511,0.00013161717,0.00027216613,0.012338668],"genre_scores_gemma":[0.0712448,0.000056202534,0.92781883,0.000089409994,0.000127996,0.00032091397,0.00004799082,0.000062788444,0.00023109213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99076253,0.002869185,0.00070346444,0.001306603,0.0031377098,0.0012204892],"domain_scores_gemma":[0.9603196,0.036922075,0.000030013618,0.0014040077,0.0002763681,0.0010479686],"candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020504858,0.00028548756,0.00058666675,0.00054534717,0.00010138724,0.00019198169,0.0016092798,0.00029755718,0.0011769792],"category_scores_gemma":[0.089626595,0.00020016539,0.000024753688,0.0018531907,0.0010414672,0.00021593549,0.0016030545,0.0031246976,0.000058967973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008775378,0.00023056095,0.00020810208,0.000449826,0.000030926603,0.000803859,0.00019338082,0.0000027895012,0.000065843815,0.7344351,0.005750314,0.25774157],"study_design_scores_gemma":[0.00020962139,0.00052751857,0.0005369954,0.0009231188,0.000021122567,0.00007000905,0.00014135528,0.1353916,0.00016924638,0.8566943,0.0049960446,0.0003191075],"about_ca_topic_score_codex":0.00017195135,"about_ca_topic_score_gemma":0.00018277466,"teacher_disagreement_score":0.25742245,"about_ca_system_score_codex":0.00029679434,"about_ca_system_score_gemma":0.0010176639,"threshold_uncertainty_score":0.9997361},"labels":[],"label_agreement":null},{"id":"W4407415052","doi":"10.1177/09622802241310326","title":"Using Bayesian evidence synthesis to quantify uncertainty in population trends in smoking behaviour","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; Simon Fraser University","funders":"National Health and Medical Research Council; Department of Health and Aged Care, Australian Government","keywords":"Bayesian probability; Econometrics; Bayesian inference; Credible interval; Tobacco control; Bayesian hierarchical modeling; Population; Calibration; Blueprint; Prediction interval; Confidence interval; Smoking cessation; Uncertainty analysis; Psychological intervention; Statistics; Medicine; Computer science; Environmental health; Mathematics; Engineering","score_opus":0.4034743928626631,"score_gpt":0.6493406843584507,"score_spread":0.2458662914957876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407415052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20731525,0.00008252067,0.7692857,0.020137861,0.0001865775,0.0005467475,0.000018210203,0.000021001631,0.0024061513],"genre_scores_gemma":[0.689949,0.00002435252,0.30924168,0.0006613362,0.000015506203,0.0000546932,0.0000021630076,0.000008227721,0.000043049095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9880261,0.007748459,0.0008245176,0.00060743047,0.0017523391,0.001041164],"domain_scores_gemma":[0.97675645,0.022313908,0.00003675452,0.00029478536,0.000018312327,0.00057976233],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03600958,0.00013196318,0.00038682035,0.0008316013,0.00012992266,0.000038784725,0.00044634094,0.00027675185,0.005440901],"category_scores_gemma":[0.121376336,0.00012360502,0.000024158135,0.0035057326,0.00039409546,0.00013853164,0.0004336046,0.0014369193,0.000015734637],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010911913,0.00010701569,0.3484753,0.000054818574,0.000001019861,0.00008889755,0.00030623414,0.00061422214,0.000044651177,0.004743303,0.00021522185,0.6452402],"study_design_scores_gemma":[0.00015162291,0.000055611126,0.85117584,0.0010701807,0.0000032181279,0.0000011236716,0.00020445824,0.12837875,0.000031451596,0.01869498,0.0001267049,0.000106055675],"about_ca_topic_score_codex":0.05778947,"about_ca_topic_score_gemma":0.019376496,"teacher_disagreement_score":0.64513415,"about_ca_system_score_codex":0.0018335583,"about_ca_system_score_gemma":0.00019908656,"threshold_uncertainty_score":0.99851733},"labels":[],"label_agreement":null},{"id":"W4409900557","doi":"10.1177/09622802241313289","title":"On flexible inverse probability of treatment and intensity weighting: Informative censoring, variable selection, and weight trimming","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Weighting; Censoring (clinical trials); Inverse probability weighting; Inverse probability; Statistics; Marginal structural model; Confounding; Trimming; Econometrics; Computer science; Observational study; A-weighting; Mathematics; Propensity score matching; Posterior probability; Bayesian probability; Medicine","score_opus":0.2843125504702238,"score_gpt":0.5949416301576912,"score_spread":0.3106290796874674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409900557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024409363,0.000029248768,0.9649509,0.0002727355,0.0000405483,0.0006231852,0.000013029991,0.00006268575,0.009598308],"genre_scores_gemma":[0.02045568,0.00012649619,0.9790116,0.000047732727,0.000012661174,0.000107817454,0.0000021065152,0.000008992147,0.00022693086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965354,0.0015738249,0.00060375006,0.0003535674,0.000505715,0.0004277373],"domain_scores_gemma":[0.97044486,0.028589698,0.000072696625,0.00023210661,0.0004278116,0.00023285545],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009100064,0.00015611772,0.00052009337,0.0003597561,0.00012351289,0.000020494757,0.0001333216,0.00020305805,0.00023679082],"category_scores_gemma":[0.095802605,0.000117700445,0.00001797853,0.0007412735,0.00086968776,0.00009062745,0.000248016,0.0008839231,9.475107e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022420114,0.00018022729,0.0008398531,0.00038335536,0.00002500853,0.0000042419815,0.00041889766,9.307844e-7,0.00028851742,0.8914398,0.00034026563,0.10585468],"study_design_scores_gemma":[0.00052510586,0.0006823773,0.00052112807,0.00041072836,0.000012592741,0.000003637291,0.00021070574,0.009473127,0.012813037,0.97443503,0.0008257969,0.00008674679],"about_ca_topic_score_codex":0.00022766378,"about_ca_topic_score_gemma":0.000044199078,"teacher_disagreement_score":0.105767936,"about_ca_system_score_codex":0.00043774868,"about_ca_system_score_gemma":0.00045258677,"threshold_uncertainty_score":0.91181386},"labels":[],"label_agreement":null},{"id":"W4410351772","doi":"10.1177/09622802251338387","title":"Rank-based estimators of global treatment effects for cluster randomized trials with multiple endpoints on different scales","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Estimator; Statistics; Wilcoxon signed-rank test; Confidence interval; Sample size determination; Mathematics; Fraction (chemistry); Variance (accounting); Coverage probability; Point estimation; Cluster (spacecraft); Rank (graph theory); Interval (graph theory); Econometrics; Computer science; Mann–Whitney U test","score_opus":0.19560503028694087,"score_gpt":0.6096647113663234,"score_spread":0.4140596810793825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410351772","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002540844,0.000073287745,0.9900814,0.0012036909,0.00023776329,0.0045432965,0.0003457684,0.00003442582,0.00093949126],"genre_scores_gemma":[0.063701905,0.000022152115,0.93404335,0.0001302071,0.000046794044,0.0019862624,0.000013744412,0.000026215663,0.000029339373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9640867,0.030597782,0.0018246523,0.00075550424,0.0018181417,0.0009171996],"domain_scores_gemma":[0.4871419,0.51162636,0.00015950324,0.0004087716,0.00027729935,0.00038615227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040114723,0.0004028964,0.0033611753,0.00030745674,0.00012579122,0.000049471433,0.00043270722,0.00034087632,0.00033755807],"category_scores_gemma":[0.6456198,0.00022135068,0.0002959555,0.00066920446,0.0019294794,0.000021745116,0.00010769995,0.0006009416,0.0000030942388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.060405996,0.00091046555,0.00039385355,0.0009844264,0.00015048585,0.0000317351,0.000020729593,0.0000013402614,0.000034945253,0.5307945,0.00029427704,0.40597725],"study_design_scores_gemma":[0.103458464,0.0014235742,0.0012271245,0.0015039598,0.0001788784,0.0000012484606,0.00002480757,0.057911493,0.003950262,0.83010244,0.000039397288,0.0001783475],"about_ca_topic_score_codex":0.00009000991,"about_ca_topic_score_gemma":0.00010394399,"teacher_disagreement_score":0.6055051,"about_ca_system_score_codex":0.00041141428,"about_ca_system_score_gemma":0.00066266145,"threshold_uncertainty_score":0.9884039},"labels":[],"label_agreement":null},{"id":"W4411436605","doi":"10.1177/09622802251348999","title":"Permutation tests for detecting treatment effect heterogeneity in cluster randomized trials","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases; Patient-Centered Outcomes Research Institute","keywords":"Permutation (music); Resampling; Randomized controlled trial; Cluster (spacecraft); Statistics; Computer science; Mathematics; Multiple comparisons problem; Medicine; Internal medicine; Physics","score_opus":0.5711598577785493,"score_gpt":0.7277796225742554,"score_spread":0.15661976479570616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411436605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013268373,0.00012984437,0.98013043,0.0006697861,0.0001106467,0.004825944,0.000020687823,0.00007245516,0.00077182683],"genre_scores_gemma":[0.086551905,0.000080115446,0.90819776,0.0000662428,0.0000527549,0.0049444833,0.000009121546,0.000024515026,0.00007309574],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94831187,0.046842974,0.0020229307,0.0007017891,0.0011672392,0.0009532103],"domain_scores_gemma":[0.43114078,0.568006,0.00011654359,0.00032403466,0.00021578644,0.000196874],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13950892,0.00023304365,0.0019474323,0.0006422535,0.000097439886,0.00004618948,0.00027403125,0.0003437494,0.0001862958],"category_scores_gemma":[0.8028297,0.0001535478,0.0001797112,0.00069826376,0.00056692725,0.00005727031,0.00015062674,0.000849881,0.0000028141337],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016481498,0.00021323202,0.00012583272,0.00041080688,0.000053169315,0.000040645846,0.00014425137,0.000002544673,0.00088730716,0.123295605,0.00012735625,0.8582178],"study_design_scores_gemma":[0.044181492,0.0005112345,0.00009011546,0.0004573266,0.000043546457,0.0000021281837,0.000049880815,0.027094273,0.02122809,0.9061276,0.00009506062,0.000119280296],"about_ca_topic_score_codex":0.0001268956,"about_ca_topic_score_gemma":0.00035218368,"teacher_disagreement_score":0.85809845,"about_ca_system_score_codex":0.0006926228,"about_ca_system_score_gemma":0.00036022376,"threshold_uncertainty_score":0.88605666},"labels":[],"label_agreement":null},{"id":"W4411932894","doi":"10.1177/09622802251350263","title":"Group sequential analysis of marked point processes: Plasma donation trials","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interim; Donation; Medicine; Interim analysis; Clinical endpoint; Adverse effect; Sample size determination; Computer science; Statistics; Intensive care medicine; Clinical trial; Internal medicine; Mathematics","score_opus":0.7478914177986117,"score_gpt":0.7468351539420226,"score_spread":0.0010562638565890792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411932894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013009451,0.00010153562,0.98453957,0.0016455138,0.00060781575,0.0013311835,0.00038715496,0.000058958987,0.010027318],"genre_scores_gemma":[0.013960501,0.00024419738,0.98477244,0.00014920077,0.00014923819,0.0003753591,0.000028497747,0.000036231744,0.00028435796],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89770764,0.085958466,0.007155378,0.0015864267,0.0060719377,0.0015201282],"domain_scores_gemma":[0.20933428,0.7870988,0.00054304354,0.00094657723,0.0014281708,0.00064907223],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2604762,0.00034905612,0.0035989627,0.0025672044,0.00014032745,0.00008393583,0.0012211545,0.00082966476,0.011870182],"category_scores_gemma":[0.962221,0.0002750083,0.00039735314,0.0099653285,0.0021091679,0.00008874768,0.0006912634,0.0022860882,0.000012328015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010603872,0.00069359806,0.00025338324,0.0010829162,0.0010169344,0.000068276066,0.00009115213,0.0000019830447,0.00033404306,0.6376349,0.0017631523,0.35599926],"study_design_scores_gemma":[0.002214394,0.0002535744,0.001730371,0.00054316944,0.0010398556,0.0000012830244,0.00020684583,0.01986921,0.0012275709,0.9719726,0.0007218738,0.00021924083],"about_ca_topic_score_codex":0.00016447129,"about_ca_topic_score_gemma":0.00020351881,"teacher_disagreement_score":0.7017448,"about_ca_system_score_codex":0.00032783448,"about_ca_system_score_gemma":0.0014132732,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W4412115660","doi":"10.1177/09622802251338409","title":"Health utility adjusted survival: A composite endpoint for clinical trial designs","year":2025,"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":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"Princess Margaret Cancer Foundation","keywords":"Sample size determination; Clinical endpoint; Clinical trial; Survival analysis; Quality of life (healthcare); Medicine; Randomized controlled trial; Statistical power; Statistics; Econometrics; Mathematics; Surgery; Internal medicine","score_opus":0.9207298509088987,"score_gpt":0.7660337274815276,"score_spread":0.15469612342737105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412115660","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013598223,0.0015874295,0.886362,0.10071944,0.0020046239,0.0032777453,0.0005920063,0.000046531793,0.004050406],"genre_scores_gemma":[0.01935688,0.00093569374,0.96254945,0.013940559,0.0008289756,0.0013723667,0.0001481798,0.000055827702,0.00081205677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9471559,0.036014363,0.012347152,0.0017551132,0.0008726196,0.001854831],"domain_scores_gemma":[0.7836606,0.21243362,0.0010175203,0.0011011214,0.00036265433,0.001424524],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4407431,0.00023456529,0.0025491416,0.00077725964,0.00035968912,0.00009854938,0.0008459619,0.0005403138,0.0021347415],"category_scores_gemma":[0.44137537,0.00026245194,0.00021519432,0.0009189703,0.0009685327,0.00011024275,0.00030144127,0.0018654465,0.00022780777],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004990905,0.0008331564,0.0068123816,0.0010333557,0.00008221648,0.0000061112637,0.00023031613,0.0000013189947,2.5306656e-7,0.79021996,0.063219026,0.13257103],"study_design_scores_gemma":[0.0282167,0.001103558,0.06280681,0.0003580584,0.000007268797,0.0000011686701,0.00062808645,0.05472798,0.0000022601187,0.65615714,0.19565436,0.00033660402],"about_ca_topic_score_codex":0.0016560688,"about_ca_topic_score_gemma":0.000524093,"teacher_disagreement_score":0.17641926,"about_ca_system_score_codex":0.0009332932,"about_ca_system_score_gemma":0.0028985785,"threshold_uncertainty_score":0.9999828},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4412488270","doi":"10.1177/09622802251357021","title":"Design of egocentric network-based studies to estimate causal effects under interference","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"National Institute on Drug Abuse; National Institute of Mental Health","keywords":"Spillover effect; Psychological intervention; Leverage (statistics); Sample size determination; Randomized experiment; Randomized controlled trial; Intervention (counseling); Population; Psychology; Causal inference; Econometrics; Statistics; Computer science; Medicine; Mathematics; Environmental health","score_opus":0.47673270997648753,"score_gpt":0.6947664410253729,"score_spread":0.21803373104888535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412488270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025947174,0.0003655541,0.99642074,0.001058439,0.00017068493,0.0010185515,0.0000049154455,0.00009600701,0.0006056143],"genre_scores_gemma":[0.04021196,0.000082885716,0.9589065,0.00026239277,0.000028958833,0.0003782861,0.0000015530068,0.00002423106,0.00010324952],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98889256,0.007239085,0.0008764617,0.00054220745,0.0014347704,0.0010149255],"domain_scores_gemma":[0.84383976,0.15467654,0.00006664445,0.00047409654,0.0005945381,0.0003484142],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020011988,0.00022883901,0.0008407351,0.0005668985,0.0000923283,0.00002199564,0.0006784976,0.00023700955,0.000259252],"category_scores_gemma":[0.2543436,0.00018254705,0.000034984678,0.002062419,0.0010417156,0.000041339244,0.0006353974,0.0013432563,0.000008966639],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002620692,0.00022696528,0.00016266046,0.0010530552,0.00005667135,0.00014152373,0.00010866428,0.00047977956,0.00065395574,0.73841673,0.0052818432,0.25315607],"study_design_scores_gemma":[0.00039853595,0.0005587285,0.000392609,0.0020505341,0.000021251533,0.0000012285373,0.000069064634,0.029001787,0.008504368,0.9588051,0.00005345548,0.00014333882],"about_ca_topic_score_codex":0.000026591793,"about_ca_topic_score_gemma":0.000033135908,"teacher_disagreement_score":0.25301275,"about_ca_system_score_codex":0.0003935236,"about_ca_system_score_gemma":0.00071059534,"threshold_uncertainty_score":0.7519374},"labels":[],"label_agreement":null},{"id":"W4413298197","doi":"10.1177/09622802251362642","title":"Imputation of incomplete ordinal and nominal data by predictive mean matching","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Categorical variable; Missing data; Imputation (statistics); Statistics; Multinomial logistic regression; Mathematics; Ordinal data; Logistic regression; Ordinal regression; Regression analysis; Econometrics; Computer science","score_opus":0.23644908515090432,"score_gpt":0.619632349005499,"score_spread":0.38318326385459467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413298197","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009926641,0.00013415526,0.99232584,0.0009885384,0.00010183412,0.00035613705,0.0005288508,0.000019120469,0.0045528444],"genre_scores_gemma":[0.032514967,0.00004697051,0.96719956,0.00006353048,0.00003879491,0.00003748336,0.00003944911,0.000016122678,0.000043114203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9902934,0.0059183375,0.0009621166,0.00071430055,0.0014984872,0.00061334646],"domain_scores_gemma":[0.91630936,0.082425974,0.00008897059,0.00055694405,0.00026851858,0.00035026256],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024009362,0.00017682914,0.00064276444,0.0003330265,0.00012500802,0.00005046876,0.0008033797,0.00021862712,0.000629115],"category_scores_gemma":[0.124404885,0.00014716364,0.000021400549,0.00077251607,0.0014809559,0.00009838229,0.0011528876,0.0013540457,0.0000023834318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012886614,0.00011458201,0.00015773205,0.00034235336,0.000022737791,0.000025742778,0.00013001039,5.224624e-8,0.00043010007,0.51547086,0.0017968856,0.4813801],"study_design_scores_gemma":[0.0005792084,0.0002128978,0.0038176351,0.00045682056,0.000028236796,0.00000701532,0.00042811557,0.048303664,0.00019478895,0.94554174,0.0003170541,0.0001128206],"about_ca_topic_score_codex":0.0005022485,"about_ca_topic_score_gemma":0.00007163268,"teacher_disagreement_score":0.48126727,"about_ca_system_score_codex":0.00008971461,"about_ca_system_score_gemma":0.00045743023,"threshold_uncertainty_score":0.88297063},"labels":[],"label_agreement":null},{"id":"W4414642432","doi":"10.1177/09622802251374838","title":"Augmented two-stage estimation for treatment switching in oncology trials: Leveraging external data for improved precision","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MD Precision (Canada); University of British Columbia","funders":"","keywords":"Censoring (clinical trials); Randomized controlled trial; Estimation; Control (management); Sample size determination; Randomized response","score_opus":0.772245160354316,"score_gpt":0.7629188039075026,"score_spread":0.009326356446813455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414642432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004600968,0.00006432655,0.9930835,0.0018568824,0.00017783136,0.0036339005,0.000301905,0.00006410564,0.0003574945],"genre_scores_gemma":[0.0027349768,0.00009999938,0.9946623,0.000106039646,0.00007231757,0.001969447,0.00012009385,0.000028352022,0.0002064723],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895927,0.006345415,0.0016603761,0.00083780295,0.00071959913,0.0008441133],"domain_scores_gemma":[0.7769428,0.22171709,0.00016468987,0.0007303865,0.00023360667,0.00021141455],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.071187235,0.00020932843,0.0010467153,0.000593213,0.00012983572,0.000059892798,0.0007774284,0.0002796317,0.00019979177],"category_scores_gemma":[0.46413344,0.00016354403,0.000059365597,0.0004759026,0.00020204613,0.0001561796,0.00052605226,0.0007185936,7.698102e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009225113,0.0003502815,0.000008447838,0.00020436497,0.000021252521,0.000016171158,0.00011493027,0.0000080006785,0.003495459,0.17622532,0.00040367423,0.81822956],"study_design_scores_gemma":[0.0025413258,0.0004314802,0.000021530128,0.00039799302,0.000016431333,9.082125e-7,0.000118344986,0.4373301,0.002329523,0.5543333,0.0024025769,0.00007647387],"about_ca_topic_score_codex":0.0002481035,"about_ca_topic_score_gemma":0.00050951296,"teacher_disagreement_score":0.8181531,"about_ca_system_score_codex":0.001273445,"about_ca_system_score_gemma":0.001067796,"threshold_uncertainty_score":0.9564082},"labels":[],"label_agreement":null},{"id":"W4414897958","doi":"10.1177/09622802251382586","title":"Assessing spillover effects: Handling missing outcomes in network-based studies","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; National Institute of Mental Health; National Institute on Drug Abuse; Center for Drug Use and HIV Research; NYU Grossman School of Medicine; York University","keywords":"Censoring (clinical trials); Spillover effect; Estimator; Inverse probability; Observational study; Consistency (knowledge bases); Missing data; Intervention (counseling)","score_opus":0.5414715348528748,"score_gpt":0.7334598063847874,"score_spread":0.19198827153191256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414897958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002130053,0.0007342682,0.990243,0.0019872983,0.00023639188,0.00057492557,0.0000022113127,0.00011491393,0.003976898],"genre_scores_gemma":[0.033519585,0.00008860245,0.9655411,0.00045853676,0.000054442677,0.00020209333,0.0000019564634,0.00002969373,0.00010398154],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98842466,0.00713605,0.0010171258,0.0006041414,0.0016199502,0.0011980755],"domain_scores_gemma":[0.80491513,0.19410616,0.000068697605,0.0004104633,0.00026867085,0.00023088203],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03133349,0.00025048814,0.0010269629,0.00061159366,0.00016942492,0.00011288533,0.0004757421,0.00032446883,0.00018979414],"category_scores_gemma":[0.41746658,0.00019741392,0.0000566285,0.0015238164,0.0010875991,0.00015219423,0.00044708367,0.0024318795,0.000003972145],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051387273,0.00023461471,0.0080438005,0.0010981462,0.000039262773,0.00045169904,0.00009521809,0.000016606135,0.00024912122,0.38347167,0.0008367349,0.60541177],"study_design_scores_gemma":[0.0007163744,0.000086471366,0.0042393557,0.0037862041,0.000013358054,8.780464e-7,0.00019621641,0.016753418,0.0014621267,0.97223765,0.0003305377,0.00017740704],"about_ca_topic_score_codex":0.000053501106,"about_ca_topic_score_gemma":0.00007908083,"teacher_disagreement_score":0.6052343,"about_ca_system_score_codex":0.0005956888,"about_ca_system_score_gemma":0.00065453956,"threshold_uncertainty_score":0.9998695},"labels":[],"label_agreement":null},{"id":"W4415525767","doi":"10.1177/09622802251387430","title":"Two-stage Bayesian network meta-analysis of individualized treatment rules for multiple treatments with siloed data","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Mental Health Research Topics","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Generalizability theory; Leverage (statistics); Covariate; Bayesian probability; Statistical power; Patient data; Missing data; Data sharing; Bayesian network","score_opus":0.6766060736978984,"score_gpt":0.7188792600766557,"score_spread":0.04227318637875732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415525767","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010078019,0.0022881648,0.97297025,0.0021864655,0.00016664213,0.0034313905,0.0058532264,0.000029678753,0.0120664025],"genre_scores_gemma":[0.010161754,0.0001515671,0.97957647,0.0002307195,0.0000678748,0.00238245,0.0016312785,0.00003806338,0.0057598012],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9806325,0.013151276,0.0012107135,0.0012513694,0.0021794443,0.0015747169],"domain_scores_gemma":[0.9322441,0.06482065,0.00012702463,0.0018312361,0.00025213332,0.00072483026],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02398885,0.00030852895,0.0020995582,0.0010731948,0.0002268966,0.000041868556,0.001348986,0.00028057495,0.014839854],"category_scores_gemma":[0.01731666,0.00020113942,0.00025048095,0.0029013366,0.0011251968,0.00005603891,0.00058673864,0.0008137261,0.000014783229],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004030698,0.0027549607,0.010048843,0.00036289214,0.10663928,0.00032896118,0.0005065402,0.00003899962,0.000010827436,0.23419653,0.0029463647,0.63813514],"study_design_scores_gemma":[0.058780875,0.013188822,0.09749524,0.00035610198,0.16230349,0.000010567602,0.0051402184,0.36574045,0.00045175763,0.15679808,0.13812369,0.0016106904],"about_ca_topic_score_codex":0.0050457846,"about_ca_topic_score_gemma":0.0040119416,"teacher_disagreement_score":0.63652444,"about_ca_system_score_codex":0.00036657002,"about_ca_system_score_gemma":0.0009562251,"threshold_uncertainty_score":0.9909609},"labels":[],"label_agreement":null},{"id":"W4417427848","doi":"10.1177/09622802251403355","title":"Joint mixed-effects models for causal inference in clustered network-based observational studies","year":2025,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; University of North Carolina at Chapel Hill; National Institute of Child Health and Human Development; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Canada Research Chairs; McGill University","keywords":"Causal inference; Inference; Observational study; Context (archaeology); Outcome (game theory); Bayesian inference; Causal model; Bayesian probability; Latent variable","score_opus":0.7591763701323779,"score_gpt":0.7047860776338563,"score_spread":0.054390292498521675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417427848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004807859,0.00028318202,0.9938835,0.0025940565,0.00023009731,0.001611077,0.000032124644,0.00009326185,0.00079194206],"genre_scores_gemma":[0.04294894,0.000110328314,0.9540013,0.0005002192,0.00007584406,0.0021869233,0.000020040497,0.000028407752,0.00012797744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99074394,0.004750789,0.0011593063,0.00066269585,0.0015275553,0.0011557221],"domain_scores_gemma":[0.7696446,0.22883403,0.00008220669,0.00044019308,0.0007423557,0.00025662518],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02450163,0.00025837307,0.00091506634,0.0005077508,0.00013356649,0.000037695947,0.00052790693,0.0003779626,0.00010976116],"category_scores_gemma":[0.39039317,0.00022145269,0.0000616079,0.0013050768,0.0009915913,0.00012016591,0.0004999603,0.0016964464,0.000002224249],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014774254,0.00020526795,0.00029322162,0.001051001,0.000026351809,0.00005821443,0.00008349265,0.00050742296,0.00007445574,0.87335676,0.0043409723,0.11985509],"study_design_scores_gemma":[0.000762269,0.00018812377,0.0008258141,0.0012790457,0.000008640114,3.3816096e-7,0.00006976505,0.25329748,0.0005910456,0.74268633,0.00015133865,0.0001398147],"about_ca_topic_score_codex":0.000050468516,"about_ca_topic_score_gemma":0.00039318023,"teacher_disagreement_score":0.36589155,"about_ca_system_score_codex":0.0005716009,"about_ca_system_score_gemma":0.0010856315,"threshold_uncertainty_score":0.9030579},"labels":[],"label_agreement":null}]}